Search

Electronic devices get smaller and smaller in every generation. In micro-/nano-electronic devices such as high electron mobility transistors, heat dissipation has become a crucial design consideration due to the ultrahigh heat flux that has a negative effect on devices' performance and their lifetime. Therefore, thermal transport performance enhancement is required to adapt to the device size reduction. β-Ga2O3 has recently gained significant scientific interest for future power devices because of its inherent material properties such as extremely wide bandgap, outstanding Baliga's figure of merit, large critical electric field, etc. This work aims to use a machine learning approach to search promising substrates or heat sinks for cooling β-Ga2O3, in terms of high interfacial thermal conductance (ITC), from large-scale potential structures taken from existing material databases. With the ITC dataset of 1633 various substrates for β-Ga2O3 calculated by full density functional theory, we trained our recently developed convolutional neural network (CNN) model that utilizes the fused orbital field matrix (OFM) and composition descriptors. Our model proved to be superior in performance to traditional machine learning algorithms such as random forest and gradient boosting. We then deployed the CNN model to predict the ITC of 32 716 structures in contact with β-Ga2O3. The CNN model predicted the top 20 cubic and noncubic substrates with ITC on the same level as density functional theory (DFT) results on β-Ga2O3/YN and β-Ga2O3/MgO interfaces, which has the highest ITC of 1224 and 1211 MW/m2K, respectively, among the DFT-ITC datasets. Phonon density of states, group velocity, and scattering effect on high heat flux transport and consequently increased ITC are also investigated. Moderate to high phonon density of states overlap, high group velocity, and low phonon scattering are required to achieve high ITC. We also found three Magpie descriptors with strong Pearson correlation with ITC, namely, mean atomic number, mean atomic weight, and mean ground state volume per atom. Calculations of such descriptors are computationally efficient, and therefore, these descriptors provide a new route for quickly screening potential substrates from large-scale material pools for high-performance interfacial thermal management of high-electron mobility transistor devices. [ABSTRACT FROM AUTHOR]

The Lattice Boltzmann Method (LBM) is an approach for modeling mesoscopic fluid flow and heat transfer, based on modeling distributions of particles moving and colliding on a lattice. Using a perturbative formulation of the Boltzmann equation, it scales to the macroscopic Navier–Stokes equation. We simulate natural thermal convection via LBM in a 2D rectangular box being heated from below and cooled from above, and use the results as training, testing, and generalization datasets to build a deep learning model. GoogLeNet, a convolutional neural network, is used to classify the simulation results based on two parameters: Rayleigh (R a) and Prandtl (P r) numbers, from a single snapshot of either the entire modeling field of resolution 1024 × 1024 , or a 224 × 224 crop. For each fixed P r in a range from 1 to 128, increasing by a factor of 2, we estimate R a with an accuracy varying from 40% to 90%, depending on the chosen augmentation strategy. For each fixed R a in the range from 10 5 to 10 9 , increasing of a factor 10 , the method predicts P r with a systematically lower accuracy ranging from 30% to 80%. This approach has great potential for industrial applications like being able to control the industrial flow or scientific research on geophysical ones including the transport of heat in the earth's interiors, ocean, and atmosphere. [ABSTRACT FROM AUTHOR]

Disordered molecular systems, such as amorphous catalysts, organic thin films, electrolyte solutions, and water, are at the cutting edge of computational exploration at present. Traditional simulations of such systems at length scales relevant to experiments in practice require a compromise between model accuracy and quality of sampling. To address this problem, we have developed an approach based on generative machine learning called the Morphological Autoregressive Protocol (MAP), which provides computational access to mesoscale disordered molecular configurations at linear cost at generation for materials in which structural correlations decay sufficiently rapidly. The algorithm is implemented using an augmented PixelCNN deep learning architecture that, as we previously demonstrated, produces excellent results in 2 dimensions (2D) for mono-elemental molecular systems. Here, we extend our implementation to multi-elemental 3D and demonstrate performance using water as our test system in two scenarios: (1) liquid water and (2) samples conditioned on the presence of pre-selected motifs. We trained the model on small-scale samples of liquid water produced using path-integral molecular dynamics simulations, including nuclear quantum effects under ambient conditions. MAP-generated water configurations are shown to accurately reproduce the properties of the training set and to produce stable trajectories when used as initial conditions in quantum dynamics simulations. We expect our approach to perform equally well on other disordered molecular systems in which structural correlations decay sufficiently fast while offering unique advantages in situations when the disorder is quenched rather than equilibrated. [ABSTRACT FROM AUTHOR]

Inferring transient molecular structural dynamics from diffraction data is an ambiguous task that often requires different approximation methods. In this paper, we present an attempt to tackle this problem using machine learning. Although most recent applications of machine learning for the analysis of diffraction images apply only a single neural network to an experimental dataset and train it on the task of prediction, our approach utilizes an additional generator network trained on both synthetic and experimental data. Our network converts experimental data into idealized diffraction patterns from which information is extracted via a convolutional neural network trained on synthetic data only. We validate this approach on ultrafast electron diffraction data of bismuth samples undergoing thermalization upon excitation via 800 nm laser pulses. The network was able to predict transient temperatures with a deviation of less than 6% from analytically estimated values. Notably, this performance was achieved on a dataset of 408 images only. We believe that employing this network in experimental settings where high volumes of visual data are collected, such as beam lines, could provide insights into the structural dynamics of different samples. [ABSTRACT FROM AUTHOR]

A computational framework that leverages data from self-consistent field theory simulations with deep learning to accelerate the exploration of parameter space for block copolymers is presented. This is a substantial two-dimensional extension of the framework introduced in the work of Xuan et al. [J. Comput. Phys. 443, 110519 (2021)]. Several innovations and improvements are proposed. (1) A Sobolev space-trained, convolutional neural network is employed to handle the exponential dimension increase of the discretized, local average monomer density fields and to strongly enforce both spatial translation and rotation invariance of the predicted, field-theoretic intensive Hamiltonian. (2) A generative adversarial network (GAN) is introduced to efficiently and accurately predict saddle point, local average monomer density fields without resorting to gradient descent methods that employ the training set. This GAN approach yields important savings of both memory and computational cost. (3) The proposed machine learning framework is successfully applied to 2D cell size optimization as a clear illustration of its broad potential to accelerate the exploration of parameter space for discovering polymer nanostructures. Extensions to three-dimensional phase discovery appear to be feasible. [ABSTRACT FROM AUTHOR]

Known for their efficiency in analysing large data sets, machine learning-based classifiers have been widely used in wide-field sky survey pipelines. The upcoming Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will generate millions of real-time alerts every night, enabling the discovery of large samples of rare events. Identifying such objects soon after explosion will be essential to study their evolution. Using ∼5400 transients from the Zwicky Transient Facility (ZTF) Bright Transient Survey as training and test data, we develop NEEDLE (NEural Engine for Discovering Luminous Events), a novel hybrid (convolutional neural network + dense neural network) classifier to select for two rare classes with strong environmental preferences: superluminous supernovae (SLSNe) preferring dwarf galaxies, and tidal disruption events (TDEs) occurring in the centres of nucleated galaxies. The input data includes (i) cutouts of the detection and reference images, (ii) photometric information contained directly in the alert packets, and (iii) host galaxy magnitudes from Pan-STARRS (Panoramic Survey Telescope and Rapid Response System). Despite having only a few tens of examples of the rare classes, our average (best) completeness on an unseen test set reaches 73 per cent (86 per cent) for SLSNe and 80 per cent (87 per cent) for TDEs. While very encouraging for completeness, this may still result in relatively low purity for the rare transients, given the large class imbalance in real surveys. However, the goal of NEEDLE is to find good candidates for spectroscopic classification, rather than to select pure photometric samples. Our system will be deployed as an annotator on the UK alert broker, Lasair , to provide predictions of real-time alerts from ZTF and LSST to the community. [ABSTRACT FROM AUTHOR]

