The popularity and development of social media has made it more and more convenient to spread rumors, and it has become especially important to detect rumor information from massive amounts of information. Most of the traditional rumor detection methods use content characteristics or propagation structure to mine rumor characteristics, ignoring the fusion characteristics of content and structure and their interaction characteristics. Therefore, a novel rumor detection method based on heterogeneous convolutional networks is proposed. Firstly, this paper constructs a heterogeneous map of joint rumor content and propagation structure to explore the interaction between content and propagation structure during rumor propagation and obtain rumor representation. On that basis, this paper uses the deep residual graph convolutional neural network to construct the content and structure interaction information of the current network propagation model. Finally, this paper uses the two datasets of Twitter15 and Twitter16 to verify the proposed method. Experimental results show that the proposed method has higher detection accuracy than the traditional rumor detection method.

To effectively preserve marine environments and manage endangered species, it is necessary to employ efficient, precise, and scalable solutions for environmental monitoring. Ecoacoustics provides several benefits as it enables non-intrusive, prolonged sampling of environmental sounds, making it a promising tool for conducting biodiversity surveys. However, analyzing and interpreting acoustic data can be time-consuming and often demands substantial human supervision. This challenge can be addressed by harnessing contemporary methods for automated audio signal analysis, which have exhibited remarkable performance due to advancements in deep learning research. This paper introduces a research investigation into developing an automatic computerized system to detect dolphin whistles. The proposed method utilizes a fusion of various resnet50 networks integrated with data augmentation techniques. Through extensive experiments conducted on a publically available benchmark, our findings demonstrate that our ensemble yields significant performance enhancements across all evaluated metrics. The MATLAB/PyTorch source code is freely available at: https://github.com/LorisNanni/

Existing Knowledge Graph (KG) models for commonsense question answering present two challenges: (i) existing methods retrieved entities related to questions from the knowledge graph, which may extract noise and irrelevant nodes, and (ii) lack of interaction representation between questions and graph entities. However, current methods mainly focus on retrieving relevant entities with some noisy and irrelevant nodes. In this paper, we propose a novel Retrieval-augmented Knowledge Graph (RAKG) model, which solves the above issues through two key innovations. First, we leverage the density matrix to make the model reason along the corrected knowledge path and extract an enhanced knowledge graph subgraph. Second, we fuse representations of questions and graph entities through a bidirectional attention strategy, in which two representations fuse and update by Graph Convolutional Network (GCN). To evaluate the performance of our method, we conduct experiments on two widely-used benchmark datasets CommonsenseQA and OpenBookQA. The case study gives insight into findings that the augmented subgraph provides reasoning along the corrected knowledge path for question answering.

Open System Interconnection (OSI) model is the best means to understand the way the internet works and the communication of computers over a network system. It is considered as the standard model for network communication. This article describes the OSI model with an example and provides a brief description of the seven layers of the OSI model.

Selecting the optimal activation function for training deep neural networks has always been challenging because it significantly impacts the neural network’s performance and training speed. At this point, researchers are more likely to employ RELU than other well-known activation functions. After RELU, researchers have proposed many activation functions to improve RELU. None of them was capable of surpassing RELU as their most significant rival. SWISH outperformed RELU in several challenging experiments like classification, object detection, and tracking. Replacing RELU units with SWISH, which improves performance in many tasks. This paper proposed a new activation function surpassing Google’s brain’s SWISH function, Which we named AIF. Experiments indicate that our proposed activation function outperforms SWISH in various tasks.

Acoustic energy mapping provides the functionality to obtain characteristics of acoustic sources, such as: presence, localization, type and trajectory of sound sources. Several beamforming-based techniques can be used for this purpose, however, they rely on the difference of arrival times of the signal at each capture node (or microphone), so it is of major importance to have synchronized multi-channel recordings. A Wireless Acoustic Sensor Network (WASN) can be very practical to install when used for mapping the acoustic energy of a given acoustic environment. However, they are known for having low synchronization between the recordings from each node. The objective of this paper is to characterize the impact of current popular synchronization methodologies as part of the WASN to capture reliable data to be used for acoustic energy mapping. The two evaluated synchronization protocols are: Network Time Protocol (NTP) y Precision Time Protocol (PTP). Additionally, three different audio capture methodologies were proposed for the WASN to capture the acoustic signal: two of them, recording the data locally and one sending the data through a local wireless network. As a real-life evaluation scenario, a WASN was built using nodes conformed by a Raspberry Pi 4B+ with a single MEMS microphone. Experimental results demonstrate that the most reliable methodology is using the PTP synchronization protocol and audio recording locally.

Communication is a key method of expressing one's thoughts and opinions. Amongst many modalities, speech and writing are the most powerful and common forms of human communication. Analysing what and how people think has inherently been an interesting and progressive research domain. This includes bimodal sentiment analysis which is an emerging area in natural language processing (NLP) and has received a great deal of attention in recent years in a variety of areas including social opinion mining, health care, banking, and so on. At present, there are limited studies on bimodal conversational sentiment analysis as it proves to be a challenging area given the complex nature of the way humans express sentiment cues across various modalities. To address this gap, a comparison of the performance of multiple data modality models has been conducted on the MELD dataset, a widely-used dataset for benchmarking sentiment analysis within the research community. Our work then demonstrates the results of combining acoustic and linguistic representations. Lastly, our proposed neural network-based ensemble learning technique is employed over six transformer and deep learning-based models, achieving a State-Of-The-Art (SOTA) accuracy.

We present a Deep Learning generative model specialized to work with graphs with a regular geometry. It is build on a Variational Autoencoder framework and employs Graph convolutional layers in both encoding and decoding phases. We also introduce a pooling technique (ReNN-Pool), used in the encoder, that allows to downsample graph nodes in a spatially uniform and highly interpretable way. In the decoder, a symmetrical un-pooling technique is used to retrieve the original dimensionality of graphs. Performance of the model are tested on the standard Sprite benchmark dataset, a set of 2D images of video game characters, adequately transforming images data into graphs, and on the more realistic use-case of a dataset of cylindrical-shaped graph data that describe the distributions of the energy deposited by a particle beam in a medium.

In the modern world where research is taking a huge leap, the collaboration network between authors is also expanding, increasing the probability of different authors coming together to work on the same project, same research paper making them co-authors. In coauthorship, link prediction is used to anticipate new interactions between its members that are likely to occur in the future. Researchers have concentrated their efforts on studying and suggesting methods for providing effective reviews for authors who can collaborate on a scientific endeavor. In order to provide a precise link prediction, a graph database approach is proposed in this paper using nodes to determine most possible co-authors in future. In order to forecast the connections, we preprocessed the data set for the maximum relative contents. A supervised learning approach is used to execute the solution, which includes random forest classifier and logistic regression. The first findings of our technique reveal that the total of two author node’s research collaboration indices has the greatest influence on the performance of supervised link prediction than that of the traditional approach, which stimulates us to conduct further study on employing such a forecast.

Abstract: Background: Pain management is one of the main parts of treatments for Temporomandibular Disorders (TMDs). However, there is still a lack of high-quality evidence that compare the overall effects of these non-surgical treatments. The objective of this systematic review is to identify the most potential treatment protocol in dealing with pain caused by TMDs through a mixed comparison of interventions based on network meta-analysis. Methods: A systematic review and network meta-analysis of studies identified by searching PubMed, Embase, Medline, Ovid, and CINAHL. All the included studies should have characteristics that: (1) participants with TMDs of any age; (2) non-surgical treatments; (3) score of Visual Analog Scale (VAS) as the outcome measure; (4) randomized controlled trials. The Cochrane Bias Assessment Toll was used to assess the bias, the CINeMA website was applied to rate the confidence of evidence, and ADDIS software was used to conduct the network meta-analysis. Results: 46 studies were included in this review. The agreement between authors reached a kappa value of 0.78. The results of the network meta-analysis showed that wearable therapy devices are more likely to be the best choice for reducing the pain of patients with myogenic TMDs, whereas a combination of platelet-rich plasma injection and wearable therapy devices is more likely to be the best choice for reducing the pain in a long term after treatment for patients with mix-type TMDs. Moreover, the application of therapy equipment has the most potential in reducing pain in a long term after treatment for patients with articular TMDs. Discussion: Wearable devices have a great potential for pain syndrome caused by TMDs, the mechanism might come from a biomechanical perspective. However, the overall confidence rating of evidence is low. Studies with high quality are still needed in the future. Other: The PROSPERO Registration Number of this systematic review is CRD42021253442.

A correctly obtained Land-use/land-cover (LULC) prediction map is essential to under-standing and assessing future patterns. In the study, the LULC map of Urmia/Iran in 2030 was produced using two different prediction methods CA-Markov and Artificial Neural Network (ANN). In general, the study followed a methodology consisting of three steps. In the first steps, Landsat satellite images acquired in 2000, 2010 and 2020 were classified with maximum likelihood algorithm and LULC maps were prepared for each year. In the second stage, to investigate the LULC prediction methods' validation (CA-Markov and ANN) the LULC prediction map of 2020 was produced using the LULC map of 2000 and 2010; In this step, the predicted LULC map of 2020 and the actual LULC map of 2020 were evaluated by correctness, completeness and quality indexes. Finally, The LULC map for 2030 was prepared using all two algorithms and the change map was extracted. The results show that the area of soil and vegetation decreased, and built-up regions increased during the research period. The methods validation results show that the two algorithms are much closer to each other. Nevertheless, in general, ANN has the highest completeness (96.21%) and quality (93.8%) and CA-Markov the most correctness (96.47). This study shows that the CA-Markov algorithm is most successful in predicting the future that had larger areas and a higher percentage in the region (urban and vegetation cover) and the ANN algorithm in predicting phenomena that had smaller levels with fewer percentages (soil and rock).

Building a widely distributed hotspot network is a very tedious task due to its complexity. Providing security, fully distributed network services, and cost-conscious impact are the major challenges behind this goal. To overcome these issues, we have presented a novel distributed hotspot network architecture with five layers that can provide large-scale hotspot coverage as an assimilated result. Our contributions to this new architecture highlight important aspects. First, scalability can be increased by including many Internet-of-Things (IoT) devices with sensors and Wi-Fi and/or LoraWAN connectivity modules. Second, hotspot owners can rent out their hotspots to create a distributed hotspot network in which the hotspots can act as an ordinary data gateway, a full-fledged hotspot miner, and a lightweight hotspot miner to earn crypto tokens as rewards for certain activities. Third, the advantages of Wi-Fi and LoraWAN can be seamlessly leveraged to achieve optimal coverage, higher network security, and suitable data transmission rate for transferring sensor data from IoT devices to remote application servers and users. Fourth, blockchain is used to enhance the decentralized behavior of the architecture presented here by providing immutability and independence from a centralized regulator and making the network architecture more reliable and transparent. The main feature of our paper is the use of the tau-computing paradigm along with hotspots to improve availability, Internet backhaul-agnostic network coverage, and synchronous update capability, and tau-aware leasing to strengthen and improve coverage. We also discuss the key challenges and future roadmap that require further investment and deployment.

Since the process of waste recycling generates dust and flammable gas during fragmentation, there is always a risk of fire resulting therefrom, and fire does, in fact, frequently occur. However, research on disaster management at recycling facilities deals only with the problem of processing systems from a technical point of view, but it does not suggest concrete alternatives from a management point of view. Therefore, in this study, we analyzed the influence of the disaster response network of a waste recycling center at the organizational level based on the concept of the cognitive accuracy of a network when considering administrative aspects. Through this analysis, we confirmed that factors affecting the influence of the network exist, such that the entire network and the networks of different levels of position are different. We suggest that this can be improved by deploying members who perform formal tasks at the center of the network so that everyone can agree political approach.

