Tracking and early identification of suspected cases are essential to control and prevent potential COVID-19 outbreaks. One of the most popular techniques used to track this disease is the use of Infrared cameras to identify individuals with elevated body temperatures. However, they are limited by their inability to be implemented in open public settings such as public parks or even outdoor recreational centers. This limits their ability to effectively track possible COVID-19 patients as open public recreational places such as parks, concert venues and other public venues are hotspots for the spreading of the virus. Other technological solutions such as thermal scanners require an individual to perform the actual testing as they are not individual standalone technologies. This method of testing can potentially cause the transmission of the virus between the tester and the individual getting tested. As can be seen, an alternative solution is essential to solving this issue. In this study, we aim to present the system, design and potential scope of a non-invasive system that can diagnose and identify potential COVID-19 patients using thermal and optical images of the individual using drone technology. The proposed system (COVIDRONE) combines multi-modal machine intelligence, computer vision and real-time monitoring to enable scalable monitoring. The system will also involve the use of machine learning algorithms for better and more accurate diagnosis. We envisage that development of such technologies may help in developing technological solutions to combat infectious disease threats in the future pandemics.

Modal testing is a common step in aerostructure design, serving to validate the predicted natural frequencies and mode shapes obtained through computational methods. The strategic placement of sensors during testing is crucial to accurately measuring the intended natural frequencies. However, conventional methodologies for sensor placement are often time-consuming and involve iterative processes. This study explores the potential of machine learning techniques to enhance sensor selection methodologies. Three machine learning-based approaches are introduced and assessed, comparing their efficiency with established techniques. The evaluation of these methodologies is conducted using a numerical model of a beam to simulate real-world scenarios. The results offer insights into the efficacy of machine learning in optimizing sensor placement, presenting an innovative perspective on enhancing the efficiency and precision of modal testing procedures in aerostructure design.

A method for classification is introduced in this article, and it is tested on ADNI database to diagnose alzheimer’s disease (AD). It is obvious that tunning the performance of a classification to get better results is a complicated problem, and when we want model’s accuracy or other peformance measurments higher than 90%, the problem will be more complicated. In this study, we tried and succeeded to discover a method to solve this problem. The final feature set can be used clustering too, because outgrowth feature set of the proposed method is invigorated. In the recent years, a lot of activities is done to develop computer aided systems (CAD) for alzheimer’s disease diagnosis. Most of these recently developed systems concenterated on extracting and combining features from MRI, PET, CSF, and …; in this article, we made attempt to do so and utilized one more technique to increase classification performance. Finding and producing the best features to solve three binary classification problems of AD vs. Normal Control (NC), Mild Cognitive Impairment (MCI) vs. NC, and MCI vs. AD are the purposes of this article. Experiments indicate performance and effectiveness rates of the proposed method, which are accuracies of 98.81%, 81.61%, and 81.40% for AD vs. NC, MCI vs. NC, and AD vs. MCI classification problems, respectively. As can be seen, using this method increased the performance of the three binary problems incredibly.

The essence of cross-modal generation and retrieval modeling for image-text interactions lies in semantic consistency. Among these, cross-modal representation alignment serves as the foundational requirement for achieving cross-modal semantic consistency. The crux of our proposed method entails the collaborative training of an image captioning model(referred to as the ’captioner’) and a pair of contrastive encoders for image-text matching(referred to as the ’concoder’). This synergistic approach yields concurrent enhancements in concoder’s performance, captioner’s proficiency, and cross-modal semantic coherence. We coin the proposed method as ‘ReCap’. To begin, we initialize the concoder through knowledge distillation from a pre-trained model. During the training process, we use the output of the initialized concoder as input to a residual attention network, jointly training it with the captioner to achieve semantic consistency. Subsequently, we iteratively update the concoder during the image-text momentum encoding phase using the residual attention network, creating a closed-loop for semantic consistency resolution. Upon completion of training, the concoder and captioner modules can be used independently to perform tasks related to cross-modal retrieval and cross-modal generation of text and images. In order to substantiate the efficacy of our proposed method, we initially conducted empirical experiments encompassing image-text retrieval and image captioning tasks, employing a widely recognized benchmark dataset, MSCOCO. Subsequently, we assessed the fine-grained cross-modal alignment performance of the concoder through an image classification task on the iNaturalist 2018 dataset. The achieved performance metrics notably surpassed those achieved by several incumbent state-of-the-art models, thus validating the proficiency of our method. Finally, motivated by the practical requirements of handling the nature conservation image data, we performed caption annotation for the iNaturalist 2018 dataset. Subsequently, we trained the ReCap on this annotated data. Experimental results demonstrate that our proposed method can maintain semantic consistency between cross-modal retrieval and image caption generation for species with similar visual features but distinct semantics. This achievement signifies a meaningful exploration in the field of cross-modal semantic consistency representation, holding significant practical value in the domain of biological research.

In daily travel and activities, pathfinding is a significant process. They are often used in transportation routes calculation. They have now evolved to be able to solve most situations of the pathfinding and its related problems. This review describes previous and recent studies on the pathfinding algorithms. It reviews the development of pathfinding algorithms in a classification base on their usage. The aim is to summarize the application of the pathfinding algorithms for the readers interested in the subject that can be used as a supplement.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Along with the popularity of the Internet, people are exposed to more and more ways of micro-videos, and a huge amount of micro-video data has emerged. micro-videos have gradually become the Internet content preferred by the public, and a large number of micro-video apps have also emerged, such as Tiktok and Kwai. Intelligent classification and mining of micro-videos can greatly enhance user experience, improve business operation efficiency and enhance user experience. Through deep intelligent analysis and mining of micro-videos, important information in micro-videos can be extracted to provide an important basis for beautifying videos, content appreciation, video recommendation, content search, etc. In the past, content understanding for short videos often used human work annotation, but in recent years, with the great success of deep convolutional neural networks in image recognition, short video content understanding based on this method has gradually developed. Nowadays, most recognition algorithms extract the feature representation of each frame independently and then fuse them. However, while extracting the feature representation, some low-level semantic features are lost, which makes the algorithm unable to accurately distinguish the category of the video. At present, the algorithm of micro-video recognition based on deep learning has surpassed the iDT algorithm, making these traditional methods fade out of people’s view. In this paper according to the micro-video classification task, a new network model is proposed to concatenate features of each modality into the overall features of various modalities through the network, and then fuse the various modal features with the attention mechanism to obtain the whole micro-video features, which will be used for classification. In order to verify the effectiveness of the algorithm proposed in this paper, experiments are conducted in the public dataset, and it is shown the effectiveness of our model.

In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., Ozone, PM_2.5 and Sulfur Dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exists some works applying machine learning to air quality prediction, most of the prior studies are restricted to small scale data and simply train standard regression models (linear or non-linear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration based on meteorological data of previous days by formulating the prediction of 24 hours as a multi-task learning problem. It enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other, and compare with several typical regularizations for multi-task learning including standard Frobenius norm regularization, nuclear norm regularization, ℓ_2,1 norm regularization. Our experiments show the proposed formulations and regularization achieve better performance than existing standard regression models and existing regularizations.

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

Land cover mapping provides spatial information on the physical properties of the Earth’s surface, for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems such as destruction of important wetlands/forests, and loss of fish and wildlife habitats. This has made land cover mapping one of the most widespread application areas in remote sensing computational imaging. However, due to the differences between modalities in terms of resolutions, content, and sensors, integrating complementary information that multi-modal remote sensing imagery exhibits into a robust and accurate system still remains challenging, and classical segmentation approaches generally do not give satisfactory results for land cover mapping. In this paper, we propose a novel dynamic deep network architecture, AMM-FuseNet, that promotes the use of multi-modal remote sensing images for the purpose of land cover mapping. The proposed network exploits the hybrid approach of the Channel Attention mechanism and Densely Connected Atrous Spatial Pyramid Pooling (DenseASPP). In the experimental analysis, in order to to verify the validity of the proposed method, we test AMM-FuseNet applied to four datasets whilst comparing it to the 6 state-of-the-art models of DeepLabV3+, PSPNet, UNet, SegNet, DenseASPP, and DANet. In addition, we also demonstrate the capability of AMM-FuseNet under minimal training supervision (reduced number of training samples) compared to the state-of-the-art, achieving less accuracy loss even for the case with 1/20 of the training samples.

Existing Reynolds Averaged Navier-Stokes based transition models do not accurately predict separation induced transition for low pressure turbines. Therefore, in this study, a novel framework based on computational fluids dynamics driven machine learning coupled with multi-expression and multi-objective optimization is explored to develop models which can improve the transition prediction for the T106A low pressure turbine at an isentropic exit Reynolds number of Re2is=100,000. Model formulations are proposed for the transfer and laminar eddy viscosity terms of the laminar kinetic energy transition model using seven non-dimensional pi groups. The multi-objective optimization approach makes use of cost functions based on the suction-side wall-shear stress and the pressure coefficient. A family of solutions is thus developed, whose performance is assessed using Pareto analysis and in terms of physical characteristics of separated-flow transition. Two models are found which bring the wall-shear stress profile in the separated region at least two times closer to the reference high-fidelity data than the baseline transition model. As these models are able to accurately predict the flow coming off the blade trailing edge, they are also able to significantly enhance the wake-mixing prediction over the baseline model.

With the proliferation and development of social media platforms, social media data has become an important source for acquiring spatio-temporal information on various urban events. Providing accurate spatio-temporal information for events contributes to enhancing the capabilities of urban management and emergency response. However, existing research on mining spatio-temporal information of events often focuses solely on textual content, neglecting data from other modalities such as images and videos. Therefore, this study proposes an innovative spatio-temporal information extraction method for multi-modal social media data (MIST-SMMD), which extracts the spatio-temporal information of events from multi-modal data on Weibo at coarse and fine-grained hierarchical levels, serving as a beneficial supplement to existing urban event monitoring methods. This paper takes the "July 20th Zhengzhou Heavy Rainfall" incident as an example, to evaluate and analyze the effectiveness of the proposed method. The results indicate that in the coarse-grained spatial information extraction using only textual data, our method achieves a Spatial Precision of 87.54% within a 60m range, and reaches 100% Spatial Precision for ranges beyond 200m. For fine-grained spatial information extraction, the introduction of other modal data such as images and videos results in a significant improvement in Spatial Error. These results demonstrate the ability of the MIST-SMMD method to extract spatio-temporal information from urban events at both coarse and fine levels, and confirms the significant advantages of multi-modal data in enhancing the precision of spatial information extraction.

