Even today, the automatic digitisation of scanned documents in general but especially the automatic optical music recognition (OMR) of historical manuscripts still remain an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th-12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes, that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neume and pitch, that is melody information that can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm, based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F1-score of over 99% for both detecting lines and complete staves. For the music symbol detection we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm recognises these symbols with an F1-score of over 96% if the type is ignored and predicts the true symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87%. If only the NCs without their respective connection to a neume, all clefs, and accidentals are of interest the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90%.

Land Surface Temperature (LST) is significant for climatological and environmental studies. LST products from satellites, however, suffer from the tradeoff between spatial and temporal resolution. Spatial downscaling has emerged as a well explored field aiming to overcome limitations arising from this tradeoff. Previous research on regression based LST downscaling models focused on utilizing predictors derived from optical imagery. Weather-dependency of optical imagery data, however, can influence downscaling models by the weather conditions. To cope this issue, in this study, we involve predictors derived from the weather-independent Sentinel-1 Synthetic Aperture Radar (SAR) imagery to downscale Landsat-8 LST data. In this context, we propose to use machine learning techniques, namely Random Forest (RF) and Convolutional Neural Networks (CNN). To demonstrate the applicability and performance of the proposed method, extensive experimental analyses were conducted over Zuid-Holland in the Netherlands. From the experiments, we found that the results obtained with radar predictors were comparable to those achieved using optical predictors. This confirms that the proposed method indeed paves a new way for mapping land surface temperature using SAR images.

Radio Frequency Interference (RFI) detection and characterization play a critical role to in ensuring the security of all wireless communication networks. Advances in Machine Learning (ML) have led to the deployment of many robust techniques dealing with various types of RFI. To sidestep an unavoidable complicated feature extraction step in ML, this paper proposes an efficient end-to-end method using the latest advances in deep learning to extract the appropriate features of the RFI signal. Moreover, this study utilizes the benefits of transfer learning to determine both the type of received RFI signals and their modulation types. To this end, the scalogram of the received signals is used as the input of the pre-trained convolutional neural networks (CNN), followed by a fully-connected classifier. This study considers a digital video stream as the signal of interest (SoI), transmitted in a real-time satellite-to-ground communication using DVB-S2 standards. To create the RFI dataset, the SoI is combined with three well-known jammers namely, continuous-wave interference (CWI), multi- continuous-wave interference (MCWI), and chirp interference (CI). This study investigated four well-known pre-trained CNN architectures, namely, AlexNet, VGG-16, GoogleNet, and ResNet-18, for the feature extraction to recognize the visual RFI patterns directly from pixel images with minimal preprocessing. Moreover, the robustness of the proposed classifiers is evaluated by the data generated at different signal to noise ratios (SNR).

Detailed flow distributions in vascular systems are the key to identifying hemodynamic risk factors for the development and progression of vascular diseases. Although computational fluid dynamics (CFD) has been widely used in bioengineering research on hemodynamics predictions, not only are high-fidelity CFD simulations time-consuming and computing-expensive, but also not friendly to clinical applications due to the difficulty of comprehensive numerical calculations. Machine learning (ML) algorithums to estimate the flow field in vascular systems based on the angiographic images of the blood flow using existed diagnostic tools are emerging as a new pathway to facilitate the mapping of hemodynamics. In present work, the dye injection in a water flow was simulated as an analogy of the contrast perfusion in blood flow using CFD. In the simulation, the light passes through the flow field and generates projective images, as an analogy of X-ray imaging. The simulations provide both the ground truth velocity field and the projective images of the flow with dye patterns. A rough velocity field was estimated using the optical flow method (OFM) based on projective images. ML algorithums are then trained using the ground truth CFD data and the OFM velocity estimation as the input. Finally, the interpretable (logistic regression) and deep (neural networks, convolutional neural networks, long short term memory) machine learning models are validated by using parallel in vitro experiments on the same flow setup. The validation results showed that the employed ML model significantly reduced the error rate from 53.5% to 2.5% in average for the v-velocity estimation.

Accurate and efficient medicinal plant image classification is of utmost importance as these plants produce a wide variety of bioactive compounds that offer therapeutic benefits. With a long history of medicinal plant usage, different parts of plants, such as flowers, leaves, and roots, have been recognized for their medicinal properties and are used for plant identification. However, leaf images are extensively used due to their convenient accessibility and are a major source of information. In recent years, transfer learning and fine-tuning, which use pre-trained deep convolutional networks to extract pertinent features, has emerged as an extremely effective approach for image identification problems. This study is leveraging the power of three component deep convolutional neural networks, namely VGG16, VGG19 and DenseNet201, to derive features from the input images of the medicinal plant dataset, containing leaf images of 30 classes. The models were compared and ensembled to make four hybrid models to enhance the predictive performance by utilizing the averaging and weighted averaging strategies. Quantitative experiments were carried out to evaluate the models on the Mendeley medicinal leaf dataset. The resultant ensemble of VGG19+DensNet201 with fine-tuning showcases enhanced capability in identifying medicinal plant images with an improvement of 7.43% and 5.8% compared with VGG19 and VGG16. Furthermore, VGG19+DensNet201 can outperform its standalone counterparts by achieving an accuracy of 99.12% on the test set. A thorough assessment with metrics such as accuracy, recall, precision, and f1-score firmly establishes the effectiveness of the ensemble strategy.

The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.

Iron ore processing involves critical steps that affect the quality of the final product. Determining the diameter of the pellets is the necessary initial step for volume measurement and, ultimately, for porosity and bulk density measurement, crucial characteristics for optimizing the burning process in the blast furnace. Traditional measurement methods using mercury present issues related to operator safety and environmental preservation, while the practices described in ISO 4698 standard require lengthy preparation and execution time. In light of environmental needs, operator safety, and the time consumed in tests, implementing a new method based on digital image processing and convolutional neural networks for measuring the diameter of burnt iron ore pellets is proposed. The methodology involves capturing images of the pellets using a high-resolution camera and utilizing digital image processing and neural networks capable of performing pixel-by-pixel object segmentation in the images, providing precise information about the pellets to calculate their volume automatically. The results were compared with those obtained using traditional methods, evaluating their conformity with the ISO 4698 standard. In conclusion, this study offers a new approach to measuring the volume of burnt iron ore pellets, providing accurate and reliable results in compliance with safety and environmental preservation standards.

During planetary exploration mission operations, one of the key responsibilities of the instrument teams to determine data viability for subsequent analysis. During the 2019 CanMoon Lunar Sample Return Analogue Mission, the Lead Raman Specialist manually examined each spectra to provide quality assurance/validation. This non-trivial process requires years of experience to complete accurately. With the proven efficacy of Convolutional Neural Networks (CNNs) in classification tasks, and the increased use of automation and control loops on planetary space platforms for navigation and science targeting, an opportunity presents itself to approach this validation problem utilising CNNs. We present the Generalised Raman Validation Network (GRaVN), an neural network focused specifically on extracting the generalised structure of Raman spectra for quality assurance/validation. This work demonstrates the viability of utilising a CNN network in validation activities for Raman spectroscopy. Utilising only two hidden layers, a configuration was developed that provided good levels of accuracy on a manually curated dataset. This indicates that such a system could be useful as part of an autonomous control loop during planetary exploration activities.

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or additional aides and do not have a global optimum guarantee. We propose the use of the multi-label manifold ranking (MR) method in solving the linear objective energy function in a continuous domain to delineate visual objects and solve these problems. We present a novel embedded single stream optimization method based on the manifold ranking (MR) model to avoid approximations without sacrificing expressive power. In addition, we propose a novel network, which we refer to as dual multi-scale manifold ranking (\textbf{DMSMR}) network, that combines the dilated, multi-scale strategies with the single stream MR optimization method in the deep learning architecture to further improve the performance. Experiments on high resolution images, including close-range and remote sensing datasets, demonstrate that the proposed approach can achieve competitive accuracy without additional aides in an end-to-end manner.

In recent times, using image-based deep learning techniques has been very useful for classifying fruits. However, mango is a particular challenge because its shelf life is directly related to the degree of maturity at the time of harvest, which is determined mainly through the visual assessment of the operators when sorting them, doing it incorrectly, coupled with the blows and compressions exposed during storage and transport, trigger the deterioration in their quality, hence the importance of this operation. In this sense, the purpose of this study focuses on designing a computational model based on Deep Learning that uses a convolutional neural network (CNN) parameterized to select mangoes according to their color tone based on their maturity stage. A dataset was established from 201 labeled images, then a CNN architecture was built, obtaining a model on which 3 criteria were evaluated: the number of convolution and grouping layers, the resolution of the input images and the number of training epochs required. As a result, an input image resolution of 32 x 32 pixels was achieved, the process included a convolution layer followed by pooling that fed another layer that processed the results and ended in an output layer with 2 neurons under the One Hot Encoding representation. The model required 20 epochs to perfect its training, achieving 96.04 % accuracy in mango image selection. This study supports the potential of CNNs in quality analysis through mango color selection, even in uncertainty scenarios.

Accurate detection of forest restoration sites using deep learning is crucial for effective ecosystem management, optimizing reforestation efforts, and ensuring environmental sustainability. While various deep learning-based systems have been developed for this purpose, the influence of different neural network architectures on model performance during the identification of forest restoration sites remains underexplored. This study aimed to address this gap by exploring the optimal methodology for extracting and classifying candidate sites for forest restoration based on Convolutional Neural Networks (CNNs), specialized for image recognition. Four categories—arable land, road and barren, quarry, and forest—were defined as candidate sites for forest restoration. A dataset comprising 17,043 samples was divided into training (11,929) and validation (5,114) sets at a ratio of 7:3 for model learning. Model accuracy was evaluated using pixel accuracy (PA) and mean intersection over union (mean IoU). The Resnet152-U-Net model demonstrated a pixel accuracy of 95.2% and a mean IoU of 61.3%, indicating excellent performance in extracting candidate sites for forest restoration. This approach offers spatial and temporal advantages over conventional field surveys or aerial image-based assessments, potentially serving as valuable data for selecting future forest restoration sites.

Insulator defect detection is of great significance to compromise the stability of the power transmission line. The state-of-the-art network of object detection, YOLOv5, has been widely used on insulator and defect detection. However, YOLOv5 network has some limitations like poor detection rate and high computational loads in detecting small insulator defects. To solve these problems, we proposed a light-weight network for insulator and defect detection. In this network, we introduced Ghost module into YOLOv5 backbone and neck to reduce the parameters and model size to enhance the performance in unmanned aerial vehicles (UAVs). Besides, we added small object detection anchors and layers for small defect detection. In addition, we optimized the backbone of YOLOv5 by applying convolutional block attention module (CBAM) to focus on critical information for insulator and defect detection and suppress uncritical information. The experiment result shows the mean average precision (mAP) 0.5 and the mAP0.5:0.95 of our model can reach 99.4% and 91.7%, the parameters and model weight are reduced to 3807372 and 8.79M, which can easily deploy to embedded devices like UAVs. And the speed of detection can reach 10.9ms/image, which can meet the real-time detection requirement.