This work attempts to answer in a clear way the following key questions regarding the optimal initialization of the Sysmon tool, towards the identification of Lateral Movement in the MS Windows ecosystem. First, from an expert’s standpoint and with reference to the relevant literature, what are the criteria of determining the possibly optimal initialization features of the Sysmon’s event monitoring tool, which are also applicable as custom rules within the config.xml configuration file? Second, based on the identified features, how can a functional configuration file, able to identify as many LM variants as possible, be generated? To answer these questions, we relied on the MITRE ATT&CK knowledge base of adversary tactics and techniques, and focused on the execution of the nine commonest LM methods. The conducted experiments, performed on a properly configured testbed, suggested a great number of interrelated networking features, that were implemented as custom rules in the Sysmon’s config.xml file. Moreover, by capitalizing on the rich corpus of the 870K Sysmon logs collected, we create and evaluate in terms of TP and FP rates an extensible Python .evtx file analyzer, dubbed PeX, which can be used towards automatizing the parsing and scrutiny of such voluminous files. Both the .evtx logs dataset and the developed PeX tool are provided publicly for further propelling future research in this interesting and rapidly evolving field.

Antibodies constitute a major component of serum on protein mass basis. We also know that the structural diversity of these antibodies exceeds that of all other proteins in the body and they react with an immense number of molecular targets. What we still cannot quantitatively describe is, how antibody abundance is related to affinity, specificity and cross reactivity. This ignorance has important practical consequences: we also do not have proper biochemical units for characterizing polyclonal serum antibody binding. The solution requires both a theoretical foundation, a physical model of the system, and technology for the experimental confirmation of theory. Here we argue that the quantitative characterization of interactions between serum antibodies and their targets requires systems-level physical chemistry approach and generates results that should help create maps of antibody binding landscape.

Bearings are widely used in various types of electrical machinery and equipment. As their core components, failures will often cause serious consequences . At present, most methods of parameter adjustment are still manual adjustment of parameters. This adjustment method is susceptible to prior knowledge and easy to fall into the local optimal solution, failing to obtain the global optimal solution and requires a lot of resources.Therefore, this paper proposes a new method of bearing fault diagnosis based on wavelet packet transform and convolutional neural network optimized by simulated annealing algorithm.The experimental results show that the method proposed in this paper has a more accurate effect in feature extraction and fault classification compared with traditional bearing fault diagnosis methods. At the same time, compared with the traditional artificial neural network parameter adjustment, this paper introduces the simulated annealing algorithm to automatically adjust the parameters of the neural network, thereby obtaining an adaptive bearing fault diagnosis method. To verify the effectiveness of the method, the Case Western Reserve University bearing database was used for testing, and the traditional intelligent bearing fault diagnosis method was compared. The results show that the method proposed in this paper has good results in bearing fault diagnosis. Provides a new way of thinking in the field of bearing fault diagnosis in parameter adjustment and fault classification algorithms

One of the most dangerous diseases that threaten people is Cancer. Cancer if diagnosed in earlier stages can be eradicated with its life threatening consequences. In addition, accuracy in prediction plays a major role. Hence, developing a reliable model that contributes much towards the medical community in early diagnosis of Biopsy images with perfect accuracy come to the scenario. The article aims towards development of better predictive models using multi-variate data and high-resolution diagnostic tools in clinical cancer research. This paper proposes the social spider optimization (SSO) algorithm tuned neural network to classify microscopic biopsy images of cancer. The significance of the proposed model relies on the effective tuning of the weights of the NN classifier by the SSO algorithm. The performance of the proposed strategy is analysed with the performance metrics, such as accuracy, sensitivity, specificity, and MCC measures, and are attained to be 95.9181%, 94.2515%, 97.125%, and 97.68% respectively, which shows the effectiveness of the proposed method in effective cancer disease diagnosis.

Explaining the emergence of behavior and understanding on the basis of neuronal mechanisms is still elusive. One renowned proposal is the Free Energy Principle (FEP), which uses an information-theoretic framework derived from thermodynamic considerations to describe how behavior and understanding would emerge. FEP starts from a whole organism approach, based on mental states and phenomena, mapping them into the neuronal substrate. An alternative approach, the Energy Homeostasis Principle (EHP), initiates a similar explanatory effort, but starting from single neuron phenomena and building up to the whole organism’s behavior and understanding. In this work, we develop the EHP as an alternative but complementary vision to FEP and try to explain how behavior and understanding would emerge from the local requirements of the neurons. Based on EHP and a strict naturalist approach that sees living beings as physical and deterministic systems, we explain scenarios where learning would emerge without the need for volition or goals. Given these starting points, we state several considerations of how we see the nervous system, particularly the role of function, purpose, and the conception of goal-oriented behaviors. We problematize these conceptions, giving an alternative teleology-free framework in which behavior and, ultimately, understanding would still emerge. We reinterpret neural processing explaining basic learning situations up to simple anticipatory behavior. Finally, we end the work with an evolutionary perspective of how this non-goal-oriented behavior appears. We acknowledge that in the current form of our proposal, we are still far from explaining the emergence of understanding. Still, we set the ground for an alternative neuron-based framework to ultimately explain understanding.

Legacy IPv4 networks are strenuous to manage and operate. Network operators are in need to minimize the capital and operational expenditure of running network infrastructure. The implementation of Software-defined networking (SDN) addresses those issues by minimizing the expenditures in the long run. Legacy networks need to integrate with the SDN networks for the smooth migration towards the fully functional SDN environment. In this paper, we compare the network performance of the legacy network with the SDN network for IP routing in order to determine the feasibility of the SDN deployment in the Internet Service provider (ISP) network. The simulation of the network is performed in the Mininet test-bed and the network traffic is generated using distributed Internet traffic generator. Open network operating system is used as a controller for the SDN network in which SDN-IP application is used for IP routing. Round trip time, bandwidth, and packet transmission rate from both SDN and legacy networks are first collected and then the comparison is done. We found that SDN-IP performs better in terms of bandwidth and latency as compared to legacy routing. The experimental analysis of interoperability between SDN and legacy networks shows that SDN implementation in production level carrier-grade ISP network is viable and progressive.

Surrogate model based optimization method is widely-used to accelerate the design and optimization process~\cite{marler2004survey}. The input of regression model used in the surrogate model are numbers, which requires users to parametrize the geometries. In this paper, a new parameterization-free surrogate model is introduced and its corresponding uncertainty quantification and sensitivity analysis method are discussed. The input of new surrogate model methods is surface mesh of simulation domain. \Gls{gnns} is used to extract geometric information, and \Gls{cnns} is used to predict contours. This framework bypasses parameterization,as a consequence, uncertainties introduced by manual parameterization is reduced. However, such changes compared with conventional surrogate model methods impose great challenge on uncertainties quantification and sensitivity analysis. Uncertainties quantification in this paper means the error bar of prediction results, which is calculated by Gaussian Process Regression method in current surrogate method. In this paper, a new quantification method achieved by Kullback-Leibler divergence (KLD) is introduced. And the sensitivity analysis is conducted by Automatic Differentiation, which gives a Jacobian matrix of inputs. The method and analysis mentioned above are demonstrated by a low-pressure steam turbine rotator and its exhaust system.

Abstract: The Hanqu Joint Station of the Dingbian Oil Production Plant of Yanchang Oilfield Co., Ltd is located at the edge of the desert in northern China. the bad field conditions and strong sandstorm, the hardware of computer monitoring system of Joint Station is often damaged. At the same time, the core equipment of the joint station three-phase separator oil chamber liquid level is hard to achieve high precision constant value control, the general control algorithm is difficult to meet the control requirements.This paper proposed a design scheme of a oilfield joint station computer monitoring system based on the Siemens S7-300 PLC, the hardware of the monitoring system adopts the redundancy scheme of dual monitoring computers, dual programmable logic controllers (PLCs), and dual industrial Ethernet. The BP neural network PID control algorithm was used to realize constant value control of the oil chamber liquid level of the three-phase separator of the core equipment of the joint station，and realized high control precision. The monitoring system could well adapt to the harsh environment of the scene, and showed high reliability and efficiency.

Surveillance along the Kenya-Somalia border has been a big challenge that has continuously puzzled the security personnel, due to insurgency of armed militia Al-Shabaab from Somalia , the Kenyan government proposed construction of a barrier wall. This project developed a low cost wireless sensor network surveillance system to be deployed along the Kenya-Somalia border. The research study utilized two PIR sensor for detecting human intrusion, one motion is detected the sensor transmit the data via an Xbee module. Arduino microcontroller was used to process the data collected by the sensor before transmission. The system developed has two units, the Transmitter unit and a User Graphic interface running on Tuna Term software that displays the received data. During testing, the prototype system detected human intrusion, using the Arduino serial monitor the results were displayed before being package for transmission.

Weight gain affects about 10-20% of patients after bariatric surgery. It is a phenomenon that is difficult to understand and to intervene due to its complexity and etiological heterogeneity. In the present study, we investigated, from a network analysis perspective, the associations between weight regain, psychological, sociodemographic factors and physical activity in patients undergoing bariatric surgery. The sample consisted of 124 patients, of both sexes, aged 39 ± 9.1 years, who had undergone surgical intervention for more than 18 months. After voluntary consent, respondents answered questionnaires and instruments directly on the Google Forms platform. The results indicated that weight gain was negatively associated with the items of depression, anxiety and stress, binge eating and with the dimensions of the personality questionnaire (negative affectivity -0.182; detachment -0.078; antagonism -0.107; disinterest - 0.198 and psychoticism -0.158). The centrality indicators revealed that the characteristics of disinterest and negative affectivity and most of the items on the depression, anxiety and stress scale had a greater expected influence (values ​​from 1,043 to 1,502), indicating that these are the most sensitive variables to intervention and who need more attention from health professionals.

The great importance of estimating dissolved oxygen (DO) dictates utilizing proper evaluative models. In this work, a multi-layer perceptron (MLP) network is trained by three capable metaheuristic algorithms, namely multi-verse optimizer (MVO), black hole algorithm (BHA), and shuffled complex evolution (SCE) for predicting the DO using the data of the Klamath River Station, Oregon, US. The records (DO, water temperature, pH, and specific conductance) belonging to the water years 2015 - 2018 (USGS) are used for pattern analysis. The results of this process showed that all three hybrid models could properly infer the DO behavior. However, the BHA and SCE accomplished this task by simpler configurations. Next, the generalization ability of the developed patterns is tested using the data of the 2019 water year. Referring to the calculated mean absolute errors of 1.0161, 1.1997, and 1.0122, as well as Pearson correlation coefficients of 0.8741, 0.8453, and 0.8775, the MLPs trained by the MVO and SCE perform better than the BHA. Therefore, these two hybrids (i.e., the MLP-MVO and MLP-SCE) can be satisfactorily used for future applications.

Shrinking farm size and fragile farm resources pose a significant challenge to the sustainability of small-scale farms. Efficient resource utilization in small-scale farms is crucial to achieving farm sustainability through endogenous mechanisms. However, the precise mechanisms to integrate physical resources to achieve farm sustainability are not very clear yet. By capturing the interaction among farm resources as a network phenomenon, we identify the discrete resource interactions (RIs) in different types of small-scale farms of Indian Sundarbans, which are associated with higher farm sustainability. Thirty-two linkages, 11 reciprocal linkages, 22 triads, and three ‘core elements’ that occurred and cooccurred on highly sustainable farms are found to be critical in achieving farm sustainability. Using the properties of resource interaction networks as explanators of farm sustainability, we anticipate that sustainability in small-scale farms can be achieved by strategically creating new RIs on the farm. However, there may be limitations to such achievement depending on the nature of RI and type of farm. The analytical approach helps to understand the structural basis of sustainability in small-scale farms, and this approach can be used to achieve farm sustainability through the strategic integration of existing farm resources in the smallholder systems.

