The very first infected novel coronavirus case (COVID-19) was found in Hubei, China in Dec. 2019. The COVID-19 pandemic has spread over 215 countries and areas in the world, and has significantly affected every aspect of our daily lives. At the time of writing this article, the numbers of infected cases and deaths still increase significantly and have no sign of a well-controlled situation, e.g., as of 14 April 2020, a cumulative total of 1,853,265 (118,854) infected (dead) COVID-19 cases were reported in the world. Motivated by recent advances and applications of artificial intelligence (AI) and big data in various areas, this paper aims at emphasizing their importance in responding to the COVID-19 outbreak and preventing the severe effects of the COVID-19 pandemic. We firstly present an overview of AI and big data, then identify their applications in fighting against COVID-19, next highlight challenges and issues associated with state-of-the-art solutions, and finally come up with recommendations for the communications to effectively control the COVID-19 situation. It is expected that this paper provides researchers and communities with new insights into the ways AI and big data improve the COVID-19 situation, and drives further studies in stopping the COVID-19 outbreak.

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

Aiming at the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, Deep Deterministic Policy Gradient (DDPG) and vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to equivalent virtual abstract scene by transfer model, furthermore, the control action and trajectory sequences are calculated according to trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model generalization performance. Compared with the traditional trajectory planning, the proposed method output continuous rotation angle control sequence, meanwhile, the lateral control error is also reduced.

Oil spillage over a sea or ocean’s surface is a threat to marine and coastal ecosystems. Spaceborne synthetic aperture radar (SAR) data has been used efficiently for the detection of oil spills due to its operational capability in all-day all-weather conditions. The problem is often modeled as a semantic segmentation task. The images need to be segmented into multiple regions of interest such as sea surface, oil spill, look-alikes, ships and land. Training of a classifier for this task is particularly challenging since there is an inherent class imbalance. In this work, we train a convolutional neural network (CNN) with multiple feature extractors for pixel-wise classification; and introduce to use a new loss function, namely ‘gradient profile’ (GP) loss, which is in fact the constituent of the more generic Spatial Profile loss proposed for image translation problems. For the purpose of training, testing and performance evaluation, we use a publicly available dataset with selected oil spill events verified by the European Maritime Safety Agency (EMSA). The results obtained show that the proposed CNN trained with a combination of GP, Jaccard and focal loss functions can detect oil spills with an intersection over union (IoU) value of 63.95%. The IoU value for sea surface, look-alikes, ships and land class is 96.00%, 60.87%, 74.61% and 96.80%, respectively. The mean intersection over union (mIoU) value for all the classes is 78.45%, which accounts for a 13% improvement over the state of the art for this dataset. Moreover, we provide extensive ablation on different Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) based hybrid models to demonstrate the effectiveness of adding GP loss as an additional loss function for training. Results show that GP loss significantly improves the mIoU and F1 scores for CNNs as well as ViTs based hybrid models. GP loss turns out to be a promising loss function in the context of deep learning with SAR images.

The Bayes filters, such as Kalman and particle filters, have been used in sensor fusion to integrate two sources of information and obtain the best estimate of the unknowns. Efficient integration of multiple sensors requires deep knowledge of their error sources and it is not trivial for complicated sensors, such as Inertial Measurement Unit (IMU). Therefore, IMU error modelling and efficient integration of IMU and Global Navigation Satellite System (GNSS) observations has remained a challenge. In this paper, we develop deep Kalman filter to model and remove IMU errors and consequently, improve the accuracy of IMU positioning. In other words, we add modelling step to the prediction and update steps of Kalman filter and the IMU error model is learned during integration. Therefore, our deep Kalman filter outperforms Kalman filter and reaches higher accuracy.

Deep learning (DL) algorithms have recently emerged from machine learning and soft computing techniques. Since then, several deep learning (DL) algorithms have been recently introduced to scientific communities and are applied in various application domains. Today the usage of DL has become essential due to their intelligence, efficient learning, accuracy and robustness in model building. However, in the scientific literature, a comprehensive list of DL algorithms has not been introduced yet. This paper provides a list of the most popular DL algorithms, along with their applications domains.

Physics-informed neural networks can be trained to serve as surrogate models by learning how spatial physical fields develop with change of parameters. This is an advantage over traditional numerical methods that can only be used to calculate a single solution field for a single discrete setting of a parameter. While many studies report accurate results of physics-informed deep learning of laminar flows, evaluations of surrogate modeling of high Reynolds number flows remain sparse. To contribute to this question, we here explore the capabilities and limits of physics-informed deep learning to solve the Reynolds-averaged Navier-Stokes equations for the flow around two airfoils under variable angles of attack. No labeled training data were provided and a single network was trained to simultaneously learn several solution fields in a single training run. The network captured essential flow features such as boundary layers and high and low pressure regions. Moreover, the qualitative correlations of lift and drag with the angle of attack and the higher drag of the thicker airfoil were captured. However, comparisons with reference simulations revealed an underestimation of the shear layer gradients as well as deviations of the fields' extrema. Thus, we also debate potential future improvements to increase the accuracy of the predicted flow. This work offers a prospect on the capabilities and current limitations of physics-informed neural networks for surrogate modeling of high Reynolds number flows. We argue that the method is promising and this work is aimed to encourage further research and development of the method when applied to Reynolds-averaged flows at high Reynolds numbers.

CT scans are currently the most common imaging modality used for suspected stroke patients due to their short acquisition time and wide availability. However, MRI offers superior tissue contrast and image quality. In this study, eight deep learning models are developed, trained, and tested using a dataset of 181 CT/MR pairs from stroke patients. The resultant synthetic MRIs generated by these models are compared through a variety of qualitative and quantitative methods. The synthetic MRIs generated by a 3D UNet model consistently demonstrated superior performance across all methods of evaluation. Overall, the generation of synthetic MRIs from CT scans using the methods described in this paper produces realistic MRIs that can guide the registration of CT scans to MRI atlases. The synthetic MRIs enable the segmentation of white matter, gray matter, and cerebrospinal fluid using algorithms designed for MRIs, exhibiting a high degree of similarity to true MRIs.

ABSTRACT Background It is important to be able to predict, for each individual patient, the likelihood of later metastatic occurrence, because the prediction can guide treatment plans tailored to a specific patient to prevent metastasis and to help avoid under- or over-treatment. Deep Neural Network (DNN) learning, commonly referred to as deep learning, has become popular due to its success in image detection and prediction, but questions such as whether deep learning outperforms other machine learning methods when using non-image clinical data remain unanswered. Grid search has been introduced to deep learning hyperparameter tunning for the purpose of improving its prediction performance, but the effect of grid search on other machine learning methods are under-studied. In this research, we take the empirical approach to study the performance of deep learning and other machine learning methods when using non-image clinical data to predict the occurrence of breast cancer metastasis (BCM) 5, 10, or 15-years after the initial treatment. We developed DNN models as well as models using 9 other machine learning methods including Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), LASSO, Decision Tree (DT), k-Nearest Neighbors (KNN), Random Forrest (RF), AdaBoost (ADB), and XGBoost (XGB). We used grid search to tune hyperparameters for all methods. We then compared the deep learning models to the models trained using the 9 other machine learning methods. Results Based on the mean test AUC results, DNN ranks 6th, 4th, and 3rd when predicting 5-year, 10-year, and 15-year BCM respectively, out of 10 machine learning methods. The top performing methods in predicting 5-year BCM are XGB(1^st), RF(2^nd), and KNN(3^rd). For predicting 10-year BCM the top performers are XGB (1^st), RF(2^nd), and NB(3^rd) . Finally, for 15-year BCM the top performers are SVM (1^st), LR and LASSO (tied for 2^nd), and DNN (3^rd). The ensemble methods RF and XGB outperform other methods when data are less balanced, while SVM, LR, LASSO, and DNN outperform other methods when data are more balanced. Our statistical testing results show that at a significance level of 0.05 DNN overall performs no worse than other machine learning methods when predicting 5-year, 10-year, and 15-year BCM. Conclusions Our results show that deep learning with grid search overall performs at least as well as other machine learning methods when using non-image clinical data. It is interesting to note that some of the other machine learning methods such as XGB, RF, and SVM are very strong competitors of DNN when incorporating grid search. It is also worth noting that the computation time required to do grid search with DNN is way more than that required to do grid search with the other 9 machine learning methods.