• AI improves infectious waste management. • Ensemble model exceeds 97.81% accuracy. • Reinforcement learning optimizes classification. • Geometric augmentation boosts model robustness. • Study addresses urgent urban waste challenges. This research paper focuses on effective infectious municipal waste management in urban settings, highlighting a dearth of dedicated research in this domain. Unlike general or specific waste types, infectious waste poses distinct health and environmental risks. Leveraging advanced artificial intelligence techniques, we prioritize infectious waste categorization and optimization, integrating metaheuristics into optimization methods to create a robust dual-ensemble framework. Our model, the "Enhanced Artificial Intelligence for Infectious Municipal Waste Classification System," combines ensemble image segmentation methods and diverse convolutional neural network models. Innovative geometric image augmentation enhances model robustness, diversifies training data, and improves accuracy across waste types. A pivotal aspect is the integration of a reinforcement learning-differential evolution algorithm as a decision fusion strategy, optimizing classification by harmonizing outputs from ensemble methods and convolutional neural network models. Computational results, using a newly collected dataset, demonstrate our model's accuracy exceeding 96.54% while using the existing solid waste dataset we achieve the accuracy of 97.81%, outperforming advanced approaches by margins ranging from 2.02% to 8.80%. This research significantly advances sustainable waste management, showcasing artificial intelligence's transformative potential in addressing intricate waste challenges. It establishes a foundational framework prioritizing efficiency, effectiveness, and sustainability for future waste management solutions. Acknowledging the importance of diverse datasets, customization for urban contexts, and practical integration into existing infrastructures, our work contributes to the broader discourse on the role of artificial intelligence in evolving waste management practices. [ABSTRACT FROM AUTHOR]

Due to their persistent widespread severe winds, derechos pose significant threats to human safety and property, and they are as hazardous and fatal as many tornadoes and hurricanes. Yet, automated detection of derechos remains challenging due to the absence of spatiotemporally continuous observations and the complex criteria employed to define the phenomenon. This study proposes a physically based definition of derechos that contains the key features of derechos described in the literature and allows their automated objective identification using either observations or model simulations. The automated detection is composed of three algorithms: the Flexible Object Tracker algorithm to track mesoscale convective systems (MCSs), a semantic segmentation convolutional neural network to identify bow echoes, and a comprehensive algorithm to classify MCSs as derechos or non-derecho events. Using the new approach, we develop a novel high-resolution (4 km and hourly) observational dataset of derechos over the United States east of the Rocky Mountains from 2004 to 2021. The dataset is analyzed to document the derecho climatology in the United States. Many more derechos (increased by ~50–400 %) are identified in the dataset (~31 events per year) than in previous estimations (~6–21 events per year), but the spatial distribution and seasonal variation patterns resemble earlier studies with a peak occurrence in the Great Plains and Midwest during the warm season. In addition, around 20 % of damaging gust (≥ 25.93 m s-1) reports are produced by derechos during the dataset period over the United States east of the Rocky Mountains. The dataset is available at https://doi.org/10.5281/zenodo.10884046 (Li et al., 2024). [ABSTRACT FROM AUTHOR]

The earthquake early warning (EEW) system is critical in mitigating the effects of seismic hazards by providing valuable response time. Damage to buildings can be determined based on peak ground acceleration (PGA). If PGA can be predicted in advance, the seismic risk of a building can be estimated. A novel method for predicting PGA using wavelet packet transform (WPT) and convolutional neural networks (CNN) is proposed. Early arrival waves generated by earthquakes are decomposed using WPT to produce a matrix of wavelet coefficients. This matrix serves as the input to the CNN model to predict the PGA. To achieve the best prediction performance, different setups were investigated, including the use of Daubechies Wavelet 4 (db4) and four-level decomposition. The results indicate that this configuration yields better prediction accuracy. P-waves of three-second duration are commonly used for EEW. Compared to the prediction results of a CNN model used to validate the method, the proposed method has a lower average error and better use of early arrival waves with shorter duration. Overall, the proposed method demonstrates the potential of WPT and CNN in EEW systems. The proposed approach can utilize shorter early arrival waves to predict PGA and gain more reaction time to get rid of seismic hazards. To estimate structural damage using the predicted PGA under an impending earthquake, a method is proposed to quickly determine structural damage based on the predicted PGA and fragility curves. It provides a method to estimate the potential structural damage caused by an impending earthquake. [ABSTRACT FROM AUTHOR]

Detecting emotions from facial images is difficult because facial expressions can vary significantly. Previous research on using deep learning models to classify emotions from facial images has been carried out on various datasets that contain a limited range of expressions. This study expands the use of deep learning for facial emotion recognition (FER) based on Emognition dataset that includes ten target emotions: amusement, awe, enthusiasm, liking, surprise, anger, disgust, fear, sadness, and neutral. A series of data preprocessing was carried out to convert video data into images and augment the data. This study proposes Convolutional Neural Network (CNN) models built through two approaches, which are transfer learning (fine-tuned) with pre-trained models of Inception-V3 and MobileNet-V2 and building from scratch using the Taguchi method to find robust combination of hyperparameters setting. The proposed model demonstrated favorable performance over a series of experimental processes with an accuracy and an average F1-score of 96% and 0.95, respectively, on the test data. [ABSTRACT FROM AUTHOR]

Video‐based facial expression recognition (VFER) technique intends to categorize an input video into different kinds of emotions. It remains a challenging issue because of the gap between visual features and emotions, problems in handling the delicate movement of muscles, and restricted datasets. One of the effective solutions to solve this problem is the exploitation of efficient features defining facial expressions to carry out FER. Generally, the VFER find useful in several areas like unmanned driving, venue management, urban safety management, and senseless attendance. Recent advances in computer vision and deep learning (DL) techniques enable the design of automated VFER models. In this aspect, this study establishes a new Marine Predators Optimization with Deep Learning Model for Video‐based Facial Expression Recognition (MPODL‐VFER) technique. The presented MPODL‐VFER technique mainly aims to classify different kinds of facial emotions in the video. To accomplish this, the presented MPODL‐VFER technique derives features using the deep convolutional neural network based densely connected network (DenseNet) model. The presented MPODL‐VFER technique employs MPO technique for the hyperparameter adjustment of the DenseNet model. Finally, Elman Neural Network (ENN) model is exploited for emotion recognition purposes. For assuring the enhanced recognition performance of the MPODL‐VFER approach, a comparison study was developed on benchmark dataset. The comprehensive results have shown the significant outcome of MPODL‐VFER model over other approaches. [ABSTRACT FROM AUTHOR]

High‐fidelity segmentation of blood vessels plays a pivotal role in numerous biomedical applications, such as injection assistance, cancer detection, various surgeries, and vein authentication. Near‐infrared (NIR) transillumination imaging is an effective and safe method to visualize the subcutaneous blood vessel network. However, such images are severely blurred because of the light scattering in body tissues. Inspired by the Vision Transformer model, this paper proposes a novel deep learning network known as transformer connection (TRC)‐Unet to capture global blurred and local clear correlations while using multi‐layer attention. Our method mainly consists of two blocks, thereby aiming to remap skip connection information flow and fuse different domain features. Specifically, the TRC extracts global blurred information from multiple layers and suppresses scattering to increase the clarity of vessel features. Transformer feature fusion eliminates the domain gap between the highly semantic feature maps of the convolutional neural network backbone and the adaptive self‐attention maps of TRCs. Benefiting from the long‐range dependencies of transformers, we achieved competitive results in relation to various competing methods on different data sets, including retinal vessel segmentation, simulated blur image segmentation, and real NIR blood vessel image segmentation. Moreover, our method remarkably improved the segmentation results of simulated blur image data sets and a real NIR vessel image data set. The quantitative results of ablation studies and visualizations are also reported to demonstrate the superiority of the TRC‐Unet design. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

With the development of convolutional neural networks (CNNs), deep learning-based face super-resolution (FSR) approaches have achieved remarkable results in recent years. However, existing FSR methods often rely on face prior knowledge, which greatly increases network complexity and computation. In this paper, we propose DAFNet, a dual attention fusion-based FSR network comprising numerous face attention fusion modules (FAFMs). FAFM is a residual structure containing attention mechanism, which is divided into feature branches and attention branches. The feature branch introduces an hourglass block to extract multi-scale information, while the attention branch incorporates channel attention and spatial attention in series. This design ensures that the network prioritizes important information and effectively recovers detailed facial features. Luminance-chrominance error loss and gradient loss are introduced to guide the training process. Additionally, adversarial loss and perceptual loss are incorporated to enhance the recovery of visually realistic face images. Notably, our method can produce clear faces at a high-scale factor of eight times without relying on any facial prior information, effectively reducing network complexity. Quantitative and qualitative experiments conducted on the CelebA and Helen datasets underscore the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