Epithelial-mesenchymal transition (EMT) plays an important role in the acquisition of cancer stem cell (CSC) feature and drug resistance, which are the main hallmarks of cancer malignancy. Although previous findings have shown that several signaling pathways are activated in cancer progression, the precise mechanism of signaling pathways in EMT and CSCs are not fully understood. In this study, we focused on the intestinal and diffuse-type gastric cancer (GC), and analyzed the gene expression of public RNAseq data to understand the molecular pathway regulation in different subtypes of gastric cancer. Network pathway analysis was performed by Ingenuity Pathway Analysis (IPA). Total 2815 probe set IDs were significantly different between intestinal- and diffuse-type GC data in cBioPortal Cancer Genomics. The 10 genes including male-specific lethal 3 homolog (Drosophila) pseudogene 1 (MSL3P1), CDC28 protein kinase regulatory subunit 1B (CKS1B), DEAD-box helicase 27 (DDX27), golgi to ER traffic protein 4 (GET4), chromosome segregation 1 like (CSE1L), translocase of outer mitochondrial membrane 34 (TOMM34), YTH N6-methyladenosine RNA binding protein 1 (YTHDF1), ribonucleic acid export 1 (RAE1), par-6 family cell polarity regulator beta (PARD6B), and MRG domain binding protein (MRGBP) were found to have difference in gene expression in intestinal- and diffuse-type GC. Total 463 direct relationships with 3 molecules (MYC, NTRK1, UBE2M) were found in the biomarker-filtered network generated by network pathway analysis. The networks and features in intestinal- and diffuse-type GC have been investigated and profiled in bioinformatics. Our results revealed the signaling pathways networks in intestinal- and diffuse-type GC, bringing new light for the elucidation of drug resistance mechanisms in CSCs.

The evolution in imaging technologies and artificial intelligence algorithms, coupled with improvements in UAV technology, has enabled the use of unmanned aircraft in a wide range of applications. The feasibility of this kind of approach for cattle monitoring has been demonstrated by several studies, but practical use is still challenging due to the particular characteristics of this application, such as the need to track mobile targets and the extensive areas that need to be covered in most cases. The objective of this study was to investigate the feasibility of using a tilted angle to increase the area covered by each image. Deep Convolutional Neural Networks (Xception architecture) were used to generate the models for the experiments, which covered aspects like ideal input dimensions, effect of the distance between animals and sensor, effect of classification error on the overall detection process, and impact of physical obstacles on the accuracy of the model. Experimental results indicate that oblique images can be successfully used under certain conditions, but some practical limitations need to be addressed in order to make this approach appealing.

The genetic heterogeneity of autism has stymied the search for causes and cures. Whole-genomic studies on large numbers of families have helped identify combinations of inherited and de novo signal. In the present work, we re-analyze DNA microarrays using a novel strategy that takes prior knowledge of genetic relationships into account and that was designed to boost signal important to our understanding of the molecular basis of autism. Our strategy was designed to identify significant genomic variation within a priori defined biological concepts and improves signal detection while lessening the severity of multiple test correction seen in standard analysis of genome-wide association data. Upon application of our approach using 3,244 biological concepts, we detected genomic variation in 68 biological concepts with significant association to autism in comparison to family-based controls. These concepts clustered naturally into a total of 19 classes, principally including cell adhesion, cancer, and immune response. The top-ranking concepts contained high percentages of genes already suspected to play roles in autism or in a related neurological disorder. In addition, many of the sets associated with autism at the DNA level also proved to be predictive of changes in gene expression within a separate population of autistic cases, suggesting that the signature of genomic variation may also be detectable in blood-based transcriptional profiles. This cross-validation with gene expression data from individuals with autism coupled with the enrichment within autism-related neurological disorders supported the possibility that the mutations play important roles in the onset of autism and should be given priority for further study. Our work provides new leads into the genetic underpinnings of autism and highlights the importance of reanalysis of genomic studies of complex disease using prior knowledge of genetic organization.

Predicting the popularity of posts on social networks has taken on significant importance in recent years, and several social media management tools now offer solutions to improve and optimize the quality of published content and to enhance the attractiveness of companies and organizations. Scientific research has recently moved in this direction, with the aim of exploiting advanced techniques such as machine learning, deep learning, natural language processing, etc., to support such tools. In light of the above, in this work we aim to address the challenge of predicting the popularity of a future post on Instagram, by defining the problem as a classification task and by proposing an original approach based on Gradient Boosting and feature engineering, which led us to promising experimental results. The proposed approach exploits big data technologies for scalability and efficiency and is general enough to be applied to other social media as well.

Long non-coding RNA (lncRNA) can regulate several aspects of gene expression, being associated with complex phenotypes in humans and livestock species. In taurine beef cattle, recent evidence points to the involvement of lncRNA in feed efficiency (FE), a proxy for increased productivity and sustainability. Here, we hypothesized specific regulatory roles of lncRNA in FE of indicine cattle. Using RNA-Seq data from liver, muscle, hypothalamus, pituitary and adrenal gland from Nellore bulls with divergent FE, we submitted new transcripts to a series of filters to confidently predict lncRNA. Then, we identified lncRNA that were differentially expressed (DE) and/or key regulators of FE. Finally, we explored lncRNA genomic location and interactions with miRNA and mRNA to infer potential function. We were able to identify 126 relevant lncRNA for FE in Bos indicus, some with high homology to previously identified lncRNA in Bos taurus and some possible specific regulators of FE in indicine cattle. Moreover, lncRNA identified here were linked to previously described mechanisms related to FE in hypothalamus-pituitary-adrenal axis and are expected to help elucidate this complex phenotype. This study contributes to expanding the catalogue of lncRNA, particularly in indicine cattle, and identifies candidates for further studies in animal selection and management.

Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained as one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered as a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR is heavily dependent on the clinical presentation and non-specific features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose the Myocarditis. The hybrid CNN-KCL method performs the early and accurate diagnosis of Myocarditis. To the best-of-our-knowledge, a Convolutional neural network has never been used before for the diagnosis of Myocarditis. In this study, we used 47 subjects to diagnose myocarditis patients from Tehran's Omid Hospital. The total number of data examined is 10425. Our results demonstrate that CNN-KCL achieves 92.3% in terms of diagnosis myocarditis prediction accuracy which is significantly better than those reported in previous studies.

The article’s goal is to overview challenges and problems on the way from the state of the art CUDA accelerated neural networks code to multi-GPU code. For this purpose, the authors describe the journey of porting the existing in the GitHub, fully-featured CUDA accelerated Darknet engine to OpenCL. The article presents lessons learned and the techniques that were put in place to make this port happen. There are few other implementations on the GitHub that leverage the OpenCL standard, and a few have tried to port Darknet as well. Darknet is a well known convolutional neural network (CNN) framework. The authors of this article investigated all aspects of the porting and achieved the fully-featured Darknet engine on OpenCL. The effort was focused not only on the classification with the use of YOLO1, YOLO2, and YOLO3 CNN models. They also covered other aspects, such as training neural networks, and benchmarks to look for the weak points in the implementation. The GPU computing code substantially improves Darknet computing time compared to the standard CPU version by using underused hardware in existing systems. If the system is OpenCL-based, then it is practically hardware independent. In this article, the authors report comparisons of the computation and training performance compared to the existing CUDA-based Darknet engine in the various computers, including single board computers, and, different CNN use-cases. The authors found that the OpenCL version could perform as fast as the CUDA version in the compute aspect, but it is slower in memory transfer between RAM (CPU memory) and VRAM (GPU memory). It depends on the quality of OpenCL implementation only. Moreover, loosening hardware requirements by the OpenCL Darknet can boost applications of DNN, especially in the energy-sensitive applications of Artificial Intelligence (AI) and Machine Learning (ML).

In this paper, we presented a method of retrieving sea surface wind speed from Sentinel-1 synthetic aperture radar (SAR) horizontal-horizontal (HH) polarization data in extra-wide mode, which have been extensively acquired over the Arctic for sea ice monitoring. In contrast to the conventional algorithm, i.e., using a geophysical model function (GMF) to retrieve sea surface wind by spaceborne SAR, we introduced an alternative method based on physical model guided neural network. Parameters of SAR normalized radar cross section, incidence angle, and wind direction are used as the inputs of the backward propagation (BP) neural network, and the output is the sea surface wind speed. The network is developed based on more than 11,000 HH-polarized EW images acquired in the marginal ice zone (MIZ) of the Arctic and their collocations with scatterometer measurements. Verification of the neural network based on the testing dataset yields a bias of 0.23 m/s and a root mean square error (RMSE) of 1.25 m/s compared to the scatterometer wind speed. Further comparison of the SAR retrieved sea surface wind speed with independent buoy measurements shows a bias and RMSE of 0.12 m/s and 1.42 m/s, respectively. We also analyzed the uncertainty of retrieval when the wind direction data of a reanalysis model are used as inputs to the neural network. By combining the detected sea ice cover information based on the EW data, one can expect to derive simultaneously sea ice and marine-meteorological parameters by spaceborne SAR in a high spatial resolution in the Arctic.

Recently, various relations and criteria have been presented to establish a proper relationship between control systems and control Global Positioning System (GPS)-intelligent buoy system. Given the importance of controlling the position of buoys and the construction of intelligent systems, in this paper, dynamic system modeling is applied to position marine buoys through the improved neural network with a backstepping technique. This study aims at developing a novel controller based on adaptive fuzzy neural network to optimally track the dynamically positioned vehicle on water with unavailable velocities and unidentified control parameters. In order to model the network with the proposed technique, uncertainties and the unwanted disturbances are studied in the neural network. The presented study aims at developing a neural controlling which applies the vectorial back-stepping technique to the surface ships, which have been dynamically positioned with undetermined disturbances and ambivalences. Moreover, the objective function is to minimize the output error for the neural network (NN) based on closed-loop system. The most important feature of the proposed model for the positioning buoys is its independence from comparative knowledge or information on the dynamics and the unwanted disturbances of ships. The numerical and obtained consequences demonstrate that the controller system can adjust the routes and the position of the buoys to the desired objective with relatively few position errors.

The COVID-2019 disease caused by the SARS-CoV-2 virus (aka 2019-nCoV) has raised significant health concerns in China and worldwide. While novel drug discovery and vaccine studies are long, repurposing old drugs against the COVID-2019 epidemic can help identify treatments, with known preclinical, pharmacokinetic, pharmacodynamic, and toxicity profiles, which can rapidly enter Phase 3 or 4 or can be used directly in clinical settings. In this study, we presented a novel network based drug repurposing platform to identify potential drugs for the treatment of COVID-2019. We first analysed the genome sequence of SARS-CoV-2 and identified SARS as the closest disease, based on genome similarity between both causal viruses, followed by MERS and other human coronavirus diseases. Using our AutoSeed pipeline (text mining and database searches), we obtained 34 COVID-2019-related genes. Taking those genes as seeds, we automatically built a molecular network for which our module detection and drug prioritization algorithms identified 24 disease-related human pathways, five modules and finally suggested 78 drugs to repurpose. Following manual filtering based on clinical knowledge, we re-prioritized 30 potential repurposable drugs against COVID-2019 (including pseudoephedrine, andrographolide, chloroquine, abacavir, and thalidomide) . We hope that this data can provide critical insights into SARS-CoV-2 biology and help design rapid clinical trials of treatments against COVID-2019.

We introduce a new, and quite general variational model for opinion dynamics based on pairwise interaction potentials and a range of opinion evolution protocols ranging from random interactions to global synchronous flows in the opinion state space. The model supports the concept of topic “coupling”, allowing opinions held by individuals to be changed via indirect interaction with others on different subjects. Interaction topology is governed by a graph that determines interactions. Our model, which is really a family of variational models, has, as special cases, many of the previously established models for the opinion dynamics. After introducing the model, we study the dynamics of the special case in which the potential is either a tent function or a constructed bell-like curve. We find that even in these relatively simple potential function examples there emerges interesting behavior. We also present results of preliminary numerical explorations of the behavior of the model to motivate questions that can be explored analytically

Water quality forecasting is increasingly significant for agricultural management and environmental protection. Enormous amounts of water quality data are increasingly being collected by advanced sensors, which leads to an interest in using data-driven models for predicting trends in water quality. However, the unpredictable background noises introduced during water quality monitoring seriously degrade the performance of those models. Meanwhile, artificial neural networks (ANN) with feed-forward architecture lack the capability of maintaining and utilizing the accumulated temporal information, which leads to biased predictions in processing time series data. Hence, we propose a water quality predictive model based on a combination of Kernal Principal Component Analysis (kPCA) and Recurrent Neural Network (RNN) to forecast the trend of dissolved oxygen. Water quality variables are reconstructed based on kPCA method, which aims to reduce the noise from the raw sensory data and preserve actionable information. With the RNN's recurrent connections, our model can make use of the previous information in predicting the trend in the future. Data collected from Burnett River, Australia was applied to evaluate our kPCA-RNN model. The kPCA-RNN model achieved R2 scores up to 0.908, 0.823 and 0.671 for predicting the concentration of dissolved oxygen in the upcoming 1, 2 and 3 hours, respectively. Compared to current data-driven methods like ANN and SVR, the predictive accuracy of the kPCA-RNN model was at least 8 %, 17 % and 21 % better than the comparative models in these 3 cases. The study demonstrates the effectiveness of the kPAC-RNN modeling technique in predicting water quality variables with noisy sensory data.