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. The epileptic seizure prediction models face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model that enhances the capability by utilizing the significant amount of seizure patterns from globally distributed patients with data privacy. The determination of the preictal state is influenced by global and local model-assisted decision-making by modeling the two-level edge layer. Integrating the Spiking Encoder (SE) with Graph Convolutional Neural Network (Spiking-GCNN) works as the local model trained using the bi-timescale approach. Each local model utilizes the aggregated seizure knowledge from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. The proposed seizure prediction is evaluated using benchmark datasets by comparing them with the existing works to demonstrate the potential results.

This research project aimed to address the growing concern about methane emissions from seaweed by developing a Convolutional Neural Network (CNN) model capable of accurately predicting these emissions. The study used PANDAS to read and analyze the dataset, incorporating statistical measures like mean, median, and standard deviation to understand the dataset. The CNN model was trained using the ReLU activation function and mean absolute error as the loss function. Model performance was evaluated through MAPE graphs, comparing the mean absolute percentage error (MAPE) between training and validation sets and between true and predicted emissions, and analyzing trends in yearly greenhouse gas emissions. The results demonstrated that the CNN model achieved a high level of accuracy in predicting methane emissions, with a low MAPE between the expected and actual values. This approach should enhance our understanding of methane emissions from Sargassum, contributing to more accurate environmental impact assessments and effective mitigation strategies.

Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, Convolutional Neural Network-based Deep Neural Network techniques are investigated for the Remaining Useful Life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pre-trained models, using a classic machine learning approach, i.e., Support Vector Regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE=0.058) to that of transfer learning which, instead, remains at a lower or slightly higher level (MAPE=0.416) than Support Vector Regression (MAPE=0.857).

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.

Plant leaf diseases can affect the plants’ leaves to an extent that the plants can collapse and die completely. These diseases may drastically drop the supply of vegetables and fruits to the market, and result in a low agricultural economy. In the literature, different laboratory methods of plant leaf disease detection have been used. These methods were time consuming and could not cover large areas for the detection of leaf diseases. This study infiltrates through the facilitated principles of the Convolutional Neural Networks (CNN) in order to model a network for image recognition and classification of these diseases. Neuroph was used to perform the training of a CNN network that recognized and classified images of the maize leaf diseases that were collected by use of a smart phone camera. A novel way of training and the methodology used, expedite a quick and easy implementation of the system in practice. The developed model was able to recognize 3 different types of maize leaf diseases out of healthy leaves. The Northern Corn Leaf Blight (Exserohilum), Common Rust (Puccinia sorghi) and Gray Leaf Spot (Cerospora) diseases were chosen for this study as they affect most parts of Southern Africa’s maize fields.

Age estimation in dental radiographs Orthopantomography (OPG) is a medical imaging technique that physicians and pathologists utilise for disease identification and legal matters. For example, for estimating post-mortem interval, detecting child abuse, drug trafficking, and identifying an unknown body. Recent development in automated image processing models improved the age estimation's limited precision to an approximate range of +/- one year. While this estimation is often accepted as accurate measurement, age estimation should be as precise as possible in most serious matters, such as homicide. Current age estimation techniques are highly dependent on manual and time-consuming image processing. Age estimation is often a time-sensitive matter in which the image processing time is vital. Recent development in Machine learning-based data processing methods has decreased the imaging time processing; however, the accuracy of these techniques remains to be further improved. We proposed an ensemble method of image classifiers and transfer learning techniques to enhance the accuracy of age estimation using OPGs from one year to a couple of months (1-3-6). This hybrid model is based on convolutional neural networks (CNN) and K nearest neighbours (KNN). The hybrid (HCNN-KNN) model was used to investigate 1,922 panoramic dental radiographs of patients aged 15 to 23. These OPGs were obtained from the various teaching institutes and private dental clinics in Malaysia. To minimise the chance of overfitting in our model, we used the principal component analysis (PCA) algorithm and eliminated the features with high correlation. To further enhance the performance of our hybrid model, we performed systematic image pre-processing. We applied a series of classifications to train our model. We have successfully demonstrated that combining these innovative approaches has improved the classification and segmentation and thus the age-estimation outcome of the model. Our findings suggest that our innovative model, for the first time, to the best of our knowledge, successfully estimated the age in classified studies of one year old, six months, three months and one-month-old cases with accuracies of 99.98, 99.96, 99.87, and 98.78 respectively.

The detection performance of small objects in remote sensing images has not been satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) showed remarkable image enhancement performance, but reconstructed images usually miss high-frequency edge information. Therefore, object detection performance showed degradation for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we applied a new edge-enhanced super-resolution GAN (EESRGAN) to improve the quality of remote sensing images and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance. We proposed an architecture with three components: ESRGAN, EEN, and Detection network. We used residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we used a faster region-based convolutional network (FRCNN) (two-stage detector) and a single-shot multibox detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) dataset and another self-assembled (oil and gas storage tank) satellite dataset showed superior performance of our method compared to the standalone state-of-the-art object detectors.

Machine learning (ML) has a large capacity to learn and analyze a large volume of data. This study aimed to train different algorithms to discriminate between healthy and pathologic corneal images by evaluating digitally processed spectral-domain optical coherence tomography (SD-OCT) corneal images. A set of 22 SD-OCT images belonging to a random set of corneal pathologies was compared to 71 healthy corneas (control group). A binary classification method was applied; three approaches of ML were used. Once all images were analyzed, representative areas from every digital image were also processed and analyzed for a statistical feature comparison between healthy and pathologic corneas. The best performance was obtained from transfer learning - support vector machine (TL-SVM) (AUROC = 0.94, SPE 88%, SEN 100%) and transfer learning – random forest (TL- RF) method (AUROC = 0.92, SPE 84%, SEN 100%), followed by convolutional neural network (CNN) (AUROC = 0.84, SPE 77%, SEN 91%) and random forest (AUROC = 0.77, SPE 60%, SEN 95%). The highest diagnostic accuracy in classifying corneal images was achieved with the TL-SVM and the TL-RF models. In image classification, CNN was a strong predictor. This pilot experimental study developed a systematic mechanized system to discern pathologic from healthy corneas.

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, etc. on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment - pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2022, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, which are multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset and the approach of pre-classification in order to raise the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations. We also found that the ITF reweighting of the training subset increases the approximation quality substantially. The estimates of the SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site.

Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

This paper presents the Advanced Syntactic-Graph Convolutional Model (ASGCM), a pioneering approach in Aspect-Based Sentiment Analysis (ABSA) that integrates syntactic dependency features within a graph convolution framework. ASGCM stands out for its novel use of dependency edge encoding and tag-based graph convolutions, providing a fine-grained analysis of sentiments associated with specific aspects in text. This model meticulously captures the intricacies of syntactic structures, thereby offering enhanced precision in sentiment analysis. Notably, ASGCM incorporates a dual-layer graph convolution system: one layer processes syntactic dependencies (edges), while the other interprets semantic roles (tags), ensuring a comprehensive understanding of both structural and contextual elements in text. We rigorously tested ASGCM on multiple datasets, including both English and Chinese languages, and our findings reveal a significant improvement in sentiment classification accuracy compared to existing models. The versatility of ASGCM makes it a robust tool for diverse linguistic environments, setting a new standard for ABSA methodologies.

Chickpea is one of the most widely consumed pulses globally because of its high protein content. The morphological features of chickpea seed, such as colour, texture, are observable and play a major role in classifying different chickpea varieties. This process is often carried out by human experts, and is time-consuming, inaccurate, and expensive. The objective of the study was to design an automated chickpea classifier using an RGB colour image-based model by considering the morphological features of chickpea seed. As part of the data acquisition process, five hundred and fifty images were collected per variety for four varieties of chickpea (CDC-Alma, CDC-Consul, CDC-Cory, and CDC-Orion) using an industrial RGB camera and a mobile phone camera. Three CNN-based models such as NasNet-A (mobile), MobileNetV3 (small), and EfficientNetB0 were evaluated using a transfer learning-based approach. The classification accuracy was 97%, 99%, and 98% for NasNet-A (mobile), MobileNetV3 (small), and EfficientNetB0 models, respectively. The MobileNetV3 model was used for further deployment on an Android mobile and Raspberry Pi 4 devices based on its higher accuracy and light-weight architecture. The classification accuracy for the four chickpea varieties was 100% while the MobileNetV3 model was deployed on both Android mobile and Raspberry Pi 4 platforms.

Model understanding is critical in many domains, particularly those involved in high-stakes decisions, i.e., medicine, criminal justice, and autonomous driving. Explainable AI (XAI) methods are essential for working with black-box models such as Convolutional Neural Networks. This paper evaluates the traffic sign classifier of Deep Neural Network (DNN) from the Programmable Systems for Intelligence in Automobiles (PRYSTINE) project for explainability. The results of explanations were further used for the CNN PRYSTINE classifier vague kernels` compression. After all, the precision of the classifier was evaluated in different pruning scenarios. The proposed classifier performance methodology was realised by creating the original traffic sign and traffic light classification and explanation code. First, the status of the kernels of the network was evaluated for explainability. For this task, the post-hoc, local, meaningful perturbation-based forward explainable method was integrated into the model to evaluate each kernel status of the network. This method enabled distinguishing high and low-impact kernels in the CNN. Second, the vague kernels of the classifier of the last layer before the fully connected layer were excluded by withdrawing them from the network. Third, the network's precision was evaluated in different kernel compression levels. It is shown that by using the XAI approach for network kernel compression, the pruning of 5% of kernels leads only to a 1% loss in traffic sign and traffic light classification precision. The proposed methodology is crucial where execution time and processing capacity prevail.

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.

Convolutional neural network architectures have become increasingly complex, which has improved the performance slowly on well-known benchmark datasets in the recent years. In this research, we have analyzed the true need for such complexity. We have introduced G-Net light, a lightweight modified GoogleNet with improved filter count per layer to reduce feature overlaps and complexity. Additionally, by limiting the amount of pooling layers in the proposed architecture, we have exploited the skip connections to minimize the spatial information loss. The investigations on the proposed architecture are evaluated on three retinal vessel segmentation publicly available datasets. The proposed G-Net light outperforms other vessel segmentation architectures by reducing the number of trainable parameters..