In modern security situations, tracking multiple human objects in real-time within challenging urban environments is a critical capability for enhancing situational awareness, minimizing response time, and increasing overall operational effectiveness. Tracking multiple entities enables informed decision-making, risk mitigation, and the safeguarding of civil-military operations to ensure safety and mission success. This paper presents a multi-modal electro-optical/infrared (EO/IR) and radio frequency (RF) fused sensing (MEIRFS) platform for real-time human object detection, recognition, classification, and tracking in challenging environments. By utilizing different sensors in a complementary manner, the robustness of the sensing system is enhanced, enabling reliable detection and recognition results across various situations. Specifically designed Radar tag and thermal tag can be used to discriminate friendly and non-friendly objects. The system incorporates deep learning-based image fusion and human object recognition and tracking (HORT) algorithms to ensure accurate situation assessment. After integrating into an all-terrain robot, multiple ground tests were conducted to verify the consistent HORT in various environments. The MEIRFS sensor system has been designed to meet the Size, Weight, Power, and Cost (SWaP-C) requirements for installation on autonomous ground and aerial vehicles.

The combination of new-generation information technology and manufacturing technology has resulted in major and profound impact on future development paradigm of manufacturing. It is challenging for existing methods to conduct a multidimensional trend exploration related to machine tool domain, which is the basis of virtually everything in manufacturing. In this paper, we proposed an integrating approach framework combined topic models, bibliometric, trend analysis and patent analysis to mine insightful information about future development from multi-source data related to machine tool, such as papers, grants, patents and news. Specifically, papers and grants provided two different perspectives to explore the current focuses and future trends in machine tool research. Furthermore, the future technology development of machine tool was investigated through patents analysis. Finally, news related to machine tool industry in recent years was analyzed to analyze future machine tool business mode. The integration of the above various analytical methods and the multi-dimensional mining of literatures enabled the analysis of the future development of machine tool domain systematically from multi-perspectives which include research, technology development and industry. The conclusions obtained in this paper is beneficial to different communities of machine tool in terms of determining the research directions for researchers, identifying industry opportunities for corporations and developing reasonable industry policy for policy makers.

Purposes: To provide abdominal contrast-enhanced MR image synthesis, we developed an image gradient regularized multi-modal multi-discrimination sparse-attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. Methods: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural-similarity-index (SSIM), and mean-squared-error (MSE). A Turing test and experts’ contours evaluated the image synthesis quality. Results: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values <0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90, compared to the inter-operator DICE of 0.91. Conclusion: We demonstrated the function of a novel multi-modal MR image synthesis neural network, GRMM-GAN, for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

The multi-modal data fusion method based on IA-net and CHMM technical proposed is designed to solve the problem that the incompleteness of target behavior information in complex family environment leads to the low accuracy of human behavior recognition.The two improved neural networks(STA-ResNet50、STA-GoogleNet)are combined with LSTM to form two IA-Nets respectively to extract RGB and skeleton modal behavior features in video. The two modal feature sequences are input CHMM to construct the probability fusion model of multi-modal behavior recognition.The experimental results show that the human behavior recognition model proposed in this paper has higher accuracy than the previous fusion methods on HMDB51 and UCF101 datasets. New contributions: attention mechanism is introduced to improve the efficiency of video target feature extraction and utilization. A skeleton based feature extraction framework is proposed, which can be used for human behavior recognition in complex environment. In the field of human behavior recognition, probability theory and neural network are cleverly combined and applied, which provides a new method for multi-modal information fusion.

A new method for multi-shot reconstruction of high-energy photon distributions in the context of studying the interaction between a beam and a plasma in plasma wakefield acceleration (PWFA) experiments is presented. The study investigates the effects of beam perturbations on betatron radiation and analyzes how these perturbations can lead to hosing, a transverse instability that can degrade the quality of the beam. The potential of betatron radiation spectroscopy as a non-invasive diagnostic technique for PWFA experiments is also emphasized.

With the rapid development of Internet and the widely usage of smart devices, massive multimedia data are generated, collected, stored and shared on the Internet. This trend makes cross-modal retrieval problem become a hot issue in this years. Many existing works pay attentions on correlation learning to generate a common subspace for cross-modal correlation measurement, and others uses adversarial learning technique to abate the heterogeneity of multi-modal data. However, very few works combine correlation learning and adversarial learning to bridge the inter-modal semantic gap and diminish cross-modal heterogeneity. This paper propose a novel cross-modal retrieval method, named ALSCOR, which is an end-to-end framework to integrate cross-modal representation learning, correlation learning and adversarial. CCA model, accompanied by two representation model, VisNet and TxtNet is proposed to capture non-linear correlation. Beside, intra-modal classifier and modality classifier are used to learn intra-modal discrimination and minimize the inter-modal heterogeneity. Comprehensive experiments are conducted on three benchmark datasets. The results demonstrate that the proposed ALSCOR has better performance than the state-of-the-arts.

Research within the field of hydrology often focuses on comparing stochastic to machine learning (ML) forecasting methods. The comparisons performed are all based on case studies, while an extensive study aiming to provide generalized results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 large-scale computational experiments based on simulations. Each of these experiments uses 2 000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the performance of the methods using 18 metrics. The results indicate that stochastic and ML methods perform equally well.

The potential of quantum computing for scientific and industrial breakthroughs is immense, however, we are still in the Noisy Intermediate-Scale Quantum (NISQ) era, where the currently available quantum devices contain small numbers of qubits, are very sensitive to environmental conditions and prone to quantum decoherence. Even so, existing NISQ computers have already been shown to outperform conventional computers on specific problems and the key question is how to make use of today’s NISQ devices to achieve quantum advantage in the field of computational science and engineering (CSE). In this direction, this work proposes a hybrid computing formulation by combining quantum computing with machine learning for accelerating the solution of parameterized linear systems in NISQ devices. In particular, it focuses on the Variational Quantum Linear Solver (VQLS), which is a hybrid quantum- classical algorithm for solving linear systems of equations. VQLS employs a short-depth quantum circuit to efficiently evaluate a cost function related to the system solution. The algorithm’s circuit consists of a quantum gate sequence (unitary operators) that involves a set of tunable parameters. Then, well-established classical optimizers are utilized to tune the parameters of the sequence in order to minimize the cost function, which is equivalent to finding the system solution at an acceptable level of accuracy. In this work, it is demonstrated that machine learning tools such as feed-forward neural networks and nearest-neighbor interpolation techniques can be successfully employed to accelerate the convergence of the VQLS algorithm towards the optimal values for the circuit parameters when applied to parameterized linear systems that need to be solved for multiple parameter instances.

In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

A full electrification of many local railway lines is often not feasible or sustainable in terms of construction and maintenance costs or alternatively for the presence of additional constraints and limitations deriving from environmental or infrastructural limitations. Battery Operated or other kind of hybrid solutions powertrains are currently proposed as sustainable alternatives to Internal combustion engines for the propulsion of rolling stock on not electrified lines. In this work, authors propose the adoption of a partial electrification of lines to assure higher performances and reliability of battery-operated rolling stock designed to be recharged and feed using standard technologies such as pantographs gathering power from suspended catenaries. This innovative solution is designed for a benchmark test vehicle inspired from an existing one and simulated considering some possible scenario of application corresponding to some existing railway lines in Italy.

Deep neural networks (DNNs) have gained prominence in addressing regression problems, offering versatile architectural designs that cater to various applications. In the field of earthquake engineering, seismic response prediction is a critical area of study. Simplified models such as single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) systems have traditionally provided valuable insights into structural behavior, known for their computational efficiency facilitating faster simulations. However, these models have notable limitations in capturing the nuanced nonlinear behavior of structures and the spatial variability of ground motions. This study focuses on leveraging ambient vibration (AV) measurements of buildings, combined with earthquake (EQ) time-history data, to create a predictive model using a neural network (NN) in image format. The primary objective is to predict a specific building's earthquake response accurately. The training dataset consists of 1,197 MDOF 2D shear models, generating a total of 32,319 training samples. To evaluate the performance of the proposed model, termed MLPER (Machine Learning based Prediction of building structures' Earthquake Response), several metrics are employed. These include mean absolute percentage error (MAPE) and mean deviation angle (MDA) for comparisons in the time domain. Additionally, we assess magnitude-squared coherence values and phase differences (Δφ) for comparisons in the frequency domain. This study underscores the potential of MLPER as a reliable tool for predicting building earthquake response, addressing the limitations of simplified models. By integrating AV measurements and EQ time-history data into a neural network framework, MLPER offers a promising avenue for enhancing our understanding of structural behavior during seismic events, ultimately contributing to improved earthquake resilience in building design and engineering.

Multi-criteria decision analysis (MCDA), one of the prevalent branches of operations research, aims to design mathematical and computational tools for selecting the best alternative among several choices with respect to specific criteria. In the cloud, MCDA based online brokers uses customer specified criteria to rank different service providers. However, subjected to limited domain knowledge, the customer may exclude relevant or include irrelevant criterion, which could result in suboptimal ranking of service providers. To deal with such misspecification, this research proposes a model, which uses notion of factor analysis from the domain of unsupervised machine learning. The model is evaluated using two quality-of-service (QoS) based datasets. The first dataset i.e., feedback from customers, was compiled using leading review websites such as Cloud Hosting Reviews, Best Cloud Computing Providers, and Cloud Storage Reviews and Ratings. The second dataset i.e., feedback from servers, was generated from cloud brokerage architecture that was emulated using high performance computing (HPC) cluster at University of Luxembourg (HPC @ Uni.lu). The simulation runs in a stable cloud environment i.e. when uncertainty is low, shows that online broker (equipped with the proposed model) produces optimized ranking of service providers as compared to other brokers. This is due the fact that proposed model assigns priorities to criteria objectively (using machine learning) rather than using priorities based on subjective judgments of the customer. This research will benefit potential cloud customers that view insufficient domain knowledge as a limiting factor for acquisition of web services in the cloud.

Miscanthus holds a great potential in the frame of the bioeconomy and yield prediction can help improving Miscanthus logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. Random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass and standing biomass) using VIs time series and predicted yield using peak descriptor derived from VIs time series with 2.3 Mg DM ha-1 of RMSE. The study demonstrates the potential of UAVs multispectral in HTP applications and in yield prediction for providing important information needed to increase sustainable biomass production.

Current methods for assessing individual well-being in team collaboration at the workplace rely often on manually collected surveys. This limits continuous real-world data collection and proactive measures to improve team member workplace satisfaction. We propose a method to automatically derive social signals related to individual well-being in team collaboration from raw audio and video data collected in teamwork contexts. The goal is to develop computational methods and measurements to facilitate the mirroring of individuals’ well-being to themselves. We are focusing on how speech behavior is perceived by team members to improve their well-being. Our main contribution is the assembly of an integrated toolchain to perform multi-modal extraction of robust speech features in noisy field settings and to find which features are predictors of self-reported satisfaction scores. We apply the toolchain to a case study where we collected videos of 22 teams with 56 participants collaborating over a four-day period in a team project. Our audiovisual speaker diarization extracts individual speech features in a noisy environment. As the dependent variable team members filled out a daily PERMA (positive emotion, engagement, relationships, meaning, and accomplishment) survey. These well-being scores have been predicted with speech features extracted from the videos using machine learning. The results suggest that the proposed toolchain is able to automatically predict individual well-being in teams, leading to better teamwork and happier team members.