Medical brain image analysis is a necessary step in the Computers Assisted /Aided Diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of White Matter Hyperintensities (WMHs) of brain MRI images specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used the bibliometric networks. Out of a total of 140 documents we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and proposal of new models of deep learning to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with indicators (Dice Score, DSC: 0.99) were found, however with little practical application due to the uses of small datasets and lack of reproducibility. Therefore, the main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment.

Machine learning (ML) methods has recently contributed very well in the advancement of the prediction models used for energy consumption. Such models highly improve the accuracy, robustness, and precision and the generalization ability of the conventional time series forecasting tools. This article reviews the state of the art of machine learning models used in the general application of energy consumption. Through a novel search and taxonomy the most relevant literature in the field are classified according to the ML modeling technique, energy type, perdition type, and the application area. A comprehensive review of the literature identifies the major ML methods, their application and a discussion on the evaluation of their effectiveness in energy consumption prediction. This paper further makes a conclusion on the trend and the effectiveness of the ML models. As the result, this research reports an outstanding rise in the accuracy and an ever increasing performance of the prediction technologies using the novel hybrid and ensemble prediction models.

(1) Background: Efficient detection and rectification of defects or post-processing manufacturing conditions such as sharp edges and burrs on metal components are crucial for quality control in precision manufacturing industries. (2) Methods: This paper describes a lab-scale integrated system for real-time and automated metal edge image detection using a customized YOLOv5 ma-chine vision algorithm. The YOLOv5 algorithm and model were developed and embedded in the NVIDIA Jetson Nano microprocessor. The YOLOv5 model can detect three different image types for classification i.e., normal, sharp, and burrs edge on aluminum workpiece blocks. An integrated system connects the NVIDIA Jetson Nano with an embedded YOLOv5 model to a Mitsubishi Electric Melfa RV-2F-1D1-S15 manipulator to perform selective automated chamfer-ing and grinding when certain condition defects are detected. (3) Results: The model demonstrates durable performance, achieving a mean average precision of 0.886 across defect classes with minimal misclassifications. The Mitsubishi Electric Melfa RV-2F-1D1-S15 manipulator received input from the machine vision system and performed an automated chamfering and grinding process accordingly; (4) Conclusions: By integrating camera, embedded deep learning in the microprocessor and manipulator, automated chamfering and grinding process in metal component shapes can be efficiently rectified. This tailored solution promises to improve productivity and consistency in metal manufacturing and remanufacturing.

In this study, we propose a scalable deep learning approach to automated phenotyping using UAV multispectral imagery, exemplified by yellow rust detection in winter wheat. We adopt a high granularity scoring method (1 to 9 scale) to align with international standards and plant breeders’ needs. Using a lower spatial resolution (60m flight height at 2.5cm GSD), we reduce the data volume by a factor of 3.4, making large-scale phenotyping faster and more cost-effective while obtaining results comparable to those of the state-of-the-art. Our model incorporates explainability components to optimise spectral bands and flight schedules, achieving top-3 accuracies of 0.87 for validation and 0.67 and 0.70 on two separate test sets. We demonstrate that a minimal set of bands (EVI, Red, and GNDVI) can achieve results comparable to more complex setups, highlighting the potential for cost-effective solutions. Additionally, we show that high performance can be maintained with fewer time steps, reducing operational complexity. Our interpretable model components improve performance through regularisation and provide actionable insights for agronomists and plant breeders. This scalable and explainable approach offers an efficient solution for yellow rust phenotyping and can be adapted for other phenotypes and species, with future work focusing on optimising the balance between spatial, spectral, and temporal resolutions.

Deep convolutional neural networks (CNNs) have revolutionised computer vision technology by automatically learning hierarchical representations of image data, leading to state-of-the-art performance in visual recognition tasks. This article presents a comprehensive review of deep CNNs, from their evolution and architectures to the current state-of-the-art research. The review also provides the core concepts and building blocks of CNNs and their concise mathematical representations. Furthermore, it explores applications of deep CNNs in three popular domains, including medical diagnosis, remote sensing, and facial recognition. This review will benefit researchers and practitioners in computer vision and artificial intelligence, as well as industry professionals seeking to leverage the latest advancements in deep learning technologies.

As the use of AI in medical imaging has increased, so has the need to explain a model’s results. Segmentation models are one technique used to produce explainable results. Due to larger size and sophistication, segmentation models which operate on 2D data can often produce better results than models operating on 3D data. In the real world, imaging is combined with clinical factors for diagnosis. To replicate this, multimodal models are used which combine image and text modalities. I propose a multimodal arrangement that converts 3D scans to 2D and uses a 2D segmentation model (DeepLabV3) to analyze the images. This is combined with clinical biomarkers to achieve a complete confidence score. Using the Medical Segmentation Decathlon Lung (MSDL) dataset and the LUng CAncer Screening dataset (LUCAS), I achieved a testing Dice coefficient of 0.91 on segmentation with a receiver operating characteristic (ROC), average precision (AP), and F-Score of 0.89, 0.91, and 0.85 respectively on the final multimodal results. This approach raises the F-score from the previously achieved value of 0.508 to 0.85, creating a new baseline of what is achievable with multimodal lung cancer diagnostics and possible methods to achieve these accuracies.

Background: Gliomas, including the most severe form known as glioblastomas, are primary brain tumors arising from glial cells, with significant impact on adults, particularly men aged 45 to 70. Recent advancements in the WHO classification now correlate genetic markers with glioma phenotypes, enhancing diagnostic precision and therapeutic strategies. Aims and Methods: This scoping review aims to evaluate the current state of deep learning (DL) applications in the genetic characterization of adult gliomas, addressing the potential of these technologies for a reliable virtual biopsy. Results: We reviewed 17 studies, analyzing the evolution of DL algorithms from fully convolutional networks to more advanced architectures (ResNet and DenseNet). The methods involved various validation techniques, including k-fold cross-validation and external dataset validation. Conclusions: Our findings highlight significant variability in reported performance, largely due to small, homogeneous datasets and inconsistent validation methods. Despite promising results, particularly in predicting individual genetic traits, the lack of robust external validation limits the generalizability of these models. Future efforts should focus on developing larger, more diverse datasets and integrating multidisciplinary collaboration to enhance model reliability. This review underscores the potential of DL in advancing glioma characterization, paving the way for more precise, non-invasive diagnostic tools.

The integration of sign language recognition systems into digital platforms has the potential to bridge communication gaps between the deaf community and the broader population. This paper introduces an advanced Israeli Sign Language (ISL) recognition system designed to interpret dynamic motion gestures, addressing a critical need for more sophisticated and fluid communication tools. Unlike conventional systems that focus solely on static signs, our approach incorporates both Deep Learning and Computer Vision techniques to analyze and translate dynamic gestures captured in real-time video. We provide a comprehensive account of our preprocessing pipeline, detailing every stage from video collection to the extraction of landmarks using MediaPipe, including the mathematical equations used for preprocessing these landmarks and the final recognition process. The dataset utilized for training our model is unique in its comprehensiveness and is publicly accessible, enhancing the reproducibility and expansion of future research. The deployment of our model on a publicly accessible website allows users to engage with ISL interactively, facilitating both learning and practice. We discuss the development process, the challenges overcome, and the anticipated societal impact of our system in promoting greater inclusivity and understanding.

Traffic anomaly detection is crucial for urban management, yet current research is often confined to small-scale endeavors. This study collected nine months of real-time Wuhan traffic monitoring data from Amap. We proposed Traffic-ConvLSTM, a multi-scale spatial-temporal technique based on long and short-term memory networks (LSTM) and convolutional neural networks (CNN) to effectively achieve long-term anomaly detection at the city level. First, we convert the traffic flow data into image representation, which enables the capture of the spatial correlation between traffic flow and roads and the correlation between traffic flow and roads, as well as the surrounding environment. Second, The model utilizes convolution kernels of different sizes to extract spatial features at road-level, regional-level, and city-level scales, while incorporating temporal features of different time steps to capture hourly, daily, and weekly dynamics. Additionally, varying weights are assigned to the convolution kernels and temporal features of varying spatio-temporal scales to capture the heterogeneous strengths of spatio-temporal correlations within patterns of traffic anomalies. The proposed Traffic-ConvLSTM model exhibits improved performance over existing techniques in the task of identifying long-term and large-scale traffic anomaly occurrences. Furthermore, the analysis reveals significant traffic anomalies during holidays and urban sporting events. The diverse travel patterns observed in response to various activities offer insights for large-scale urban traffic anomaly management, providing recommendations for city-level traffic control strategies.