Optical neural networks (ONNs), or optical neuromorphic hardware accelerators, have the potential to dramatically enhance the computing power and energy efficiency of mainstream electronic processors, due to their ultra-large bandwidths of up to 10’s of terahertz together with their analog architecture that avoids the need for reading and writing data back-and-forth. Different multiplexing techniques have been demonstrated to demonstrate ONNs, amongst which wavelength-division multiplexing (WDM) techniques make sufficient use of the unique advantages of optics in terms of broad bandwidths. Here, we review recent advances in WDM-based ONNs, focusing on methods that use integrated microcombs to implement ONNs. We present results for human image processing using an optical convolution accelerator operating at 11 Tera operations per second. The open challenges and limitations of ONNs that need to be addressed for future applications are also discussed.

Convolutional Neural Networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the Discrete Wavelet Transform and the other on the Constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across three benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art performance across all three data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification (code available at https://github.com/LorisNanni).

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.

In this paper, we present a framework to study the spatial structure of noctilucent clouds formed by ice particles in the upper atmosphere at mid and high latitude during summer. We study noctilucent cloud activity in optical images taken from three different locations and under different atmospheric conditions. In order to identify and distinguish noctilucent cloud activity from other objects in the scene, we employ linear discriminant analysis (LDA) with feature vectors ranging from simple metrics to higher-order local autocorrelation (HLAC), and histogram of oriented gradients (HOG). Finally, we propose a Convolutional Neural Networks (CNN) based method for the detection of noctilucent clouds. The results clearly indicate that the CNN based approach outperforms LDA based methods used in this article. Furthermore, we outline suggestions for future research directions to establish a framework that can be used for synchronizing the optical observations from ground based camera systems with echoes measured with radar systems like EISCAT in order to obtain independent additional information on the ice clouds.

Automated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challenging. These paper present an advanced version of the system presented in [1]. The described system contains several novelties, compared both with its previous version and related work. It is a part of a project of the automatic weeding machine, developed by Warsaw University of Technology and MCMS Warka Ltd. The obtained model reaches satisfying accuracy at over 10~FPS on the Raspberry Pi 3B+ computer. It was tested for four different plant species at different growth stadiums and lighting conditions. The system performing semantic segmentation is based on Convolutional Neural Networks. Its custom architecture mixes U-Net, MobileNets, DenseNet and ResNet concepts. Amount of needed manual ground truth labels was significantly decreased by the usage of knowledge distillation process, learning final model to mimic an ensemble of complex models on the large database of unlabeled data. Further decrease of the inference time was obtained by two custom modifications: in the usage of separable convolutions in DenseNet block and in the number of channels in each layer. In the authors’ opinion, described novelties can be easily transferred to other agrorobotics tasks.

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.

The use of convolutional neural networks (CNNs) in image classification has become the standard method of approaching computer vision problems. Here we apply pre-trained networks to classify images of non-breaking, plunging and spilling breaking waves. The CNNs are used as basic feature extractors and a classifier is then trained on top of these networks. The dynamic nature of breaking waves is exploited by using image sequences to gain extra information and improve the classification results. We also see improved classification performance in using pre-computed image features such as the optical flow between image pairs. The inclusion of the dynamic information improves the classification between breaking wave classes. We also provide corrections to the methodology from the article from which the data originates to achieve a more accurate assessment of performance.

In the context of artificial intelligence's pervasive integration across sectors, the rigorous examination of methodologies used in constructing mathematical models is imperative. This study delves into facial recognition models, particularly in their ability to extract features such as age. We address the prevalent practice of training models with unbalanced datasets and its implications for model performance and bias introduction. Utilizing 27,305 facial images, we investigate the influence of dataset imbalance on age prediction based on ethnicity. Employing preprocessing and oversampling techniques, we equalize sample sizes across ethnicities. A Convolutional Neural Network trained on the balanced dataset serves as our baseline, while three additional models undergo training with a 50% sample size reduction for each group to assess accuracy degradation. Our findings reveal a notable decline in accuracy for ethnic groups with reduced representation. The Asian group experiences a 67.94% accuracy deterioration, followed by a 51.60% drop for the Black group, and a 38.46% decline for the White group. These results underscore the sensitivity of certain ethnic groups to underrepresentation, highlighting the nuanced impact on age prediction accuracy. While a 50% reduction in representation does not uniformly result in a 50% accuracy decline, it unquestionably influences predictive accuracy for affected groups.

Convolutional neural networks (CNNs) have proven to be a very efficient class of machine learning (ML) architectures for handling multidimensional data by maintaining data locality, especially in the field of computer vision. Data pooling, a major component of CNNs, plays a crucial role for extracting important features of the input data and downsampling its dimensionality. Multidimensional pooling, however, is not efficiently implemented in existing ML algorithms. In particular, quantum machine learning (QML) algorithms have a tendency to ignore data locality for higher dimensions by representing/flattening multidimensional data as simple one-dimensional data. In this work, we propose using the quantum Haar transform (QHT) and quantum partial measurement for performing generalized pooling operations on multidimensional data. We present the corresponding decoherence-optimized quantum circuits for the proposed techniques along with their theoretical circuit depth analysis. Our experimental work was conducted using multidimensional data, ranging from 1-D audio data, to 2-D image data, to 3-D hyperspectral data, to demonstrate the scalability of the proposed methods. In our experiments, we utilized both noisy and noise-free quantum simulations on a state-of-the-art quantum simulator from IBM Quantum. We also show the efficiency of our proposed techniques for multidimensional data by reporting the fidelity of results.

Keywords: Convolutional Neural Network, Deep Learning, Skin cancer, Generative Adversarial Network

With the continuous progress of remote sensing image object detection tasks in recent years, researchers in this field have gradually shifted the focus of their research from horizontal object detection to the study of object detection in arbitrary directions. It is worth noting that some properties are different from the horizontal object detection during oriented object detection that researchers have yet to notice much. This article presents the design of a straightforward and efficient arbitrary-oriented detection system, leveraging the inherent properties of the orientation task, including the rotation angle and box aspect ratio. In the detection of low aspect ratio objects, the angle is of little importance to the orientation bounding box, and it is even difficult to define the angle information in extreme categories. Conversely, in the detection of objects with high aspect ratios, the angle information plays a crucial role and can have a decisive impact on the quality of the detection results. By exploiting the aspect ratio of different targets, this letter proposes a ratio-balanced angle loss that allows the model to make a better trade-off between low-aspect ratio objects and high-aspect ratio objects. The rotation angle of each oriented object, which we naturally embed into a two-dimensional Euclidean space for regression, thus avoiding an overly redundant design and preserving the topological properties of the circular space. The performance of the UCAS-AOD, HRSC2016, and DLR-3K datasets show that the proposed model in this paper achieves a leading level in terms of both accuracy and speed. The code is released at https://github.com/minghuicode/Periodic-Pseudo-Domain.

This paper introduces a multi-class hand gesture recognition model developed to identify a set of defined hand gesture sequences in two-dimensional RGB video recordings. The work presents an action detection classifier that looks at both appearance and spatiotemporal parameters of consecutive frames. The classifier utilizes a convolutional-based network combined with a long-short-term memory unit. To leverage the need for a large-scale dataset, the model uses an available dataset to then adopt a technique known as transfer learning to fine-tune the model on the hand gestures of relevance. Validation curves performed over a batch size of 64 indicate an accuracy of 93.95% (± 0.37) with a mean Jaccard index of 0.812 (± 0.105) for 22 participants. The presented model illustrates the possibility of training a model with a small set of data (113,410 fully labelled frames). The proposed pipeline embraces a small-sized architecture that could facilitate its adoption.

Emotion recognition defined as identifying human emotion and is directly related to different fields such as human-computer interfaces, human emotional processing, irrational analysis, medical diagnostics, data-driven animation, human-robot communi- cation and many more. The purpose of this study is to propose a new facial emotional recognition model using convolutional neural network. Our proposed model, “ConvNet”, detects seven specific emotions from image data including anger, disgust, fear, happiness, neutrality, sadness, and surprise. This research focuses on the model’s training accuracy in a short number of epoch which the authors can develop a real-time schema that can easily fit the model and sense emotions. Furthermore, this work focuses on the mental or emotional stuff of a man or woman using the behavioral aspects. To complete the training of the CNN network model, we use the FER2013 databases, and we test the system’s success by identifying facial expressions in the real-time. ConvNet consists of four layers of convolution together with two fully connected layers. The experimental results show that the ConvNet is able to achieve 96% training accuracy which is much better than current existing models. ConvNet also achieved validation accuracy of 65% to 70% (considering different datasets used for experiments), resulting in a higher classification accuracy compared to other existing models. We also made all the materials publicly accessible for the research community at: https://github.com/Tanoy004/Emotion-recognition-through-CNN.

Obesity and overweight is a foremost concern around the globe for each group of age. This can be accelerated by the current imposed lockdown. However, excessive weight gain may result in other chronic diseases. This study has been considering the age group of 25 to 55 years as the sample populations and monitoring them from July, 2020 to November, 2020. The lifestyle of this population, food habit, mental health conditions are explored using deep learning based framework. All these parameters need to be monitored as these have close relation with currently imposed constraints due to COVID-19. A predictive model is constructed using deep learning techniques to predict the risk of gaining weight. The predictive model hybridizes the convolutional layer and gated recurrent neural networks as a unified entity for achieving the objective of early weight gain prediction. The result obtained by this model exhibits an encouraging predictive efficiency of 93.7%.