Image fusion is the process of combining multiple input images from single or multiple imaging modalities into a fused image, which is expected to be more informative for human or machine perception as compared to any of the input images. In this paper, we propose a novel method based on deep learning for fusing infrared images and visible images, named the LBP-based proportional input generative adversarial network (LPGAN). In the image fusion task, the preservation of structural similarity and image gradient information is contradictory, and it is difficult for both to achieve good performance at the same time. To solve this problem, we innovatively introduce Local Binary Patterns (LBP) into Generative Adversarial Networks (GANs), which effectively utilize the texture features of the source images, so that the network has stronger feature extraction ability and anti-interference ability. In the feature extraction stage, we introduce a pseudo-siamese network for the generator to extract the detailed features and the contrast features. At the same time, considering the characteristic distribution of different modal images, we propose a 1:4 scale input mode. Extensive experiments on the publicly available TNO dataset and CVC14 dataset show that the proposed method achieves the state-of-the-art performance. We also test the universality of LPGAN through the fusion of RGB and infrared images on the RoadScene dataset. In addition, LPGAN is applied to multi-spectral remote sensing image fusion. Both qualitative and quantitative experiments demonstrate that our LPGAN can not only achieve good structural similarity, but also retain rich detailed information.

Several factors impact the durability of concrete bridge decks, including traffic loads, fatigue, temperature changes, environmental stress, and maintenance activities. Detecting problems such as corrosion, delamination, or concrete degradation early on can lower maintenance costs. Nondestructive evaluation (NDE) techniques can detect these issues at early stages. Each NDE method, meanwhile, has limitations that reduce the accuracy of the assessment. In this study, multiple NDE technologies were combined with machine learning algorithms to improve the interpretation of half-cell potential (HCP) and electrical resistivity (ER) measurements. A parametric study was performed to analyze the influence of five parameters on HCP and ER measurements, such as degree of saturation, corrosion length, delamination depth, concrete cover, and moisture condition of delamination. The results were obtained through finite element simulations and used to build two machine learning algorithms, a classification algorithm and a regression algorithm, based on the Random Forest methodology. The algorithms were tested using data collected from a bridge deck in the BEAST® facility. Both machine learning algorithms were effective in improving the interpretation of ER and HCP measurements using data from multiple NDE technologies.

The dynamic behaviour of a machine tool (MT) directly influences the machining performances. The adoption of lightweight structures may reduce the effects of undesired vibrations and increasing the workpiece quality. This paper aims to present and compare a set of hybrid materials that may be excellent candidate to fabricate the MT moving parts. The selected materials have high dynamic characteristics and capacity to damp mechanical vibrations. In this way, starting by the kinematic model of a milling machine that highlights the main critical factors, this study paper evaluates a number of prototypes made of Al Foam sandwiches (AFS), Al Corrugated sandwiches (ACS) and materials reinforced by carbon fibres (CFRP). A set of prototypes has been fabricated, represented the Z-axis ram of a commercial milling machine. The static and dynamical properties have been evaluated by using both FE simulations and experimental tests. The obtained results show that the proposed structures may be a valid alternative to the conventional materials of MT moving parts, increasing machining performances. In particular, the AFS prototype highlighted a damping coefficient that is 20 times greater than a conventional ram (e.g. steel). The CFRP structure is able to satisfy the machining requirements with a reduced weight of 48.5%, while the ACS prototype showed a good trade-off between stiffness and damping.

Recent years have seen a proliferation of platform-based “shared mobility services” (SMS) such as car-, bike-, and e-scootersharing in many cities in Germany and around the world. At the same time, these services have become the subject of intense debates: Are they replacing private car travel, thus contributing to sustainable mobility in cities? Or are they drawing users away from public transit and cycling while obstructing public space? From the perspective of sustainable mobility politics it seems far from clear which role these new services could play in transitioning to a less car-centric mobility system. While a number of potential effects and ensuing governance issues of shared mobility services (e.g. regarding questions of equitable access, data governance, the role of public versus private actors) have already been studied this article explores the role of shared mobility services (SMS) in triggering system dynamics and feedback loops in the context of sustainability transitions. The article connects questions regarding the sustainability effects of “shared mobility services” with the role of “push” measures to reduce private car traffic in cities. Using a theoretical framework from socio-technical transitions research and from the sociology of technology it describes the recent growth of shared mobility services in Berlin as an example of the upscaling dynamics of socio-technical niche innovations. Drawing on a series of workshops with mobility service providers and representatives of public authorities it analyses the potential for conflict as well as for coalition building between service providers and public authorities. Based on the theoretical concept of the role of feedback loops and windows of opportunity for transitions it shows how the market growth of shared mobility services added momentum to an already ongoing political debate over the legitimate use of public space in Berlin. Against this backdrop the article shows how growing numbers of car-, bike-, and e-scootersharing vehicles could open up windows of opportunity for re-distributing space away from private cars. The article concludes that supporting and regulating SMS will be key to steering their growth into the direction of sustainability.

With a mild Mediterranean-type climate, Corsica is endemic for canine vector-borne diseases (CVBDs) such as dirofilariosis (a mosquitoes borne-diseases: MBDs), leishmaniosis and ehrlichiosis. The aim of this present study was to evaluate a monthly multi-modal prophylactic strategy (MMP) against CVBDs occurring in Corsica. The study was conducted as a comparative field trial in which eighty dogs allocated into two groups were included: (i) Group 1 consisted of 25 dogs under the MMP [per-os administration of 1.5 tablet of milbemycine oxime-praziquantel and a topical line-on application of a 3.6 mL solution of dinotefuran-permethrin-pyriproxyfen] and (ii) Group 2 under various real-life prophylactic treatment (RLP) based on the use of ectoparasiticide products [different formulations: deltamethrin, fluralaner, fipronil] and/or macrocyclic lactones based-products [milbemycin oxime/praziquantel, milbemycin oxime, moxidectin] during the period ranging from June to October 2017. All animals were followed for one year and had blood drawn at day 0, followed by follow-up at 6 and 12 months. Samples were screened for filariosis using molecular tools as well as for leishmaniosis and ehrlichiosis using indirect immunofluorescence assay (IFA). At the end of the study, no new cases of CVBDs were recorded within Group 1. In Group 2, the cumulative incidence of CVBDs was 20.0% (n= 11; p= 0.015) including dirofilarioses due to Dirofilaria immitis and/or D. repens, with 16.4% (n= 9; p=0.027). Ehrlichiosis was 5.5% (n= 3; p=0.241). No new cases of leishmaniosis were detected in Group 2. The data illustrated that, unlike the RLP treatment which failed to protect at least 20% of dogs, the MMP based on the concurrent administration of milbemycine oxime-praziquantel and dinotefuran-permethrin-pyriproxyfen is efficient to protect dogs against CVBDs in a high-risk area.

Robotic odor source localization (OSL) is a technology that enables mobile robots or autonomous vehicles to find an odor source in unknown environments. An effective navigation algorithm that guides the robot to approach the odor source is the key to successfully locating the odor source. While traditional OSL approaches primarily utilize an Olfaction-only strategy, guiding robots to find the odor source by tracing emitted odor plumes, our work introduces a fusion navigation algorithm that combines both vision and olfaction-based techniques. This hybrid approach addresses challenges such as turbulent airflow, which disrupts olfaction sensing, and physical obstacles inside the search area, which may impede vision detection. In this work, we propose a hierarchical control mechanism that dynamically shifts the robot’s search behavior among four strategies: crosswind maneuver, Obstacle-avoid Navigation, Vision-based Navigation, and Olfaction-based Navigation. Our methodology includes a custom-trained deep-learning model for visual target detection and a moth-inspired algorithm for Olfaction-based navigation. To assess the effectiveness of our approach, we implemented the proposed algorithm on a mobile robot in a search environment with obstacles. Experimental results demonstrate that our Vision and Olfaction Fusion algorithm significantly outperforms Vision-only and Olfaction-only methods, reducing average search time by 54% and 30%, respectively.

One of the most promising advancements in healthcare is the application of digital twin technology. Digital twins are virtual replicas of real-world human patients and can be used for monitoring, and diagnosis, and as a tool to design treatment strategies tailored to individual patients. Furthermore, digital twins could also be helpful in finding novel treatment targets and predicting the effects of drugs and other chemical substances in development. This review article delves into the various data sources and methodologies that contribute to the construction of digital twins. Each data source, including blood glucose levels, heart MRI and CT scans, cardiac electrophysiology, written reports, and multi-omics data, comes with different challenges regarding standardization, integration, and interpretation. We showcase how various datasets and methods are used to overcome these obstacles and generate a digital twin. While digital twin technology has seen significant progress, there are still hurdles in the way to achieving a fully comprehensive patient digital twin. Developments in non-invasive and high-throughput data collection, as well as advancements in modeling and computational power will be crucial to improve digital twin systems. We discuss a few critical developments in light of the current state of digital twin technology. Despite challenges, digital twin research holds great promise for personalized patient care and has the potential to shape the future of healthcare innovation.

In this paper we describe and exploit a geometric framework for Gibbs probability densities and the associated concepts in statistical mechanics, which unifies several earlier works on the subject, including Souriau's symplectic model of statistical mechanics, its polysymplectic extension, Koszul model, and approaches developed in quantum information geometry. We emphasize the role of equivariance with respect to Lie group actions and the role of several concepts from geometric mechanics, such as momentum maps, Casimir functions, coadjoint orbits, and Lie-Poisson brackets with cocycles, as unifying structures appearing in various applications of this framework to information geometry and machine learning. For instance, we discuss the expression of the Fisher metric in presence of equivariance and we exploit the property of the entropy of the Souriau model as a Casimir function to apply a geometric model for energy preserving entropy production. We illustrate this framework with several examples including multivariate Gaussian probability densities, and the Bogoliubov-Kubo-Mori metric as a quantum version of the Fisher metric for quantum information on coadjoint orbits. We exploit this geometric setting and Lie group equivariance to present symplectic and multisymplectic variational Lie group integration schemes for some of the equations associated to Souriau symplectic and polysymplectic models, such as the Lie-Poisson equation with cocycle.

Exploiting the linguistic knowledge of the source language for neural machine translation (NMT) has recently achieved impressive performance on many large-scale language pairs. However, since the Turkish→English machine translation task is low-resource and the source-side Turkish is morphologically-rich, there are limited resources of bilingual corpora and linguistic information available to further improve the NMT performance. Focusing on the above issues, we propose a multi-source NMT approach that models the word feature in parallel to external linguistic features by using two separate encoders to explicitly incorporate linguistic knowledge into the NMT model. We extend the word embedding layer of the knowledge-based encoder to accommodate for each word’s linguistic annotations in the context. Moreover, we share all parameters across encoders to enhance the representation ability of the NMT model on the source language. Experimental results show that our proposed approach achieves substantial improvements of up to 2.4 and 1.1 BLEU scores in Turkish→English and English→Turkish machine translation tasks, respectively, which points to a promising way to utilize the source-side linguistic knowledge for the low-resource NMT.