China is not only short of fresh water resources per capita, but also faces a serious problem of water pollution in recent years, with 190 million people suffering from excessive levels of harmful substances in their drinking water. Such as arsenic poisoning and fluorosis and other endemic water diseases high incidence. As a series of water pollution prevention plan of action by the Chinese government announced that, this paper uses the modified Undesirable Dynamic Network model empirical analysis of China's 31 provincial administrative region economic growth, wastewater treatment, and water disease control efficiency between 2013 and 2017. The results show that the efficiency of water pollution disease in all four regions of China and the total efficiency in the three regions of east, west and central China all show a decreasing trend, and the efficiency scores and rankings of all provinces and cities within the region fluctuate greatly. The eastern region with the most developed economy has the best overall performance, with higher efficiency in Water consumption and Water disease control. However, the efficiency of wastewater treatment in northeast China is stable and better. Given the high level of economic development in China and the results of the above mentioned efficiency in water pollution and water diseases, improving the efficiency and quality of wastewater treatment in China is regarded as an important factor in achieving the strategic goal of green growth.

Speech signals are degraded in real-life environments, product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions.To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long and short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combination of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation has been made based on quality measurements of the signal's spectrum, training time of the networks and statistical validation of results. Results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, with advantages in efficiency, but without a significan drop in quality.

The article is devoted to the assessment of the network community as a collective subject, as a group of interconnected and interdependent persons performing joint activities. According to the main research hypothesis, various forms of group subjectness, which determine its readiness for joint activities, are manifested in the discourse of the network community. Discourse constitutes a network community, mediates the interaction of its participants, represents ideas about the world, values, relationships, attitudes, sets patterns of behavior. A procedure is proposed for identifying discernible traces of the subjectness of a network community at various levels (lexical, semantic, content-analytical scales, etc.). The subjective structure of the network community is described based on experts’ implicit representations. The revealed components of the subjectness of network communities are compared with the characteristics of the subjectness of offline social groups. It is shown that the structure of the subjectness of network communities for some components is similar to the structure of the characteristics of the subjectness of offline social groups: the discourse of the network community represents a discussion of joint activities, group norms and values, problems of civic identity. The specificity of network communities’ subjectness is revealed, which is manifested in the positive support of communication within the community, the identification and support of distinction between “us” and “them”. Two models of the relationship between discursive features and the construct “subjectness” are compared: additive-cumulative and additive. The equivalence of models is established based on the discriminativeness and the level of consistency with expert evaluation by external criteria.

We have developed an application aiming at federated search for EU and Hungarian legislation and jurisdiction. It now contains above 1 million documents, with daily updates. The database holds documents downloaded from the EU sources EUR-Lex and Curia Online as well as public jurisdiction documents from the Constitutional Court of Hungary and The National Office for The Judiciary. The application is termed Justeus. Justeus provides comprehensible search possibilities. Besides free text and metadata (dropdown list) searches, it features hierarchical data structures (concept hierarchy trees) of directory codes and classification as well as subject terms. Justeus collects all links of a particular document to other documents (court judgements citing other case law documents as well as legislation, national court decisions referring to EU regulation etc.) as tables and directed graph networks. Choosing a document, its relations to other documents are visualized in real time as a network. Network graphs help in identifying key documents influencing or referred by many other documents (legislative and/or jurisdictive) and sets of documents predominantly referring to each other (citation networks).

The key issue in the post-genomic era is how to systematically describe the association between small molecule transcripts or translations inside cells. With the rapid development of high-throughput “omics” technologies, the achieved ability to detect and characterize molecules with other molecule targets opens up the possibility of investigating the relationships between different molecules from a global perspective. In this article, a Molecular Associations Network(MAN) is constructed and comprehensively analyzed by integrating the associations among miRNA, lncRNA, protein, drug, and disease, in which any kind of potential associations can be predicted. More specifically, each node in MAN can be represented as a vector by combining two kinds of information including the attributes of the node itself (e.g. sequences of ncRNAs and proteins, semantics of diseases and molecular fingerprints of drugs) and the manner of the node in the complex network (associations with other nodes). Random Forest classifier is trained to classify and predict new interactions or associations between biomolecules. In the experiment, the proposed method achieves a superb performance with 0.9735 AUC in 5-fold cross-validation, which show that the proposed method can provide new insight for exploration of the molecular mechanisms of disease and valuable clues for disease treatment.

Boiler efficiency is called to some extent of total thermal energy which can be recovered from the fuel. Boiler efficiency losses are due to four major factors: the dry gas flux, the latent heat of steam in the flue gas, the combustion loss or the loss of unburned fuel, radiation and convection losses. In this research, the thermal behavior of boilers in gas refinery facilities is studied and their efficiency and their losses are calculated. The main part of this research is comprised of analyzing the effect of various parameters on efficiency such as excess air, fuel moisture, air humidity, fuel and air temperature, the temperature of combustion gases, and thermal value of the fuel. Based on the obtained results, it is possible to analyze and make recommendations for optimizing boilers in the gas refinery complex using response-surface method (RSM).

The availability of rail infrastructure resources is a major driver of rail operations performance. To evaluate the impact of infrastructure provision, network simulation models can be used to accurately represent train traffic behavior in a wide range of scenarios. However, performing this task can result in a problem of high combinatorial nature as the number of factors and their associated levels increase. This requires more sophisticated techniques such as experimental design formulations or optimization modeling in order to yield satisfactory results. Yet the research in network simulation models for rail systems has hitherto been limited to simple what-if analysis, made up from few factors that cannot represent the whole spectrum of interventions. This is especially critical in closed-loop rail systems where trains are subject to various interferences. Local improvements can be misleading as the queues are merely transferred within the network. Considering this, we propose a hybrid simulation-optimization model to aid the strategic decision of minimizing supplementary capital costs in a heavy-haul Brazilian railroad under construction. As soon as the railroad is completed, investments in both loading and unloading rail terminals will be necessary. First, we developed a representative and flexible model capable of dealing with complex relations between variable infrastructure provision and the resulting operational performance. Then, we simulated this system to prove that the current set of proposed infrastructure resources cannot meet the transportation demands. Afterwards, we demonstrate that local improvements can be delusive as the queues are shifted from loading to unloading operations, reciprocally. Then, we solve an optimization model to define the minimal supplementary investment in order to meet the commercial goals of mining companies. This is done by choosing the best trackage configuration, equipment quantity and capacity and fleet sizing in 3 different production scenarios. The best values of the objective function were found by improving both loading and unloading equipment and increasing the number of trains.

Layout estimation is a challenge of segmenting a cluttered room image into floor, walls and ceiling. We applied Double refinement network proved to be efficient in the depth estimation to generate heat maps for room key points and edges. Our method is the first not using encoder-decoder architecture for the room layout estimation. ResNet50 was utilized as a backbone for the network instead of VGG16 commonly used for the task, allowing the network to be more compact and faster. We designed a special layout score function and layout ranking algorithm for key points and edges output. Our method achieved the lowest pixel and corner errors on the LSUN data set. The input image resolution is 224*224.

With the increase of the Artificial Neural Network (ANN), machine learning has taken a forceful twist in recent times. One of the most spectacular kinds of ANN design is the Convolutional Neural Network (CNN). The Convolutional Neural Network (CNN) is a technology that mixes artificial neural networks and up to date deep learning strategies. In deep learning, Convolutional Neural Network is at the center of spectacular advances. This artificial neural network has been applied to several image recognition tasks for decades and attracted the eye of the researchers of the many countries in recent years as the CNN has shown promising performances in several computer vision and machine learning tasks. This paper describes the underlying architecture and various applications of Convolutional Neural Network.

Health differences across socioeconomic strata have always pointed out that poorer and minorities have higher mortality and morbidity than richer and majorities. This difference is exacerbated for particular populations such as the victims of ongoing armed conflicts, who are also much harder to quantify due to the conflict itself. This study applies network analysis to a combination of three large administrative records for the health system and mortality records in the province of Risaralda (Colombia) between 2011 and 2016. It produces the most common causes of morbi-mortality for both victims of violence and the poorest inhabitants of Risaralda, defined as those who qualify as recipients of subsidies from the Colombian welfare program called SISBEN in the categories of highest need. Both populations show high morbidity frequencies for non-communicable diseases such as Type II diabetes, hypertension, and hyperglyceridaemia, mostly associated with exposure to unhealthy lifestyles. Additionally, the mortality outcomes reflect the different lifestyles and medical treatments of both subpopulations. While the poorest replicate the same causes identified for morbidity, the victims of armed conflict die of additional causes including Type II diabetes, which reflects the even worse conditions they face.

For development and successful application of any material, a clear understanding of their mechanical behavior is one of the most important things, but when it comes to nanofibers networks it become a challenge due to, their high porosity, many scales in their structure, and characteristics non-linear. Therefore, an experimental methodology in conjunction with a theoretical model that can fully consider their characteristics is still needed. In this work we proposed a model that incorporates the propagation of the elastic waves in two-phase media to determine the effective elastic modulus of electrospun membranes of PLA/gelatin given the mechanical properties of nanofibers, shape, distribution and concentration. The model was verified via laser ultrasonic testing. It was found that the values predicted for the effective modulus by the model were higher than the values obtained from experimental results. One explanation is due to the experimental density. As a result, the P-Wave velocity from the model best fit to experimental results and it has the same behavior, decrees as the concentration of gelatin in the solution. These results indicate the model and experimental methodology can assist in the dressing of nanofibers networks and electrospun materials.

Here we present a fast and highly scalable community structure preserving network module detection that recursively integrates graph sparsification and clustering. Our algorithm, called SparseClust, participated in the most recent DREAM community challenge on disease module identification, an open competition to comprehensively assess module identification methods across a wide range of biological networks.

Here is shown method for the hydraulic solution of a looped gas-pipeline networks. Calculation of presented network is done according to principles of Hardy Cross method. The optimization was carried out by iteration of the pipes diameters, node consumptions are known and flow velocities through pipes have to stand below certain values. Accent is on determination of appropriate friction factor, and on selection of representative equation for natural gas flow under presented conditions in the network. Inappropriate usage of friction factor, equally as inappropriate usage of gas flow equation can lead to inaccurate final results. Here is shown new facts in comparison to previous calculation of gas distribution network in Kragujevac, Serbia which is done in 1994. After the implementation, measurements in situ have performed, and real measured values deviate from calculated. Causes for these errors are investigated, and improved and more accurate procedure is shown.

Panax notoginseng, as traditional Chinese medicine, has a long history of high clinical value, such as anti-inflammatory, anti-oxidation, inhibition of platelet aggregation, regulation of blood glucose and blood pressure, inhibition of neuronal apoptosis and neuronal protection, and its main ingredients are Panax notoginseng saponins (PNS). Currently, Panax notoginseng may improve mental function, have anti-insomnia and anti-depression effects, alleviate anxiety, and decrease neural network excitation. However, the underlying effects and the mechanisms of Panax notoginseng and its containing chemical constituents (PNS) on these depression-related or anxiety-related diseases has not been completely established. This review summarized the antidepressant or anxiolytic effects and mechanisms of PNS, and analyzed network targets of antidepressant or anxiolytic actions with network pharmacology tools to provide directions and references for further pharmacological studies and new ideas for clinical treatment of nervous system diseases and drug studies and development.

Small and micro hydropower represents an attractive solution for electricity generation, with low cost and low environmental impact. The pump-as-turbine (PAT) approach has promise in this application owing to its low purchase and maintenance costs. In this paper, a new method to predict the inverse characteristic of industrial centrifugal pumps is presented. This method is based on results of simulations performed with commercial three-dimensional CFD software. Model results have been first validated in pumping mode using data supplied by pump manufacturers. Then, results have been compared to experimental data for a pump running in reverse condition. Experimentation has been performed on a dedicated test bench installed in the Department of Civil Construction and Environmental Engineering of the University of Naples Federico II. Three different pumps, with different specific speeds, have been analyzed. Using the model results, the inverse characteristic and the best efficiency point have been evaluated. Finally, results of this methodology have been compared to prediction methods available in the literature.