Color distortion in an image poses a challenge for classification and regression when the input data consists of pictures. Because of that, a new algorithm for color standardization of photos is proposed, which serves as a base for a deep neural network regression model. This approach utilizes a custom color template, which was developed based on an initial series of studies and digital imaging. Using the equalized histogram of R, G, B channels from the digital template and its photo, a color mapping strategy is computed. By applying this approach, the histograms are adjusted, and the colors of photos taken with a smartphone are standardized. The proposed algorithm has been developed for a series of photos where the entire surface roughly maintains a uniform color, and the differences in color between the photographs of individual objects are minor. The optimized approach was validated in the colorimetric determination procedure of vitamin C. The dataset for deep neural network in the regression variant was formed from photos of samples under two separate lighting conditions. For the concentration range of vitamin C from 0 to 87.72 µg·mL-1, the RMSE for the test set ranged between 0.75 and 1.95 µg·mL-1, in comparison to the non-standardized variant, where this indicator was at the level of 1.48-2.29 µg·mL-1. The consistency of the predicted concentration results with actual data expressed using R2 was between 0.9956 and 0.9999, for each of the standardized variants. This approach allows for the removal of light reflections on the shiny surface of solutions, which is a common problem in liquid samples. The color matching algorithm has a universal character, and its application scope is not limited.

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, through the review of traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to effectively improve abnormal traffic detection's accuracy and efficiency. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

Underwater imaging presents unique challenges, notably color distortions and reduced contrast due to light attenuation and scattering. Most underwater image enhancement methods, first use linear transformations for color compensation and then enhance the image. We observed that linear transformation for color compensation is not suitable for certain images. For such images, a non-linear mapping is a better choice. Our paper introduces a unique underwater image restoration approach leveraging a streamlined convolutional neural network (CNN) for dynamic weight learning for linear and non-linear mapping. In the first phase, a classifier is applied that classifies the input images into Type-I or Type-II. In the second phase, depending on the classification, the Deep Line Model (DLM) for Type-I images or the Deep Curve Model (DCM) for Type-II images. For mapping an input image to an output image, DML creatively combines color compensation and contrast adjustment in a single step and uses deep lines for transformation, whereas DCM employs higher-order curves. Both models utilize lightweight neural networks that learn per-pixel dynamic weights based on the input image’s characteristics. Comprehensive evaluations on benchmark datasets using metrics like peak signal-to-noise ratio(PSNR) and root mean squares error (RMSE) affirm our method’s effectiveness in accurately restoring underwater images, outperforming existing techniques.

Background and Objective: Segmentation of the femur in Dual Energy X-ray (DXA) images poses challenges due to reduced contrast, noise, bone shape variations, and inconsistent X-ray beam penetration. In this study, we investigate the relationship between noise and certain deep learning (DL) techniques for semantic segmentation of the femur to enhance segmentation and bone mineral density (BMD) accuracy by incorporating noise reduction methods into DL models. Methods: Convolutional neural network (CNN) based models were employed to segment femurs in DXA images and evaluate the effects of noise reduction filters on segmentation accuracy and its effect on BMD calculation. Various noise reduction techniques were integrated into DL-based models to enhance image quality before training. We assessed the performance of the fully convolutional neural network (FCNN) in comparison to noise reduction algorithms and manual segmentation methods. Results: Our study demonstrated that FCNN outperformed noise reduction algorithms in enhancing segmentation accuracy and enabling precise calculation of BMD. The FCNN-based segmentation approach achieved a segmentation accuracy of 98.84% and a correlation coefficient of 0.9928 for BMD measurements, indicating its effectiveness in the clinical diagnosis of osteoporosis. Conclusions: In conclusion, integrating noise reduction techniques into DL-based models significantly improves femur segmentation accuracy in DXA images. The FCNN model, in particular, shows promising results in enhancing BMD calculation and clinical diagnosis of osteoporosis. These findings highlight the potential of DL techniques in addressing segmentation challenges and improving diagnostic accuracy in medical imaging.

Visualising textual content could be helpful to professionals as well as amateurs across several fields. However, training a text-to-image generator in the mainstream domain requires large amounts of paired text-image and data, which is too expensive to collect since labeling millions of images and videos can be tiresome. GANs like StackGAN and StyleGAN can be considered as solutions to generate images from text. But the images generated may be of low accuracy and resolution, and the entire processing can be highly time-consuming. Moreover, image generation is a notion that is still being researched. Hence, the process of developing a Video Generation model necessitates substantial research. Despite the need for such a model, modern technology has lagged behind the solutions to this problem. This proposal suggests combining two methods, Text modification for Action Definition (TexAD) and SeQuential Image Generation for Video Synthesis (SQIGen). The proposed solution synthesises a sequence of images from textual information feeds and combines these images to create a video. TexAD uses Natural Language Processing and Deep Learning techniques to process, classify and modify text data. SQIGen is an extension of the VQGAN+CLIP neural network architecture that generates a sequence of images from the modified text data

Objectives: The study aimed to develop a deep learning-based edge AI model deployed on electrocardiograph (ECG) devices for real-time detection of atrial fibrillation (AF)-risk during sinus rhythm (SR) using standard 10-second 12-lead electrocardiograms (ECGs). Methods: A novel approach was used to convert standard 12-lead ECGs into binary images for model input, and a lightweight convolutional neural network (CNN)-based model was trained using data collected by the Japan Agency for Medical and Research Development (AMED) between 2019 and 2022. Patients over 40 years old with digital, SR ECGs were retrospectively enrolled and divided into AF and non-AF groups. Data labeling was supervised by cardiologists. The dataset was randomly allocated into training, validation, and internal testing datasets. External testing was conducted on data collected from other hospitals.　Results: The best-trained model achieved an AUC of 0.82 and 0.80, sensitivity of 79.5% and 72.3%, specificity of 77.8% and 77.7%, precision of 78.2% and 76.4%, and overall accuracy of 78.6% and 75.0% in the internal and external testing datasets, respectively. The deployed model and app package utilized 2.5MB and 40MB of the available ROM and RAM capacity on the edge ECG device, correspondingly. Processing time for AF-risk detection was approximately 2 seconds.　Conclusion: The model maintains comparable performance and improves its suitability for deployment on resource-constrained ECG devices, thereby expanding its potential impact to a wide range of healthcare settings. Its successful deployment enables real-time AF-risk detection during SR, allowing for timely intervention to prevent AF-related serious consequences like stroke and premature death.

Background: In today’s competitive market, predicting customer churn with high accuracy is crucial for enterprises to maintain growth and profitability. Traditional predictive models often lack in accuracy due to the complexity of customer behavior.Objective: This research aims to improve the accuracy of predicting customer churn by utilizing the Particle Swarm Optimization (PSO) algorithm for optimizing the hyperparameters of a composite deep learning model. The performance of this enhanced model is evaluated against traditional models such as LSRM_GRU, LSTM, GRU, and CNN_LSTM to demonstrate the effectiveness of PSO in hyperparameter tuning.Methods: A composite deep learning approach was employed, integrating various neural network architectures to leverage their strengths in modeling complex customer interactions. The PSO algorithm was used to optimize the model’s hyperparameters. Customer transaction and interaction data from different business operations served as the dataset for testing and analyzing the model’s performance. Evaluation metrics including accuracy, precision, recall, F1 score, and ROC AUC were utilized for a detailed comparison with established models.Findings: The PSO-enhanced composite deep learning model showed superior performance across all metrics, significantly outperforming the LSRM_GRU, LSTM, GRU, and CNN_LSTM models. Notably, improvements in ROC AUC and F1 score highlight the robustness and balanced precision-recall trade-off of the proposed model, demonstrating its effectiveness in identifying potential churners.Conclusion: The integration of PSO for hyperparameter optimization in composite deep learning models for customer churn prediction has proven to significantly enhance predictive accuracy and performance metrics over conventional models. This underscores the potential of evolutionary algorithms in improving deep learning applications. Future research should explore the scalability of this approach across various sectors and further refine predictive accuracy with evolving customer data.