In this work, we propose a self-supervised multi-agent system that meets the online learning of clustering tasks for video behavior recognition spatio-temporal tasks. Encoding visual behavioral actions as discrete temporal sequence(DTS). Real-time clustering recognition task in a multi-agent system for continuous model building, training, and correction. Finally, we implemented a fully decentralized multi-agent system and completed its feasibility verification in a surveillance video application scenario on vehicle path clustering.

In this work, we show that a late fusion approach to multi-modality in sign language recognition improves the overall ability of the model in comparison to the singular approaches of Computer Vision (88.14%) and Leap Motion data classification (72.73%). With a large synchronous dataset of 18 BSL gestures collected from multiple subjects, two deep neural networks are benchmarked and compared to derive a best topology for each. The Vision model is implemented by a CNN and optimised MLP and the Leap Motion model is implemented by an evolutionary optimised deep MLP topology search. Next, the two best networks are fused for synchronised processing which results in a better overall result (94.44%) since complementary features are learnt in addition to the original task. The hypothesis is further supported by application of the three models to a set of completely unseen data where a multi-modality approach achieves the best results relative to the single sensor method. When transfer learning with the weights trained via BSL, all three models outperform standard random weight distribution when classifying ASL, and the best model overall for ASL classification was the transfer learning multi-modality approach which scored 82.55% accuracy.

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) will contribute to vehicle decision-making in the Intelligent Transportation System (ITS). Multi-Vehicle Pursuit games (MVP), a multi-vehicle cooperative ability to capture mobile targets, is becoming a hot research topic gradually. Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games. We define an Observation-constrained MVP (OMVP) problem in this paper and propose a Transformer-based Time and Team Reinforcement Learning scheme (T3OMVP) to address the problem. First, a new multi-vehicle pursuit model is constructed based on decentralized partially observed Markov decision processes (Dec-POMDP) to instantiate this problem. Second, by introducing and modifying the transformer-based observation sequence, QMIX is redefined to adapt to the complicated road structure, restricted moving spaces and constrained observations, so as to control vehicles to pursue the target combining the vehicle’s observations. Third, a multi-intersection urban environment is built to verify the proposed scheme. Extensive experimental results demonstrate that the proposed T3OMVP scheme achieves significant improvements relative to state-of-the-art QMIX approaches by 9.66%~106.25%. Code is available at https://github.com/pipihaiziguai/T3OMVP.

We addressed whether arbitrary top–down regulation based on self-referential thinking could be valid for sensorimotor synchronization. We hypothesized that the dorsal anterior cingulate cortex (dACC) could regulate sensorimotor synchronization in accordance with internal models generated by self-referential processing. To illustrate the validity of the hypothesis, we conducted a missing oddball task with musical students. Utilizing the event-related deep-brain activity (ER-DBA) method cooperatively with the event-related potential (ERP) method, we found that dACC activation promotes repetitive tapping supported by modal completion, whereas dACC deactivation promotes precise tapping under avoiding erroneous responses for the missing pulses. Endogenous ERP components including P150 as a marker of modal completion and N200 as a marker of response inhibition supported this claim. Furthermore, combining the ER-DBA and ERP results, it was suggested that the brain creates a coherent story to promote repetitive tapping by mediating sensory evidence via modal completion. The free energy measurements theoretically support these findings, thereby confirming the validity of our hypothesis.

The Sei Dareh Bridge is a cable-stayed bridge located in West Sumatra Province, Indonesia. The bridge, has a main span of 123 meters length and 9 meters wide, crosses the Batanghari River. Traffic load is transmitted through 4 prestressed cables to a 42.4 meter high pylon made of concrete. Bridge deck and traffic loads are directly supported by steel box girders as main beams that are reinforced laterally with cross beams IWF 800.300.16.24 and stringers IWF 350.350.12.19. This paper discusses static and dynamic testing on the bridge which aims to assess the feasibility before it is opened for public. Based on the test, it was concluded that the 73% static load could not be achieved because the deflection that occurred was beyond the allowable deflection. This is exacerbated by the sound of a loud clanging sound on the ST2-X1 prestressed cable when loading to 240 tons or 58% of the targeted load. In addition, this bridge is included in the "lazy bridge" category because it takes 24 hours to return to an undeformed condition after loading. As a recommendation for this bridge, it is necessary to carry out a structural health monitoring system (SHMS) regularly on the vehicle floor and cables.

Users on the social networking platform have the freedom to express themselves freely. Towards the same time, this has created a forum for disagreement and hate directed at someone, society, racism, sexual orientation, and so on. Identifying hate online is a challenging task. Researchers from all around the world have contributed major methods for detecting hate speech, but owing to the issue's complexity, there are still many unresolved issues. In this research, we offer a multi-model learning strategy for detecting hate speech on Twitter. We utilised the Kaggle TwitterHate dataset, which had 31962 tweets categorised as binary hate or non-hate, to evaluate our technique. The suggested method is tested using commonly used machine learning classifiers with multi-model technique. Using TF-IDF features, we acquired detection results of 96.29 %, precision of 96%, recall of 96%, and f1-score of 96%.

In this paper, a new approach to retrieve semantic images based on shape and geometric features of image in conjunction with multi-class support vector machine is proposed. Zernike moment as shape feature is to verify the invariance of objects for silhouette image. In addition, a set of geometrical features is to explore the objects shape using two features of rectangularity and circularity. Then the extracted features are normalized and employed for multi-class support vector machine either for learning or retrieving processes. The retrieving process relies on three main tasks which namely Query Engine, Matching Module and Ontology Manger, respectively. Query Engine is to build the input text or image query using SPARQL language. The matching module extracts the shape and geometric features of image’s objects and employ them to Ontology Manger which in turn inserts them in ontology knowledge base. Benchmark mammals have been conducted to empirically conclude the outcome of proposed approach. Our experiment on text and image retrieval yields efficient results to problematic phenomena than previously reported.

The prediction of drug-target interactions plays a fundamental role in facilitating drug discovery, where the goal is to find prospective drug candidates. With the increase in the number of drug-protein interactions, machine learning techniques, especially deep learning methods, have become applicable for drug-target interaction discovery because they significantly reduce the required experimental workload. In this paper, we present a spontaneous formulation of the drug-target interaction prediction problem as an instance of multi-instance learning. We address the problem in three stages, first organizing given drug and target sequences into instances via a private-public mechanism, then identifying the predicted scores of all instances in the same bag, and finally combining all the predicted scores as the output prediction. A comprehensive evaluation demonstrates that the proposed method outperforms other state-of-the-art methods on three benchmark datasets.

The Sei Dareh Bridge is a cable-stayed bridge located in West Sumatra Province, Indonesia. The bridge, which crosses the Batanghari River, has a main span of 123 meters long and 9 meters wide. Traffic load is transmitted through 24 prestressed cables to a 42.4-meter-high pylon made of concrete. The bridge deck and traffic loads are directly supported by steel box girders as main beams that are reinforced laterally with cross beams IWF 800.300.16.24 and stringers IWF 350.350.12.19. This paper discusses static and dynamic testing on the bridge which aims to assess its feasibility before it is opened to the public. Based on the test, it was concluded that a static load of 73% could not be achieved because the deflection that occurred was beyond the allowable deflection. This is exacerbated by a loud clanging sound on the ST2-X1 prestressed cable when loading to 240 tons or 58% of the targeted load. In addition, this bridge is included in the "lazy bridge" category because it takes 24 hours to return to an undeformed condition after loading. As a recommendation for this bridge, it is necessary to carry out a structural health monitoring system (SHMS) regularly on bridge slabs and cables.

In response to escalating global demand for poultry, the industry grapples with an array of intricate challenges, from enhancing productivity to improving animal welfare and attenuating environmental impacts. This comprehensive review explores the transformative potential of digital phenotyping, an emergent technological innovation at the cusp of dramatically reshaping broiler production. The central aim of this study is to critically examine digital phenotyping as a pivotal solution to these multidimensional industry conundrums. Our investigation spotlights the profound implications of 'digital twins' in the burgeoning field of broiler genomics, where the production of exact digital counterparts of physical entities accelerates genomics research and its practical applications. Further, this review probes into the ongoing advancements in the research and development of a context-sensitive, multimodal digital phenotyping platform, custom-built to monitor broiler health. I critically evaluate this platform's potential in revolutionizing health monitoring, fortifying the resilience of broiler production, and fostering a harmonious balance between productivity and sustainability. Subsequently, the paper provides a rigorous assessment of the unique challenges that may surface during the integration of digital phenotyping within the industry. These span from technical and economic impediments to ethical deliberations, thus offering a comprehensive perspective. The paper concludes by highlighting the game-changing potential of digital phenotyping in the broiler industry and identifying potential future directions for the field, underlining the significance of continued research and development in unlocking digital phenotyping's full potential. In doing so, it charts a course towards a more robust, sustainable, and productive broiler industry. The insights garnered from this study hold substantial value for a broad spectrum of stakeholders in the broiler industry, setting the stage for an imminent technological evolution in poultry production.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

Fast convergence routing is an important issue for LEO constellation network, due to its dynamical topology changing and time varying transmission requests. Most of existing research focus on the OSPF routing algorithm, which cannot handle the frequently links state changing of network. In this paper, we propose a Fast-Convergence Reinforcement Learning Satellite Routing Algorithm (FRL-SR) for LEO satellite networks, in which the satellite gets the network links status fast and adjusts its routing strategy. In FRL-SR, each satellite node is regarded as an agent. The agent selects the port for packet forwarding according to its own routing policy. When the satellite network state changes, agent would send ’hello’ packets to the neighbor node to update the neighbor node’s routing policy. Compared with traditional reinforcement learning, FRL-SR can perceive network information faster, and then converge faster. Also, FRL-SR can mask the dynamics of satellite network topology and adaptively adjust the forwarding strategy according to the link state. Various simulation is constructed, the results show that the proposed FRL-SR algorithm out performance the Dijkstra algorithm in performance of average delay, packet arriving ratio, network load balance.

As a new distributed machine learning (ML) approach, federated learning (FL) shows the great potential to preserve data privacy by enabling distributed data owners to collaboratively build a global model without sharing their raw data. However, the heterogeneity in terms of data distribution and hardware configurations make it hard to select participants from the thousands of nodes. In this paper, we propose a multi-objective node selection approach to improve time-to-accuracy performance while resisting malicious nodes. We firstly design a deep reinforcement learning assisted FL framework. Then the problem of multi-objective node selection under this framework is formulated as a Markov decision process (MDP), which aims to reduce the training time and improve model accuracy simultaneously. Finally, a deep Q-netwok (DQN) based algorithm is proposed to efficiently solve the optimal set of participants for each iteration. Simulation results show that the proposed method not only significantly improves the accuracy and training speed of FL, but has stronger robustness to resist malicious nodes.