Lily tepals have a short lifespan. Once the tepals senesce, the ornamental value of the flower is lost. Some cultivars have attractive purple ovaries and fruits which greatly enhance the ornamental value of Asiatic hybrid lilies. However, little is known about the molecular mechanisms of anthocyanin biosynthesis in Asiatic hybrid lily ovaries. To investigate the transcriptional network that governs purple ovary coloration in Asiatic hybrid lilies, we obtained transcriptome data from green ovaries (S1) and purple ovaries (S2) of Asiatic ‘Tiny Padhye’. Comparative transcriptome analysis revealed 4228 differentially expressed genes. Differential expression analysis revealed that nine unigenes including four CHS genes, one CHI gene, one F3H gene, one F3′H gene, one DFR gene, and one UFGT gene were significantly up-regulated in purple ovaries. One MYB gene, LhMYB12-Lat, was identified as a key transcription factor determining the distribution of anthocyanins in Asiatic hybrid lily ovaries. Further qPCR results showed unigenes related to anthocyanin biosynthesis were highly expressed in purple ovaries of Asiatic ‘Tiny Padhye’ at stages 2 and 3, while they showed an extremely low level of expression in ovaries of Asiatic ‘Yellow Pixels’ during all developmental stages. In addition, shading treatment significantly decreased pigment accumulation by suppressing the expression of several unigenes related to anthocyanin biosynthesis in ovaries of Asiatic ‘Tiny Padhye’. These results could further our understanding of the molecular mechanisms of anthocyanin biosynthesis in Asiatic hybrid lily ovaries.

Security has become a critical issue in today’s highly distributed and networked systems. Network intrusion detection systems (NIDSs), especially signature-based NIDSs, are being widely deployed in a distributed network environment with the purpose of defending against a variety of network attacks. Most of the commercially available NIDSs are software based and rely on pattern matching to extract the threat from network traffic. The increase in network speed and traffic may make existing algorithms to become a performance bottleneck. Therefore it is very necessary to develop faster and more efficient pattern matching algorithm in order to overcome the troubles on performance of NIDSs. Therefore, we propose a multi fusion pattern matching algorithm for Network Intrusion Detection Systems. The results obtained in percentages from the proposed fusion algorithm given better values in terms processing time in milliseconds than the existing algorithms when data English text are applied to evaluate the fusion performances.

In 2023, the technological landscape witnessed an unprecedented surge of transformative innovations, including Web 3.0 and machine learning, poised to revolutionize various aspects of our daily lives. At the forefront of this revolution stands artificial intelligence (AI), which has evolved from a concept once confined to science fiction into an indispensable force reshaping industries on a global scale. Notably, recent years have seen remarkable strides in AI functionalities, particularly in machine learning, computer vision, and natural language processing. These advancements have empowered AI to generate diverse interactions and media autonomously. This study ultimately provides invaluable insights into the dynamic intersection of AI and Advertising, con-tributing to a deeper comprehension of this evolving field. This study conducts a comprehensive review of Artificial Intelligence within the advertising domain, employing network analysis. By meticulously examining the evolution of AI through co-occurrences of terms, keywords, and co-authorship analysis, we aim to unveil the relationship of AI & Advertising through the lens of Generative models to identify pivotal trends, core concepts, and seminal studies that have profoundly influenced the industry. The analysis charts the trajectory leading to the emergence of Generative Artificial Intelligence (GenAI), a transformative development poised to revolutionize advertising practices and consumer engagement. In tandem with these objectives, the results highlight vital trends, emphasizing the growing prominence machine learning tools and techniques such as deep learning techniques and advanced natural language processing methods like word2vec, GANs, and more in shaping the future of advertising practices.

Although the statistical methods of downscaling climate data have progressed significantly, the development of high-resolution precipitation products continues to be a challenge. This is especially true when interest centres on downscaling value over several study sites. In this paper , we report a new downscaling method termed the multi-site Climate Generative Adversarial Network (MSCliGAN), which can simulate annual maximum precipitation to the regional scale during the 1950-2010 period in different cities in Canada by using different AOGCM's from the Coupled Model Inter-Comparison Project 6 (CMIP6) as input. Auxiliary information provided to the downscaling model included topography and land-cover. The downscaling framework uses a convolution encoder-decoder U-net network to create a generative network and a convolution encoder network to create a critic network. An adversarial training strategy is used to train the model. The critic/discriminator used Wasserstein distance as a loss measure and on the other hand the generator is optimized using a summation of content loss on Nash-Shutcliff Model Efficiency (NS), structural loss on structural similarity index (SSIM), and adversarial loss Wasserstein distance. Downscaling results show that downscaling AOGCMs by incorporating topography and land-use/land-cover can produce spatially coherent fields close to observation over multiple-sites. We believe the model has sufficient downscaling potential in data sparse regions where climate change information is often urgently needed.

Optical networks offer a wide range of benefits to the telecommunication sector world- wide with its provision of higher bandwidth which leads to faster data speed, longer transmission distance, and improved latency. Currently, the complexity associated with advancements in optical networks poses problems to network flexibility, reliability, and quality of service. Over the years, many reviews and proposals have been implemented by several literatures to provide solutions for optical networks using software-defined networks and network service orchestrators. This paper reviews the significant challenges in current optical network applications, the various solutions rendered by software-defined networks as well as network service orchestration, the impediments, and gaps in these software – defined networks. This paper will go a step further to look into the various improvements and implementations of software-defined networks tailored to solve specific optical network problems. This paper further proposes a flexible orchestration architecture for software-defined networks for solving flexibility and scalability problems in optical networks. This proposal uses Open Network System (ONOS) SDN controller, leveraging on dockerisation as well as kubernetes clusterisation and orchestration. This solution presents a more flexible, reliable, customable, and higher quality of service which is an improvement upon current solutions in literature.

In recent years, data providers are generating and streaming a large number of images. More particularly, processing images that contain faces have received great attention due to its numerous applications, such as entertainment and social media apps. The enormous amount of images shared on these applications presents serious challenges and requires massive computing resources to ensure efficient data processing. However, images are subject to a wide range of distortions in real application scenarios during the processing, transmission, sharing, or combination of many factors. So, there is a need to guarantee acceptable delivery content, even though some distorted images do not have access to their original version. In this paper, we present a framework developed to estimate the images' quality while processing a large number of images in real-time. Our quality evaluation is measured using an integration of a deep network with random forests. In addition, a face alignment metric is used to assess the facial features. Experimental results have been conducted on two artificially distorted benchmark datasets, LIVE and TID2013. We show that our proposed approach outperforms the state-of-art methods, having a Pearson Correlation Coefficient (PCC) and Spearman Rank Order Correlation Correlation Coefficient (SROCC) with subjective human scores of almost 0.942 and 0.931 while minimizing the processing time from 4.8ms to 1.8ms.

Direct measurement of strain within muscle is important for understanding muscle function in health and disease. Current technology (kinematics, dynamometry, electromyography) provides limited ability to measure strain within muscle. Regional fiber orientation and length are related with active/passive strain within muscle. Currently, ultrasound imaging provides the only non-invasive means of observing regional fiber orientation within muscle during dynamic tasks. Previous attempts to automatically estimate fiber orientation from ultrasound are not adequate, often requiring manual region selection, feature engineering, providing low-resolution estimations (one angle per muscle), and deep muscles are often not attempted. Here, we propose deconvolutional neural networks (DCNN) for estimating fiber orientation at the pixel-level. Dynamic ultrasound images sequences of the calf muscles were acquired (25 Hz) from 8 healthy volunteers (4 male, ages: 25–36, median 30). A combination of expert annotation and interpolation/extrapolation provided labels of regional fiber orientation for each image. We then trained DCNNs both with and without dropout using leave one out cross-validation. Our results demonstrated robust estimation of regional fiber orientation with approximately 3° error, which was an improvement on previous methods. The methods presented here provide new potential to study muscle in disease and health.

This review explores the potential of Intelligent Reflecting Surfaces (IRS) to address limitations of traditional antennas and empower next-generation wireless networks. IRS technology offers a paradigm shift by passively manipulating radio waves, enhancing signal coverage, network capacity, and energy efficiency. IRS technology utilizes flat surfaces equipped with tiny, adjustable reflectors. Unlike traditional antennas that actively send and receive radio waves, IRS passively manipulates incoming signals by reflecting them in specific directions with controlled adjustments. This approach significantly improves signal coverage and strength, particularly in areas with poor reception. The review reveals the IRS technology offers significant advantages over traditional antennas. It can enhance signal coverage by reflecting radio waves, boost network capacity which allows networks to handle a larger number of users simultaneously, promote lower energy consumption compare, and unlock potential of 6G Networks and beyond. Additionally, IRS enables functionalities such as enhanced localization and ultra-fast data transfer. Integrating IRS with next-generation antennas unlocks new possibilities. This includes reconfigurable antennas that dynamically adjust radiation patterns, compact and low-profile designs, and multi-functional antennas that support various services simultaneously. In conclusion, this paves the way for a new generation of robust and sustainable wireless communication systems.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a positive sense single stranded RNA genome containing virus which has infected millions of people all over the world particularly China. The virus has been mutating rapidly enough resulting in the emergence of new variants and sub-variants which have reportedly been spread from Wuhan city of China, the epicenter of the virus, to the rest of China and all over the world. The occurrence of mutations in the viral genome especially in the viral spike protein region has resulted in the evolution of multiple variants and sub-variants which gives the virus benefit of host immune evasion and render the modern-day vaccines and therapeutics ineffective. Therefore, there is a continuous need to study the genetic characteristics and evolutionary dynamics of the SARS-CoV-2 variants. Hence, in this study, a total of 833 complete genomes of SARS-CoV-2 variants (including the wild-type or reference sequence) from Taiyuan and Wuhan cities of China were genetically characterized and studies their phylogenetic and evolutionary dynamics using phylogenetics, genetic similarity, and phylogenetic network analysis. Our results show a lot of useful information regarding the evolutionary dynamics of the viral variants, their genetic similarities/dissimilarities, and their phylogenetic relationships. It has been reported in this study that the SARS-CoV-2 variants have nine recombinant events which suggest very important information regarding the viral evolution. In addition, the phylogenetic network analysis shows the number of mutations resulting in emergence and clustering of the viral variants of both cities which reveal significant information regarding the phylodynamics of the virus. This study, to the best of our knowledge, is the first ever genetic comparative study of Taiyuan and Wuhan cities. This study will help better understand the virus, cope with the emergence, and spread of new variants at local level as well as at international level and inform the public health authorities to make better informed decisions in designing new viral vaccines and therapeutics.

The increasing use of Convolutional Neural Networks (CNN) has brought about a significant transformation in numerous fields, such as image categorization and identification. In the development of a CNN model for classifying images of sericea lespedeza (SL; Lespedeza cuneata) from weed images, four architectures were explored: CNN-Model Variant 1, CNN-Model Variant 2, VGG16, and ResNet50. The CNN-Model Variant 1 demonstrated 100 % validation accuracy, while Variant 2 achieved 90.78% validation accuracy. Pre-trained models, like VGG16 and ResNet50, were also analyzed. In contrast, ResNet50's steady learning pattern indicated potential for better generalization. A detailed evaluation of these models revealed that Variant 1 achieved a perfect score in precision, recall, and F1-score, indicating superior optimization and feature utilization. Variant 2 presented a balanced performance, with metrics between 86% and 93%. The VGG16 mirrored the behavior of Variant 2, both maintaining around 90% accuracy, but ResNet50's results revealed a conservative approach for class 0 predictions. Overall, Variant 1 stood out in performance, while both Variant 2 and VGG16 showed balanced results. The reliability of CNN model Variant 1 is highlighted by the significant accuracy percentages, which demonstrate its potential for practical implementation in agriculture. Smartphone application for the identification of SL in a field-based trial has shown promising results with an accuracy of 98%-99%. Using a CNN model with batch normalization has the potential to play a crucial role in redefining and optimizing the management of undesirable vegetation in the future.