In the medical field, the demanding task is predicting the type of cancer cell, and the analysis to reduce the death rate. MRI technique is used for capturing the brain image because of its high-quality performance and non-ionizing radiation. These collected input images carry only the area of tissues as bright and remove the cerebrospinal fluid to increase the quality of the image. The supervised learning method indicates marvelous performances in solving the problems related to the segmentation and detection of medical images. In the existing model, Convolutional Neural Network (CNN) is used, and the execution of CNN is carried out in different layers. This network consists of different layers that lead to various challenges, such as execution cost and time being high, fetching the wrong input, arising misdiagnosis of the disease. Prediction using different datasets is difficult and creates an overfitting problem, and large memory is needed in the existing method. To overcome this entire issue, an advanced model is developed. Input images collected from online sources are given to the Brain tumor segmentation stage, where the Adaptive Hybrid Convolutional Neural Network (AHCNN) is utilized. Here, the TransResUNet and Fully Convolutional Network (FCN) is utilized to construct the AHCNN for effectively segmenting brain tumors. Here, the parameters are optimized using Flock Member Movement-Based Hybrid Coati with Tomtit Flock Optimization (FMM-HCTFO). The TransResUNet and FCN outcomes are fed to the prediction stage. Here, the brain tumor classification is done using the Multi-scale Dilated Adaptive MobileNet with Attention Mechanism (MSDM-AM) technique. Here, also the parameters are optimized using FMM-HCTFO. Finally, the brain tumor will be classified using the MSDM-AM technique. The achievement of the developed model for the prediction of the brain is increased by tuning the variables using the proposed algorithms. [ABSTRACT FROM AUTHOR]

Hand gestures (HGs) have been extensively acknowledged as a communication standard for the deaf and dumb school system in the Indian sign language (ISL). We suggested an automated Indian sign language recognition (ISLR) method for English in this study. Initially, the hand region is segmented using the Grasshopper optimization algorithm (GOA) based on the skin color model method. The segmentation’s efficacy is further assessed using three techniques: GOA-based skin color detection algorithm (SCDA), particle swarm optimization-based SCDA (PSO-SCDA), and artificial bee colony-based SCDA (ABC-SCDA). Finally, a database for the retrieved motions representing distinct English alphabets is created. For gesture recognition, the system is trained, and a template-based matching approach is used. The classification technique employs the support vector machine (SVM) and the convolution neural network (CNN). Our suggested recognition method achieved the highest accuracy of 97.85% with GOA-SCDA, compared to 89.29% and 93.96% with PSO-SCDA and ABC-SCDA, respectively. Furthermore, CNN outperformed SVM in classification, with a high accuracy of 99.2% and precision of 81.8%. [ABSTRACT FROM AUTHOR]

Deep learning shows great promise for medical image analysis but often lacks explainability, hindering its adoption in healthcare. Attribution techniques that explain model reasoning can potentially increase trust in deep learning among clinical stakeholders. In the literature, much of the research on attribution in medical imaging focuses on visual inspection rather than statistical quantitative analysis. In this paper, we proposed an image-based saliency framework to enhance the explainability of deep learning models in medical image analysis. We use adaptive path-based gradient integration, gradient-free techniques, and class activation mapping along with its derivatives to attribute predictions from brain tumor MRI and COVID-19 chest X-ray datasets made by recent deep convolutional neural network models. The proposed framework integrates qualitative and statistical quantitative assessments, employing Accuracy Information Curves (AICs) and Softmax Information Curves (SICs) to measure the effectiveness of saliency methods in retaining critical image information and their correlation with model predictions. Visual inspections indicate that methods such as ScoreCAM, XRAI, GradCAM, and GradCAM++ consistently produce focused and clinically interpretable attribution maps. These methods highlighted possible biomarkers, exposed model biases, and offered insights into the links between input features and predictions, demonstrating their ability to elucidate model reasoning on these datasets. Empirical evaluations reveal that ScoreCAM and XRAI are particularly effective in retaining relevant image regions, as reflected in their higher AUC values. However, SICs highlight variability, with instances of random saliency masks outperforming established methods, emphasizing the need for combining visual and empirical metrics for a comprehensive evaluation. The results underscore the importance of selecting appropriate saliency methods for specific medical imaging tasks and suggest that combining qualitative and quantitative approaches can enhance the transparency, trustworthiness, and clinical adoption of deep learning models in healthcare. This study advances model explainability to increase trust in deep learning among healthcare stakeholders by revealing the rationale behind predictions. Future research should refine empirical metrics for stability and reliability, include more diverse imaging modalities, and focus on improving model explainability to support clinical decision-making. [ABSTRACT FROM AUTHOR]

In a clinical context, conventional optical microscopy is commonly used for the visualization of biological samples for diagnosis. However, the availability of molecular techniques and rapid diagnostic tests are reducing the use of conventional microscopy, and consequently the number of experienced professionals starts to decrease. Moreover, the continuous visualization during long periods of time through an optical microscope could affect the final diagnosis results due to induced human errors and fatigue. Therefore, microscopy automation is a challenge to be achieved and address this problem. The aim of the study is to develop a low-cost automated system for the visualization of microbiological/parasitological samples by using a conventional optical microscope, and specially designed for its implementation in resource-poor settings laboratories. A 3D-prototype to automate the majority of conventional optical microscopes was designed. Pieces were built with 3D-printing technology and polylactic acid biodegradable material with Tinkercad/Ultimaker Cura 5.1 slicing softwares. The system's components were divided into three subgroups: microscope stage pieces, storage/autofocus-pieces, and smartphone pieces. The prototype is based on servo motors, controlled by Arduino open-source electronic platform, to emulate the X-Y and auto-focus (Z) movements of the microscope. An average time of 27.00 ± 2.58 seconds is required to auto-focus a single FoV. Auto-focus evaluation demonstrates a mean average maximum Laplacian value of 11.83 with tested images. The whole automation process is controlled by a smartphone device, which is responsible for acquiring images for further diagnosis via convolutional neural networks. The prototype is specially designed for resource-poor settings, where microscopy diagnosis is still a routine process. The coalescence between convolutional neural network predictive models and the automation of the movements of a conventional optical microscope confer the system a wide range of image-based diagnosis applications. The accessibility of the system could help improve diagnostics and provide new tools to laboratories worldwide. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have shown great performance in computer vision tasks, from image classification to pattern recognition. However, CNNs′${\rm CNNs}^{\prime }$ superior performance arises at the expense of high computational costs, which restricts their employment in real‐time decision‐making applications. Computationally intensive convolutions can be offloaded to optical metasurfaces, enabling sub‐picosecond latency and nearly zero energy consumption, but the currently reported approaches require additional bulk optics and can only process polarized light, which limits their practical usages in integrated lightweight systems. To solve these challenges, a novel design of the metasurface‐based optical convolutional accelerator is experimentally demonstrated, offering an ultra‐compact volume of 0.016 mm3${\rm mm}^{3}$, a low cross‐talk of ‐20 dB, polarization insensitivity, and is capable of implementing multiple convolution operations and extracting simultaneously various features from light‐encoded images. The ultra‐compact metasurface‐based optical accelerator can be compactly integrated with a digital imaging system to constitute an optical‐electronic hybrid CNN, which experimentally achieves a consistent accuracy of 96 % in arbitrarily polarized MNIST digits classification. The proposed ultra‐compact metasurface‐based optical convolutional accelerator paves the way for power‐efficient edge‐computing platforms for a range of machine vision applications. [ABSTRACT FROM AUTHOR]

Research on continuous hand gesture recognition is motivated by applications of deaf people to provide effective communication between one another. Numerous techniques are adapted for effectively identifying the hand gesture. Moreover, the collection of data becomes a challenging task in the existing models. In some instances, hand gesture in low-resolution images becomes a complicated task. In this research work, a deep learning-based hand gesture detection model is designed using hand data points to uncover patterns that are used to convey information. Initially, hand gesture images are obtained from public sources. The collected inputs are preprocessed through Contrast-Limited Adaptive Histogram Equalization and filtering to eliminate the unnecessary blurs in the images. The preprocessed images undergo hand segmentation using four methods color space transformation, skin color detection, active contour, and morphological operation. The segmented image is subjected to data point feature extraction, where the Adaptive Weighted Scale-Invariant Feature Transform is utilized for further enhancement. The hand data point-extracted features are given to the recognition of hand gestures with the support of an attention-based hybrid network, where the Attention-based Hybrid 1D Convolutional Neural Network with Recurrent Neural Network recognizes the hand gestures from the hand data points. In the hybridization network, the values are optimized with the help of the investigated Adaptive Dandelion White Shark Optimizer to enhance recognition effectiveness. The test results are validated with the existing hand gesture recognition models using diverse evaluation metrics. The findings of the recommended method show 97% and 99% in terms of accuracy and NPV. Thus, the developed model is validated to outperform significant performance rather than the existing models. [ABSTRACT FROM AUTHOR]