Digital twins are the foundation of autonomous off-road vehicles. Dynamic reduction methods are one of several ways to develop digital twins for off-road vehicles. The article commences with a comprehensive overview of the most widely used dynamic reduction methods and then introduces performance metrics for assessing their efficacies in the context of digital twins. The paper additionally includes a detailed mathematical derivation of the state-space representation for reduced-order finite element models. The state-space representation of the reduced finite element models facilitates their export to problem-solving environments for dynamic analysis. The state-space models are eventually solved utilizing the built-in libraries of numerical solvers in textual and graphical programming platforms. In addition, the article identifies the set of solvers that best suit the simulation of virtual models for off-road vehicles. This article also includes an evaluation of the simulation results of digital models with modes ranging from 0 to 30 Hz. In addition, the article demonstrates the lower bound of the frequency range necessary and sufficient to be retained in off-road vehicle virtual models. Finally, the paper presents the simulation outcomes for digital models of commercial off-road vehicles with custom-built control, electrical, and control systems.

This paper presents an approach to damage identification in beams by modal curvatures based on the use of beamforming algorithms. These processors have been successfully used in acoustics for the last thirty years to solve the inverse problems encountered in source recognition and image reconstruction, based on ultrasonic waves. In addition, beamformers apply to a broader range of problems in which the forward solutions are computable and measurable, especially regarding the field of structural vibrations, where the use of such estimators has not received attention to date. In this paper, modal curvatures will play the role of the replica vectors of the imaging field. By means of numerical studies and experimental tests on a steel beam, we motivate the choice of modal curvatures as observed quantities. Furthermore, we compare the performance of the Bartlett and minimum variance distortionless beamformers (MVDR) with an estimator based on the simple minimization of the difference between model and measured data. The results suggest that the application of the MVDR beamformer is highly effective, especially in cases of slight damage between two sensors. MVDR enabled both damage localization, and quantification.

Like traditional single label learning, multi-label learning is also faced with the problem of dimensional disaster.Feature selection is an effective technique for dimensionality reduction and learning efficiency improvement of high-dimensional data. In this paper, Logistic regression, manifold learning and sparse regularization were combined to construct a joint framework for multi-label feature selection (LMFS). Firstly, the sparsity of the eigenweight matrix is constrained by the $L_{2,1}$-norm. Secondly, the feature manifold and label manifold can constrain the feature weight matrix to make it fit the data information and label information better. An iterative updating algorithm is designed and the convergence of the algorithm is proved.Finally, the LMFS algorithm is compared with DRMFS, SCLS and other algorithms on eight classical multi-label data sets. The experimental results show the effectiveness of LMFS algorithm.

In order to solve the problem of fault diagnosis for CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and ensemble learning model is proposed. First, various monitoring signals including vibration signal, noise signal and current signal are collected. Then, the monitoring signals are preprocessed and the time-domain, frequency-domain and time-frequency domain feature indexes are extracted to construct a multi-dimensional mixed domain feature set. Finally, the feature set is putting into the constructed DoubleEnsemble-LightGBM model to realize the fault diagnosis of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the public data set and the feed system test bench data set, and the average overall accuracy is 91.07% and 98.06% respectively. Compared with XGBoost and other advanced ensemble learning models, the method has better accuracy. It provides technical support for the stable operation and intelligent of CNC machine tools..

We describe a new approach for integrating multiple views of data into a common latent space using non-negative tensor factorization (NTF). This approach, which we refer to as the "Integrated Sources Model" (ISM), consists of two main steps: embedding and analysis. In the embedding step, each view is transformed into a matrix with common non-negative components. In the analysis step, the transformed views are combined into a tensor and decomposed using NTF. Noteworthy, ISM can be extended to process multi-view data sets with missing views. We illustrate the new approach using two examples: the UCI digit dataset and a public cell type gene signatures dataset, to show that multi-view clustering of digits or marker genes by their respective cell type is better achieved with ISM than with other latent space approaches. We also show how the non-negativity and sparsity of the ISM model components enable straightforward interpretations, in contrast to latent factors of mixed signs. Finally, we present potential applications to single-cell multi-omics and spatial mapping, including spatial imaging and spatial transcriptomics, and computational biology, which are currently under evaluation. ISM relies on state-of-the-art algorithms invoked via a simple workflow implemented in a Jupyter Python notebook.

Precise monitoring of different environmental parameters and contaminations during food processing and storage is a key factor for maintaining its safety and nutritional value. Thus, developing reliable, efficient, cost-effective sensor devices for these purposes is of utmost importance. In this paper, we show that Poly-(diallyl-dimethylammonium chloride)/reduced Graphene oxide (PDAC/rGO) films produced by a simple Layer-by-Layer deposition can be effectively used to monitor temperature, relative humidity and the presence of volatile organic compounds as indicators for spoilage odors. At the same time, they show potential for electrochemical detection of organophosphate pesticide dimethoate. By monitoring the resistance/impedance changes during temperature and relative humidity variations or upon the exposure of PDAC/rGO films to methanol, good linear responses were obtained in the temperature range of 10-100 °C, 15-95 % relative humidity, and 35 ppm - 55 ppm of methanol. Moreover, linearity in the electrochemical detection of dimethoate is shown for the concentrations in the order of 102 µmol dm−3. The analytical response to different external stimuli and analytes depends on the number of layers deposited, affecting sensors’ sensitivity, response and recovery time, and long-term stability. The presented results could serve as a starting point for developing advanced multimodal sensor devices and sensor arrays with high potential for analytical applications in food safety and quality monitoring.

In response to the issue of vehicle escape guidance, this manuscript proposes a unified intelligent control strategy synthesizing optimal guidance and Meta Deep Reinforcement Learning (DRL). Optimal control with minor energy consumption is introduced to meet terminal latitude, longitude and altitude. Maneuvering escape is realized by adding longitudinal and lateral direction maneuver overloads. Maneuver command decision model is calculated based on Soft-Actor-Critic (SAC) networks. Meta learning is introduced to enhance autonomous escape capability, which improves generalization performance to time-varying scenarios not encountered in the training process. In order to obtain training samples at a faster speed, this manuscript uses the prediction method to solve reward values, which avoiding a large number of numerical integration. The simulation results manifest that the proposed intelligent strategy can achieve high precise guidance and effective escape.

An electrocardiograph (ECG) reflects the health of the human heart and is used to help diagnose arrhythmia and myocardial infarction(MI) in clinical practice. Early diagnosis of arrhythmia helps implement preventive measures and plays a crucial role in saving a patient's life. With the increasing demand of clinicians for ECG analysis technology, intelligent detection and diagnosis of ECG signals has become a more efficient means to assist physicians in diagnosing cardiovascular diseases. This paper introduces an ECG diagnosis approach based on an ensemble deep learning combination of CNN(convolutional neural network) and SLAP(stacked-long short term memory architecture for prediction) architecture. ECG data is denoised and further divided into single heartbeats to achieve data standardization and sample diversity. Adam optimizer and BCEwithlogitsloss multi-classification loss function were used to enhance the model effect, and the system achieved the classification effect of 99.3% average accuracy, 99.0% F1-value, and 99.2% sensitivity in MIT-BIH standard database classification. It also shows good generalization ability on the Tianchi data set.

Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single-source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi-source domain called adaptive multi-source domain collaborative fine-tuning to address this issue. This approach utilizes multiple source domain models for collaborative fine-tuning, thereby improving the model's feature extraction capability in the target task. Specifically, this approach employs an adaptive multi-source domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models. The objective is to extract more efficient features. Furthermore, a novel multi-source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of the proposed the adaptive multi-source domain collaborative fine-tuning framework, it is analyzed and compared with the most widely used fine-tuning methods by applying them to seven publicly available visual categorization datasets commonly employed in transfer learning. Experimental results demonstrate that, in comparison with the existing fine-tuning approaches, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, resulting in state-of-the-art performance.

A heterogeneous disease like cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), patients’ survival vary significantly and show different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score. We observed that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we also compared the effect of feature selection and similarity measures for subtype detection. To evaluate the results obtained, we selected the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes identified by the autoencoders; the obtained results coincide well with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

In recent years, intelligent identification and prediction of ore deposits based on deep learning algorithm and image processing technology has gradually become one of the research frontiers in the field of geological and metallogenic prediction. However, this method also has many problems that need to be solved. For example, (1) very few trainable image samples containing mineral point labels; (2) The geological image features are small and irregular, and the image similarity is high; (3) It is difficult to calculate the influence of different geological prospecting factors on ore mineralization. Based on this, this paper constructs a deep learning network model Multiscale Feature Attention Framework (MFAF) based on geo-image data. The results show that MFCA-Net module in MFAF model can solve the problem of scarce mine label images to a certain extent. In addition, the channel attention mechanism SE-Net module can quantify the difference of influence of different source factors on mineralization. The prediction map is obtained by applying the MFAF model in the study of deposit identification and prediction in the research area of the southern section of Qin-hang metallogenic Belt. In the forecast map, many regions have high metallogenic potential. Through observation, it is found that the above predicted area covers 100% of the known ore deposits at present, which has a good prediction effect. Later, we can find out the specific reasons through field verification. The multi-scale feature fusion and attention mechanism MFA Framework in this paper can provide a new way of thinking for geologists in mineral exploration. The research of this paper also provides resource guarantee and technical support for the sustainable exploitation of mineral resources and the sustainable growth of society and economy.

The devastating COVID-19 pandemic forced academia to go virtual. Educational institutions around the world have stressed online learning programs in the aftermath of the pandemic. However, because of insufficient access to ICT, a substantial number of students failed to harness the opportunity of online learning. This study explores the latent digital divide exhibited during the COVID-19 pandemic while online learning activities are emphasized among Bangladeshi students. It also investigates the digital divide exposure and the significant underlying drivers of the divide. A cross-sectional survey was employed to collect quantitative data mixed with open-ended questions to collect qualitative information from the student community. The findings revealed that despite the majority of students have physical access to ICT but only 32.5% of students could attend online classes seamlessly, 34.1% of the students reported the data prices as the critical barrier, and 39.8% of students identified the poor network infrastructure is the significant barrier for them to participate in online learning activities. Although most students possess physical access to the device and the Internet, they face the first-level digital divide due to the quality of access and maintaining subscriptions. Consequently, they fail to take advantage of physical access, resulting in the third-level digital divide (Utility Gap) and submerging them into a digital divide cycle. This paper aimed to explore the underlying issues of the digital divide among Bangladeshi students to assist relevant stakeholders (e.g., the Bangladesh government, Educational Institutions, Researchers) in providing the necessary insights and theoretical understanding to arrange adequate support for students to undertake conducive online learning activities.

The ANSYS 2024R1 student edition was used to create a finite element model of a basketball rim and backboard. This finite element model included the use of steel for the rim and its mount, a tempered glass backboard, and an aluminum frame behind the backboard. After a mesh was created, fixed support boundary conditions were applied to the four corners of the aluminum frame. The subsequently calculated mode shapes and frequencies were compared to empirical modal analysis previously done at the United States Military Academy at West Point, New York. Four mode shapes and frequencies agreed rather well between the theoretical finite element analysis and previously published empirical modal analysis, specifically where the rim was vibrating in the vertical direction, which was the direction that the accelerometer was aligned for modal analysis. However, three mode shapes missed by the empirical modal analysis were found where the vibration of the rim was confined to the horizontal plane, which was orthogonal to the orientation of our accelerometer.