Paraphrase generation is an important yet challenging task in NLP. Neural network-based approaches have achieved remarkable success in sequence-to-sequence(seq2seq) learning. Previous paraphrase generation work generally ignores syntactic information regardless of its availability, with the assumption that neural nets could learn such linguistic knowledge implicitly. In this work we make an endeavor to probe into the efficacy of explicit syntactic information for the task of paraphrase generation. Syntactic information can appear in the form of dependency trees which could be easily acquired from off-the-shelf syntactic parsers. Such tree structures could be conveniently encoded via graph convolutional networks(GCNs) to obtain more meaningful sentence representations, which could improve generated paraphrases. Through extensive experiments on four paraphrase datasets with different sizes and genres, we demonstrate the utility of syntactic information in neural paraphrase generation under the framework of seq2seq modeling. Specifically, our GCN-enhanced models consistently outperform their syntax-agnostic counterparts in multiple evaluation metrics.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these type of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand, and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

Quantum computing (QC) has opened the door to advancements in machine learning (ML) tasks that are currently implemented in the classical domain. Convolutional neural networks (CNNs) are classical ML architectures that exploit data locality and possess a simpler structure than fully-connected multi-layer perceptrons (MLPs) without compromising the accuracy of classification. However, the concept of preserving data locality is usually overlooked in the existing quantum counterparts of CNNs, particularly for extracting multi-features in multidimensional data. In this paper, we present a multidimensional quantum convolutional classifier (MQCC) that performs multidimensional and multi-feature quantum convolution with average and Euclidean pooling and thus adapting the CNN structure to a variational quantum algorithm (VQA). Average pooling is based on the quantum Haar transform (QHT) and Euclidean pooling is based on partial quantum measurement. The experimental work was conducted using multidimensional data to validate the correctness and demonstrate the scalability of the proposed method utilizing both noisy and noise-free quantum simulations. We evaluated the MQCC model with reference to reported work on state-of-the-art quantum simulators from IBM Quantum and Xanadu using a variety of standard ML datasets. The experimental results showed favorable characteristics of our proposed techniques compared to existing work with respect to a number of quantitative metrics such as the number of training parameters, cross-entropy loss, classification accuracy, circuit depth, and quantum gate count.

Against the backdrop of the current carbon peaking and carbon neutrality policies, higher requirements have been put forward for the upgrading and construction of smart grids. Non-intrusive load monitoring (NILM) technology is a key technology for advanced measurement systems at the end of the power grid. It obtains detailed power information of the load, without the need for traditional hardware deployment. The key step to solve this problem is load decomposition and identification. This paper first utilized Long Short Term Memory-Denoising Autoencoder(LSTM-DAE) to decompose the mixed current signal on the household busbar and obtain the current signals of multiple independent loads that constituted the mixed current. Then, the obtained independent current signals were combined with voltage signals to generate multi-cycle colored Voltage-Current(VI) trajectories, which were color-coded according to the background. These colored VI trajectories with background colors formed a feature library. When the CNN network was used for load recognition, considering the influence of hyperparameters on recognition results, the BOA algorithm was used for optimization, and the optimized CNN network was employed for VI trajectory recognition. Finally, the proposed method was validated using the PLAID dataset. Experimental results showed that the proposed method exhibited better performance in load decomposition and identification.

This research highlights the importance of error-correcting codes in ensuring secure and efficient data transmission over noisy channels. It discusses the application of Convolutional codes and the Viterbi algorithm for error detecting and correcting in applications where the data rate is high and the error probability is relatively low. This research extends beyond previous studies by conducting a comparative analysis of Convolutional codes, the Viterbi algorithm, and alternative coding methods utilized in satellite communication systems, by evaluating their effectiveness and efficiency relative to other coding approaches like BCH, LDPC, and turbo codes. The evaluation encompasses key performance metrics including error correction capabilities, computational complexity, and robustness against various error types. Additionally, practical implementation factors such as power consumption, computational requirements, and compatibility with existing hardware are considered. The analysis sheds light on the advantages and disadvantages of each coding method, offering insights into why convolutional codes and the Viterbi algorithm are particularly suitable for GPS systems.

Recently, deep learning models have been widely applied to modulation recognition, which have become a hot topic due to their excellent end-to-end learning capabilities. However, current methods are mostly based on uni-modal inputs, which suffer from incomplete information and local optimization. To complement the advantages of different modalities, we focus on the multi-modal fusion method. Therefore, we introduce an iterative dual-scale attentional fusion (iDAF) method to integrate multimodal data. Firstly, two feature maps with different receptive field sizes are constructed using local and global embedding layers. Secondly, the feature inputs are iterated into the Iterative Dual Scale Attention Module (iDCAM), where the two branches capture the details of high-level features and the global weights of each modal channel, respectively. The iDAF not only extracts the recognition characteristics of each specific domains, but also complements the strengths of different modalities to obtain a fruitful view. Our iDAF achieves a recognition accuracy of 93.5\% at 10dB and 0.6232 at full SNR. The comparative experiments and ablation studies effectively demonstrate the effectiveness and superiority of the iDAF.

The mutton sheep breeding industry has transformed significantly in recent years, from traditional grassland free-range farming to a more intelligent approach. As a result, automated sheep face recognition systems have become vital to modern breeding practices and have gradually replaced ear tagging and other manual tracking techniques. Although sheep face datasets have been introduced in previous studies, they have often involved pose or background restrictions (e.g., fixing of the subject’s head, cleaning of the face), which restrict data collection and have limited the size of available sample sets. As a result, a comprehensive benchmark designed exclusively for the evaluation of individual sheep recognition algorithms is lacking. To address this issue, this study develops a large-scale benchmark dataset, Sheepface-107, comprised of 5,350 images acquired from 107 different subjects. Images were collected from each sheep at multiple angles, including front and back views, in a diverse collection that provides a more comprehensive representation of facial features. In addition to the dataset, an assessment protocol is developed by applying multiple evaluation metrics to the results produced by three different deep learning models: VGG16, GoogLeNet, and ResNet50, which achieved F1-scores of 83.79%, 89.11%, and 93.44%, respectively. A statistical analysis of each algorithm suggested that accuracy and the number of parameters were the most informative metrics for use in evaluating recognition performance.

Defect detection and identification from fruits and vegetables are particularly challenging for Indian agriculture. Defect Detection is a process to identify the defects or damages in vegetables and fruits, based on the shapes, colors and textures. The local market finds it difficult to cope with the defects and other infections in fruits and vegetables as quality evaluations and classification of vegetables and fruits have become tedious process. Recently, several approaches based on Image processing, Machine Learning and Artificial Intelligence methods have been proposed for the purpose of defect detection. On the basis of classifying the types of defects, related pathogens, and physical and morphological characteristics descriptors, we review the different approaches based on a corpus of 57 articles between 2016 and 2021. In the process of describing the defect analysis, steps from the target articles, algorithms, and methods including qualitative and quantitative evaluation are mainly summarized. The aim of this current review work is to present-day novel images and collects recent defective area calculation methods to detect surface defects of fruits and vegetables using RGB images and to classify whether the fruit is defected or fresh. A rigorous evaluation of many new algorithms provided for quality assurance by researcher’s probes of vegetables and fruits have been conducted in this work. This review work conveys that using the recent identification features will help to decrease the disadvantages in fruit storeroom owing to storage of the affected vegetables and fruits, ie. Preventing the spread of defects and other infections from the infected fruits and vegetables to the fresh ones.

Polar coding gives rise to the first explicit family of codes that provably achieve capacity with efficient encoding and decoding for a wide range of channels. Recently, Arikan presented a new polar coding scheme, which he called polarization-adjusted convolutional (PAC) codes. At short blocklengths, such codes offer a dramatic improvement in performance as compared to CRC-aided list decoding of conventional polar codes. PAC codes are based primarily upon the following main ideas: replacing CRC codes with convolutional precoding (under appropriate rate profiling) and replacing list decoding by sequential decoding. Simulation results show that PAC codes, resulting from the combination of these ideas, are close to finite-length lower bounds on the performance of any code under ML decoding. One of our main goals in this paper is to answer the following question: is sequential decoding essential for the superior performance of PAC codes? We show that similar performance can be achieved using list decoding when the list size $L$ is moderately large (say, $L \geq 128$). List decoding has distinct advantages over sequential decoding in certain scenarios, such as low-SNR regimes or situations where the worst-case complexity/latency is the primary constraint. Another objective is to provide some insights into the remarkable performance of PAC codes. We first observe that both sequential decoding and list decoding of PAC codes closely match ML decoding thereof. We then estimate the number of low weight codewords in PAC codes, and use these estimates to approximate the union bound on their performance. These results indicate that PAC codes are superior to both polar codes and Reed-Muller codes. We also consider random time-varying convolutional precoding for PAC codes, and observe that this scheme achieves the same superior performance with constraint length as low as $\nu = 2$.

This article focuses on generating an alternative in order to identify traffic officers during driving. This research employed the latest You Only Look Once (YOLO) model, using a six-phase methodology: data collection, data preparation involving resizing and labeling, implementation of various filters to avoid overfitting, model training, prediction evaluation, and result interpretation. The YOLO model was applied across three iterations using a dataset of 1862 images. To enhance training efficiency and detection speed, the graphics processing unit (GPU) acceleration was utilized, further enhancing the experimental process. The results of this study revealed that the YOLOv8x variant produced the most promising results. This proposed model attained a remarkable F1 score of 0.95, bolstered by a confidence score of 0.631, with the potential for an increase to 0.80 in confidence without significantly compromising the F1-score. These findings are poised to make a substantial contribution to the broader research landscape, particularly in advancing the effectiveness of detection models for traffic officers.

Facial Emotion Recognition (FER) is crucial across psychology, neuroscience, computer vision, and machine learning due to the diversified and subjective nature of emotions, varying considerably across individuals, cultures, and contexts. This paper investigates the impact of histogram equalization, data augmentation and model optimization strategies on three well-known FER datasets using pre-trained VGG models. Additionally, this paper showcases the effectiveness of different regularization techniques, callbacks, and learning schedulers in enhancing model performance by conducting extensive experiments. The model evaluation is discussed in terms of the following metrics: Accuracy, Area Under the Receiver Operating Characteristic Curve (AUC-ROC), Area Under the Precision-Recall Curve (AUC-PRC), and Weighted F1 score. Notably, the fine-tuned VGG models exhibit state-of-the-art performance compared to more complex conventional transfer learning models resulting in accuracies of 100%, 95.92%, and 69.65% on the CK+, KDEF, and FER2013 datasets, respectively.

Despite the impressive performance of deep neural networks on many different vision tasks, they have been known to be vulnerable to intentionally added noise to input images. To combat these adversarial examples (AEs), improving the adversarial robustness of models has emerged as an important research topic, and research has been conducted in various directions including adversarial training, image denoising, and adversarial purification. Among them, this paper focuses on adversarial purification, which is a kind of pre-processing that removes noise before AEs enter a classification model. The advantage of adversarial purification is that it can improve robustness without affecting the model’s nature, while another defense techniques like adversarial training suffer from a decrease in model accuracy. Our proposed purification framework utilizes a Convolutional Autoencoder as a base model to capture the features of images and their spatial structure. We further aim to improve the adversarial robustness of our purification model by distilling the knowledge from teacher models. To this end, we train two Convolutional Autoencoders (teachers), one with adversarial training and the other with normal training. Then, through ensemble knowledge distillation, we transfer the ability of denoising and restoring of original images to the student model (purification model). Our extensive experiments confirm that our student model achieves high purification performance(i.e., how accurately a pre-trained classification model classifies purified images). The ablation study confirms the positive effect of our idea of ensemble knowledge distillation from two teachers on performance.