BACKGROUND RESULTS CONCLUSION Different varieties of rice vary in planting time, stress resistance, and other characteristics. With advances in rice‐breeding technology, the number of rice varieties has increased significantly, making variety identification crucial for both trading and planting.This study collected RGB images of 20 hybrid rice seed varieties. An enhanced deep super‐resolution network (EDSR) was employed to enhance image resolution, and a variety classification model utilizing the high‐resolution dataset demonstrated superior performance to that of the model using the low‐resolution dataset. A novel training sample selection methodology was introduced integrating deep learning with the Kennard–Stone (KS) algorithm. Convolutional neural networks (CNN) and autoencoders served as supervised and unsupervised feature extractors, respectively. The extracted feature vectors were subsequently processed by the KS algorithm to select training samples. The proposed methodologies exhibited superior performance over the random selection approach in rice variety classification, with an approximately 10.08% improvement in overall classification accuracy. Furthermore, the impact of noise on the proposed methodology was investigated by introducing noise to the images, and the proposed methodologies maintained superior performance relative to the random selection approach on the noisy image dataset.The experimental results indicate that both supervised and unsupervised learning models performed effectively as feature extractors, and the deep learning framework significantly influenced the selection of training set samples. This study presents a novel approach for training sample selection in classification tasks and suggests the potential for extending the proposed method to image datasets and other types of datasets. Further exploration of this potential is warranted. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Background: Pesticide efficacy directly affects crop yield and quality, making targeted spraying a more environmentally friendly and effective method of pesticide application. Common targeted cabbage spraying methods often involve object detection networks. However, complex natural and lighting conditions pose challenges in the accurate detection and positioning of cabbage. Results: In this study, a cabbage detection algorithm based on the YOLOv8n neural network (YOLOv8-cabbage) combined with a positioning system constructed using a Realsense depth camera is proposed. Initially, four of the currently available high-performance object detection models were compared, and YOLOv8n was selected as the transfer learning model for field cabbage detection. Data augmentation and expansion methods were applied to extensively train the model, a large kernel convolution method was proposed to improve the bottleneck section, the Swin transformer module was combined with the convolutional neural network (CNN) to expand the perceptual field of feature extraction and improve edge detection effectiveness, and a nonlocal attention mechanism was added to enhance feature extraction. Ablation experiments were conducted on the same dataset under the same experimental conditions, and the improved model increased the mean average precision (mAP) from 88.8% to 93.9%. Subsequently, depth maps and colour maps were aligned pixelwise to obtain the three-dimensional coordinates of the cabbages via coordinate system conversion. The positioning error of the three-dimensional coordinate cabbage identification and positioning system was (11.2 mm, 10.225 mm, 25.3 mm), which meets the usage requirements. Conclusions: We have achieved accurate cabbage positioning. The object detection system proposed here can detect cabbage in real time in complex field environments, providing technical support for targeted spraying applications and positioning. [ABSTRACT FROM AUTHOR]

PURPOSE: Prostate cancer (PCa) represents a highly heterogeneous disease that requires tools to assess oncologic risk and guide patient management and treatment planning. Current models are based on various clinical and pathologic parameters including Gleason grading, which suffers from a high interobserver variability. In this study, we determine whether objective machine learning (ML)–driven histopathology image analysis would aid us in better risk stratification of PCa. MATERIALS AND METHODS: We propose a deep learning, histopathology image–based risk stratification model that combines clinicopathologic data along with hematoxylin and eosin– and Ki-67–stained histopathology images. We train and test our model, using a five-fold cross-validation strategy, on a data set from 502 treatment-naïve PCa patients who underwent radical prostatectomy (RP) between 2000 and 2012. RESULTS: We used the concordance index as a measure to evaluate the performance of various risk stratification models. Our risk stratification model on the basis of convolutional neural networks demonstrated superior performance compared with Gleason grading and the Cancer of the Prostate Risk Assessment Post-Surgical risk stratification models. Using our model, 3.9% of the low-risk patients were correctly reclassified to be high-risk and 21.3% of the high-risk patients were correctly reclassified as low-risk. CONCLUSION: These findings highlight the importance of ML as an objective tool for histopathology image assessment and patient risk stratification. With further validation on large cohorts, the digital pathology risk classification we propose may be helpful in guiding administration of adjuvant therapy including radiotherapy after RP. We proposed a risk stratification model to combine clinical data with H&E- and Ki-67–stained images. [ABSTRACT FROM AUTHOR]

Computational fluid dynamics (CFD) can be used for non-invasive evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep learning model to both generate patient-specific volume-meshes of the pulmonary artery from 3D cardiac MRI data and directly estimate CFD flow fields. This proof-of-concept study used 135 3D cardiac MRIs from both a public and private dataset. The pulmonary arteries in the MRIs were manually segmented and converted into volume-meshes. CFD simulations were performed on ground truth meshes and interpolated onto point-point correspondent meshes to create the ground truth dataset. The dataset was split 110/10/15 for training, validation, and testing. Image2Flow, a hybrid image and graph convolutional neural network, was trained to transform a pulmonary artery template to patient-specific anatomy and CFD values, taking a specific inlet velocity as an additional input. Image2Flow was evaluated in terms of segmentation, and the accuracy of predicted CFD was assessed using node-wise comparisons. In addition, the ability of Image2Flow to respond to increasing inlet velocities was also evaluated. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.91 (IQR: 0.86–0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.75% (IQR: 9.60–15.30%) and 9.90% (IQR: 8.47–11.90), respectively. Image2Flow also showed an expected response to increased inlet velocities with increasing pressure and velocity values. This proof-of-concept study has shown that it is possible to simultaneously perform patient-specific volume-mesh based segmentation and pressure and flow field estimation using Image2Flow. Image2Flow completes segmentation and CFD in ~330ms, which is ~5000 times faster than manual methods, making it more feasible in a clinical environment. Author summary: Computational fluid dynamics is an engineering tool that can be used in a clinical setting to non-invasively model blood flow through blood vessels, such as the pulmonary artery. This information can be used to inform treatment planning for patients, especially those with cardiovascular conditions. However, its routine use is limited by a labor-intensive process, requiring substantial expertise and computational resources. Recently, machine learning has offered solutions to automate parts of this process, but no single model has addressed the entire workflow. Therefore, we created Image2Flow, a machine learning model capable of generating a patient-specific representation of a pulmonary artery while predicting blood flow through the vessel. Image2Flow can generate highly accurate pulmonary artery representations and reasonably accurate blood flow predictions. Notably, it performs this whole process in 330ms, which is ~5000x faster than the manual methods. With its speed and accuracy, Image2Flow holds substantial promise for facilitating computational fluid dynamics in clinical settings. [ABSTRACT FROM AUTHOR]

Background: Recognition of enhancer–promoter Interactions (EPIs) is crucial for human development. EPIs in the genome play a key role in regulating transcription. However, experimental approaches for classifying EPIs are too expensive in terms of effort, time, and resources. Therefore, more and more studies are being done on developing computational techniques, particularly using deep learning and other machine learning techniques, to address such problems. Unfortunately, the majority of current computational methods are based on convolutional neural networks, recurrent neural networks, or a combination of them, which don't take into consideration contextual details and the long-range interactions between the enhancer and promoter sequences. A new transformer-based model called EPI-Trans is presented in this study to overcome the aforementioned limitations. The multi-head attention mechanism in the transformer model automatically learns features that represent the long interrelationships between enhancer and promoter sequences. Furthermore, a generic model is created with transferability that can be utilized as a pre-trained model for various cell lines. Moreover, the parameters of the generic model are fine-tuned using a particular cell line dataset to improve performance. Results: Based on the results obtained from six benchmark cell lines, the average AUROC for the specific, generic, and best models is 94.2%, 95%, and 95.7%, while the average AUPR is 80.5%, 66.1%, and 79.6% respectively. Conclusions: This study proposed a transformer-based deep learning model for EPI prediction. The comparative results on certain cell lines show that EPI-Trans outperforms other cutting-edge techniques and can provide superior performance on the challenge of recognizing EPI. [ABSTRACT FROM AUTHOR]