The need for cross-modal retrieval (CMR) among users is growing because of the swift advancements in computer vision and natural language processing. Promoting home operating systems is greatly aided by the openKylin home operating system. It is focused on enhancing the functionality of the operating system with safe and dependable operating technologies. Practical implications abound for integrating computer vision research into home operating systems. A multimodal retrieval approach based on openKylin is presented to improve the usability of text search graphs, audio, and video. The overview of pertinent domestic and international research is the main topic of this article. This technological advancement. It then offers details on the design, implementation procedure, and final implementation outcomes for demonstration. The works of natural operations show that this strategy has excellent accuracy and performance.

Six mode shapes, including bending and torsion, were documented for five different basketball rims and backboards at the United States Military Academy, West Point, New York, USA. The frequency and damping ratio of each mode shape were also determined. The empirical process began with the time-domain excitation and response of each rim-backboard system. The impulse of excitation came from an impact hammer separately applied to sequentially, to each node. The sinusoidal response was gathered from an accelerometer at a fixed location, node 1. Each time-domain excitation-response was then converted to a frequency domain Bode plot for each node by a B&K 2034 Signal Analyzer, giving transfer functions of output/input versus frequency. Structural Measurements System (SMS) Software was used to fit mode shapes to the Bode plots. Each of the six mode shapes were fitted to the Bode plots of each node at a specific modal frequency. Each of the six mode shapes were a function of the locations of the nodes, and the Bode plot gathered at each node. The first and second modes were critical for showing that the Energy Rebound Testing Device statistically correlated with the energy transferred to the rim and backboard. A known perturbation mass was selectively attached to the rim, to help isolate the dynamic masses and spring rates for the rim and backboard, to ascertain the kinetic energy transferred to the rim had a 95.67% inverse correlation with rim stiffness.

In this work we discuss the numerical challenges involved in the computation of the complex eigenvalues of damped multi-flexible-body problems. Aiming at the highest generality, the candidate method must be able to deal with arbitrary rigid body modes (free-free mechanisms), arbitrary algebraic constraints, and must be able to exploit the sparsity pattern of Jacobians of large systems. We propose a custom implementation of the Krylov-Schur method, proving its robustness and its accuracy in a variety of different complex test cases.

Ever-increasing need for improving the livability of a city and improve outcomes for its residents, over the last decade, the adoption of technology to develop urbanised societies around the world has given rise to the need for developing smart cities. The speed at which the world population is growing, the use of Internet of Things in smart cities have really advanced the quality of life. One significant area of concern within the smart city framework is waste management. If the waste within a city is not adequately managed, then it leads to issues in the health of the citizens. Additionally, the waste management has such a high impact on the environmental footprint, hence the need to have a smart way of managing waste is of critical importance. Through our research, we analyse the challenges of waste management within a city to understand the impact of the problem on to the citizens and overall city operations. We then investigate ways in which we can solve these problems using the emerging technologies, such as the Internet of Things, to collect valuable data of large volumes arriving at an astronomical rate, then apply multi-agent deep reinforcement learning algorithms to harness the power of big data to extract meaningful information and actionable insights. We ingest data generated by our Internet of Things into our algorithm for three main purposes including providing the notifications to an external system, for example, a map navigation engine out of the scope for this project but a future extension for route optimisation and waste vehicle tracking; extracting and reporting the actionable insights from the underlying data; and consuming the extracted data for predictive forecasting to draw out the unknown patterns of waste fill levels within various geographical locations and again send out triggers and notification to external systems for example a waste collection authority who can efficiently schedule the waste collection vehicles and optimise the route. To achieve the above mentioned outcomes, we propose a framework that is agnostic of the hardware that it connects to and can effectively interface with a wide variety of hardware keeping a level of abstraction in the architecture.

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverages a high-resolution Convolution neural network (CNN) to extract texture information from images. For the feature maps from three different scales produced by the backbone network, each branch performs the coordinate attention operations. The feature maps are then spatially and channel-wise flattened, combined with keypoint tokens generated through random initialization, and fed into a parallel Transformer structure to learn spatial dependencies between features. As the Transformer outputs one-dimensional sequential features, the mainstream two-dimensional heatmap method is abandoned in favor of one-dimensional coordinate vector regression. The experiments show that MSTPose outperforms other CNN-based pose estimation models and demonstrates clear advantages over CNN + Transformer networks of similar types.

In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non-iid data, a challenge not adequately tackled by the commonly used MFedAvg method. Additionally, one of the key innovations of this research is the introduction of uniformity, a metric that quantifies the disparity in training time amongst participants in a federated learning setup. This novel concept not only aids in identifying stragglers but also provides valuable insights into assessing the fairness and efficiency of the system. Experimental results underscore the merits of the integrated multi-branch network with the Oort client selection algorithm and highlight the crucial role of uniformity in designing and evaluating federated learning systems.

In recent years, the viability of employing multi-agent reinforcement learning technology for adaptive traffic signal control has been extensively validated. However, owing to restricted communication among agents and the partial observability of the traffic environment, the process of mapping road network states to actions encounters numerous challenges. To address this problem, this paper proposes a multi-agent deep reinforcement learning model with an emphasis on communication content (CMARL). The model decouples the complex relationships between multi-signal agents through centralized training and decentralized execution. Specifically, we first pass the traffic state through an improved deep neural network to achieve the extraction of high-dimensional semantic information and the learning of the communication matrix. Then the agents selectively interact with each other based on the learned communication matrix and generate the final state features. Finally, the features are inputted to the QMIX network to achieve the final action selection. We compare the CMARL model with 6 other baseline algorithms in real traffic networks. The results show that CMARL can significantly reduce vehicle congestion, and run stably in various scenarios.

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well-informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs, through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first application of policy graphs in the context of explaining agent behaviour in collaborative multi-agent scenarios and presents experimental results that sets this kind of scenario apart from previous application in single-agent scenarios: when requiring collaborative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one is designed using a Jetson TX or AGX Xavier, and the other is based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-art deep-learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep-learning-based association metric approach (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep-learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

The utilization of smart IoT devices, commonly referred to as digital twins, is aimed at the digitalization of human knowledge within aquaculture processes. This involves the incorporation of cutting-edge technologies, including information-based management with big data and modeling, to automate machinery and gain comprehensive insights into the aquaculture environment and fish farm conditions. The ultimate objective is to empower farmers to make informed decisions, furnishing them with objective data to enhance their capacity in monitoring and controlling the various factors impacting fish production. As a result, farming decisions can be fine-tuned to enhance fish health and optimize farm output. In the context of large and modern aquaculture farms, technological innovation becomes imperative to automate processes, minimize labor requirements, and streamline fish feeding operations. Remarkably, the literature currently offers limited discussions on the digital transformation of aquaculture through the application of digital twin methodologies. A prior study underscores the critical influence of factors such as market prices and fish survival rates on the profitability of offshore caging culture. In this study, we embark on an analysis of the prerequisites for establishing a digital twin infrastructure tailored to intelligent fish feeding management. This infrastructure is designed to facilitate the integration of technology and data-driven decision-making, ultimately enhancing the efficiency of fish feeding processes. The proposed architecture for the fish feeding digital twin encompasses various digital twin components, encompassing water quality forecasting, fish population assessment, fish metrics estimation, fish feed prediction, and evaluation of fish feeding intensity. Furthermore, we optimize the daily fish feeding process through reinforcement learning algorithms. Finally, we implement a cloud-based AIoT system that provides the runtime environment for executing digital twins and controlling our intelligent fish feeding machinery. Experimental findings underscore the efficacy of the proposed digital twin system in significantly improving traditional fish feeding processes, notably in terms of reducing food costs and labor requirements.

Fabry-Pérto (FP) cavity is the essential component of ultra-stable laser (USL) for gravitational wave detection, which couples multi-physic (Optical/Thermal/Mechanics) fields and requires ultra-high precision. To satisfy the requirements of precise and efficient design, a multi-physic coupling optimization method for fixing cubic FP cavity based on data learning is proposed. A multi-physic model for the cubic FP cavity is established and the performance is obtained by finite element analysis. The key performance indices (V, wF, wF) and key design variables (d, l, F) are determined considering the features of the FP cavity. The 49 sets of data by orthogonal experiment are acquired for the establishment and comparison of different data learning models (NN, RSF, KRG). The result turns out that the neural network has the best performance. Based on NSGA-II, the Pareto optimal front is obtained and the optimal combination of design variables is finally determined as {5,32,250}. The performance after optimization has proven to be a great improvement, of which the displacement under the fixing force and vibration test are decreased by more than 60%. The optimization strategy can not only help the design of the FP cavity but also enlighten other optimization fields.

The classical approach to non-linear regression in physics, is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then, using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterised by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built-in the models to compensate for the impossibility of modeling things that are, by construction, impossible to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here the MTL architecture allows predicting multiple parameters, the oxygen concentration and the temperature, from a single set of measurements.

In order to reduce the vibration of the transporter and improve the stability of the transporter, the vibration characteristics and key structure optimization research of the mountain orchard transporter are carried out. In this paper, the vibration of electric monorail transporters under different working conditions is tested, and the causes of vibration generated by monorail transporter during operation are explored. The three-dimensional model of the trailer and transmission box is established using Solidworks, and the modal vibration modes of the structure are analyzed theoretically. The modal test system is used for modal test analysis of trailers and transmission boxes. By comparing the results of finite element and experimental modal analysis, the second-order frequency of the trailer is close to the motor's rotating excitation frequency of 50 Hz at rated speed, which is easy to generate resonance. By optimizing the structure of the trailer, the second and third natural frequencies are increased to 54.79 Hz and 58.35 Hz respectively, which avoid the resonance of the trailer during operation and effectively reduce the vibration generated during the transportation of the trailer. Through vibration testing of the optimized electric monorail transporter, the results of vibration testing before and after structural optimization are compared and analyzed, and it is found that the vibration amplitudes of the transporter in X, Y and Z directions are reduced by 0.308m/s², 0.351m/s² and 0.334m/s² respectively, the running stability of the conveyer is improved.

Recently deep cross-modal hashing networks have received increasing interests due to its superior query efficiency and low storage cost. However, most of existing methods concentrate less on hash representations learning part, which means the semantic information of data cannot be fully used. Furthermore, they may neglect the high-ranking relevance and consistency of hash codes. To solve these problems, we propose a Self-Attention and Adversary Guided Hashing Network (SAAGHN). Specifically, it employs self-attention mechanism in hash representations learning part to extract rich semantic relevance information. Meanwhile, in order to keep invariability of hash codes, adversarial learning is adopted in the hash codes learning part. In addition, to generate higher-ranking hash codes and avoid local minima early, a new batch semi-hard cosine triplet loss and a cosine quantization loss are proposed. Extensive experiments on two benchmark datasets have shown that SAAGHN outperforms other baselines and achieves the state-of-the-art performance.