Understanding park events and their categorization offer pivotal insights into urban parks and their integral roles in cities. This study utilized images and event category data from the New York City Parks Events Listing database to train a Convolutional Neural Network (CNN) for image-based park event categorization. Different CNN models were tuned to complete this multi-label classification task, their performances compared. Preliminary results underscore the efficacy of deep learning in automating the event classification process, revealing the multifaceted activities within urban green spaces. The CNN showcased proficiency in discerning various event nuances, emphasizing the diverse recreational and cultural offerings of urban parks. Such categorization has potential applications in urban planning, aiding decision-making processes related to resource distribution, event coordination, and infrastructure enhancements tailored to specific park activities.

Forest fire identification is important for forest resource protection. Effective monitoring of forest fires requires the deployment of multiple monitors with different viewpoints, while most traditional recognition models can only effectively recognize images from a single source, often because they ignore the correlation information between images from different viewpoints, resulting in inaccurate visual similarity estimation for multiple source samples and generating the problems of missed and high false alarm rates. In order to solve the problems, a similarity-guided graph neural network model based on the dynamic characteristics of images is proposed in this paper. The method converts the input features of the nodes on the graph into relational features of different gallery pairs by establishing pairs (nodes) that represent different viewpoint images and gallery images. The dynamic feature update of the image gallery using the new feature-bank relationship enables the estimation of the similarity between images and improves the image recognition rate of the model. Besides, to reduce the complicated pre-processing process and extract the key features in the images effectively, this paper also proposes a dynamic feature extraction method for fire regions based on image segment ability. By setting the threshold value of HSV color space, the fire region is segmented from the image and the fire region frames are calculated for dynamic feature extraction. The experimental results on the open-source forest fire dataset and our collected forest fire dataset show that the performance of the method in this paper is improved by 4% compared with Resnet, the theme during this paper may be tailored to totally different fire eventualities and has sensible generalization and interference resistance.

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

Banks are normally offered two kinds of deposit accounts. It consists of deposits like current/saving account and term deposits like fixed or recurring deposits. For enhancing the maximized profit from bank as well as customer perspective, term deposit can accelerate uplifting of finance fields. This paper focuses on likelihood of term deposit subscription taken by the customers. Bank campaign efforts and customer detail analysis can influence term deposit subscription chances. An automated system is approached in this paper that works towards prediction of term deposit investment possibilities in advance. This paper proposes deep learning based hybrid model that stacks Convolutional layers and Recurrent Neural Network (RNN) layers as predictive model. For RNN, Gated Recurrent Unit (GRU) is employed. The proposed predictive model is later compared with other benchmark classifiers such as k-Nearest Neighbor (k-NN), Decision tree classifier (DT), and Multi-layer perceptron classifier (MLP). Experimental study concludes that proposed model attains an accuracy of 89.59% and MSE of 0.1041 which outperform well other baseline models.

Rapid increase in digital data coupled with advances in deep learning algorithms is opening unprecedented opportunities for incorporating multiple data sources for modeling spatial dynamics of human infectious diseases. We used Convolutional Neural Networks (CNN) in conjunction with satellite imagery-based urban housing and socio-economic data to predict disease density in a developing country setting. We explored both single (uni) and multiple input (multimodality) network architectures for this purpose. We achieved maximum test set accuracy of 81.6 per cent using a single input CNN model built with one convolutional layer and trained using housing image data. However, this fairly good performance was biased in favor of specific disease density classes due to an unbalanced data set despite our use of methods to address the problem. These results suggest CNN are promising for modeling spatial dynamics of human infectious diseases, especially in a developing country setting. Urban housing signals extracted from satellite imagery seem suitable for this purpose, under the same context.

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks(CNN) for face verification. In this work, we explore to use identification signal to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on LFW dataset.

Timely and accurate acquisition of information on distribution of the crop planting structure in Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in western China, is crucial for promoting fine management of agriculture and ensuring food security. In this study, the Object-Based Image Classification (OBIC), the Random Forest (RF) and Convolutional Neural Network (CNN) models were employed to classify the crop planting structure of four representative test areas in Qingyang City in a precise manner. Firstly, different optimal segmentation scales for various crops were selected using the Estimation of Scale Parameter 2 (ESP2) tool and the Ratio of Mean Difference to Neighbors(ABS) to Standard Deviation (RMAS)model. The images were then segmented through multiresolution segmentation combined with the Canny Edge Detection algorithm. Secondly, the L1 regularized logistic regression model was utilized to select and optimize 39 spatial feature factors including spectral, textural, geometric, and index features, in conjunction with phenological factors. Lastly, under the multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model, combined with object-based multiresolution segmentation, was used to classify the crop planting structure. The findings show that: Thanks to the Canny Edge Detection algorithm, we can obtain a more complete boundary of the segmented objects and improve the separability. The optimal segmentation scales for corn, vegetables, and buckwheat were found to be 55, 70, and 35, respectively, while wheat and apple had optimal segmentation scales of 65. In addition to phenological characteristics, the number of selected spatial features for corn, vegetables, buckwheat, wheat, and apple were 9, 7, 16, 12, and 10, respectively. The CNN model demonstrated high consistency with the RF model in the classification results, but the accuracy of RF model is higher than that of CNN model on the whole. The overall accuracy of classification using RF model in four test areas registered 91.93%, 94.92%, 89.37% and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields.

Air quality is one of the most concerning problems in major industrialized cities in the world. Prediction of future air quality is highly relevant to public health. In some big cities, multiple air quality measurement stations are deployed at different locations to monitor air pollutants, such as NO2, CO, PM 2.5 and PM 10, over time. At every monitoring time stamp t, we observe one station×feature matrix xt of the pollutant data, which represents a spatio–temporal process. Traditional methods on prediction of air quality typically use data from one station or can only predict a single pollutant (such as PM 2.5) at a time, which ignores the spatial correlation among different stations. Moreover, the air pollution data are typically highly nonstationary, We propose a de-trending graph convolutional LSTM (long short term memory) to continuously predict the whole station×feature matrix in the next 1 to 48 hours, which not only captures the spatial dependency among multiple stations by replacing an inner product with convolution, but also incorporates the de-trending signals (transform a nonstationary process to a stationary one by differencing the data) into our model. Experiments on the air quality data of the city Chengdu and multiple major cities in China demonstrate the feasibility of our method and show promising results.

Accurate prediction of the degree of airport delays under the influence of convective weather is crucial for collaborative traffic management implementation and improving the efficiency of airport operations. However, existing studies usually only consider numerical-type quantitative features of weather-affected traffic in their models, and lack the introduction of spatial information to comprehensively portray the traffic operation scenarios under the influence of weather. In order to overcome this problem, this paper firstly designs a new image representation of weather-affected air traffic, and constructs a multi-channel traffic and weather scene image (MTWSI) by populating the airspace two-dimensional grid with traffic and meteorological information to represent the overall traffic operation situation in the terminal area under the influence of convective weather; then, a deep convolutional neural network-based airport delay prediction model ( ADLCNN), which takes MTWSI images as input and uses a specific CNN model to extract the deep features that affect traffic operation in it to input into the subsequent classification algorithm to predict the flight delay level; finally, a series of comparative experiments are carried out on the operational data of Guangzhou Baiyun Airport, and the experimental validation shows that, compared with the traditional machine learning methods, the proposed CNN-based airport delay prediction The experimental validation shows that the proposed CNN-based airport delay prediction model has satisfactory prediction performance compared with the traditional machine learning methods, which also proves that the proposed MTWSI method can more comprehensively respond to the real traffic conditions.

Human activity recognition (HAR) using wearable sensors is gaining popularity in the healthcare domain, enabling continuous monitoring and timely interventions. The conventional HAR systems are centralised and need data sharing with a server for processing and model training. However, this data sharing leads to various challenges, such as privacy concerns, increased communication and storage costs, inefficient computational algorithms, data scarcity due to unwillingness to share, and difficulty achieving high accuracy and personalised models simultaneously. To overcome these challenges, this paper introduces a privacy and energy-aware federated learning (FL) framework for model training without data sharing. The proposed scheme incorporates spiking neural networks (SNNs), which are particularly suited for resource-constrained devices due to their event-driven information processing. The key idea is to synergise the strengths of SNNs and long short-term memory (LSTM) to create a hybrid model for robust HAR. The proposed hybrid spiking LSTM (S-LSTM) model uses the LSTM as an input layer to capture temporal dependencies efficiently, followed by spiking layers that replace the typical activation using leaky integrate-and-fire neurons. We employ the combination of surrogate gradient learning and backpropagation through time (BPTT) to update the weights of SNN layers in a supervised manner. The performance of the proposed model is evaluated using two publicly available datasets for both indoor and outdoor scenarios. The results show that the proposed S-LSTM performs much better than spike convolutional neural networks (S-CNN) and simple CNN, achieving the accuracy of 97% and 87% for indoor and outdoor datasets, respectively. Personalisation, also known as fine-tuning the global model using local data, is crucial in HAR. It allows the model to adapt to individual behaviour and preferences, making predictions more accurate. The results also show that personalisation improves the performance of participants up to 9% on average. Additionally, analysis with 50% random client participation reduces communication costs by 50% with minimal impact on accuracy.

Generally, when cognitive radio users are in Underlay mode, through the analysis of the electromagnetic spectrum in time, frequency, space, and field of multiple dimensional data accounts for judging the inherent correlation of the radio spectrum used/idle state, this is the realization of cognitive radio users (secondary users, SUs) efficient access to the foundation of the limited spectrum resources. Therefore, how to efficiently use of spectrum status of each SU implementation of reception multidimensional combination forecasting is the core of this paper addressing the problem. In this paper, we propose a deep-learning hybrid model called TensorGCN-LSTM based on the tensor data structure. The model treats SUs deployed at different spatial locations under the same frequency and the spectrum status of SUs themselves under different frequencies in the task area as nodes and constructs two types of graph structures. Graph convolutional operations are used to sequentially extract corresponding spatial-domain and frequency-domain features from the two types of graph structures. Then, the long short-term memory (LSTM) model is used to fuse the spatial, frequency, and temporal features of the cognitive radio environment data. Finally, the prediction task of the spectrum distribution situation is accomplished through fully connected layers. Specifically, the model constructs a tensor graph based on the spatial similarity of SUs' locations and the frequency correlation between different frequency signals received by SUs, which describes the electromagnetic wave's dependency relationship in spatial and frequency domains. LSTM is used to capture the electromagnetic wave's dependency relationship in the temporal domain. To evaluate the effectiveness of the model, we conducted ablation experiments on LSTM, GCN, GC-LSTM, and TensorGCN-LSTM models using simulated data. The experimental results show that our model achieved better prediction performance in RMSE, and the correlation coefficient R2 of 0.8753 also confirmed the feasibility of the model.