The quality prediction of quaternary structure models of a protein complex, in the absence of its true structure, is known as the Estimation of Model Accuracy (EMA). EMA is useful for ranking predicted protein complex structures and using them appropriately in biomedical research, such as protein-protein interaction studies, protein design, and drug discovery. With the advent of more accurate protein complex (multimer) prediction tools, such as AlphaFold2-Multimer and ESMFold, the estimation of the accuracy of protein complex structures has attracted increasing attention. Many deep learning methods have been developed to tackle this problem; however, there is a noticeable absence of a comprehensive overview of these methods to facilitate future development. Addressing this gap, we present a review of deep learning EMA methods for protein complex structures developed in the past several years, analyzing their methodologies and impacts. We also provide a prospective summary of some potential new developments for further improving the accuracy of the EMA methods.

The task of human action recognition (HAR) based on skeleton data is a challenging yet crucial technique owing to its wide-ranging applications in numerous domains, including patient monitoring, security surveillance, and observation of human-machine interactions. While numerous algorithms have been proposed in an attempt to distinguish between a myriad of activities, most practical applications necessitate highly accurate detection of specific activity types. This study proposes a novel and highly accurate spatiotemporal graph autoencoder network for HAR based on skeleton data. Furthermore, an extensive investigation was conducted employing diverse modalities. To this end, a spatiotemporal graph autoencoder was constructed to automatically learn both spatial and temporal patterns from human skeleton datasets. The powerful graph convolutional network, designated as GA-GCN, developed in this study, notably outperforms the majority of existing state-of-the-art methods when evaluated on two common datasets, namely NTU RGB+D and NTU RGB+D 120. On the first dataset, the proposed approach achieved accuracies of 92.3\% and 96.8\% for the cross-subject and cross-view evaluations, respectively. On the more challenging NTU RGB+D 120 dataset, GA-GCN attained accuracies of 88.8\% and 90.4\% for the cross-subject and cross-set evaluations, respectively.

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.

Accurate geometric modeling of blood vessels lumen given their 3D images is a basis for vessel quantification in support of cardiovascular diseases diagnosis, treatment and monitoring. Unlike other approaches, which assume circular or elliptical vessel cross-section, the proposed method employs parametric B-splines combined with the image formation system equations to accurately localize the highly curved lumen boundaries. No image segmentation is involved which might reduce the localization accuracy in effect of spatial discretization. It is shown that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. Two example applications: modeling the lower extremities artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA), are presented and discussed to demonstrate the method potential. Besides application to medical diagnosis, blood-flow simulation and vessel-phantom design, it can serve as a tool for automated annotation of image datasets required to train machine-learning algorithms.

The content of this paper is a very significant contribution to the heritage regional reconstruction and conservation interventions. The results about the iconographic analysis of the Early-Renaissance frescoes of St. Leocadia Church, in Chaves, in the north-east of Portugal, were presented for the first time. This paper aims to study facial similarity analysis applied to identification of the personages represented in the 1511-1513 mural paintings of the apse of St. Leocadia Church, in Chaves Municipality (North of Portugal) and those ones in the oil paintings by the Proto-Renaissance Portuguese painter Nuno Gonçalves. In this work, it was explored the feasibility of face recognition technologies in answering many ambiguities concerning Manueline stylistic identity and iconography. A proposal was made to identify the characters, fundamental to the meaning of the frescoes. It has been experimentally proved on 7 characters of St. Leocadia Church’s paintings, in comparison with the referred old master portraits. It was used an in-house trained deep face recognition model to extract facial features from images of 15th and 16th century portraits to compare their degree of similarity. It was undertaken facial similarity analysis of the faces in the formidable portrait gallery of the 15th century Portuguese society represented in the Panels of St. Vicent, which has been subject of national and international research for 130 years. On the other, in the oil painting of St. Peter and St. Paul and Infanta St. Joana, of the same old master. The iconographic interpretation of the mural paintings of St. Leocadia, based in the deep facial features of the images, is plausible: a catechetical purpose; the ritual practices of royal ancestor worship in royal portrait apses of the churches; the Portuguese maritime expansion and the macro-imperial ideology of D. Manuel I.

This paper introduces a novel ensemble adjustment Kalman filter (EAKF) that integrates a machine-learning approach. The approach employs nonlinear variable relationships established by a deep neural network (DNN) during the analysis stage of the EAKF. This process nonlinearly projects observation increments into the state variable space. The newly developed DNN-EAKF algorithm can be applied to coupled data assimilation using coupled ocean-atmosphere models. It enhances cross-component updates in strongly coupled data assimilation (SCDA) by diminishing errors in estimating cross-component error covariance arising from insufficient ensemble members, thereby improving the SCDA analysis. This paper employs a conceptual model to conduct twin experiments, validating the DNN-EAKF’s capability to utilize cross-component observation information in SCDA effectively. The approach is anticipated to offer insights for future methodological integrations of machine learning and data assimilation and provide methods for SCDA applications in coupled general circulation models.

Chinese calligraphy, revered globally for its therapeutic and mindfulness benefits, encompasses styles such as Regular (Kai Shu), Running (Xing Shu), Official (Li Shu), and Cursive (Cao Shu) scripts. Beginners often start with Regular script, advancing to more intricate styles like Cursive. Each style, marked by unique historical calligraphers' contributions, requires learners to discern distinct nuances. The integration of AI in calligraphy analysis, collection, recognition, and classification are pivotal. This study introduces an innovative Convolutional Neural Network (CNN) architecture, pioneering the application of CNN in the classification of Chinese calligraphy. Focusing on the four principal calligraphers' styles from the Tang dynasty (690-907 A.D), this research spotlights the era when the traditional regular script font (Kai Shu) was refined. A comprehensive dataset of 8282 samples from these calligraphers, representing the zenith of regular style, was compiled for CNN training and testing. The model distinguishes personal styles for classification, showing superior performance over existing networks. Achieving 89.5-96.2% accuracy in calligraphy classification, our approach underscores the significance of CNN in both font and artistic style categorization. This research paves the way for advanced studies in Chinese calligraphy and its cultural implications.

Estimating Visual Quality of Street Space (VQoSS) is pivotal for urban design, environmental sustainability, civic engagement, etc. Recent advancements, notably in deep learning, have enabled large-scale analysis. However, traditional deep learning approaches are hampered by extensive data annotation requirements and limited adaptability across diverse VQoSS tasks. Multimodal Large Language Models (MLLMs) have recently demonstrated proficiency in various computer vision tasks, positioning them as promising tools for automated VQoSS assessment. In this paper, we pioneer the application of MLLMs to VQoSS change estimation, with our empirical findings affirming their effectiveness. In addition, we introduce Street Quality GPT (SQ-GPT), a model that distills knowledge from the current most powerful but inaccessible (not free) GPT-4, requiring no human efforts. SQ-GPT approaches GPT-4’s performance and is viable for large-scale VQoSS change estimation. In a case study of Nanjin, we showcase the practicality of SQ-GPT and knowledge distillation pipeline. Our work promises to be a valuable asset for future urban studies research.

Deep learning is emerging in many industrial sectors in hand with big data analytics to streamline production. In the biomanufacturing sector, big data infrastructure is lagging comparatively to other industries. A promising approach is to combine Deep Neural Networks (DNN) with prior knowledge in Hybrid Neural Network (HNN) workflows that are less dependent on the quality and quantity of data. This paper reviews published articles over the past 30 years on the topic of HNN applications to bioprocesses. It revealed that HNNs were applied to various bioprocesses, including microbial cultures, animal cells cultures, mixed microbial cultures, and enzyme biocatalysis. HNNs were mainly applied for process analysis, process monitoring, development of software sensors, open- and closed-loop control, batch-to-batch control, model predictive control, intensified design of experiments, quality-by-design, and recently for the development of digital twins. Most previous HNN studies combined shallow Feedforward Neural Networks (FFNNs) with physical laws, such as macroscopic material balance equations, following the semiparametric design principle. Only recently, deep HNNs based on deep FFNNs, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM) networks and Physics Informed Neural Networks (PINNs) have been reported. The biopharma sector is currently a major driver but applications to biologics quality attributes, new modalities, and downstream processing are significant research gaps.