Time series forecasting has been a challenging area in the field of Artificial Intel-ligence. Various approaches such as linear Neural Networks, Recurrent Linear Neural Networks, Convolutional Neural Networks and recently Transformers have been attempted for the time series forecasting domain. Although, Trans-former-based architectures have been outstanding in the Natural Language Pro-cessing domain, especially in autoregressive language modeling, the initial at-tempts to use transformers in the time series arena have met with mixed success. One of the recent papers demonstrated that modeling the multi-variate time se-ries problem as independent channels on a transformer architecture produced lower mean square and mean absolute errors on benchmarks, however, another recent paper claimed that a simple linear neural network out-performs previous approaches including transformer-based designs. We investigate this paradox in detail comparing the linear Neural Network and Transformer based designs, provide insights to why a certain approach may be better for a particular type of problem. We also improve upon the recently proposed simple linear Neural Network based architecture by using dual pipelines with batch normalization and reversible instance normalization. Our enhanced architecture outperforms all existing architectures for time series forecasting on majority of the popular benchmarks.

Camouflage evaluation typically involves human visual search and detection experiments that are time-consuming and expensive. Hence, there is a need for models that compute camouflage effectiveness from digital imagery. Convolutional neural networks are a powerful tool for automatic object detection and recognition. We investigated whether such a network (YOLO) can also provide a measure of camouflage effectiveness that is related to human perception. To this end, human performance measures of camouflage effectiveness such as detection time and target conspicuity were obtained in observer experiments and compared with the performance of the (standard, i.e. pre-trained) YOLO-V4-tiny algorithm. YOLO provides the probability that a detected object is correctly classified, and this is adopted as our measure of camouflage effectiveness. We compared the YOLO-predicted classification probability for a person in camouflage clothing moving through rural and urban scenes to human detection performance. Overall, camouflage effectiveness predicted by YOLO correlates with human observer performance. At close distances, YOLO’s classification performance appears sensitive to high-contrast shape-breaking elements of a camouflage pattern. This suggests that YOLO may be adapted to assess camouflage effectiveness for a wide range of applications, such as evaluating or optimizing one’s signature and predicting optimal hiding locations in a given environment. Further research is required to fully establish YOLO’s limitations and applicability for this purpose.

Reasonable allocation of production plans and saving the overall electricity cost are crucial for large manufacturing conglomerates, which is an effective way for conglomerates to realize open-source and cost-saving. This paper develops an optimization model of off-site industrial production scheduling for enterprises in response to the problems of high electricity costs due to the irrational allocation of production schedules on the demand side of China's electric power and the difficulty of promoting industrial and commercial distributed photovoltaic (PV) projects in China. The model makes full use of the conditions of different PV resources and different electricity prices in different places to optimize the scheduling of industrial production in different places. The model is embedded with two sub-models of the electricity price prediction model and distributed photovoltaic kWh cost model to complete the model parameters, in which the electricity price prediction model utilizes the LSTM neural network. The integrated model is then solved by the particle swarm algorithm. To verify the effectiveness of the model in solving the problem of off-site production scheduling on the demand side of electricity, the research team researched two off-site pharmaceutical factories belonging to the same large pharmaceutical company. Finally, the research data were substituted into the model for solving, and it was concluded that the optimization model could significantly reduce the cost of electricity consumption of the enterprise by about 7.9 %.

Military medical service is an important component of the Armed Forces of any country [1]. In wartime, healthcare performs critical functions of medical support for military operations, providing effective and qualified care to the wounded and sick. Consequently, it is imperative to equip military hospitals with state-of-the-art materials and technical resources commensurate with the predefined requirements. In this study, we examine a series of enhancements applied to the TurtleBot 3 Waffle Pi-based medical assistant robot, tailored for deployment in military hospital settings.

Blockchain technology has emerged as a necessity for the decentralization of payment methods and transactions, but it has brought with it many properties of distributed systems that have made it a crucial technology for overcoming some of society's challenges, especially in the context of decentralizing services, transparency of information, availability, and security. Its architecture and communication methods, although possessing some complex nuances to understand, particularly for the lay audience in the field of distributed systems, protocols, and computer networks. In this article, we will explore some topics of distributed systems related to blockchain technology.

Taekwondo has evolved from a traditional martial art into an official Olympic sport. This study introduces a novel action recognition model tailored for Taekwondo unit actions, utilizing joint motion data acquired via wearable inertial measurement unit (IMU) sensors. The utilization of IMU sensor-measured motion data facilitates the capture of the intricate and rapid movements characteristic of Taekwondo techniques. The model, underpinned by a conventional convolutional neural network (CNN)-based image classification framework, synthesizes action images to represent individual Taekwondo unit actions. These action images are generated by mapping joint motion profiles onto the RGB color space, thus encapsulating the motion dynamics of a single unit action within a solitary image. To further refine the representation of rapid movements within these images, a time-warping technique was applied, adjusting motion profiles in relation to the velocity of the action. The effectiveness of the proposed model was assessed using a dataset compiled from 40 Taekwondo experts, yielding remarkable outcomes: an accuracy of 0.998, precision of 0.983, recall of 0.982, and an F1-score of 0.982. These results underscore the time-warping technique's contribution to enhancing feature representation, as well as the proposed method's scalability and effectiveness in recognizing Taekwondo unit actions.

Evolutionary algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using evolutionary algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. In Part1 and Part2, the author previously reported experimental evaluations on Genetic Algorithm and Evolution Strategy for reinforcement learning of neural networks, utilizing the Acrobot control task. This article constitutes Part3 of the series of comparative research. In this study, Differential Evolution is adopted as the third instance of major evolutionary algorithms. The experimental results show a statistically significant superiority of DE over both GA and ES (p < .01). In addition, DE exhibits its robustness to variations in hyperparameter configurations (the number of offsprings and generations). In the previous experiments, both ES and GA showed significant performance differences depending on the configurations, whereas in the experiment reported in this article, such differences are not detected for DE.

This paper reviews several techniques, including analytical theories and real frequency techniques, to design ultra-wideband impedance matching networks for low-power applications. The comparison of solutions obtained using the simplified real frequency technique to the published solution using Chebyshev filter theory is demonstrated.

This study explores the use of Bayesian Neural Networks (BNNs) for estimating chlorophyll-a concentration ([CHL-a]) from remotely sensed data. The BNN model enables uncertainty quantification, offering additional layers of information compared to traditional ocean colour models. An extensive in situ bio-optical dataset is utilized, generated by merging 27 data sources across the world’s oceans. The BNN model demonstrates remarkable capability in capturing mesoscale features and ocean circulation patterns, providing comprehensive insights into spatial and temporal variations in [CHL-a] across diverse marine ecosystems. In comparison to established ocean colour algorithms, such as Ocean Colour 4 (OC4), the BNN shows comparable performance in terms of correlation coefficients, errors, and biases when compared with the in situ data. The BNN, however, further provides critical information about the distribution of [CHL-a], which can be used to assess uncertainties in the prediction. Moreover, the BNN model’s ability to provide more information for coastal waters, especially with higher spatial resolution imagery, offers valuable advantages for marine research and management. By quantifying uncertainty, the model builds confidence in [CHL-a] predictions, even in regions with limited data coverage. This is reflected by the spread in the model predictions, where the BNN can detect a range of uncertainty bounds that reflect confidence in the retrievals. Introducing BNNs as probabilistic ocean colour models represents a significant advancement, enabling more accurate and reliable predictions of [CHL-a] in the global oceans.

In our digital era, digital platforms become an unprecedented opportunities for manufacturing enterprises to leverage their business strategy. This study investigates how manufacturing enterprises can enhance organizational duality through digital platforms. Specifically, this study examines the effect of digital platforms and capability reconfiguration on entrepreneurial organizational duality. The study also examines how network digital atmosphere moderates this relationship. Based on analysis of 286 manufacturing enterprises undergoing digital transformation, the results indicate that digital platforms positively affect both organizational duality and the capability reconfiguration. The results indicate that digital platforms have a positive indirect effect on organizational duality via evolutionary capability reconfiguration and substitutional capability reconfiguration, respectively. The study also shows that network digital atmosphere moderate this effect.These findings contribute theoretically to the research on digital platforms and manufacturing enterprises while also providing important managerial implications for policymakers and manufacturing enterprises to help firms implement digital strategies.

In the pursuit of energy-efficient spiking neural network (SNN) hardware, synaptic devices lev-eraging emerging memory technologies hold significant promise. This study investigates the ap-plication of the recently proposed HfO2/SiO2-based interface dipole modulation (IDM) memory for synaptic spike timing-dependent plasticity (STDP) learning. Firstly, through pulse measure-ments of IDM metal-oxide-semiconductor (MOS) capacitors, we demonstrate that IDM exhibits an inherently nonlinear and near-symmetric response. Secondly, we discuss the drain current re-sponse of a field-effect transistor (FET) incorporating a multi-stack IDM structure, revealing its nonlinear and asymmetric pulse response, and suggest that the degree of the asymmetry depends on the modulation current ratio. Thirdly, to emulate synaptic STDP behavior, we implement dou-ble-pulse-controlled drain current modulation of IDMFET using a simple bipolar rectangular pulse. Additionally, we propose a double-pulse-controlled synaptic depression that is valuable for optimizing STDP-based unsupervised learning. Integrating the pulse response characteristics of IDMFETs into a two-layer SNN system for synaptic weight updates, we assess training and classification performance on handwritten digits. Our results demonstrate that ID-MFET-based synaptic devices can achieve classification accuracy comparable to previously re-ported simulation-based results.

Survival models have become popular for credit risk estimation. Most current credit risk survival models use an underlying linear model. This is beneficial in terms of interpretability but is restrictive for real-life applications since it cannot discover hidden nonlinearities and interactions within the data. This study uses discrete time survival models with embedded neural networks as estimators of time to default. This provides flexibility to express nonlinearities and interactions between variables, and hence allows for models with better overall model fit. Additionally, the neural networks are used to estimate Age-Period-Cohort (APC) models so that default risk can be decomposed into time components for loan age (maturity), origination (vintage) and environment (e.g., economic, operational and social effects). These can be built as general models, or as local APC models for specific customer segments. The local APC models reveal special conditions for different customer groups. The corresponding APC identification problem is solved by a combination of regularization and fitting the decomposed environment time risk component to macroeconomic data, since the environmental risk is expected to have a strong relationship with macroeconomic conditions. Our approach is shown to be effective when tested on a large publicly available US mortgage data set. This novel framework can be adapted by practitioners in the financial industry to improve modelling, estimation and assessment of credit risk.

River bed materials serve multiple environmental functions as a habitat for aquatic invertebrates and fishes. At the same time, the particle size of the bed material reflects the tractive force of the flow regime in a flood and provides useful information for flood control. The traditional river bed particle size surveys, such as sieving, require time and labor to investigate river bed materials. The authors proposed a method to classify aerial images taken by unmanned aerial vehicle (UAV) using convolutional neural networks (CNN), our previous study showed that terrestrial riverbed material could be classified with high accuracy. In this study, we attempted to classify riverbed materials distributed in shallow waters where the bottom can be seen from UAVs. After training the CNN to classify the images with the same grain size as being in the same class even if the surface flow types taken overlapping the riverbed material were different, the total accuracy reached 90.3%. Moreover, the proposed method was applied to the wide-ranging area to determine the distribution of the particle size. In parallel, the microtopography was surveyed using Lidar-UAV, and the relationship between the microtopography and particle size distribution was discussed. In the steep section, coarse particles were distributed and formed a rapid. Fine particles were deposited on the upstream side of those rapids, where the slope had become gentler due to the damming. There was good agreement between the microtopographical trends and the grain size distribution.

Wearing gloves while operating machinery in workshops is an essential precaution to prevent mechanical injuries and burns from high temperatures, among other potential hazards. Ensuring workers are properly equipped with gloves, which is a crucial measure in accident prevention. Glove images often occupy a minimal proportion of the frame and are easily obscured by cluttered backgrounds, especially with limited edge computing resources. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model's sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, we conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 90.1% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.