The preservation and transmission of traditional villages is crucial to the prosperity and development of ethnic cultures. However, current traditional village surveys usually require a large number of experts and scholars to conduct field research, which is an expensive and time-consuming method, especially for large-scale tasks. Therefore, this study proposes an automatic classification method based on deep learning (DL) for the identification of traditional village heritage value elements (TVHVE). The study evaluates four selected convolutional neural network (CNN) frames using traditional villages in Hubei Province as a sample dataset. The results show that Residual Network152 (ResNet152) is the most suitable CNN frame for identifying TVHVE in Hubei. The stability and consistency of various TVHVE present in the ResNet152 model were evaluated using Area Under Curve (AUC) and Precision Recall Curve (PRC), which indicated satisfactory prediction performance for most elements, except for specific elements such as tombstones and stone carvings, which showed lower accuracy. In addition, the study sheds light on the areas of concern of the model with respect to different TVHVE images and elucidates the reasons behind the confusion between elements through semantic clustering based on image classification and interpretability analysis using the Gradient-Weighted Class Activation Mapping (Grad-CAM) heat map. By using an automated classification method based on DL, this study significantly reduces the cost and effort associated with traditional surveys. At the same time, insight into areas of concern and confusion in the model improves guidance for conservation efforts and provides valuable references for subsequent research. [ABSTRACT FROM AUTHOR]

Deep neural networks have been widely adopted in numerous domains due to their high performance and accessibility to developers and application-specific end-users. Fundamental to image-based applications is the development of Convolutional Neural Networks (CNNs), which possess the ability to automatically extract features from data. However, comprehending these complex models and their learned representations, which typically comprise millions of parameters and numerous layers, remains a challenge for both developers and end-users. This challenge arises due to the absence of interpretable and transparent tools to make sense of black-box models. There exists a growing body of Explainable Artificial Intelligence (XAI) literature, including a collection of methods denoted Class Activation Maps (CAMs), that seek to demystify what representations the model learns from the data, how it informs a given prediction, and why it, at times, performs poorly in certain tasks. We propose a novel XAI visualization method denoted CAManim that seeks to simultaneously broaden and focus end-user understanding of CNN predictions by animating the CAM-based network activation maps through all layers, effectively depicting from end-to-end how a model progressively arrives at the final layer activation. Herein, we demonstrate that CAManim works with any CAM-based method and various CNN architectures. Beyond qualitative model assessments, we additionally propose a novel quantitative assessment that expands upon the Remove and Debias (ROAD) metric, pairing the qualitative end-to-end network visual explanations assessment with our novel quantitative "yellow brick ROAD" assessment (ybROAD). This builds upon prior research to address the increasing demand for interpretable, robust, and transparent model assessment methodology, ultimately improving an end-user's trust in a given model's predictions. Examples and source code can be found at: https://omni-ml.github.io/pytorch-grad-cam-anim/. [ABSTRACT FROM AUTHOR]

Energy hubs (EHs) represent a pivotal paradigm in achieving optimal resource utilization across various energy domains. This paper presents an advanced framework for the optimal management of a smart island, leveraging the synergies within the water-electricity nexus. By integrating diverse resources, including electricity, water, heat, and hydrogen, the proposed EH model aims to meet the multifaceted demands of consumers on the island. To enhance operational efficiency, this study delves into the nuanced impacts of key EH components, elucidating their roles in meeting demand profiles and minimizing operational costs. Formulated as a mixed integer linear programming (MILP) model, the EH optimization problem is addressed using the GAMS optimization tool. The overarching objective is to fulfill consumer demand while concurrently optimizing resource utilization, considering factors such as storage degradation costs and emissions from fossil-fuel-based units. In addition to strategic optimization, this study pioneers a novel approach to stochastic parameter forecasting, integrating convolutional neural networks (CNNs) and long-short-term memory networks (LSTMs). By harnessing the capabilities of these advanced forecasting techniques, the EH model can anticipate dynamic changes in demand patterns with heightened accuracy and precision. The empirical results underscore the transformative potential of the proposed EH framework, showcasing significant reductions—up to 30%—in emission costs. Moreover, the study underscores the pivotal role of EHs as enablers for scaling up renewable energy penetration, offering a robust foundation for sustainable energy transitions in island communities and beyond. Additionally, implementing a load-shifting demand response program can lower total costs by approximately $257 per day, offering significant savings for EHs over extended periods. [Display omitted] • Modeling a mixed integer linear programming for energy management of an energy hub. • Comprehensive study on hydrogen and electric storage systems. • Uncertainty modeling using convolutional and long short-term memory networks. • Modeling water–electricity nexus to meet water and electricity demand. [ABSTRACT FROM AUTHOR]

Suicide is a significant public health issue that devastates individuals and society. Early warning systems are crucial in preventing suicide. The purpose of this research is to create a deep learning model to identify suicide risk using a combination of bidirectional encoder representations from transformers (BERT) and an ensemble of multiple convolutional neural networks (CNN). BERT is used to encode the text data into numerical representations that capture the context-aware meaning of words and phrases, while ensemble CNN is used to analyze the encoded text data to identify patterns and relationships relevant to suicide risk. The model is trained on a large corpus of text data from social media and suicide notes and evaluated on a validation set of labeled data. The results of the proposed model perform better than the recent approaches in detecting suicide risk and can potentially be a valuable tool for suicide prevention efforts. [ABSTRACT FROM AUTHOR]

Previous instance-relation knowledge distillation methods transfer structural relations between instances from the heavy teacher network to the lightweight student network, effectively enhancing the accuracy of the student. However, these methods have two limitations: (1) The modeling of relation knowledge only relies on the current mini-batch instances, causing the instance relations to be incomplete. (2) The information flow hidden in the evolution of instance relations throughout the network has been neglected. To address these problems, we propose a Global Instance Relation Distillation (GIRD) for convolutional neural network compression, which improves both the instance-level and relation-level globality. Firstly, we design a feature reutilization mechanism to store previously learned features to break through the shackles of the mini-batch. Secondly, we model the pairwise similarity-relation based on stored features to reveal more complete instance relations. Furthermore, we construct the pairwise relation-evolution across different layers to reflect the information flow. Extensive experiments on benchmark datasets demonstrate that our proposed method outperforms state-of-the-art approaches in various visual tasks. [ABSTRACT FROM AUTHOR]

Rapid detection of damages occurring as a result of natural disasters is vital for emergency response. In recent years, remote sensing techniques have been commonly used for the automatic categorization and localization of such events using satellite images. Trained based on natural disaster images, a convolutional neural network (CNN) has been applied as a highly successful method, with its ability to reveal outstanding features. Studies aiming to detect target points obtained as a result of extracting visual features from natural images within these networks have achieved their goals. In this study, ensemble learning methods have been suggested as a means to develop the detection of landslide areas from landslide satellite images. Landslide image dataset has been trained for their categorization in CNN models and then they have been used again to localize landslide regions. While model predictions develop overall performance and status, different ensemble strategies have been used and integrated to reduce the sensitivity to prediction variance and training data. Class-selective relevance mapping (CRM) has been used to visualize individual CNN models and ensemble learned behaviors. As a result of the comparisons made based on mean average precision metrics and the criteria of intersection over union, model ensembles have proved to show higher localization performance than any other individual model. [ABSTRACT FROM AUTHOR]