A systematic approach for model updating using the modal identification results is proposed. Modal identification provides mode shapes for physical quantities (acceleration strain, etc.) measured in specific directions at the location of the sensors. Besides, model updating involves the use of the mode shapes related to the nodal degrees-of-freedom of the finite element analytic model. Consequently, the mode shapes obtained by modal identification and the mode shapes of the model updating process do not coincide even for the same mode. Therefore, a method constructing transform matrices that distinguish the cases where measurement is done by acceleration, velocity and displacement sensors and the case where measurement is done by strain sensors is proposed to remedy such disagreement between the mode shapes. The so-constructed transform matrices are then applied when the mode shape residual is used as objective function or for mode pairing in the model updating process. The feasibility of the proposed approach is verified by means of a numerical example in which the strain or acceleration of a simple beam is measured and a numerical example in which the strain of a bridge is measured. Using the proposed approach, it is possible to model the structure regardless of the position of the sensors and to select the location of the sensors independently from the model.

Aim: To determine whether an AI model and single sensor measuring acceleration and ECG could model cognitive and physical fatigue for a self-paced trail run. Methods: A field-based protocol of continuous fatigue repeated hourly induced physical (~45 minutes) and cognitive (~10 minutes) fatigue on one healthy participant. Physical load was a 3.8 km, 200 m vertical gain, trail run with acceleration and electrocardiogram (ECG) data collected using a single sensor. Cognitive load was a Multi Attribute Test Battery (MATB) and separate assessment battery including the Finger Tap Test (FTT), Stroop, Trail Making A and B, Spatial Memory, Paced Visual Serial Addition Test (PVSAT), and a vertical jump. A fatigue prediction model was implemented using a Convolutional Neural Network (CNN). Results: When the fatigue test battery results were compared for sensitivity to the protocol load, FTT right hand (R2 0.71) and Jump Height (R2 0.78) were the most sensitive while the other tests were less sensitive (R2 values Stroop 0.49, Trail Making A 0.29, Trail Making B 0.05, PVSAT 0.03, spatial memory 0.003). Best prediction results were achieved with a rolling average of 200 predictions (102.4 s), during set activity types, mean absolute error for ‘walk up’ (MAE200 12.5%) and range of absolute error for ‘run down‘ (RAE200 16.7%). Conclusion: We were able to measure cognitive and physical fatigue using a single wearable sensor during a practical field protocol including contextual factors in conjunction with a neural network model. This research has practical application to fatigue research in the field.

The deployment of Artificial Intelligence (AI) systems in decentralized environments is on the rise, yet representation of shared conceptualization in such scenarios remains a challenging issue. The absence of a shared understanding can lead to suboptimal performance of AI systems and hinders the ability to comprehend the knowledge and beliefs of agents in the domain. This paper proposes a formal model for modeling conceptualization in AI systems that integrates ontology, epistemology, and epistemic logic. The model aims to address the gap in representing shared conceptualization in decentralized environments and enhance the performance of AI systems operating in such environments. The proposed model is a hybrid structure that blends extensional and intensional structures and leverages logic-based languages for modeling purposes. A case study in the healthcare sector is presented to illustrate the application of the proposed model. The study contributes to the existing literature by providing a formal model for representing shared conceptualization in decentralized environments, which can be utilized to optimize the performance of AI systems in these environments.

In this article authors shows chosen problems of technical state diagnosis with the use of identification and technical diagnostics methods such as experimental modal analysis. Relations between methods of dynamic state evaluation and methods of technical state evaluation were indicated. Example modal analysis results illustrate the complexity of projecting dynamic state researches into diagnostic researches of state evaluation.

The generation of vortices around bridge piers can lead to removal of riverbed materials from around piers, especially during flood events and heavy rainfalls, which can compromise the stability of the bridge and consequently its failure, if not properly detected and mitigated. Bridge failures pose serious threats to the local socio-economic and public safety and can cost lives. As such, real-time monitoring and early warning systems for scour-induced bridge failure can serve as a vital tool to protect the community and civil infrastructure against disastrous events. Vibration-base monitoring of bridge scour is an attractive option due to its low cost and relatively easy installation without the need to block the road and close the bridge to traffic. While limited number of previous studies have shown the capabilities of acceleration-based monitoring techniques in this area of research, they generally lack a rigorous framework for data analysis within and relating those to evaluate scour. This paper is an attempt to provide such framework that would enable a fast and low-cost analysis of vibration data within a physical modelling study on a simplified bridge pier. To achieve this, three experiments were conducted on an ideal single-pier scaled model bridge in a hydraulic flume, where water flows at a velocity near the critical velocity for the sand bed which in turn generates a scour hole around the pier. Then, the vibration data recorded using two mounted wireless accelerometers, were used to conduct an operational modal analysis through which the natural frequencies are extracted. The extracted natural frequencies and measured scour depths are then used to provide a chart that relates these two parameters. The results of this study showed the promising capability of the vibration-based data analysis in finding this relationship, indicating an up to around 30-50% reduction in natural frequencies as a result of around 50% scour ratio (ratio of maximum scour depth to buried depth), and beyond 50% scour ratio the natural frequencies remain constant. While the data presented in this paper are preliminary, they clearly show a promising potential for application in real-time monitoring of bridge stability under the effect of local scour and further works are underway to enrich the experimental data and empower the proposed methodologies at the laboratory scale.

Visual question answering (VQA) is receiving increasing attention from researchers in both the computer vision and natural language processing fields. There are two key components in the VQA task: feature extraction and multi-modal fusion. For feature extraction, we introduce a novel co-attention scheme by combining Sentence-guide Word Attention (SWA) and Question-guide Image Attention (QIA) in a unified framework. To be specific, the textual attention SWA relies on the semantics of the whole question sentence to calculate contributions of different question words for text representation. For the multi-modal fusion, we propose a “Cross-modal Multistep Fusion (CMF)” network to generate multistep features and achieve multiple interactions for two modalities, rather than focusing on modeling complex interactions between two modals like most current feature fusion methods. To avoid the linear increase of the computational cost, we share the parameters for each step in the CMF. Extensive experiments demonstrate that the proposed method can achieve competitive or better performance than the state-of-the-art.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

The central goal of few-shot scene classification is to learn a model that can generalize well to a novel scene category (UNSEEN) from only one or a few labeled examples. Recent works in the remote sensing (RS) community tackle this challenge by developing algorithms in a meta-learning manner. However, most prior approaches have either focused on rapidly optimizing a meta-learner or aimed at finding good similarity metrics while overlooking the embedding power. Here we propose a novel Task-Adaptive Embedding Learning (TAEL) framework that complements the existing methods by giving full play to feature embedding’s dual roles in few-shot scene classification - representing images and constructing classifiers in the embedding space. First, we design a lightweight network that enriches the diversity and expressive capacity of embeddings by dynamically fusing information from multiple kernels. Second, we present a task-adaptive strategy that helps to generate more discriminative representations by transforming the universal embeddings into task-specific embeddings via a self-attention mechanism. We evaluate our model in the standard few-shot learning setting on two challenging datasets: NWPU-RESISC4 and RSD46-WHU. Experimental results demonstrate that, on all tasks, our method achieves state-of-the-art performance by a significant margin.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

Generative models have recently gained popularity in Remote Sensing, offering substantial benefits for interpreting and utilizing satellite imagery across diverse applications such as climate monitoring, urban planning, and wildfire detection. These models are particularly adept at addressing the challenges posed by satellite images, which often exhibit domain variability due to seasonal changes, sensor characteristics, and especially variations in spectral bands. Such variability can significantly impact model performance across various tasks. In response to these challenges, our work introduces a novel approach that harnesses the capabilities of Generative Adversarial Networks (GANs), augmented with Contrastive Learning, to generate target domain images that account for multi-spectral band variations effectively. By maximizing mutual information between corresponding patches and leveraging the power of GANs, our model aims to generate realistic-looking images across different multi-spectral domains. We present a comparative analysis of our model against other well-established generative models, demonstrating its efficacy in generating high-quality satellite images while effectively managing domain variations inherent to multi-spectral diversity.

In this study, a matched-mode autoregressive source depth estimation method (MMAR) based on autoregressive (AR) wavenumber estimation is proposed for a moving source in shallow water waveguides. The signal original frequency and the environmental parameters, namely, the sound speed profile and bottom properties are known as a prior knowledge. The mode wavenumbers are estimated by the AR modal wavenumber spectrum. On the basis of the mode wavenumber estimation, the mode amplitudes can be estimated by the wavenumber spectrum that is obtained by generalized Hankel transform. The source depth estimation is determined by the peak of source depth function wherein the data mode best matches the replica mode that is calculated using a propagation model. Compared with other methods of moving source depth estimation, the proposed method exhibits a better performance in source depth estimation under low signal-to-noise ratio or the small range span. The selection of horizontal line array depth is illustrated by simulation and normal mode theory in details.

Multi-Faith Spaces (MFS) are a relatively recent invention that quickly gained in significance. On the one hand, they offer a convenient solution for satisfying needs of people with diverse beliefs in the institutional context of hospitals, schools, airports, etc. On the other hand, as Andrew Crompton pointed out, they are politically significant because the multi-faith paradigm “is replacing Christianity as the face of public religion in Europe” (2012, p. 493). Due to their ideological entanglement, MFS are often used as the means to promote either a more privatised version of religion, or a certain denominational preference. Two distinct designs are used to achieve these means: negative in the case of the former, and positive in the latter. Neither is without problems, and neither adequately fulfils its primary purpose of serving diverse groups of believers. Both, however, seem to follow the biases and main problems of secularism. In this paper, I analyse recent developments of MFS to detail their main problems and answer the question, whether the MFS, and the underlying Multi-Faith Paradigm, can be classified as a continuation of secularism.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Multi-channel and multi-parameter near-infrared spectrometers (NIRS) have gradually become a new research direction and hot spot due to their ability to provide real-time, continuous, comprehensive indicators of multiple parameters. However, multi-channel and multi-parameter detection may lead to crosstalk between signals. There is still a lack of benchmarks on the evaluation of reliability, sensitivity, stability and response consistency of the NIRS instrument. In this study, a set of test methods (the ink drop test, multi-channel crosstalk test and multi-parameter crosstalk test) for analysis crosstalk and verifying the reliability of NIRS were conducted to test experimental verification on a multi-channel (8-channel), multi-parameter (4-parameter) NIRS instrument independently developed by our team. Results show that these tests can be used to analyze the signal crosstalk and verify the reliability, sensitivity, stability and response consistency in the NIRS instrument. This study contributes to the establishment of benchmarks for the NIRS instrument crosstalk and reliability testing. These novel tests have the potential to become the benchmark for the NIRS instrument reliability testing.