Evolutionary algorithms find applicability in reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using evolutionary algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. The author previously reported experimental evaluations on Evolution Strategy for reinforcement learning of neural networks, utilizing the Acrobot control task. In this study, Genetic Algorithm is adopted as another instance of major evolutionary algorithms. Experimental results demonstrate that there was no statistically significant difference between the experimental performances of GA and ES, but the priority of generations and offsprings was different; GA performed better with a greater number of generations while ES performed better with a greater number of offsprings. Eight hidden units were the best among four variations (4, 8, 16 or 32 units), which aligns with previous study using ES.

Analyzing network robustness against random failures or malicious attacks is a critical research issue in network science as it helps to enhance the robustness of beneficial networks or efficiently disintegrate harmful networks. Most studies commonly neglect the impact of the attack success rate (ASR) and assume that attacks on the network will always be successful. However, in real-world scenarios, an attack may not always succeed. This paper proposes a novel robustness measure called Robustness-ASR (RASR), which utilizes mathematical expectations to assess network robustness when considering the ASR of each node. To efficiently compute the RASR for large-scale networks, a parallel algorithm named PRQMC is presented, which leverages randomized quasi-Monte Carlo integration to approximate the RASR with a faster convergence rate. Additionally, a new attack strategy named HBnnsAGP is introduced to better assess the lower bound of network RASR. Finally, the experimental results on 6 representative real-world complex networks demonstrate the effectiveness of the proposed methods compared with the state-of-the-art baselines.

A long time has passed since COVID-19 was discovered and widely disseminated. Both machine learning and deep learning have moved towards the research of diagnosing COVID-19. Compared to deep learning, traditional machine learning-based methods can also achieve good diagnostic results if they are improved based on innovative points. And deep learning remains a more popular research object. Based on the deep neural network in the field of deep learning, the convolutional neural network, recurrent neural network, long and short-term memory network, and Transformer model have been extended. These models improve the performance and processing power of neural networks by introducing new structures and algorithms. This paper will introduce the basic concepts of machine learning and deep learning, as well as the details of using the relevant methods of both to help diagnose COVID-19.

In recent years web applications and on-line business transactions have grown many folds. Consequently, also cyberattacks have increased and represent a serious threat to the pervasive digital services upon which our society relies. To mitigate cyberattacks, many countermeasures are deployed on computing nodes (e.g., anti-malware software) as well as on network devices to detect and possibly block malicious packets in transit; these monitoring devices broadly go under the name of firewalls. Firewalls are designed according to two main architectural approaches: software running on a standard or embedded computer, or purposedly designed hardware, e.g., ASICs. Software-based solutions have the advantage of high flexibility and can be ported on easily upgradable hardware. However, hardware implementation represents the only viable solution for high data rates. On the market, very fast devices of the latter kind are available, but their cost is typically very high, especially considering that their ultra-optimized design makes updating them very difficult, with the consequence of a rather short lifespan. As a more balanced alternative, we wanted to investigate the use of an FPGA architecture, , which is significantly easier to update than custom-built chips, and features low-latency and high-throughput characteristics concurrently, making it preferrable to other programmable systems based on GPUs or microcontrollers. In this paper a packet sniffer that has been designed on FPGA with a 1 Gbit/s data transfer rate is presented. The system is implemented on the FPGA development board KC705 by Xilinx, can analyze Ethernet frames, checking the frame fields against a set of rules defined by the user and calculates statistics of the received Ethernet frames over time. The designed packet sniffer has been successfully tested both with Ethernet frames ad hoc generated using a packets generator, and with real web traffic by connecting the packet sniffer to the internet.

Primary central nervous system and brain tumors are one of the global burdens that are continuously increasing in cases and requiring more treatment options. Surgery has been the leading treatment option for tumors, however, the localization of the tumor and its infiltrating nature make this option challenging. DNA microarray expression profiles of different CNS tumors provide insight into potential biomarkers for identifying different tumor types and subtypes. Here, we utilized the differentially expressed genes common in four expression profiles, GSE66354, GSE68848, GSE74195, and GSE43290 to reconstruct the gene co-expression network. In this study, we were able to identify preserved cluster genes, hub genes, co-regulating transcription factors, miRNA families, and candidate repurposed drugs. Fourteen identified hub genes, which were, CACNA1A, DNM1, GABRA1, GRIA2, MAPT, SLC17A7, SNAP25, SNAP91, STXBP1, SYT1, COL1A1, COL6A2, FBN2, and FN1 appeared to play a role in tumor progression and may serve as drug targets. We also reported the DEGs in each tumor type, which were ATRT, EPN, PA, MED, PNET, MEN, ACM, ODG, and GBM. Five identified miRNA families, which were, let-7 family, mir-124 family, mir-1 family, mir-103 family, and mir-27 family described in the literature to have tumor-suppressing characteristics. Drug-gene and drug-transcription factor network revealed 32 candidate repurposed drugs and 13 were validated through connectivity map analysis. Here, two main repurposed drugs fit the regulatory requirement for gene interaction, these were, quercetin and vorinostat. Future validation in experimental studies may utilize the future use of the candidate repurposed drugs. Our study provides insights into drug repurposing prospects and understanding tumor expressions.

With the deepening of the diversification and openness of financial system, financial vulnerability, as an endogenous attribute of financial system, becomes an important measurement of financial security. Based on network analysis, we introduce network curvature indicator improved by Copula entropy as an innovative metric of financial vulnerability. Compared with previous network curvature analysis method, CE-based curvature proposed in this paper can measure market vulnerability and systematic risk with significant advantages.

Evolutionary algorithms find applicability in the reinforcement learning of neural networks due to their independence from gradient-based methods. To achieve successful training of neural networks using evolutionary algorithms, careful considerations must be made to select appropriate algorithms due to the availability of various algorithmic variations. The author previously reported experimental evaluations on Evolution Strategy for reinforcement learning of neural networks, utilizing the pendulum control task. In this study, the Acrobot control task is adopted as another task. Experimental results demonstrate that ES successfully trained a Multi-Layer Perceptron to achieve a remarkable height of 99.85% concerning the maximum height. However, the trained MLP failed to maintain the chain end in an upright position throughout an episode. In this study, it was observed that employing 8 hidden units in the neural network yielded better results with statistical significance compared to using 4, 16, or 32 hidden units. Furthermore, the findings indicate that a larger population size in ES led to a more extensive exploration of potential solutions over a greater number of generations, which aligns with the previous study.

Near Earth Asteroids represent potential threats to human life because their trajectories may bring them in the proximity of the Earth. Monitoring these objects could help predict future impact events, but such efforts are hindered by the large numbers of objects that pass through the Earth’s vicinity. Additionally, there is also the problem of distinguishing asteroids from other objects in the night sky, which implies sifting through large sets of telescope image data. Within this context, we believe that employing machine learning techniques could greatly improve the detection process by sorting out the most likely asteroid candidates to be reviewed by human experts. At the moment, the use of machine learning techniques is still limited in the field of astronomy and the main goal of the present paper is to study the effectiveness of deep CNNs for the classification of astronomical objects, asteroids in this particular case, by comparing some of the well-known deep convolutional neural networks, including InceptionV3, Xception, InceptionResNetV2 and ResNet152V2. We have applied transfer learning and fine-tuning on these pre-existing deep convolutional networks and from the results that we have obtained one can see the potential of using deep convolutional neural networks in the process of asteroid classification. The InceptionV3 model has the best results in the asteroid class, meaning that by using it, we loose the least number of valid asteroids.

Stemming from the object overlap and undertraining from the few samples, the road dense object detection is confronted with the poor object identification performance and the inability to recognize edge objects. Based on this, one transfer learning-based YOLOv3 approach for identifying dense objects in the road has been proposed. Firstly, Darknet-53 network structure is adopted to obtain pre-trained YOLOv3 model, then the transfer training is introduced as the output layer for the special dataset of 2000 images containing vehicles; in the proposed model, one random function is adapted to intialize and optimize the weights of the transfer training model, which is seperately designed from the pre-trained YOLOv3; and the object detection classifier replaces the fully connected layer, which further improves the detection effect, the reduced size of the network model can further reduce the training and detection time, and can be better applied to actual scenarios. The experimental results demonstrate that the object detection accuracy of the presented approach is 87.75% for the Pascal VOC 2007 dataset, which is superior to the traditional YOLOv3 and the traditional YOLOv2 by 3.05% and 11.15%, respectively. Besides, the test was carried out using UA-DETRAC, a public road vehicle detection dataset, the object detection accuracy of the presented approach reaches 79.23% in detecting images, which is 4.13% better than the traditional YOLOv3, and compared with the existing relatively new object detection algorithm YOLOv5, the detection accuracy is 1.36% better. Moreover, the detection speed of the proposed YOLOv3 method reaches 31.2 Fps/s in detecting images, which is 7.6 Fps/s faster than the traditional YOLOv3, and compared with the existing relatively new object detection algorithm YOLOv5, the speed is 4.3 Fps/s faster; the proposed YOLOv3 performs 79.38Bn of floating point operations per second in detecting video, which obviously surpasses the traditional YOLOv3 and the newer object detection algorithm YOLOv5.

The increase and diversity of low-cost Air Quality (AQ) sensors, as well as their flexibility and low power consumption, offers us the opportunity to integrate them into a broad AQ wireless sensor networks with the aim of enabling real-time monitoring and higher spatial sampling density of pollution in all parts of the cities. Considering that the vast majority of the population lives in these cities and the increase in respiratory/allergic problems in a large part of the population, it is of great interest to offer services and applications to improve their quality of life. In the ECO4RUPA project we focus on this kind of service, proposing an inclusive and intelligent routing ecosystem carried out by using a network of low-cost AQ sensors with the support of 5G communications along with official AQ monitoring stations, assisted with artificial intelligence to improve the AQ monitoring data and by spatial interpolation techniques to enhance its spatial resolution. The goal of this service is to calculate healthy walking and/or cycling routes according to the particular citizen’s profile and needs. We provide and analyse the results of the proposed route planner under different scenarios (different time tables, congestion road traffic and routes) and different user’s profiles, with special interest on citizens with asthma and pregnant women, since both require special needs. In summary, our approach can lead to an approximately average reduction in pollution exposure of 17.82%, while experiencing an approximately average increase in distance travelled of 9.8 %.

Social network analysis is extensively employed for the examination of relationships and networks among actors across diverse disciplines and thematic research domains. Nevertheless, the utilization of this approach in agriculture and natural resources, particularly pertaining to watershed management, has been relatively limited. The objective of this study is to conduct an analysis of the social interaction and networks of Cidanau Watershed Management (CWM) stakeholders and measure the nodes of units as individuals or organizations in relation to the role and influence of each other through a quantitative approach. The results of the data analysis show that Fkdc has a high degree of centrality and centrality betweenness. This shows that Fkdc has a strong influence and controls CWM network interaction. Conversely, Hs (households) have a low degree of centrality, and centrality betweenness values have a low influence and role in actors’ networks. According to the closeness centrality parameter, it is observed that both Households (Hs) and Universities (Univ) have exhibited the shortest geodesic distance in relation to other stakeholders within the network, thus indicating their highest level of closeness. It means that households and universities had interdependency and were controlled by others. The lowest centrality of Fkdc means that Fkdc has independence of influence and high control access over others. There are four CWM network clusters based on total link strength. Fkdc demonstrates outstanding leadership qualities, enjoys a strong reputation, and possesses a high degree of popularity within the network. Furthermore, Fkdc serves as a positive central node that effectively brings together the interests of all actors, fostering a collective commitment towards shared goals and mutual rewards. In the CWM case, Fkdc is a sustainable watershed organization that acts as a central network body and plays a fundamental role as an intermediary between networks and interactions. Ultimately, with regards to the viewpoint of CWM, the decentralization of watersheds aimed to facilitate wider public engagement by establishing Fkdc as a central network entity and assuming a crucial role as a medium for the dissemination of information, exchange of ideas, and the exertion of influence among its members.

In this paper we derive a unified perspective for Optimal Transport (OT) theory and Mean Field Control (MFC) theory to analyse the learning process for Neural Networks algorithms in a high-dimensional framework. We consider Mean Field Neural Networks in the context of MFC theory, specifically the mean field formulation of OT theory that allows the development of highly efficient algorithms while providing a powerful tool in the context of explainable Artificial Intelligence.