Natural disasters can be unpredictable and catastrophic. Even after the event, the repercussions are prolonged due to the incompetence of disaster management strategies. To mitigate the effects of a natural hazard, disaster management teams have to rapidly come forth with innovative plans of action. To contain the damage that a disaster causes, the response time, and preparedness of a disaster management team is crucial. Having a forewarning about the nature of the disaster can prove to be beneficial for the management team. Remote/unreachable areas such as deep parts of the forests, far-flung rural areas, oceans and other hard to reach locations are at a higher risk of receiving poorer aid and response due to the lack of communication and connectivity with the rest of the world. Our paper provides a solution for this particular problem by suggesting UAV/Drones for surveillance and monitoring in these inaccessible, disaster struck areas. The drones not only monitor the situation but constantly click pictures and send them to a base station, where the images are used to collect insights about the type of disaster that has to be dealt with. The paper proposes a deep learning model based on feature concatenation for classification of disasters which can be deployed at the base station, and can receive data in the form of images from a UAV/drone hovering over the affected place. The proposed model is efficient and able to achieve a higher accuracy as compared to the leading CNN models and closely related recent works as well. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks often perform poorly when faced with datasets that suffer from quantity imbalances and classification difficulties. Despite advances in the field, existing two-stage approaches still exhibit dataset bias or domain shift. To counter this, a phased progressive learning schedule has been proposed that gradually shifts the emphasis from representation learning to training the upper classifier. This approach is particularly beneficial for datasets with larger imbalances or fewer samples. Another new method a coupling-regulation-imbalance loss function is proposed, which combines three parts: a correction term, focal loss, and LDAM loss. This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties. These approaches have yielded satisfactory results on several benchmark datasets, including Imbalanced CIFAR10, Imbalanced CIFAR100, ImageNet-LT, and iNaturalist 2018, and can be easily generalized to other imbalanced classification models. Deep convolutional neural networks often perform poorly when faced with datasets that suffer from quantity imbalances and classification difficulties. Despite advances in the field, existing two-stage approaches still exhibit dataset bias or domain shift. To counter this, a phased progressive learning schedule has been proposed that gradually shifts the emphasis from representation learning to training the upper classifier. This approach is particularly beneficial for datasets with larger imbalances or fewer samples. Another new method a coupling-regulation-imbalance loss function is proposed, which combines three parts: a correction term, focal loss, and LDAM loss. This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties. These approaches have yielded satisfactory results on several benchmark datasets, including Imbalanced CIFAR10, Imbalanced CIFAR100, ImageNet-LT, and iNaturalist 2018, and can be easily generalized to other imbalanced classification models. [ABSTRACT FROM AUTHOR]

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters change and whether the layer will continue learning or not. Based on these scores, the network is scaled down such that the number of parameters to be learned is reduced, yielding a speed-up in training. Unlike state-of-the-art methods that try to compress the network to be used in the inference phase or to limit the number of operations performed in the back-propagation phase, the proposed method is novel in that it focuses on reducing the number of operations performed by the network in the forward propagation during training. The proposed training strategy has been validated on two widely used architecture families: VGG and ResNet. Experiments on MNIST, CIFAR-10 and Imagenette show that, with the proposed method, the training time of the models is more than halved without significantly impacting accuracy. The FLOPs reduction in the forward propagation during training ranges from 17.83% for VGG-11 to 83.74% for ResNet-152. As for the accuracy, the impact depends on the depth of the model and the decrease is between 0.26% and 2.38% for VGGs and between 0.4 and 3.2% for ResNets. These results demonstrate the effectiveness of the proposed technique in speeding up learning of CNNs. The technique will be especially useful in applications where fine-tuning or online training of convolutional models is required, for instance because data arrive sequentially. [ABSTRACT FROM AUTHOR]

The search for gravitational-wave (GW) signals is limited by non-Gaussian transient noises that mimic astrophysical signals. Temporal coincidence between two or more detectors is used to mitigate contamination by these instrumental glitches. However, when a single detector is in operation, coincidence is impossible, and other strategies have to be used. We explore the possibility of using neural network classifiers and present the results obtained with three types of architectures: convolutional neural network, temporal convolutional network, and inception time. The last two architectures are specifically designed to process time-series data. The classifiers are trained on a month of data from the LIGO Livingston detector during the first observing run (O1) to identify data segments that include the signature of a binary black hole merger. Their performances are assessed and compared. We then apply trained classifiers to the remaining three months of O1 data, focusing specifically on single-detector times. The most promising candidate from our search is 4 January 2016 12:24:17 UTC. Although we are not able to constrain the significance of this event to the level conventionally followed in GW searches, we show that the signal is compatible with the merger of two black holes with masses m 1 = 50.7 − 8.9 + 10.4 M ⊙ and m 2 = 24.4 − 9.3 + 20.2 M ⊙ at the luminosity distance of d L = 564 − 338 + 812 Mpc . [ABSTRACT FROM AUTHOR]

Millions of ionograms are acquired annually to monitor the ionosphere. The accumulated data contain untapped information from a range of locations, multiple solar cycles, and various geomagnetic conditions. In this study, we propose the application of deep convolutional neural networks to automatically classify and scale high-latitude ionograms. A supervised approach is implemented and the networks are trained and tested using manually analyzed oblique ionograms acquired at a receiver station located in Skibotn, Norway. The classification routine categorizes the observations based on the presence or absence of E- and F-region traces, while the scaling procedure automatically defines the E- and F-region virtual distances and maximum plasma frequencies. Overall, we conclude that deep convolutional neural networks are suitable for automatic processing of ionograms, even under auroral conditions. The networks achieve an average classification accuracy of 93% ± 4% for the E-region and 86% ± 7% for the F-region. In addition, the networks obtain scientifically useful scaling parameters with median absolute deviation values of 118 kHz ± 27 kHz for the E-region maximum frequency and 105 kHz ± 37 kHz for the Fregion maximum O-mode frequency. Predictions of the virtual distance for the E- and F-region yield median distance deviation values of 6.1 km ± 1.7 km and 8.3 km ± 2.3 km, respectively. The developed networks may facilitate EISCAT 3D and other instruments in Fennoscandia by automatic cataloging and scaling of salient ionospheric features. This data can be used to study both long-term ionospheric trends and more transient ionospheric features, such as traveling ionospheric disturbances. [ABSTRACT FROM AUTHOR]

Background: Schizophrenia (SZ), a psychiatric disorder for which there is no precise diagnosis, has had a serious impact on the quality of human life and social activities for many years. Therefore, an advanced approach for accurate treatment is required. New method: In this study, we provide a classification approach for SZ patients based on a spatial–temporal residual graph convolutional neural network (STRGCN). The model primarily collects spatial frequency features and temporal frequency features by spatial graph convolution and single-channel temporal convolution, respectively, and blends them both for the classification learning, in contrast to traditional approaches that only evaluate temporal frequency information in EEG and disregard spatial frequency features across brain regions. Results: We conducted extensive experiments on the publicly available dataset Zenodo and our own collected dataset. The classification accuracy of the two datasets on our proposed method reached 96.32% and 85.44%, respectively. In the experiment, the dataset using delta has the best classification performance in the sub-bands. Comparison with existing methods: Other methods mainly rely on deep learning models dominated by convolutional neural networks and long and short time memory networks, lacking exploration of the functional connections between channels. In contrast, the present method can treat the EEG signal as a graph and integrate and analyze the temporal frequency and spatial frequency features in the EEG signal. Conclusion: We provide an approach to not only performs better than other classic machine learning and deep learning algorithms on the dataset we used in diagnosing schizophrenia, but also understand the effects of schizophrenia on brain network features. [ABSTRACT FROM AUTHOR]

As mechanized open-pit coal mining intensifies, assessing and predicting slope stability has become increasingly important. To address the limitations of traditional mechanical calculations, numerical simulations, and physical experiments, this paper identifies the key factors impacting slope stability in open-pit mines and develops a multi-parameter sample data set. The study employs hyperparameters optimized using a Bayesian algorithm, introduces additional convolutional layers, and combines the Adam optimizer with dropout techniques to enhance the feature extraction and performance of one-dimensional convolutional neural networks (1D-CNN). This leads to a Bayesian-optimized one-dimensional convolutional neural network (B-1D MCNN) model for predicting slope stability.The study evaluates the classification performance and accuracy of various models for slope stability, including BP neural networks, genetic algorithm-optimized convolutional neural networks, 1D-CNN, and B-1D MCNN, using accuracy, precision, and F1-score as metrics. The analysis also examines the influence of factor indicators and training set length on the model's output to assess its generalization capabilities.The research findings suggest that: (1) the B-1D MCNN model for evaluating slope stability demonstrates the capability to accurately depict the nonlinear correlation between influencing factors and slope stability. (2) Compared with other models, the B-1D MCNN model has shown enhancements of 10.96% to 27.85%, 10.26% to 28.55%, and 8.98% to 25.05% in terms of Accuracy, F1-Score, and Precision, respectively. (3) As the length of the training dataset increases, the performance of the model improves accordingly. (4) The B-1D MCNN model shows a generalization power of 87.5%. [ABSTRACT FROM AUTHOR]