Taiwan is highly susceptible to global warming, experiencing a 1.4°C increase in air temperatures from 1911-2005, which is twice the average for the Northern Hemisphere. This has led to higher rates of respiratory and cardiovascular mortality. Accurately predicting maximum temperatures during the summer season is crucial, but numerical weather models become less accurate and more uncertain beyond five days. To improve forecast reliability, statistical post-processing is needed to address systematic errors. In September 2020, NOAA NCEP implemented the Global Ensemble Forecast System version 12 (GEFSv12) to help manage climate risks. This study developed a Hybrid statistical post-processing method that combines Artificial Neural Networks (ANN) and Quantile mapping (QQ) approaches to predict daily maximum temperatures and extremes in Taiwan during the summer season. The Hybrid technique, utilizing deep learning techniques, was applied to the GEFSv12 reforecast data and evaluated against ERA5 reanalysis. The Hybrid technique was the most effective among the three techniques tested. It had the lowest bias, RMSE, and highest correlation coefficient. It successfully reduced the warm bias and overestimation of Tmax extreme days. This led to improved prediction skills for all forecast lead times. Compared to ANN and QQ, the Hybrid method was more effective in predicting summer daily Tmax and its extremes on an extended-range time scale deterministic and ensemble probabilistic forecasts over Taiwan.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

Individual investors often struggle to predict stock prices due to the limitations imposed by the computational capacities of personal laptop Graphics Processing Units (GPUs) when running intensive deep learning models. This study proposes solving these GPU constraints by integrating deep learning models with technical analysis methods. This integration significantly reduces analysis time and equips individual investors with the ability to identify stocks that may yield potential gains or losses in an efficient manner. Thus, a comprehensive buy and sell algorithm, compatible with average laptop GPU performance, is introduced in the study. This algorithm offers a lightweight analysis method that emphasizes factors identified by technical analysis methods, thereby providing a more accessible and efficient approach for individual investors. To evaluate the efficacy of this approach, we analyzed the performance of eight deep learning models: LSTM (4 layers), CNN, BiLSTM (4 layers), CNN Attention, BiGRU CNN BiLSTM Attention, BiLSTM Attention CNN, CNN BiLSTM Attention, and CNN Attention BiLSTM. These models were used to predict stock prices for Samsung Electronics and Celltrion Healthcare. The CNN Attention BiLSTM model displayed superior performance among these models, with the lowest validation mean absolute error value. In addition, an experiment was conducted using WandB Sweep to determine the optimal hyperparameters for four individual hybrid models. These optimal parameters were then implemented in each model to validate their back-testing rate of return. The CNN Attention BiLSTM hybrid model emerged as the highest-performing model, achieving an approximate rate of return of 5 percent. Overall, this study offers valuable insights into the performance of various deep learning and hybrid models in predicting stock prices. These findings can assist individual investors in selecting appropriate models that align with their investment strategies, thereby increasing their likelihood of success in the stock market.

Arrhythmia is a cardiac condition characterized by an irregular heart rhythm that hinders the proper circulation of blood, posing a severe risk to individuals’ lives. Globally, arrhythmias are recognized as a significant health concern, accounting for nearly 12 percent of all deaths. As a result, there has been a growing focus on utilizing artificial intelligence for the detection and classification of abnormal heartbeats. In recent years, self-operated heartbeat detection research has gained popularity due to its cost-effectiveness and potential for expediting therapy for individuals at risk of arrhythmias. However, building an efficient automatic heartbeat monitoring approach for arrhythmia identification and classification comes with several significant challenges. These challenges include addressing issues related to data quality, determining the range for heart rate segmentation, managing data imbalance difficulties, handling intra- and inter-patient variations, distinguishing supraventricular irregular heartbeats from regular heartbeats, and ensuring model interpretability. In this study, we propose the Reseek-Arrhythmia model, which leverages deep learning techniques to automatically detect and classify heart arrhythmia diseases. The model combines different convolutional blocks and identity blocks, along with essential components such as convolution layers, batch normalization layers, and activation layers. To train and evaluate the model, we utilized the MIT-BIH and PTB datasets. Remarkably, the proposed model achieves outstanding performance with an accuracy of 99.35% and 93.50% and an acceptable loss of 0.688 and 0.2564, respectively.

Brain-computer interfaces (BCI) from electroencephalography (EEG) provide a practical approach to support human-technology interaction. In particular, motor imagery (MI) is a widely-used BCI paradigm that guides the mental trial of motor tasks without physical movement. Here, we present a deep learning methodology, named Kernel-based Regularized EEGNet (KREEGNet), leveled on Centered Kernel Alignment and Gaussian Functional Connectivity, explicitly designed for EEG-based MI classification. The approach proactively tackles the challenge of intra-subject variability brought on by noisy EEG records and the lack of spatial interpretability within end-to-end frameworks applied for MI classification. KREEGNet is a refinement of the widely accepted EEGNet architecture, featuring an additional kernel-based layer for regularized Gaussian functional connectivity estimation based on CKA. The superiority of KREEGNet is evidenced by our experimental results from binary and multi-class MI classification databases, outperforming the baseline EEGNet and other state-of-the-art methods. Further exploration of our model’s interpretability is conducted at individual and group levels, utilizing classification performance measures and pruned functional connectivities. Our approach is a suitable alternative for interpretable end-to-end EEG-BCI based on deep learning.

Indoor localization (IL) is a significant topic of study with several practical applications. The area of IL has evolved greatly in recent years due to the introduction of numerous technologies such as WiFi, Bluetooth, cameras, and other sensors. Despite the growing interest in this field, there are numerous challenges and drawbacks that must be addressed to develop more accurate and sustainable systems for IL and its real-life applications. This review study gives an in-depth look into IL, covering the most promising artificial intelligence-based and hybrid strategies that have shown excellent potential in overcoming some of the limitations of classic methods. In addition, the paper investigates the significance of high-quality datasets and evaluation metrics in the design and assessment of IL algorithms. Furthermore, this overview study emphasizes the crucial role that machine learning techniques, such as deep learning and transfer learning, play in the advancement of IL. A focus on the importance of IL and the various technologies, methods, and techniques that are being used to improve it. Finally, The survey highlights the need for continued research and development to create more accurate and scalable techniques that can be applied across a range of industries, such as evacuation-egress routes, hazard-crime detection, smart occupancy-driven energy reduction and asset tracking and management.

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

Topic discovery is finding the main idea of large amounts of textual data. It indicates the recurring topics in the documents, allowing an overview of the texts. Current topic discovery models receive the texts, with or without pre-processing of Natural Language Processing. The processing consists of stopwords removal, text cleaning and normalization (lowercase conversion). A topic discovery model that receives texts with or without processing generates general topics since the input data is many uncategorized texts. The general topics do not offer a detailed overview of the input texts, and manual text categorization is a time-consuming and tedious task. Accordingly, it is necessary to integrate an automatic text classification task in the topic discovery process to obtain specific topics with their top words that contain relevant relationships based on belonging to a class. Text classification performs a word analysis that makes up a document to decide what class or category is being identified; then, integrating the text classification before a topic discovery process will provide latent topics depicted by top words with a high coherence in each topic based on the previously obtained classes. Therefore, this paper exposes a approach that integrates text classification into topic discovery from large amounts of English textual data, such as 20-Newsgroup and Reuters corpora. The text classification is accomplished with a Convolutional Neural Network(CNN) incorporating three embedding models based on semantic relationships. The topic discovery over categorized texts is realized with Latent Dirichlet Analysis(LDA), Probabilistic Latent Semantic Analysis(PLSA), and Latent Semantic Analysis(LSA) algorithms. An evaluation process was performed based on the normalized topic coherence metric. The 20-Newsgroup corpus was classified, and twenty topics with ten top words were discovered for each class, obtaining 0.1723 normalized topic coherence when applying LDA, 0.1622 with LSA, and 0.1716 with PLSA. The Reuters corpus was also classified, obtaining 0.1441 normalized topic coherence when applying the LDA algorithm to obtain 20 topics for each class.