This study probes the probabilistic features of major fire hazards in enclosed spaces to establish their importance to the occurrence of fires onboard ro-ro passenger ships and in turn to raise effective operational countermeasures. Distinct from the previous studies, the present research employs Bayesian Network (BN) analysis to determine the probabilities of fire hazards more effectively. The findings of the research include five critical basic events (BE) identified namely, vehicle engine fire (fuel system fault), vehicle electric fire (electrical equipment defect or short circuit), used car electrical fire, reefer units electrical fire (electrical appliances defects or short circuit), and cargo spontaneous combustion. Additionally, the risk of fire for lithium - ion battery powered vehicles is also highlighted in the process of BN analysis, which prompts the authors to propose preventive measures for mitigating the possibility of fire occurrence on this type of electric vehicles. It is hoped that these measures can be essential justifications for establishing relevant rules regarding carrying LIB vehicles in enclosed spaces on international level.

For centuries, Foeniculi fructus (F. fructus) has been used as a traditional herbal medicine in China and Europe and is widely used as a natural therapy for digestive disorders, including indigestion, flatulence, and bloating. The mechanism by which F. fructus alleviates functional dyspepsia was analyzed through network pharmacology, and its therapeutic effect on an animal model of functional dyspepsia was investigated. The compounds, targets, and related diseases of F. fructus were studied utilizing the traditional Chinese medicine systems pharmacology (TCMSP) database. Information on the target genes was classified using the UniProt database. A network was built using Cytoscape 3.9.1, and functional dyspepsia-related genes were checked using the Cytoscape string application. The efficacy of F. fructus on functional dyspepsia, including gastroparesis and gastrointestinal motility, was confirmed by treatment with its extract in a mouse model of loperamide-induced functional dyspepsia. Seven compounds targeted twelve functional dyspepsia-associated genes. In a functional dyspepsia mouse model, F. fructus significantly suppressed the symptoms when compared to that in the control group. Our animal studies showed that the mechanism of action of F. fructus is closely related to gastrointestinal motility. Based on animal experimental results, the results showed that F. fructus provides a potential means to treat functional dyspepsia, suggesting that its medical mechanism for functional dyspepsia can be described by the relationship between seven key compounds of F. fructus, including oleic acid and β-sitosterol, and 12 functional dyspepsia-related genes.

The intrinsic non-linearity and complexity of suspended sediment dynamics, which are impacted by the geographical variability of basin parameters and temporal climatic patterns, make it difficult to estimate suspended sediment concentration (SSC) accurately in hydrological processes. Deep neural networks (DNNs), a cutting-edge modeling method that can capture the innate non-linearity in hydrological systems, have emerged as a solution to this problem. Using primary data on discharge, SSC, and turbidity, the long short-term memory method of DNNs was employed in this study to simulate the discharge-suspended sediment connection for the Esopus Creek, NY, USA as the first objective. To develop effective modeling strategies, multiple scenarios of feature selection, including combinations of discharge, turbidity and SSC for preceding days, were considered. Secondly, the variations in SSC and discharge between the three USGS gages along Esopus Creek that were upper stream, lower stream, and downstream, adjacent to the pourpoint were analyzed. Statistical metrics and scenarios of feature importance were used to evaluate the effectiveness of the DNN-based models. The study shows that among 24 DNN approaches feature selection is crucial in simulating the daily SSC, and discharge and presenting novel research directions for utilizing machine learning algorithms in water quality.

With the rise of piano teaching in recent years, many people have joined the team of piano learners. However, the expensive cost of manual instruction and the unique one-on-one teaching model have made piano learning an extravagant event. Most existing approaches based on the audio modality aim to evaluate piano players' skills. Unfortunately, these methods ignored the information contained in the video, which led to a one-sided and simplistic evaluation of the piano player's skills. More recently, multimodal-based methods are proposed to assess the skill level of piano players using both video and audio information. However, existing multimodal approaches use shallow networks to extract video and audio features, which are deficient in extracting complex spatio-temporal and time-frequency features from piano performance. Furthermore, the fingering and the pitch-rhythm information of the piano performance is contained in the spatio-temporal and time-frequency features, respectively. In the paper, we propose a ResNet-based audio-visual fusion model that combines video and audio features to assess the skill level of piano players. Firstly, ResNet18-3D is used as the backbone network for our visual branches, which can extract feature information from the video data. Then, we consider ResNet18-2D as the backbone network of the aural branch and extract the feature information from the audio data. The extracted video features are fused with the audio features to generate multimodal features for the final piano skill evaluation. The experimental results on the PISA dataset show that our proposed audio-visual fusion model, with a validation accuracy of 70.80%, outperforms the state-of-the-art methods in both performance and efficiency. Then, we also explore the impact of different layers of ResNet on model performance, and the experimental results show that the audio-visual fusion model dealing with the piano skill assessment problem can make full use of both feature information when the number of video features is close to the number of audio features.

Data-driven models based on artificial intelligence are efficiently used to solve complex problems. The quality of groundwater is of utmost importance, as it directly impacts human health and the environment. In major parts of the world groundwater is the main source of drinking water, it is essential to periodically monitor water quality. Conventional water quality monitoring techniques involve periodical collection of water samples and analysis in the laboratory. This process is expensive, time consuming and involves lot of manual labor. The aim of our study is to build an ant colony optimized neural network for predicting groundwater quality parameters. We have proposed artificial neural network comprising of six hidden layers. The approach was validated using our groundwater quality dataset of a hard rock region in the northern part of Karnataka, India. Groundwater samples were collected by us periodically from March 2014 to October 2020 from 50 wells in this region. These samples where analysed for measuring the pH, Electrical Conductivity, Na+, Ca+, Na+, K+, Mg2+, F-, Cl- and U+. The temporal dataset was split for training, testing and validation of our model. Metrics such as R2 (Coefficient of Determination), RMSE (Root Mean Squared Error), NSE (Nash–Sutcliffe efficiencies) and MAE (Mean Absolute Error) were used to evaluate the prediction error and model performance. These performance evaluation metrics indicated the efficiency of our model in predicting the temporal variation in groundwater quality parameters. The method proposed by us can be used for prediction and the temporal frequency of sample collection can be reduced to save time and cost. The results also confirm that the combination of artificial neural network with ACO is a promising tool to optimize weights while training the network, and hence will help in reasonable prediction of groundwater quality parameters.

The rampant misuse of drones poses a serious threat to national security and human life. Currently, the CNN method has been widely used in drone detection. However, there is a challenge that traditional CNN cannot cope with, which is small drone targets often have reduced amplitude or even lost features in infrared images. This paper proposes a Progressive Feature Fusion Network (PFFNet) that gradually increases the response amplitude of the target in the deep network. The Feature Selection Model (FSM) is designed to improve the utilisation of the output coding graph and enhance the feature representation of the target in the network. A lightweight segmentation head is also designed to achieve progressive feature fusion with multi-layer outputs. Experimental results show that the proposed algorithm can achieve low duration and high accuracy in drone target detection. On the public dataset, the IoU is improved by 2.53% and the detection time is reduced by 81.03%.

Cancer is a major concern for people, and accurately predicting the probability of cancer incidence and mortality is an important research topic. With the development of big data and artificial intelligence technology, a new machine learning model has emerged. Using 72,591 pieces of data, including age, case count, population size, race, gender, site of onset, and year of discovery, we built a machine learning model. Through calculations, we found that the decision tree, random forest, logistic regression, support vector machine, and neural network achieved testing accuracies of 62.11%, 61.68%, 54.53%, 55.72%, and 63.10%, respectively. With the help of this model, scientists and policymakers can accurately predict future cancer incidence and mortality rates through databases, allowing them to make relevant policies (such as timely allocating doctors and medical resources) to better serve the people.

Limited accessibility in some parts of Indonesia causes difficulties in logistic distribution, especially for emergency and medical supplies. Emerging drone cargo technology is a potential solution to improve logistic distribution in those areas. However, implementing drone cargo technology involves unknown risks, both in technical and non-technical aspects. Since data on drone operations in Indonesia is limited, a new method is explored to build a Bayesian Network (BN) model for risk analysis of drone crashes in Indonesia’s outermost and underdeveloped areas. The method optimizes the modelling process, in which significant risk factors are selected based on three drone operator companies’ experiences, which include wind speed, rain intensity, and system component failure or malfunction. Real wind speed and rain probability data are then implemented in the model. The operator’s data shows that wind speed contributes to drone crashes, which can be appropriately modelled in the BN model. The model produced a probability of safe operation of 94.1%, comparable to the annual operator’s data. The result shows that most operations are safe, with a minimum case of crashing and no case of harming human life.

Diabetes mellitus is a popular life-threatening disease and patients may gradually have started suffering from other diabetes-causing diseases such as heart attacks, stroke, hypertension, blurry vision, blindness, foot ulcer, amputation, kidney damage and other organ failures before diagnosis. Early detection can help reduce the fatality of this disease. Deep learning models have proven very useful in disease detection and computer-aided diagnosis. In this work, we proposed a deep unsupervised machine learning model for early detection of diabetes using voting ensemble feature selection and deep belief neural networks (DBN). Dataset was obtained from an online repository containing responses of prediagnosed patients to direct questionnaires administered in Sylhet Diabetes Hospital in Sylhet, Bangladesh. The dataset was preprocessed and preprocessed. Features were reduced using the ensemble feature selector. The DBN model was pretrained and tuned to obtain optimal performance. The model was also compared with other models with no multiple hidden layers. The DBN performed at its relative best with F1-measure, precision and recall of 1.00, 0.92 and 1.00 respectively. We conclude that DBN is a useful tool for an unsupervised early prediction of Type II diabetes mellitus.

Herdsmen use different techniques, as per varying geographies and cultures, to keep the cohesion within herds and avoid animals getting lost or predated. However, there is no study on the social behaviour of yaks and on herdsmen management practices. Therefore, this ethology study was initiated by ethnographic inquiries. In Manang, the success of the shepherd is dictated by his personal attribute of “Khula man” or open-heartedness. This attribute refers to good intentions and emotions such as empathy that allows the shepherd to focus more on others than on ownself. This cultural method of assessing the skills required to become a successful and knowledgable shepherd guided us to study the effect of cultural values on the herd’s social behavior. We collected data from two herds living at the same settlement (Yak kharka, 4,100 m altitude, Nepal) by equipping them with loggers. One of the herdsman used the tether rope while other did not. Moreover, the Thaku herd had a more proactive shepherd than the Phurba one. In each herd, 17 animals were equipped with one actigraph wgt3x-BT to measure activity using accelerometer and spatial associations using proximity recorder. One of the herds was equipped with GPS (N=11) as well. Using GPS locations and activity, we showed that the two herds were cohesive and synchronised their activities but the herd with the tether rope was more cohesive. The shepherds also have personal knowledge of the social relationships of their herds and use these relationships to keep the group cohesive and to well manage cattle.

We propose a forward-only multi-layer encoding-decoding framework based on the principle of Maximal Coding Rate Reduction (MCR$^2$), an information-theoretic metric that measures a statistical distance between two sets of feature vectors up to the second moment. The encoder directly transforms data vectors themselves via gradient ascent to maximize the MCR$^2$ distance between different classes in the feature space, resulting in class-wise mutually orthogonal subspace representations. The decoder follows a process symmetric to the encoder, and transforms the subspace feature vectors via gradient descent to minimize the MCR$^2$ distance between the reconstructed data and the original data. We show that the encoder transforms data to linear discriminative representations without breaking the higher-order manifolds, and the decoder reconstructs the data with high fidelity.

Biochemical oxygen demand (BOD) is one of the most important factors to consider when evaluating water contamination. BOD5 is the amount of oxygen consumed in five days by microorganisms that oxidize biodegradable organic materials in an aerobic biochemical manner. The primary objective of this effort is to use microbial fuel cells (MFCs) to shorten the time required for BOD5 measurements. We created a regression artificial neural network (AI), and the predictions we obtained for BOD5 measurements were taken over 6 – 24 hours with an average error of just 7%. The outcomes demonstrated by our AI MFC/BES BOD5 sensor’s viability for use in real-world scenarios.