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

Cardiovascular disease is the leading cause of death worldwide. A key factor in assessing the risk of cardiovascular disease is left ventricular functional evaluation. Left ventricular (LV) systolic function is evaluated by measuring the left ventricular ejection fraction (LVEF) using echocardiography data. Therefore, quick and accurate left ventricle segmentation is important for estimating the LVEF. However, it is difficult to accurately segment the left ventricle due to changes in the shape and area of the left ventricle during cardiac cycles. In this study, we proposed a framework that considers changes in the shape and area of the left ventricle during the cardiac cycle by applying the convolutional long short-term memory (CLSTM) approach. In addition, we evaluated the left ventricular segmentation and multidimensional quantification of the proposed system in comparison to manual and automated segmentation methods. In addition, to assess the validity of CLSTM, the values of multi-dimensional quantification metrics were compared and analyzed using graphs and Bland–Altman plots on a frame-by-frame basis. We demonstrated that the CLSTM method effectively segments the left ventricle by considering the LV activity. In conclusion, we demonstrated that LV segmentation based on our framework may be utilized to accurately estimate LVEF values.

Autonomous systems require identifying the environment and it has a long way to go before putting it safely into practice. In autonomous driving systems, the detection of obstacles and traffic lights are of importance as well as lane tracking. In this study, an autonomous driving system is developed and tested in the experimental environment designed for this purpose. In this system, a model vehicle having a camera is used to trace the lanes and avoid obstacles to experimentally study autonomous driving behavior. Convolutional Neural Network models were trained for Lane tracking. For the vehicle to avoid obstacles, corner detection, optical flow, focus of expansion, time to collision, balance calculation, and decision mechanism were created, respectively.

Facial recognition systems are widely used systems around the globe. Their applications in real world scenarios like law enforcement, surveillance, ID card identification, information security, access control and many more has made them very important in today’s world. These systems have shown promising results and excellent performance; however, these systems need tremendous number of facial images for training before they are implemented in the real-world scenarios. The problem arises when we face lack of training images due to which the performance of such systems decreases exponentially. The problem becomes even worse when there is only one image per subject for training our facial recognition system, the probe image might contain variation like illumination, expression and disguise which are hard to be accurately recognized. Generative models have achieved great success for handling the lack of training data by generating synthetic data that resembles the original data. We have created a new method by fine tuning the basic Conditional Generative Adversarial Network (CGAN) to generate synthetic facial images provided only single image per subject. These synthetic facial images contain six variations that are smile, anger, stare, illumination and disguise. We increased the size of the dataset and then applied a convolutional neural network for facial recognition, which improved the accuracy of our system from 0.76 to 0.99.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges such as low imaging quality and high variability. There is a critical need to develop advanced automatic US image analysis methods to enhance diagnostic accuracy and objectivity. Vision transformer, a recent innovation in machine learning, has demonstrated significant potential in various research fields, including general image analysis and computer vision, due to its capacity to process large datasets and learn complex patterns. Its suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformer and discusses its applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in its application in medical US image analysis. Vision transformer has shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and is expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Efficient management of basal cell carcinoma (BCC) requires reliable assessments of both tumors and post-treatment scars. We aimed to estimate image similarity metrics that account for BCC's perceptual color and texture deviation from perilesional skin. 176 clinical photographs of BCC were assessed by six physicians using a visual deviation scale. Internal consistency and inter-rater agreement were estimated using Cronbach's α, weighted Gwet's AC2, and quadratic Cohen's Kappa. The mean visual scores were used to validate a range of similarity metrics employing different color spaces, distances, and image embeddings from pre-trained VGG16 neural network. The calculated similarities were transformed into discrete values using ordinal logistic regression models. The Bray-Curtis distance in the YIQ color model and rectified embeddings from the 'fc6' layer minimized the mean squared error and demonstrated strong performance in representing perceptual similarities. Box plot analysis and Wilcoxon rank-sum test were used to visualize and compare the levels of agreement, conducted on a random validation round between the two groups: ‘Human-System’ and ‘Human-Human’. The proposed metrics were comparable in terms of internal consistency and agreement with human raters. The findings suggest that the proposed metrics offer a robust, and cost-effective approach to monitoring BCC treatment outcomes in clinical settings.

To address the problems of poor recognition, low detection accuracy, a large number of model parameters and computation, complex network structure, and unfavorable portability to embedded devices in traditional tennis ball detection algorithms, this study proposes a lightweight tennis ball detection algorithm YOLOv5s-Z based on Robomater EP. The main work is as follows: Firstly, constructing lightweight G-Backbone and G-Neck network layers to reduce the number of parameters and computation of the network structure. Secondly, the convolutional coordinate attention is incorporated in G-Backbnone to embed the location information into the channel attention, which makes the network obtain the location information in a larger area through multiple convolutions and enhances the expression ability of the mobile network learning features. In addition, the Concat module in the original feature fusion is modified into a weighted bi-directional feature pyramid W-BiFPN with settable learning weights to improve the feature fusion capability and achieve efficient weighted feature fusion and bi-directional cross-scale connectivity. The EIOU loss is introduced to split the influence factor of aspect ratio and calculate the length and width of the target frame and anchor frame respectively, combined with Focal-EIOU Loss to solve the problem of imbalance between difficult and easy samples. The activation function Meta-ACON is introduced to achieve an adaptive selection of whether to activate the neurons and improve the detection accuracy. Finally, the experimental results show that compared with the original algorithm, the YOLOv5s-Z algorithm reduces the number of parameters and computation by 42$\%$ and 44$\%$, the model size by 39$\%$, and 2$\%$ improvement in average accuracy mean value, which verifies the effectiveness of the improved algorithm and the light weight of the model to meet the deployment requirements of embedded devices, and adapts Robomaster EP for accurate detection and real-time recognition of tennis balls.

Contrapose the highly integrated, multiple types of faults and complex working conditions of aircraft Electro Hydrostatic Actuator (EHA), to effectively identify its typical faults, we propose a fault diagnosis method based on the fusion convolutional neural networks (FCNN). First, the aircraft EHA fault data is encoded by GADF to obtain the fault feature images. Then we build an FCNN model that integrates the 1DCNN and 2DCNN, where the original 1D fault data is the input of the 1DCNN model, and the feature images obtained by GADF transformation are used as the input of 2DCNN. Multiple convolution and pooling operations are performed on each of these inputs to extract the features, next these feature vectors are spliced in the convergence layer, and the fully connected layers and the Softmax layers are finally used to attain the classification of aircraft EHA faults. Furthermore, the multi-strategy hybrid particle swarm optimization (MSPSO) algorithm is applied to optimize the FCNN to obtain a better combination of FCNN hyperparameters; MSPSO incorporates various strategies, including an initialization strategy based on homogenization and randomization, and an adaptive inertia weighting strategy, etc. The experimental result indicates that the FCNN model optimized by MSPSO achieves an accuracy of 96.86% for identifying typical faults of the aircraft EHA, respectively higher than the 1DCNN and the 2DCNN about 16.5% and 5.7%. Additionally, the FCNN model improved by MSPSO has a higher accuracy rate when compared to PSO.

Melanoma is considered to be the most aggressive form of skin cancer. Due to the similar shape of malignant and benign cancerous lesions, doctors spend considerably more time when diagnosing these findings. At present, the evaluation of malignancy is performed primarily by invasive histological examination of the suspicious lesion. Developing an accurate classifier for early and efficient detection can minimize and monitor the harmful effects of skin cancer and increase patient survival rates. This paper proposes a multi-class classification task using the CoAtNet architecture, a hybrid model that combines the depthwise convolution matrix operation of traditional convolutional neural networks with the strengths of Transformer models and self-attention mechanics to achieve better generalization and capacity. The proposed multi-class classifier achieves an overall precision of 0.901, recall 0.895, and AP 0.923, indicating high performance compared to other state-of-the-art networks.

This article presents an automated vision-based algorithm for the die-scale inspection of wafer images captured using scanning acoustic tomography (SAT). This algorithm can find defective and abnormal die-scale patterns, and produce a wafer map to visualize the distribution of defects and anomalies on the wafer. The main procedures include standard template extraction, die detection through template matching, pattern candidate prediction through clustering, and pattern classification through deep learning. To conduct the template matching, we first introduce a two-step method to obtain a standard template from the original SAT image. Subsequently, a majority of the die patterns are detected through template matching. Thereafter, the columns and rows arranged from the detected dies are predicted using a clustering method; thus, an initial wafer map is produced. This map is composed of detected die patterns and predicted pattern candidates. In the final phase of the proposed algorithm, we implement a deep learning-based model to determine defective and abnormal patterns in the wafer map. The experimental results verified the effectiveness and efficiency of our proposed algorithm. In conclusion, the proposed method performs well in identifying defective and abnormal die patterns, and produces a wafer map that presents important information for solving wafer fabrication issues.

The integration of Artificial Intelligence (AI) with Digital Twins (DTs) has emerged as a promising approach to revolutionize healthcare, particularly in the diagnosis and management of thoracic disorders. This study proposes a comprehensive framework, named Lung-DT, which leverages IoT sensors and AI algorithms to establish a digital representation of a patient’s respiratory health. Using the YOLOv8 neural network, the Lung-DT system accurately classifies chest X-Rays into five distinct categories of lung diseases, including "Normal," "Covid," "Lung Opacity," "Pneumonia," and "Tuberculosis". The system’s performance was evaluated on a chest X-Ray dataset, demonstrating an impressive average accuracy of 96.6% across all classes. Further tests (prediction) were conducted on the trained network using a third dataset available in the literature and completely unknown to the network, yielding an average accuracy of 98% across three classes. The proposed Lung-DT framework offers several advantages over conventional diagnostic methods. Firstly, it enables real-time monitoring of lung health through continuous data acquisition from IoT sensors, facilitating early diagnosis and intervention. Secondly, the AI-powered classification module provides automated and objective assessments of chest X-Rays, reducing dependence on subjective human interpretation. Thirdly, the twin digital representation of the patient’s respiratory health allows for comprehensive analysis and correlation of multiple data streams, providing valuable insights for personalized treatment plans. The integration of IoT sensors, AI algorithms, and DT technology within the Lung-DT system demonstrates a significant step towards improving thoracic healthcare. By enabling continuous monitoring, automated diagnosis, and comprehensive data analysis, the Lung-DT framework has enormous potential to enhance patient outcomes, reduce healthcare costs, and optimize resource allocation.