Recent advancements in Artificial Intelligence (AI), Deep Learning (DL), and computer vision have revolutionized various industrial processes through image classification and object detection. State-of-the-art Optical Character Recognition (OCR) and Object Detection (OD) technologies, such as YOLO and PaddleOCR, have emerged as powerful solutions for addressing challenges in recognizing textual and non-textual information on printed stickers. However, a well-established framework integrating these cutting-edge technologies for industrial applications still needs to be discovered. In this paper, we propose an innovative framework that combines advanced OCR and OD techniques to automate visual inspection processes in an industrial context. Our primary contribution is a comprehensive framework adept at detecting and recognizing textual and non-textual information on printed stickers within a company, harnessing the latest AI tools and technologies for sticker information recognition. Our experiments reveal an overall macro accuracy of 0.88 for the sticker OCR across three distinct patterns. Furthermore, the proposed system goes beyond traditional Printed Character Recognition (PCR) by extracting supplementary information, such as barcodes and QR codes present in the image, significantly streamlining industrial workflows and minimizing manual labor demands.

The appropriate maintenance of highway roads is critical for the safe operation of road networks and conserves maintenance costs. Multiple methods have been developed to investigate the surface of roads for various types of cracks and potholes, among other damage. Like road surface damage, the condition of expansion joints in concrete pavement is important to avoid unexpected hazardous situations. Thus, in this study, a new system is proposed for autonomous expansion joint monitoring using a vision-based system. The system consists of the following three key parts: (1) a camera-mounted vehicle, (2) indication marks on the expansion joints, and (3) a deep learning-based automatic evaluation algorithm. With paired marks indicating the expansion joints in a concrete pavement, they can be automatically detected. An inspection vehicle is equipped with an action camera that acquires images of the expansion joints in the road. You Only Look Once (YOLO) automatically detects the expansion joints with indication marks, which has a performance accuracy of 95%. The width of the detected expansion joint is calculated using an image processing algorithm. Based on the calculated width, the expansion joint is classified into the following two types: normal and dangerous. The obtained results demonstrate that the proposed system is very efficient in terms of speed and accuracy.

The administration of regional neuraxial analgesia for pain relief during labor is widely recognized as a safe and effective method involving medication delivery into the epidural or subarachnoid space in the lower back. This study proposes an innovative semantic image segmentation methodology emphasizing enhanced interpretability using convolutional Random Fourier Features and layer-wise weighted class-activation maps tailored explicitly for foot segmentation in regional analgesia monitoring. Namely, our contribution is twofold: i) a novel Random Fourier Features layer is introduced to deal with image data to enhance three well-known architectures (FCN, UNet, and ResUNet); ii) three novel quantitive measures are presented to evaluate the interpretability of a given deep learning model devoted to segmentation tasks. Our approach is rigorously evaluated on a demanding dataset of foot thermal images from pregnant women who received epidural anesthesia. Its small size and considerable variability characterize the dataset. Our validation results demonstrate that the proposed methodology not only achieves competitive foot segmentation performance but also significantly enhances the explainability of the process, rendering it well-suited for applications such as epidural insertion during labor.

The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network LBFNet is proposed in this paper.First, a lightweight convolutional neural network LBFNet is established as the base model. Secondly, a three-channel attention mechanism module is introduced to learn the disease features in tomato leaf disease images and reduce the interference of redundant features. Finally, a cascade module is introduced to increase the depth of the model, solve the gradient descent problem, and reduce the loss caused by increasing the depth of the model. The quantized pruning technique is also used to further compress the model parameters and optimize the model performance. The results show that the LBFNet model achieves 99.06% accuracy on the LBFtomato dataset, with a training time of 996s and a single classification accuracy of over 94%. Further training using the saved weight file after quantized pruning makes the model accuracy reach 97.66%. Compared with the base model, the model accuracy was improved by 28%, and the model parameters were reduced by 96.7% compared with the traditional Resnet50. It was found that LBFNet can quickly and accurately identify tomato leaf diseases in complex environments, providing effective assistance to agricultural producers.

Global models have been developed to tackle the challenge of forecasting sets of series that are related or share similarities, but not for heterogeneous datasets. Various methods of partitioning by relatedness have been introduced to enhance the similarities of the set, resulting in improved forecasting accuracy but often at the cost of a reduced sample size, which could be harmful. To shed light on how the relatedness between series impacts the effectiveness of global models in real-world demand forecasting problems we perform an extensive empirical study using the M5 competition dataset. We examined cross-learning scenarios driven by the product hierarchy commonly employed in retail planning, which allow global models to capture interdependencies across products and regions more effectively. Our findings show that global models outperform state-of-the-art local benchmarks by a considerable margin, indicating that they are not inherently more limited than local models and can handle unrelated time series data effectively. The accuracy of data partitioning approaches increases, as the size of the data pools and the models' complexity decrease. However, there is a trade-off between data availability and data relatedness. Smaller data pools lead to increased similarity among time series, making it easier to capture cross-product and cross-region dependencies, but this comes at the cost of a reduced sample, which may not be beneficial. Finally, it's worth noting that the successful implementation of global models for heterogeneous datasets can significantly impact forecasting practice.

Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions and coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this paper, we introduce a data set that can be used to train and evaluate deep learning models, capable of detecting frames from different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20 000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The data set contains results of intermediate processing steps that enables the research or teaching community to create new data sets for specific requirements or to provide new interesting examination examples.

The use of digital twins for the development of Autonomous Maritime Surface Vessels (AMSVs) has enormous potential to resolve the increasing need for water-based navigation and safety at the seas. Aiming at the problem of lack of broad and integrated digital twin implementations with live data along with the absence of a digital twin-driven framework for AMSV design and development, an application framework for the development of a fully autonomous vessel using an integrated digital twin in a 3D simulation environment has been presented. Our framework has four layers to ensure that the simulation and the real-world boat as well as the environment are as close as possible. Åboat, an experimental research platform for maritime automation and autonomous surface ship applications, equipped with two trolling electric motors, cameras, LiDARs, IMU and GPS has been used as the case study to provide a proof of concept. Åboat and its sensors, alongwith the environment have been replicated in a 3D simulation environment. Using the proposed application framework, we develop obstacle detection and path planning systems based on machine learning which leverage live data from a 3D simulation environment to mirror the complex dynamics of the real world.

Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operation, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying breast cancer from unregistered multi-view mammograms. This motivates us to leverage the architecture of Vision Transformers to capture long-range relationships of multiple mammograms from the same patient. For this purpose, we employ local Transformer blocks to separately learn patch relationships within a specific view (CC/MLO) of one side (right/left) of mammogram. The outputs from different views and sides are concatenated and fed into global Transformer blocks, to jointly learn patch relationships between two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of CC and MLO view mammograms, which include 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our two-view Transformer-based model achieves lesion classification accuracy of 77.0% and area under ROC curve (AUC = 0.814), outperforming state-of-the-art multi-view CNNs by 3.1% and 3%, respectively. Meanwhile, the new two-view model improves mammographic case classification accuracies of two single-view models by 7.4% (CC) and 4.5% (MLO), respectively. The promising results unveil the great potential of using Transformers to develop high-performing computer-aided diagnosis (CADx) schemes of mammography.

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 work aims to develop an autonomous system for the unmanned aerial vehicle (UAV) to land on a moving platform such as the automobile or marine vessels, providing a promising solution for a long-endurance flight operation, a large mission coverage range, and a convenient recharging ground station. Different from most state-of-the-art UAV landing frameworks which rely on UAV’s onboard computers and sensors, the proposed system fully depends on the computation unit situated on the ground vehicle/marine vessel to serve as a landing guidance system. Such novel configuration can therefore lighten the burden of the UAV and computation power on the ground vehicle/marine vessel could be enhanced. In particular, we exploit a sensor fusion-based algorithm for the guidance system to perform UAV localization, whilst a control method based upon trajectory optimization is integrated. Indoor and outdoor experiments are conducted and the result shows that a precise autonomous landing on a 43 X 43 cm platform could be performed.