This research paper presents a comprehensive investigation into the utilization of color image processing technologies and deep learning algorithms in the development of a robot vision system specifically designed for 8-ball billiards. The sport of billiards, with its various games and ball arrangements, presents unique challenges for robotic vision systems. The proposed methodology addresses these challenges through two main components: object detection and ball pattern recognition. Initially, a robust algorithm is employed to detect the billiard balls using color space transformation and thresholding techniques. This is followed by determining the position of the billiard table through strategic cropping and isolation of the primary table area. The crucial phase involves the intricate task of recognizing ball patterns to differentiate between solid and striped balls. To achieve this, a modified convolutional neural network is utilized, leveraging the Xception network optimized by an innovative algorithm known as the Improved Chaos African Vulture Optimization (ICAVO) algorithm. The ICAVO algorithm enhances the Xception network's performance by efficiently exploring the solution space and avoiding local optima. The results of this study demonstrate a significant enhancement in recognition accuracy, with the Xception/ICAVO model achieving remarkable recognition rates for both solid and striped balls. This paves the way for the development of more sophisticated and efficient billiards robots. The implications of this research extend beyond 8-ball billiards, highlighting the potential for advanced robotic vision systems in various applications. The successful integration of color image processing, deep learning, and optimization algorithms shows the effectiveness of the proposed methodology. This research has far-reaching implications that go beyond just billiards. The cutting-edge robotic vision technology can be utilized for detecting and tracking objects in different sectors, transforming industrial automation and surveillance setups. By combining color image processing, deep learning, and optimization algorithms, the system proves its effectiveness and flexibility. The innovative approach sets the stage for creating advanced and productive robotic vision systems in various industries. [ABSTRACT FROM AUTHOR]

Electronic skin (e‐skin) is an emerging technology with promising applications in various fields, including human–machine interfaces, prosthetics, and robotics. Soft and flexible sensors are vital components for the e‐skin that can mimic human skin's sensing capabilities. Among soft sensors, liquid‐metal‐based sensors have gained attention owing to their unique properties, such as high electrical conductivity, stretchability, and elasticity. Herein, a novel approach is presented that enables multidirectional pressure sensing with a machine‐learning approach from the transient response of the liquid‐metal‐based soft pressure sensor for the e‐skins. In this study, a soft sensor is developed that utilizes liquid metal and has an array of microchannels on a dome‐shaped structure to detect pressures from multiple directions. The transient response from six microchannels of the sensor is used as the input for a convolutional neural network (CNN) to predict the direction (classification accuracy of 99.1%) and magnitude (regression error of 20.13%) of the applied pressures in real time. Finally, a potential application of the developed liquid‐metal‐based soft sensor as a human–machine interface device is demonstrated by using it to control an RC model car through multidirectional predictions (pressure direction and magnitude) through machine learning in real time. [ABSTRACT FROM AUTHOR]

Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is a challenging task due to the inconsistent shape and size of different organs. Besides this, low contrast at the edges of organs due to similar types of tissue confuses the network's ability to segment the contour of organs properly. In this paper, we propose a novel convolution neural network based uncertainty-driven boundary-refined segmentation network (UDBRNet) that segments the organs from CT images. The CT images are segmented first and produce multiple segmentation masks from multi-line segmentation decoder. Uncertain regions are identified from multiple masks and the boundaries of the organs are refined based on uncertainty data. Our method achieves remarkable performance, boasting dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset, and 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. These results demonstrate the superiority of our uncertainty-driven boundary refinement technique over state-of-the-art segmentation networks such as UNet, Attention UNet, FC-denseNet, BASNet, UNet++, R2UNet, TransUNet, and DS-TransUNet. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions. The source code of our proposed method will be available at https://github.com/riadhassan/UDBRNet. [ABSTRACT FROM AUTHOR]

Machine learning (ML) and deep learning (DL) models are being increasingly employed for medical imagery analyses, with both approaches used to enhance the accuracy of classification/prediction in the diagnoses of various cancers, tumors and bloodborne diseases. To date however, no review of these techniques and their application(s) within the domain of white blood cell (WBC) classification in blood smear images has been undertaken, representing a notable knowledge gap with respect to model selection and comparison. Accordingly, the current study sought to comprehensively identify, explore and contrast ML and DL methods for classifying WBCs. Following development and implementation of a formalized review protocol, a cohort of 136 primary studies published between January 2006 and May 2023 were identified from the global literature, with the most widely used techniques and best-performing WBC classification methods subsequently ascertained. Studies derived from 26 countries, with highest numbers from high-income countries including the United States (n = 32) and The Netherlands (n = 26). While WBC classification was originally rooted in conventional ML, there has been a notable shift toward the use of DL, and particularly convolutional neural networks (CNN), with 54.4% of identified studies (n = 74) including the use of CNNs, and particularly in concurrence with larger datasets and bespoke features e.g., parallel data pre-processing, feature selection, and extraction. While some conventional ML models achieved up to 99% accuracy, accuracy was shown to decrease in concurrence with decreasing dataset size. Deep learning models exhibited improved performance for more extensive datasets and exhibited higher levels of accuracy in concurrence with increasingly large datasets. Availability of appropriate datasets remains a primary challenge, potentially resolvable using data augmentation techniques. Moreover, medical training of computer science researchers is recommended to improve current understanding of leucocyte structure and subsequent selection of appropriate classification models. Likewise, it is critical that future health professionals be made aware of the power, efficacy, precision and applicability of computer science, soft computing and artificial intelligence contributions to medicine, and particularly in areas like medical imaging. [ABSTRACT FROM AUTHOR]

Tornadoes, as highly destructive weather events, require accurate detection for effective decision‐making. Traditional radar‐based tornado detection algorithms (TDA) face challenges with limited tornado feature extraction capabilities, leading to high false alarm rates and low detection probabilities. This study introduces the Multi‐Task Identification Network (MTI‐Net), leveraging Doppler radar data to enhance tornado recognition. MTI‐Net integrates tornado detection and estimation tasks to acquire comprehensive spatial and locational information. As part of MTI‐Net, we introduce a novel backbone network of Multi‐Head Convolutional Block (MHCB), which incorporates Spatial and Channel Attention Units (SAU and CAU). SAU optimizes local tornado feature extraction, while CAU reduces false alarms by enhancing dependencies among input variables. Experiments demonstrate the superiority of MTI‐Net over TDA, with a decrease in false alarm rates from 0.94 to 0.46 and an increase in hit rates from 0.23 to 0.81, highlighting the effectiveness of MTI‐Net in handling small‐scale tornado events. Plain Language Summary: Tornadoes, highly destructive small‐scale weather phenomena, demand accurate detection for informed decision‐making. Although meteorological radars are commonly utilized for tornado identification, current methods often suffer from false alarms or missed detections due to radar noise. In this study, we introduce the multi‐task learning‐based identification network (MTI‐Net), which not only enables tornado detection but also estimates tornado counts within radar data. We integrate Convolutional Neural Networks (CNNs) with Transformer techniques to enhance the model's ability to capture tornado information. CNNs detect local details using filters, while Transformers manage global connections through attention mechanisms. A series of experiments demonstrate significant improvements in tornado detection with MTI‐Net compared to traditional methods. Key Points: A tornado dataset with detailed radar features was created over China from 2017 to 2023Multi‐task learning was designed to simultaneously infer tornado detection and tornado number estimationIntegration of spatial and channel attention units can better extract tornado features from radar data [ABSTRACT FROM AUTHOR]

The search for extraterrestrial intelligence is currently being pursued using multiple techniques and in different wavelength bands. Dyson spheres, megastructures that could be constructed by advanced civilizations to harness the radiation energy of their host stars, represent a potential technosignature, that in principle may be hiding in public data already collected as part of large astronomical surveys. In this study, we present a comprehensive search for partial Dyson spheres by analysing optical and infrared observations from Gaia , 2MASS, and WISE. We develop a pipeline that employs multiple filters to identify potential candidates and reject interlopers in a sample of five million objects, which incorporates a convolutional neural network to help identify confusion in WISE data. Finally, the pipeline identifies seven candidates deserving of further analysis. All of these objects are M-dwarfs, for which astrophysical phenomena cannot easily account for the observed infrared excess emission. [ABSTRACT FROM AUTHOR]