Drug-target affinity (DTA) prediction is crucial for understanding molecular interactions and aiding drug discovery and development. While various computational methods have been proposed for DTA prediction, their predictive accuracy remains limited, failing to delve into the structural nuances of interactions. With increasingly accurate and accessible structure prediction of targets, we developed a novel deep learning model, named S2DTA, to accurately predict DTA by fusing sequence and structural knowledge of drugs, targets, and pockets using heterogeneous models based on graph and semantic networks. Experimental findings underscored that complex feature representations imparted negligible enhancements to the model’s performance. However, the integration of heterogeneous models demonstrably bolstered predictive accuracy. In comparison to three state-of-the-art methodologies, the supremacy of S2DTA became strikingly apparent. It showcased a noteworthy 25.2% reduction in Mean Absolute Error (MAE) and an impressive 20.1% decrease in Root Mean Square Error (RMSE). Furthermore, S2DTA exhibited substantial advancements in other pivotal metrics, including Pearson Correlation Coefficient (PCC), Spearman, Concordance Index (CI), and R2. These metrics experienced remarkable increments of at least 19.6%, 17.5%, 8.1%, and a remarkable 49.4%, respectively. Finally, we conducted interpretability analysis on the effectiveness of S2DTA by bidirectional self-attention mechanism, fully proving that S2DTA is a valuable and accurate tool for predicting DTA. For further exploration, the source data and code repository can be accessed at https://github.com/dldxzx/S2DTA.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

There is a need for cost-effective and non-invasive methods of monitoring feeding behavior in livestock operations, considering the significant impact of feed costs on economic efficiency and assisting in detecting health issues of group-fed animals. This paper proposes using deep learning-based computer vision techniques to detect pen-fed beef cattle feeding behavior using Mask Region-based Convolutional Neural Network (RCNN). A deep learning model was pre-trained on the Common Objects in Context (COCO) dataset to generate cattle instance segmentation. Manually defined feed bunk polygons are compared with these segmentation masks to derive feeding time for each bunk. A full day’s worth of video data and the corresponding physical sensor data are collected for the experiment. By benchmarking the computer vision detected data with physical ground truth over random time segments from morning to evening (thus various lighting conditions), the optimal thresholds for Mask RCNN are determined to be 0.7 for bounding boxes and 0.1 for masks. Using these parameters. The reports suggest that the computer vision system achieved a precision of 87.2% and a recall of 89.1%, signifying precise detection of feeding events. Our study, to the best of our knowledge, was one of the first investigations of instance segmentation on feeding time sense, which combines deep learning methods with traditional computer vision logistics, reporting on feeding time data collection and processing, camera testing and adjustment, and performance evaluation. Future research directions include computer vision applied in feed grading and animal re-identification for individual production analysis.

The continuously developing project aims to build an informatics system enabling analysis of spatial and temporal parameters of movement activities occurring in the sport of speed climbing. The monitoring system (climbing information speed system – CISS) is to be used for conducting comprehensive scientific research in the field of speed climbing. The system enables the evaluation of the training process of climbers at various levels of competition. The study analysis was based on video. The video recording with a camera positioned at a short distance (10 m) from the wall. The marker was positioned closest to the centre of mass (gravity) BMC. Results: development of a system for data collection and analysis of the climbing run based on video recording (application of the Kanade-Lucas-Tomasi (KLT) algorithm). Our results showed that used devices can measure a wide range of specific internal and external variables during speed climbing. Some of the analyzed parameters were significantly correlated with speed climbing time. These results could be a theoretical basis for future research and for training program’s preparation.

Generative models for images, audio, text and other low-dimension data have achieved great success in recent years. Generating artificial human movements can also be useful for many applications, including improvement of data augmentation methods for human gesture recognition. The object of this research is to develop a generative model for skeletal human movement, allowing to control the action type of generated motion while keeping the authenticity of the result and the natural style variability of gesture execution. We propose to use a conditional Deep Convolutional Generative Adversarial Network (DC-GAN) applied to pseudo-images representing skeletal pose sequences using Tree Structure Skeleton Image format. We evaluate our approach on the 3D-skeleton data provided in the large NTU RGB+D public dataset. Our generative model can output qualitatively correct skeletal human movements for any of its 60 action classes. We also quantitatively evaluate the performance of our model by computing Frechet Inception Distances, which shows strong correlation to human judgement. Up to our knowledge, our work is the first successful class-conditioned generative model for human skeletal motions based on pseudo-image representation of skeletal pose sequences.

The rapid advancement of artificial intelligence (AI) and robotics has led to significant progress in various medical fields, including interventional radiology (IR). This review focuses on the research progress and applications of AI and robotics in IR, including deep learning (DL), machine learning (ML), and convolutional neural networks (CNNs) across specialties such as oncology, neurology, and cardiology. To ensure the breadth and depth of this review, we implemented a systematic literature search strategy, selecting research published within the last five years. We conducted searches in databases such as PubMed and Google Scholar to find relevant literature. Special emphasis was placed on selecting large-scale studies to ensure comprehensiveness and reliability of the results. We discuss the role of AI techniques used before, during, and after intervention treatments and the advantages of robotics in achieving precise operations and reducing intra-operative risks. Challenges faced in the implementation of these techniques are also addressed. Finally, we explore the future trends and potential applications of AI and robotics in interventional therapy, highlighting their potential to improve patient treatment outcomes and quality of life.

Melanoma is widely recognized as one of the most lethal forms of skin cancer, with its incidence showing an upward trend in recent years. Nonetheless, the timely detection of this malignancy substantially enhances the likelihood of patients’ long-term survival. Several computer-based methods have recently been proposed in the pursuit of diagnosing skin lesions at their early stages. Despite achieving some level of success, there still remains a margin of error that the machine learning community considers to be an unresolved research challenge. This study presents a novel framework for the classification of skin lesions. The framework incorporates deep features to generate a highly discriminant feature vector, while also maintaining the integrity of the original feature space. Recent deep models including Darknet53, DenseNet201, InceptionV3, and InceptionResNetV2 are employed in our study for the purpose of feature extraction. Additionally, transfer learning is leveraged to enhance the performance of our approach. In the subsequent phase, the extracted feature information from the chosen pre-existing models is combined, with the aim of preserving maximum information, prior to undergoing the process of feature selection using a novel entropy-controlled grey wolf optimization (ECGWO) algorithm. The integration of fusion and selection techniques is employed to initially incorporate the feature vector with a high level of information and subsequently eliminate redundant and irrelevant feature information. The efficacy of our design is substantiated through the evaluation on three benchmark dermoscopic datasets, namely PH2, ISIC-MSK, and ISIC-UDA. In order to validate the proposed methodology, a comprehensive evaluation is conducted, including a rigorous comparison with established techniques in the field.

The vast majority of autonomous driving systems are limited to applications on roads with clear lane markings and are implemented using commercial grade sensing systems coupled with specialized graphic accelerator hardware. This research reviews an alternative approach for autonomously steering vehicles that eliminates the dependency on road markings and specialized hardware. A combination of machine vision, machine learning and artificial intelligence based on popular pre-trained Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) was used to drive a vehicle along roads lacking lane markings (unmarked roads). The team developed and tested this approach on the ACTor (Autonomous Camus TranspORt) vehicle - an autonomous vehicle development and research platform coupled with a low-cost webcam based sensing system and minimal computational resources. The proposed solution was evaluated on real-world roads and varying environmental conditions. It was found that this solution may be used to successfully navigate unmarked roads autonomously with acceptable road following behavior.

This comprehensive review unfolds a detailed narrative of Artificial Intelligence (AI) making its foray into radiology, a move that is catalysing transformational shifts in the healthcare landscape. It sheds light on the journey of radiology, from the pioneering discovery of X-rays to today’s intricate imaging technologies, infused with machine learning and deep learning in medical image analysis. At the crux of this review lies an in-depth study of AI applications in radiology, elucidating its seminal roles in image segmentation, computer-aided diagnosis, predictive analytics, and workflow optimisation. A spotlight is cast on the profound impact of AI on diagnostic processes, personalised medicine, and clinical workflows, with empirical evidence derived from a series of case studies across multiple medical disciplines. However, the integration of AI in radiology is not devoid of challenges. The review ventures into the labyrinth of obstacles that are inherent to AI-driven radiology — data quality, the ’black box’ enigma, infrastructural and technical complexities, as well as ethical implications. Peering into the future, the review contends that the road ahead for AI in radiology is paved with promising opportunities. It advocates for continuous research, embracing avant-garde imaging technologies, and fostering robust collaborations between radiologists and AI developers. It concludes by firmly cementing the role of AI as a catalyst for change in radiology, a stance that is firmly rooted in sustained innovation, dynamic partnerships, and a steadfast commitment to ethical responsibility.

Deep learning (DL) algorithms used for DOTATATE PET lesion detection typically require large, well-annotated training datasets. These are difficult to obtain due to low incidence of gastroenteopancreatic neuroendocrine tumors (GEP-NETs), and the high cost of manual annotation. Furthermore, networks trained and tested with data acquired from site specific PET/CT instrumentation, acquisition and processing protocols have reduced performance when tested with offsite data. This lack of generalizability requires even larger, more diverse training datasets. The objective of this study is to investigate the feasibility of improving DL algorithm performance by better matching the background noise in training datasets to higher noise, out-of-domain testing datasets. 68Ga-DOTATATE PET/CT datasets were obtained from two scanners: Scanner1, a state-of-the-art digital PET/CT (GE DMI PET/CT; n=83 subjects), and Scanner2, an older-generation analog PET/CT (GE STE; n=123 subjects). Set1, the data set from Scanner1 was reconstructed with standard clinical parameters (5 minutes; Q.Clear) and list-mode reconstructions (VPFXS 2, 3, 4, and 5-minutes). Set2, data from Scanner2, representing out-of-domain clinical scans, used standard iterative reconstruction (5 minutes; OSEM). Reconstructed datasets were divided into training, validation, and testing datasets in a 60%, 20%, 20% proportion, and a deep neural network was trained with each: Network1 for Scanner1 and Network2 for Scanner2. DL performance (Network1) was tested with out-of-domain test data (Set2). To evaluate the effect of training sample size, we tested DL model performance using a fraction (25%, 50%, and 75%) of Set1 for training. Scanner1, list-mode 2-minute reconstructed data demonstrated the most similar noise level compared that of Set2, resulting in the best performance (F1=0.713). This was not significantly different compared to the highest performance, upper-bound limit using in-domain training for Network2 (F1=0.755; p-value=0.103). Regarding sample size, the F1 score significantly increased from 25% training data (F1=0.478) to 100% training data (F1=0.713; p<0.001). List-mode data from modern PET scanners can be reconstructed to better match the noise properties of older scanners. Using existing data and their associated annotations dramatically reduces the cost and effort in generating these datasets, and significantly improves the performance of existing DL algorithms. List-mode reconstructions can provide an efficient, low-cost method to improve DL algorithm generalizability.