In an industrial environment, the quality assurance of weld seams requires extensive efforts. The most commonly used methods for that are expensive and time-consuming destructive tests, since quality assurance procedures are difficult to integrate into production processes. Beyond that, available test methods allow only the assessment of a very limited set of characteristics. They are either suitable for determining selected geometric features or for locating and evaluating internal seam defects. The presented work describes an evaluation methodology based on microfocus X-ray computed tomography scans (µCT scans) which enable the 3D characterization of weld seams, including internal defects such as cracks and pores. A 3D representation of the weld contour, i.e., the complete geometry of the joint area in the component with all quality-relevant geometric criteria, is an unprecedented novelty. Both the dimensions of the weld seam and internal defects can be revealed, quantified with a resolution down to a few micrometers and precisely assigned to the welded component. On the basis of the methodology developed within the framework of this study, the results of the scans performed on the alloy AA 2219 can be transferred to other aluminum alloys. In this way, the data evaluation framework can be used to obtain extensive reference data for the calibration and validation of inline process monitoring systems employing Deep Learning-based data processing.

As a relatively high percentage of adenoma polyps are missed, a computer-aided diagnosis (CAD) tool based on deep learning can aid the endoscopist in diagnosing colorectal polyps or colorectal cancer in order to decrease polyps missing rate and prevent colorectal cancer mortality. Convolutional Neural Network (CNN) is a deep learning method and has achieved better results in detecting and segmenting specific objects in images in the last decade than conventional models such as regression, support vector machines or artificial neural networks. In recent years, based on the studies in medical imaging criteria, CNN models have acquired promising results in detecting masses and lesions in various body organs, including colorectal polyps. In this review, the structure and architecture of CNN models and how colonoscopy images are processed as input and converted to the output are explained in detail. In most primary studies conducted in the colorectal polyp detection and classification field, the CNN model has been regarded as a black box since the calculations performed at different layers in the model training process have not been clarified precisely. Furthermore, I discuss the differences between the CNN and conventional models, inspect how to train the CNN model for diagnosing colorectal polyps or cancer, and evaluate model performance after the training process.

Macula fovea detection is a crucial prerequisite towards screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither accuracy nor effectiveness of the diagnose process could be guaranteed. In this project, we proposed a deep learning approach on ultra-widefield fundus (UWF) images for macula fovea detection. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. Methods based on U-shape network (Unet) and Fully Convolutional Networks (FCN) are implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. Results are measured by calculating the Euclidean distance between proposed approaches and the accurate grounded standard, which is detected by Ultra-widefield swept-source optical coherence tomograph (UWF-OCT) approach. Through a comparation of proposed methods, we conclude that, deep learning approach of Unet outperformed other methods on macula fovea detection tasks, by which outcomes obtained are comparable to grounded standard method.

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

Annotating training data is a time consuming and labor intensive process in deep learning, especially for images with many objects present. In this paper, we propose a method to allow deep networks to be trained on data with reduced numbers of annotations (per image) in heatmap regression tasks (e.g. object detection and counting), by applying an asymmetric loss function. In a real scenario, this reduction of annotations can be imposed by the researchers (e.g. ask the annotators to label only 50% of what they see in each image), or can potentially counteract unintentionally missing labels from the annotators. To demonstrate the effectiveness of our method, we conduct experiments in two domains, crowd counting and wheat spikelet detection, using different deep network architecture. We drop various percentages of instance annotations per image in training. Results show that an asymmetric loss function is effective across different models and datasets, even in very extreme cases with limited annotations provided (e.g. 90% of the original annotations reduced). Whilst tuning of the key parameters are required, we find that setting conservative parameter values can help more realistic situations, where only small amounts of data have been missed by annotators.

Background: White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin. Method: We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2. Results: The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their method in public repositories. Conclusions: We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

The small satellite market continues to grow year after year. A compound annual growth rate of 17% is estimated during the period between 2020 and 2025. Low-cost satellites can send a vast amount of images to be post-processed at the ground to improve the quality and extract detailed information. In this domain lies the resolution enhancement task, where a low-resolution image is converted to a higher resolution automatically. Deep learning approaches to Super-Resolution (SR) reached the state-of-the-art in multiple benchmarks; however, most of them were studied in a single-frame fashion. With satellite imagery, multi-frame images can be obtained at different conditions giving the possibility to add more information per image and improve the final analysis. In this context, we developed and applied to the PROBA-V dataset of multi-frame satellite images a model that recently topped the European Space Agency’s Multi-frame Super Resolution (MFSR) competition. The model is based on proven methods that worked on 2D images tweaked to work on 3D: the Wide Activation Super Resolution (WDSR) family. We show that with a simple 3D CNN residual architecture with WDSR blocks and a frame permutation technique as data augmentation better scores can be achieved than with more complex models. Moreover, the model requires few hardware resources, both for training and evaluation, so it can be applied directly from a personal laptop.

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.

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, bio-mass estimation, etc. Deep Neural Networks (DNN) have shown superior results when comparing with conventional machine learning methods such as Multi-Layer Perceptron (MLP) in cases of huge input data. The objective of this research was to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were employed to classify tree species in a test site in Finland. The classifiers were trained with a dataset of 3039 manually labelled trees. Then the accuracies were assessed by employing independent datasets of 803 records. To find the most efficient set of feature combination, we compare the performances of 3D-CNN models trained with hyperspectral (HS) channels, RGB channels, and canopy height model (CHM), separately and combined. It is demonstrated that the proposed 3D-CNN model with RGB and HS layers produces the highest classification accuracy. The producer accuracy of the best 3D-CNN classifier on the test dataset were 99.6%, 94.8%, and 97.4% for pines, spruces, and birches, respectively. The best 3D-CNN classifier produced ~5% better classification accuracy than the MLP with all layers. Our results suggest that the proposed method provides excellent classification results with acceptable performance metrics for HS datasets. Our results show that pine class was detectable in most layers. Spruce was most detectable in RGB data, while birch was most detectable in the HS layers. Furthermore, the RGB datasets provide acceptable results for many low-accuracy applications.

Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.

The basal ganglia (BG) are a central component of the brain, crucial to the initiation, execution and learning of adaptive actions. The BG are the major site of the action of dopamine. An important aspect of the BG architecture is the existence of two paths, direct and indirect, having different projection targets and dopamine receptor expression. To understand the BG, dopamine, and related disorders, it is imperative to understand the two paths. The standard account used in neuroscience research for decades posits that the role of the direct path is to support movements, while that of the indirect path is to suppress unselected or completed movements. This account is contradicted by converging evidence. Here, we explain why the arguments supporting the standard account are flawed, and present a new account, in which the role of the indirect path is completely opposite: to support automated execution. During acute events, the direct path allows coarse responses. These are refined by competition, and the resulting focused response is executed and learned by the indirect path, assisted by cholinergic interneurons and the subthalamic nucleus (STN). The new account allows a novel understanding of the symptoms of Parkinson's disease, in particular tremor and rigidity, and of its treatment by STN deep brain stimulation.

Timely detection of surface damages on wind turbine blades is imperative for minimising downtime and avoiding possible catastrophic structural failures. With recent advances in drone technology, a large number of high-resolution images of wind turbines are routinely acquired and subsequently analysed by experts to identify imminent damages. Automated analysis of these inspection images with the help of machine learning algorithms can reduce the inspection cost, thereby reducing the overall maintenance cost arising from the manual labour involved. In this work, we develop a deep learning based automated damage suggestion system for subsequent analysis of drone inspection images. Experimental results demonstrate that the proposed approach could achieve almost human level precision in terms of suggested damage location and types on wind turbine blades. We further demonstrate that for relatively small training sets advanced data augmentation during deep learning training can better generalise the trained model providing a significant gain in precision.

This study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile statioThis study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile stations. The recurrent neural networks with multiple consecutive timestamps can be applied to extract the features of time series data for the improvement of location estimation. In practical experimental environments, there are 4,525 records, 59 different base stations, and 582 different Wi-Fi access points detected in Fuzhou University in China. The lower location errors can be obtained by the recurrent neural networks with multiple consecutive timestamps (e.g., 2 timestamps and 3 timestamps); the experimental results can be observed that the average error of location estimation was 9.19 meters by the proposed mobile positioning method with 2 timestamps.