Upcoming wide-field surveys will discover thousands of new strongly lensed quasars which will be monitored with unprecedented cadence by the Legacy Survey of Space and Time (LSST). Many of these quasars will undergo caustic-crossing events over the 10-yr LSST survey, during which the quasar's inner accretion disc crosses a caustic feature produced by an ensemble of microlenses. Such caustic-crossing events offer the unique opportunity to probe the vicinity of the central supermassive black hole, especially when combined with high cadence, multi-instrument follow-up triggered by LSST monitoring. To simulate the high-cadence optical monitoring of caustic-crossing events, we use relativistic accretion disc models which leads to strong asymmetric features. We develop analysis methods to measure the innermost stable circular orbit (ISCO) crossing time of isolated caustic-crossing events and benchmark their performance on our simulations. We also use our simulations to train a convolutional neural network (CNN) to infer the black hole mass, inclination angle, and impact angle directly from these light curves. As a pilot application of our methods, we used archival caustic-crossings of QSO 2237+0305 to estimate the black hole mass and inclination angle. From these data, two of these methods called the second derivative and wavelet methods measure an ISCO crossing time of 48.5 and 49.5 d, corresponding to a Kerr black hole mass of M BH = (1.5 ± 1.2) × 109 and (1.5 ± 1.3) × 109  M⊙, respectively. The CNN inferred log10(M BH/M⊙) = 8.35 ± 0.30 when trained on Schwarzschild black hole simulations, and a moderate inclination of i  = 45 ± 23°. These measurements are found to be consistent with previous estimates. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are becoming popular in cosmology for extracting valuable information from cosmological data. In this paper, we evaluate the performance of a convolutional neural network (CNN) trained on matter density snapshots to distinguish clustering dark energy (DE) from the cosmological constant scenario and to detect the speed of sound (c s) associated with clustering DE. We compare the CNN results with those from a Random Forest (RF) algorithm trained on power spectra. Varying the DE equation of state parameter w DE within the range of −0.7 to −0.99 while keeping |$c_s^2 = 1$|⁠ , we find that the CNN approach results in a significant improvement in accuracy over the RF algorithm. The improvement in classification accuracy can be as high as 40 per cent depending on the physical scales involved. We also investigate the ML algorithms' ability to detect the impact of the speed of sound by choosing |$c_s^2$| from the set {1, 10−2, 10−4, 10−7} while maintaining a constant w DE for three different cases: w DE ∈ {−0.7, −0.8, −0.9}. Our results suggest that distinguishing between various values of |$c_s^2$| and the case where |$c_s^2=1$| is challenging, particularly at small scales and when w DE ≈ −1. However, as we consider larger scales, the accuracy of |$c_s^2$| detection improves. Notably, the CNN algorithm consistently outperforms the RF algorithm, leading to an approximate 20 per cent enhancement in |$c_s^2$| detection accuracy in some cases. [ABSTRACT FROM AUTHOR]

Objectives. This study aimed to develop an initial deep-learning (DL) model based on computerized tomography (CT) scans for diagnosing lumbar spinal stenosis. Summary of Background Data. Magnetic resonance imaging is commonly used for diagnosing lumbar spinal stenosis due to its high soft tissue resolution, but CT is more portable, cost-effective, and has wider regional coverage. Using DL models to improve the accuracy of CT diagnosis can effectively reduce missed diagnoses and misdiagnoses in clinical practice. Materials and Methods. Axial lumbar spine CT scans obtained between March 2022 and September 2023 were included. The data set was divided into a training set (62.3%), a validation set (22.9%), and a control set (14.8%). All data were labeled by two spine surgeons using the widely accepted grading system for lumbar spinal stenosis. The training and validation sets were used to annotate the regions of interest by the two spine surgeons. First, a region of interest detection model and a convolutional neural network classifier were trained using the training set. After training, the model was preliminarily evaluated using a validation set. Finally, the performance of the DL model was evaluated on the control set, and a comparison was made between the model and the classification performance of specialists with varying levels of experience. Results. The central stenosis grading accuracies of DL Model Version 1 and DL Model Version 2 were 88% and 83%, respectively. The lateral recess grading accuracies of DL Model Version 1 and DL Model Version 2 were 75% and 71%, respectively. Conclusions. Our preliminarily developed DL system for assessing the degree of lumbar spinal stenosis in CT, including the central canal and lateral recess, has shown similar accuracy to experienced specialist physicians. This holds great value for further development and clinical application. [ABSTRACT FROM AUTHOR]

Background: Yam (Dioscorea alata L.) is the staple food of many populations in the intertropical zone, where it is grown. The lack of phenotyping methods for tuber quality has hindered the adoption of new genotypes from breeding programs. Recently, near‐infrared spectroscopy (NIRS) has been used as a reliable tool to characterize the chemical composition of the yam tuber. However, it failed to predict the amylose content, although this trait is strongly involved in the quality of the product. Results: This study used NIRS to predict the amylose content from 186 yam flour samples. Two calibration methods were developed and validated on an independent dataset: partial least squares (PLS) and convolutional neural networks (CNN). To evaluate final model performances, the coefficient of determination (R2), the root mean square error (RMSE), and the ratio of performance to deviation (RPD) were calculated using predictions on an independent validation dataset. The tested models showed contrasting performances (i.e., R2 of 0.72 and 0.89, RMSE of 1.33 and 0.81, RPD of 2.13 and 3.49 respectively, for the PLS and the CNN model). Conclusion: According to the quality standard for NIRS model prediction used in food science, the PLS method proved unsuccessful (RPD < 3 and R2 < 0.8) for predicting amylose content from yam flour but the CNN model proved to be reliable and efficient method. With the application of deep learning methods, this study established the proof of concept that amylose content, a key driver of yam textural quality and acceptance, can be predicted accurately using NIRS as a high throughput phenotyping method. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Process monitoring plays a pivotal role in elucidating the intricate interplay among process, structure, and property in additive manufacturing production. The control of powder spreading affects not only particle adhesion but also rearrangement, both of which are indispensable constituents in the selective laser melting (SLM) process. To develop a novel monitoring process, this study proposed a convolutional Takagi–Sugeno–Kang fuzzy neural network (C-TSKFNN) to assess images with uneven powder distribution. The performance of the model was compared with that of conventional image analysis and state-of-the-art deep learning models. With its fusion layer and TSKFNN design, the C-TSKFNN model retains the distinctive characteristics of input images and minimizes expenditures through trainable parameters. The experimental results demonstrated that the average F1 score of the C-TSKFNN model achieved 97.07% and that it had the lowest standard deviation compared to state-of-the-art deep learning models. The trainable parameters were only 103,506, which is lower than those of models. Defect information was also provided locally through a model interpretation technique, facilitating the monitoring of SLM manufacturing. [ABSTRACT FROM AUTHOR]

This article introduces a novel 2D shape data augmentation approach based on intra-class shape space exploration. The proposed method relies on a geodesic interpolation between shapes, leveraging invariant-based morphing techniques. By blending a 2D shape pair belonging to a given class, we are able to generate nonlinear augmentations, hence covering more variations within the shape space. In particular, we formulate data augmentation as an optimization problem that minimizes the deformations between two shapes using the Generalized Finite Fourier Invariant Descriptor. The proposed augmentation technique is evaluated using numerous Convolution Neural Network architectures for 2D shape classification. The results indicate the superiority of the proposed method as compared to state-of-the-art techniques when considering small-scale datasets. [ABSTRACT FROM AUTHOR]

Graph neural networks (GNNs) are reshaping our understanding of biomedicine and diseases by revealing the deep connections among genes and cells. As both algorithmic and biomedical technologies have advanced significantly, we are entering a transformative phase of personalized medicine. While pioneering tools like graph attention networks (GATs) and graph convolutional neural networks (Graph CNN) are advancing graph-based learning, the rise of single-cell sequencing techniques is reshaping our insights on cellular diversity and function. Numerous studies have combined GNNs with single-cell data, showing promising results. In this work, we highlight the GNN methodologies tailored for single-cell data over the recent years. We outline the diverse range of graph deep learning architectures that center on GAT methodologies. Furthermore, we underscore the several objectives of GNN strategies in single-cell data contexts, ranging from cell-type annotation, data integration and imputation, gene regulatory network reconstruction, clustering and many others. This review anticipates a future where GNNs become central to single-cell analysis efforts, particularly as vast omics datasets are continuously generated and the interconnectedness of cells and genes enhances our depth of knowledge in biomedicine. [ABSTRACT FROM AUTHOR]