With the development of artificial intelligence, the ability of capturing the background characteristics of hyperspectral imagery (HSI) is improved and promising performance in hyperspectral anomaly detection (HAD) tasks is yielded. However, existing methods proposed in recent years still suffer from certain limitations: 1) constraints are lacking in the deep feature learning process in terms of the issue for absence of prior background and anomaly information. 2) hyperspectral anomaly detectors with traditional self-supervised deep learning methods fail to ensure prioritized reconstruction of the background. 3) architectures of fully connected deep network in hyperspectral anomaly detectors lead to low utilization of spatial information and destruction for original spatial relationship of hyperspectral imagery, and disregard spectral correlation between adjacent pixels. 4) hypotheses or assumptions for background and anomaly distributions restrict the performance of many hyperspectral anomaly detectors because the distributions of background land covers are usually complex and not assumable in real-world hyperspectral imagery. With the consideration of above problems, in this paper, we propose a novel fully convolutional auto-encoder based on dual clustering and latent feature adversarial consistency (FCAE-DCAC) for HAD which is carried out in a self-supervised learning-based processing. Firstly, the density-based spatial clustering of applications with noise algorithm and connected component analysis are utilized for successive spectral and spatial clustering to obtain more precise prior background and anomaly information, which facilitates the separation between background and anomaly samples during the training of our method. Subsequently, a novel fully convolutional auto-encoder (FCAE) integrated with spatial-spectral joint attention (SSJA) is proposed to enhance the utilization of spatial information and augment feature expression. In addition, a latent feature adversarial consistency network is proposed to achieve pure background reconstruction with the ability of learning actual background distribution in hyperspectral imagery. Finally, a triplet loss is introduced to enhance the separability between background and anomaly, and the reconstruction residual serves as the anomaly detection result. We evaluate the proposed method on seven groups of real-world hyperspectral datasets, and the experimental results confirmed the effectiveness and superior performance of the proposed method versus nine state-of-the-art methods.

The automated transcription of handwritten characters into a legible output is a multi-faceted process with diverse applications. In this paper, a novel approach to optical character recognition (OCR) for handwritten digits is proposed that, in certain components, exceeds current architectures in terms of accuracy, effectiveness, adjustability, temporal efficiency, and/or computational simplicity. This model succeeds in the adoption and enhancement of deprecated or obsolete algorithms across eight steps of image pre-processing—normalization, grayscaling, thresholding/binarization, noise removal, skew-correction, skeletonization/thinning, line separation, and character segmentation. The aforementioned model is evaluated with the use of a Convolutional Neural Network (CNN) leveraging the Balanced eMNIST dataset for training and testing. By suggesting contour-based feature extraction methods as alternatives to pixel-by-pixel iteration, the proposed paradigm demonstrates its capacity to serve as a suitable alternative to current, commonly used algorithms and computational techniques for textual image classification.

Augmented reality (AR) provides an opportunity for mobile fitness applications to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user’s current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of activities of daily living. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning methods commonly used in HAR. On our data set, all CNN architectures significantly outperformed traditional machine learning methods, reaching up to 97.14±1.36% classification accuracy on the test set for ResNet. Whereas a reduced input data size invariably led to a performance loss, removing specific sensors improved the performance of all CNN architectures, with our Scaling-FCN reaching the highest accuracy of 99.86±0.11%. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively.

This paper presents preliminary research that investigates the relationship between the flow of a group of jazz musicians, quantified through multi-person pose synchronization, and their collective emotions. Building upon previous studies that measured the physical synchronicity of team members by tracking their body movements and measuring the difference in arm, leg, and head movements, we introduce a novel metric termed "team entanglement". We employ facial expression recognition to evaluate the musicians’ collective emotions. Through correlation and regression analysis, we establish that higher levels of synchronized body and head movements correspond to lower levels of disgust, anger, sadness and higher levels of joy among the musicians. Furthermore, we utilize a Convolutional Neural Network (CNN) based deep learning model to predict the collective emotions of the musicians. This model leverages 17 body synchrony keypoint vectors as features, resulting in a training accuracy of 61.47% and a test accuracy of 66.17%.

The integration of deep learning methods, especially Convolutional Neural Networks (CNN), and Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has been widely deployed in the field of radar signal processing. Nevertheless, these methods are frequently regarded as black-box models due to the limited visual interpretation of their internal feature representation and parameter organization. In this paper, we propose an innovative approach named C-RISE, which builds upon the RISE algorithm to provide a post-hoc interpretation technique for black-box models used in SAR Images Target Recognition. C-RISE generates saliency maps that effectively visualize the significance of each pixel. Our algorithm outperforms RISE by clustering masks that capture similar fusion features into distinct groups, enabling more appropriate weight distribution and increased focus on the target area. Furthermore, we employ Gaussian blur to process the masked area, preserving the original image structure with optimal consistency and integrity. C-RISE has been extensively evaluated through experiments, and the results demonstrate superior performance over other interpretation methods based on perturbation when applied to neural networks for SAR image target recognition. Furthermore, our approach is highly robust and transferable compared to other interpretable algorithms, including white-box methods.

Background: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. Methods: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes, T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20101 MRI images) was used for training, while C2 (197, 11333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics models' performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). Results: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95%-Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. 620 images were misclassified; Manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased on average the PFS model C-I by 14.6% compared to a model trained without MR-Class. Conclusions: We provide a DCNN-based method for sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

Lung cancer is the leading cause of cancer mortality worldwide, and it is urgently necessary to diagnose it as early as possible. Usually, the diagnostic process begins with a radiological examination which, when a possible tumour is present, is followed by a biopsy to extract tissue samples from the patient's lungs. Therefore, the purpose of this study is the development of an artificial intelligence algorithm that will analyse the Whole Slide Image (WSI) generated by the digitisation of the glass slides obtained from the extracted samples and detect if there is a tumour. The developed learning algorithms as well as the tested neural networks (NNs) were trained on a dataset composed of previously annotated WSI tiles, classified as Tumour or Non-Tumour. From these, four developed convolutional neural networks stood out and were selected to be compared with each other and with the tested NNs. When the best result of each of the developed architectures was compared to the highest result of the tested NNs, it was possible to denote that version 4 of CancerDetecNN achieved an average accuracy of 89.749 \% and an average loss of 0.220. Furthermore, the results for the four selected versions are in agreement with the results reported in the literature, however, the limited size of the given dataset must be considered. Given the results obtained, the fourth version has the potential to optimise the lung cancer diagnosis process.

This study presents an in-depth analysis of land use and land cover change on the Kerch Peninsula over a period spanning three decades. Utilizing convolutional neural networks alongside satellite imagery analysis, we have mapped and quantified the changes in land use and cover, revealing significant trends and transformations within the peninsula's landscape. The research aims to elucidate the interplay between anthropogenic activities, climatic variations, and policy interventions in shaping land cover dynamics, thereby providing insights into the environmental and socio-economic impacts of these changes. Our findings indicate a marked increase in urban expansion at the expense of natural ecosystems, including forests and wetlands, underscoring the urgent need for sustainable land management strategies. The study highlights the role of agricultural intensification and expansion in altering the peninsula's ecological balance and emphasizes the critical importance of integrating change analysis and prediction. By leveraging advanced remote sensing and GIS technologies, our analysis not only enhances the understanding of the complex dynamics driving land use and land cover change but also showcases the potential of predictive modeling in forecasting future land cover scenarios. The implications of this study extend beyond the Kerch Peninsula, offering valuable lessons for managing land use changes and conserving natural landscapes in similar regions globally.

Speech recognition, or automatic speech recognition (ASR), is a technology designed to convert spoken language into text using software. However, conventional ASR methods involve several distinct components, including language, acoustic, and pronunciation models with dictionaries. This modular approach can be time-consuming and may influence performance. In this study, we propose a method that streamlines the speech recognition process by incorporating a unified recurrent neural network (RNN) architecture. Our architecture integrates a convolutional neural network (CNN) with an RNN and employs a connectionist temporal classification (CTC) loss function. Key experiments were carried out using a dataset comprising 576,656 valid sentences, using erosion techniques. Evaluation of the model performance, measured by the word error rate (WER) metric, demonstrated remarkable results, achieving a WER of 2%. This approach has significant implications for the realm of speech recognition, as it alleviates the need for labor-intensive dictionary creation, enhancing the efficiency and accuracy of ASR systems, and making them more applicable to real-world scenarios. For future enhancements, we recommend the inclusion of dialectal and spontaneous data in the dataset to broaden the model's adaptability. Additionally, fine-tuning the model for specific tasks can optimize its performance for targeted objectives or domains, further enhancing its effectiveness in those areas.

Multilabel learning goes beyond standard supervised learning models by associating a sample with more than one class label. Among the many techniques developed in the last decade to handle multilabel learning best approaches are those harnessing the power of ensembles and deep learners. This work proposes merging both methods by combining a set of gated recurrent units, temporal convolutional neural networks, and long short-term memory networks trained with variants of the Adam optimization approach. We examine many Adam variants, each fundamentally based on the difference between present and past gradients, with step size adjusted for each parameter. We also combine Incorporating Multiple Clustering Centers and a bootstrap-aggregated decision trees ensemble, which is shown to further boost classification performance. In addition, we provide an ablation study for assessing the performance improvement that each module of our ensemble produces. Multiple experiments on a large set of datasets representing a wide variety of multilabel tasks demonstrate the robustness of our best ensemble, which is shown to outperform the state-of-the-art. The MATLAB code for generating the best ensembles in the experimental section will be made available at https://github.com/LorisNanni.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduced an automatic score detection model using object detection techniques. The performance of seven models belonging to two different architectural setups was compared. Models like YOLOv8n, YOLOv8s, YOLOv8m, RetinaNet-50, and RetinaNet-101 are single-shot detectors, while Faster RCNN-50 and Faster RCNN-101 belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640x640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among all, YOLOv8m performed the best with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3ms) than YOLOv8m (5.7ms) and yet generated the competitive mAP50.