The progressive impairment analysis in gait from neurological diseases patients such as Hereditary Ataxias (HA) has been carried out using gait data collected with movement sensors. This research is focused on finding the minimum amount required of gait features to recognize efficiently and less intrusive way, HA patients based on data collected with iPhone movement sensors placed on the ankles from 14 HA patients and 14 healthy people. A twofold proposal is made , first a local minimum prominent peak criterion to find out the starting point of each stride, to get 10-stride window about which 56 spatial-temporal features are derived; second a search strategy based on Hill Climbing algorithm to reduce the number of gait features and sensors. The main results were the findings that with two gait patterns a 96% of classification accuracy was achieved by using K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) algorithms, but in addition, MLP only right ankle sensor patterns were required which also allows to reduce the intrusion.

Hypoxic-ischemic encephalopathy (HIE) secondary to perinatal asphyxia occurs when the brain does not receive enough oxygen and blood. A surrogate marker for ‘intact survival’ is necessary for the successful management of HIE. The severity of HIE can be classified based on clinical presentation, including presence of seizures, using a clinical classification scale called Sarnat staging; however, Sarnat staging is subjective and the score changes over time. Furthermore, seizures are difficult to detect clinically and are associated with a poor prognosis. Therefore, a tool for continuous monitoring on the cot side is necessary, for example, electroencephalogram (EEG) that non-invasively measures the electrical activity of the brain from the scalp. Then, multimodal brain imaging, when combined with functional near-infrared spectroscopy (fNIRS), can capture the neurovascular coupling (NVC) status. In this study, we first tested the feasibility of a low-cost EEG-fNIRS imaging system to differentiate between normal, hypoxic, and ictal states in a perinatal ovine hypoxia model. Here, the objective was to evaluate a portable cot side device and autoregressive (ARX) modelling to capture the perinatal ovine brain states during a simulated HIE injury. So, ARX parameters were tested with a linear classifier using a single differential channel EEG, with varying states of tissue oxygenation detected using fNIRS, to label simulated HIE states in a perinatal ovine hypoxia model. Then, we showed the technical feasibility of the low-cost EEG-fNIRS device and ARX modeling with support vector machine classification for a human HIE case series with and without sepsis. The classifier trained with the ovine hypoxia data labelled ten severe HIE human cases (with and without sepsis) as “hypoxia” group and the four moderate HIE human cases as the “control” group. Furthermore, we showed the feasibility of experimental modal analysis (EMA) based on the ARX model to investigate the NVC dynamics using EEG-fNIRS joint-imaging data that differentiated six severe HIE human cases without sepsis from four severe HIE human cases with sepsis. In conclusion, our study showed the technical feasibility of EEG-fNIRS imaging, ARX modeling of NVC for HIE classification, and EMA that may provide a biomarker to detect sepsis effects on the NVC in HIE.

Fibre-reinforced composite structures under complex loads exhibit gradual damage behaviour with a degradation of effective mechanical properties and change of their structural dynamic behaviour. Damage manifests itself as spatial increase of inter-fibre failure and delamination-growth, resulting in local changes of stiffness. These changes affect not only the residual strengths but more importantly the structural dynamic behaviour. In case of composite rotors, this can lead to catastrophic failure if an eigenfrequency coincides with the rotational speed. The description and analysis of the gradual damage behaviour of composite rotors therefore provides the fundamentals for a better understanding of unpredicted structural phenomena. The gradual damage behaviour on the example of composite rotors and the resulting damage-dependent dynamic behaviour is experimentally investigated under propagating damage for combined out-of-plane and in-plane loads. A novel observation is reported, where monotonic increase of damage results in non-monotonic frequency shift of significant amount of eigenfrequencies.

The spread of charging infrastructure (CIS) for battery electric vehicles is crucial for coping with the increasing number of electric vehicles. Therefore, the selection of ideal (fast-) charging locations determines acceptance, utilization and, thus, the economic viability of a single site or the whole charging network. The methodology of the Integrated Model Approach STELLA[1] for site identification of CIS uses proven methods of traffic modeling such as the classic four-step traffic modeling in a new context to enable statements regarding the positioning of CIS. Based on different spatial analyzes and characterizations of urban quarters, traffic generated by individuals is calculated using the FGSV approach of 2010. Because only (electric) motorized individual traffic is of importance for CIS, the share of trips is calculated by differentiating the modal split between various transport groups. One approach is to concretize the modal split share of public transport based on analyzes of different criteria and data sets, e.g. the accessibility of stops. The model approach STELLA, which also combines various extensive data (e.g. transport networks and traffic volumes, settlement structures, vehicle characteristics, power supply data and user requirements), is currently developed for a planning area covering the entire territory of the Federal Republic of Germany. [1] STELLA is the acronym for the German term "STandortfindungsmodell für ELektrische LAdeinfrastruktur”.

Although there are several access control systems in the literature for flexible policy management in multi-authority and multi-domain environments, achieving interoperability &amp; scalability, without relying on strong trust assumptions, is still an open challenge. We present HMBAC, a distributed fine-grained access control model for shared and dynamic multi-authority and multi-domain environments, along with Janus, a practical system for HMBAC policy enforcement. The proposed HMBAC model supports: (a) dynamic trust management between different authorities; (b) flexible access control policy enforcement, defined at domain and cross-domain level; (c) a global source of truth for all entities, supported by an immutable, audit-friendly mechanism. Janus implements the HMBAC model and relies on the effective fusion of two core components. First, a Hierarchical Multi-Blockchain architecture that acts as a single access point that cannot be bypassed by users or authorities. Second, a Multi-Authority Attribute Based Encryption protocol that supports flexible shared multi-owner encryption, where attribute keys from different authorities are combined to decrypt data distributedly stored in different authorities. Our approach was implemented using Hyperledger Fabric as the underlying blockchain, with the system components placed in Kubernetes Docker container pods. We experimentally validated the effectiveness and efficiency of Janus, while fully reproducible artifacts of both our implementation and our measurements are provided.

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc, on raster images. A deep convolutional encoder--decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention'' is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

In recent years, there has been a growing interest in remote sensing image-text cross-modal retrieval due to the rapid development of space information technology and the significant increase in remote sensing image data volume. One approach that has shown promising results in cross-modal retrieval of natural images is the multimodal fusion encoding method. However, remote sensing images have unique characteristics that make the retrieval task challenging. Firstly, the semantic features of remote sensing images are fine-grained, meaning they can be divided into multiple basic units of semantic expression. Additionally, these images exhibit variations in resolution, color, and perspective. Different combinations of basic units of semantic expression can generate diverse text descriptions. These characteristics pose considerable challenges for cross-modal retrieval. To address these challenges, this paper proposes a multi-task guided fusion encoder (MTGFE) based on the multimodal fusion encoding method. The model incorporates three tasks: image-text matching (ITM), masked language modeling (MLM), and the newly introduced multi-view joint representations contrast (MVJRC) task. By jointly training the model with these tasks, we aim to enhance its capability to capture fine-grained correlations between remote sensing images and texts. Specifically, the MVJRC task is designed to improve the model’s consistency in feature expression and fine-grained correlation, particularly for remote sensing images with significant differences in resolution, color, and angle. Furthermore, to address the computational complexity associated with large-scale fusion models and improve retrieval efficiency, this paper proposes a retrieval filtering method. This method achieves higher retrieval efficiency while minimizing accuracy loss. Extensive experiments were conducted on four public datasets to evaluate the proposed method, and the results validate its effectiveness. Overall, this study focuses on remote sensing image-text cross-modal retrieval and introduces the MTGFE model, which combines multimodal fusion encoding with multiple tasks to enhance the model’s ability to capture fine-grained correlations. Additionally, a retrieval filtering method is proposed to improve retrieval efficiency. Experimental results demonstrate the effectiveness of the proposed method.

With the widespread application of Voltage Source Converter (VSC) in the power system with high penetration of renewable resources, the problem of wideband oscillations caused by the interaction between the power converters and the power grid has drawn large attention. This paper presents a new methodology for simplifying the mathematical derivations of the impedance model of VSC. Using the new simplified model, the stability and the spectrum characteristic of the performance of the VSC can be clearly analyzed. The proposed second-order d-q impedance model of the grid connected VSC at presence of PLL, not only mathematically proves that the wideband oscillatory modes always occurs in conjugate pairs, but also deliver a clear vision of the physical essence of the wideband oscillations. The classic modal analysis is executed in the paper to demonstrate the stability and frequency spectral characteristics of the wideband oscillations in the VSC integrated system. The impact of control parameters of the VSC on the wideband oscillatory stability is thouroughly analyzed using the results of the modal analysis. The methodology can be considered a powerful tool for the control design of VSC in the modern power system.

Public transport systems are considered to be a crucial aspect of a sustainable urban development, as they allow more passengers to efficiently travel across an urban area at low environmental and economic costs. Multiple factors can influence the public transport level of service. All take roots in the network structure and the operating regime, i.e. how bus lines are arranged atop the street network and how the service frequency is adjusted to meet urban mobility patterns. This is known as the bus network design problem and has been the subject of several studies. The problem is so challenging that most studies until now resort to strong assumptions such as a static description of the peak hour demand, homogeneous user behavior, and equal trip lengths. Potential effects of different types of user behavior and trip lengths patterns on the user and/or operator cost function have not been investigated whatsoever. Moreover, the existing studies have not considered the effects of the bus network structure on private car users, the level of interactions between the two modes, and the passenger mode choice that depends on the traffic conditions. This paper aims to close this gap and provide a general framework considering multiple trip length patterns, two types of user behavior, and the effects that the bus network structure might have on the traffic performance and passenger mode choice. For modeling different trip length patterns, the proposed approach combines all origin-destination pairs with the same trip length and uses the trip length distribution as an intermediate level of abstraction. As such, it allows to solve the optimal bus network design problem in an analytical way, while considering a more realistic setting including network congestion, mixed traffic, and different mode choice decisions depending on trip lengths and walking preferences. Numerical analysis reveals that both, the user behavior and the trip length patterns, have significant effects on the operator and user cost function. Results show that the probability of choosing any given mode is not constant across the user trip lengths, but follows certain distribution. This distribution is not unique, but varies across the trip length patterns, indicating the importance of modeling the mode choice at the trip length level. Finally, the analysis demonstrates the significance of addressing simplifications made in previous studies.

The paper proposes TOPSIS method for solving multi-objective multi-level programming problem (MO-MLPP) with fuzzy parameters via fuzzy goal programming (FGP). At first, - cut method is used to transform the fuzzily described MO-MLPP into deterministic MO-MLPP. Then, for specific , we construct the membership functions of distance functions from positive ideal solution (PIS) and negative ideal solution (NIS) of all level decision makers (DMs). Thereafter, FGP based multi-objective decision model is established for each level DM for obtaining individual optimal solution. A possible relaxation on decisions for all DMs is taken into account for satisfactory solution. Subsequently, two FGP models are developed and compromise optimal solutions are found by minimizing the sum of negative deviational variables. To recognize the better compromise optimal solution, the concept of distance functions is utilized. Finally, a novel algorithm for MO-MLPP involving fuzzy parameters is provided and an illustrative example is solved to verify the proposed procedure.