In recent years, weeds is responsible for most of the agricultural yield losses. To deal with this threat, farmers resort to spraying pesticides throughout the field. Such method not only requires huge quantities of herbicides but impact environment and humans health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide at the right place and at the right time (Precision Agriculture). Nowadays, Unmanned Aerial Vehicle (UAV) is becoming an interesting acquisition system for weeds localization and management due to its ability to obtain the images of the entire agricultural field with a very high spatial resolution and at low cost. Despite the important advances in UAV acquisition systems, automatic weeds detection remains a challenging problem because of its strong similarity with the crops. Recently Deep Learning approach has shown impressive results in different complex classification problem. However, this approach needs a certain amount of training data but, creating large agricultural datasets with pixel-level annotations by expert is an extremely time consuming task. In this paper, we propose a novel fully automatic learning method using Convolutional Neuronal Networks (CNNs) with unsupervised training dataset collection for weeds detection from UAV images. The proposed method consists in three main phases. First we automatically detect the crop lines and using them to identify the interline weeds. In the second phase, interline weeds are used to constitute the training dataset. Finally, we performed CNNs on this dataset to build a model able to detect the crop and weeds in the images. The results obtained are comparable to the traditional supervised training data labeling. The accuracy gaps are 1.5% in the spinach field and 6% in the bean field.

Deep learning has recently attracted much attention due to its excellent performance in processing audio, image, and video data. However, few studies are devoted to the field of automatic modulation classification (AMC). It is one of the most well-known research topics in communication signal recognition, which remains challenging for traditional methods due to the complex disturbance from other sources. This paper proposes a heterogeneous deep model fusion (HDMF) method to solve the problem in a unified framework. The contributions include: 1) The convolutional neural network (CNN) and long short-term memory (LSTM) are combined by two different ways without prior knowledge involved; 2) A large database, including eleven types of single-carrier modulation signals with various noises as well as a fading channel, is collected with various signal-to-noise ratios (SNRs) based on a real geographical environment; and 3) Experimental results demonstrate that HDMF is super capable of copping with the AMC problem, and achieves much better performance when compared with the independent network. The source code and the database will be publically available.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

Through the development of the metaverse concept from the Sumerian myth (5500 - 1800 BC) and mind-altering novel, “Snow Crash” in 1992, to today’s information age, human- and society-centred urban metaverse worlds, an extension of residents and urban society where the virtual and the physically real blend and are more organically integrated, are meant to mirror the fabric of urban life with no harm to their residents. The success of urban metaverse cybercommunities depends on the quality of data-driven Smart City (SC) Digital Twins (DTs), the seamless exchange of data between cyber and physical worlds (e.g. between residents and their counterpart “Avatars’’) and the processing of the data effectively and efficiently with no vicious interventions. The potential risks in this ecosystem that incorporates Web3 can be extremer than the ones in Web2 since users are immersed with multiple tightly coupled wearable sensor-rich devices perceiving the blend of the real and the virtual with possible imminent negative experiences. This study, by analysing potential cyberthreats in the urban metaverse cyberspaces, proposes a blockchain-based Decentralised Privacy-Preserving Machine Learning (DPPML) authentication and verification technique, which uses the metaverse immersive devices and can be instrumented effectively against identity impersonation and theft of credentials, identity, or avatars.

Currently, the Bangladeshi financial sector is undergoing significant transformations. With the expansion of the infrastructure and the increasing prevalence of digital banking services, it is essential to take measures to prevent cyberattacks. These threats can be effectively mitigated through the utilization of deep learning and machine learning techniques. Through the analysis of massive amounts of banking data in real-time, these methods make it possible to detect and prevent malicious software, fraud, and security breaches that are proactive. Because the government is actively pushing for financial inclusion and digitalization, strong cybersecurity measures are more important than they have ever been. It is the purpose of this study to investigate the application of deep learning and machine learning to improve the cybersecurity environment of Bangladesh’s banking sector in light of the country’s rapidly expanding digital economy.

This article presents a low-cost insurance system developed for small-hold farms in disaster-prone regions, primarily using free Earth Observation (EO) data and Free Open Source Software (FOSS) – collectively termed sustainable geoinformatics - with a proprietary mobile phone app that enables verification. The study examined 30 farms in Risaralda department, Colombia. A Digital Elevation Model (12.5m pixels) from the ALOS PALSAR satellite sensor was used with a Geographical Information System (GIS) to map the terrain, drainage and geohazards of each farming district. Google Earth Engine (GEE) was used to carry out Time Series Analysis of 15 EO and weather datasets for 1998 to 2020. This analysis enabled the levels of risk from hydrometeorological hazards to be determined for each farm of the study, providing key data for the setting of insurance premiums. A parametric insurance product was piloted using GPS-tagged, time-stamped mobile phone photos to verify crop health. Key features of this insurance system are its low operational cost and rapid damage verification, relative to conventional approaches to farm insurance. It is an affordable form of insurance for small-scale farmers, with the rapid verification and payment of claims. This relatively fast, low-cost and affordable approach to insurance for small-scale farming enhances sustainable development by enabling policy-holder farmers to recover more quickly from disasters.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

Accurate short-term solar irradiance forecasting is crucial for the efficient operation of solar energy driven photovoltaic (PV) power plants. In this research, we introduce a novel hybrid ensemble forecasting model that amalgamates the strengths of machine learning tree-based models and deep learning neuron-based models. The hybrid ensemble model integrates the interpretability of tree-based models with the capacity of neuron-based models to capture complex temporal dependencies within solar irradiance data. Furthermore, stacking and voting ensemble strategies are employed to harness the collective strengths of these models, significantly enhancing prediction accuracy. This integrated methodology is enhanced by incorporating pixels from satellite images provided by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT). These pixels are converted into structured data arrays and employed as exogenous inputs in the algorithm. The primary objective of this study is to improve the accuracy of short-term solar irradiance predictions, spanning a forecast horizon up to 6 hours ahead. The incorporation of EUMETSAT satellite image pixels data enables the model to extract valuable spatial and temporal information, thus enhancing the overall forecasting precision. This research also includes detailed analysis of the derivation of GHI using satellite images. The study was carried out and the models tested across three distinct locations in Austria. A detailed comparative analysis was carried out for traditional Satellite (SAT) and Numerical Weather Prediction (NWP) models with hybrid models. Our findings demonstrate a higher skill score for all of the approaches compared to smart persistent model and consistently highlight the superiority of the hybrid ensemble model for short-term prediction window of 1 to 6 hours. This research underscores the potential for enhanced accuracy of the hybrid approach to advance short-term solar irradiance forecasting, emphasizing its effectiveness at understanding the intricate interplay of the meteorological variables affecting solar energy generation worldwide. The results of this investigation carry noteworthy implications for advancing solar energy systems, thereby supporting the sustainable integration of renewable energy sources into the electrical grid.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA approved AI applications for breast imaging, but adoption and utilization are widely variable and overall low. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer and many of the most exciting research and available AI applications focus on cancer detection for mammography. There are however multiple additional potential applications for AI in breast imaging including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. We cover especially unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

In this paper, we redefine the boundaries of blood cell classification, expanding from 5 to 11 distinct blood cell types using the challenging 11-class PBC dataset. This shift enables a deeper understanding of blood cell diversity, overcoming previous limitations in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking "Naturalize" augmentation technique produces remarkable results. The 2K-PBC dataset generated with "Naturalize" boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The "Naturalize" technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

The Global natural and manmade events are exposing the fragility of the tourism industry and its impact on the global economy. Prior to the COVID-19 pandemic, tourism contributed 10.3% to the global GDP and employed 333 million people but saw a significant decline due to the pandemic. Sustainable and smart tourism requires collaboration from all stakeholders and a comprehensive understanding of global and local issues to drive responsible and innovative growth in the sector. This paper presents an approach for leveraging big data and deep learning to dis-cover holistic, multi-perspective (e.g., local, cultural, national, and international) and objective information on a subject. Specifically, we develop a machine learning pipeline to extract parameters from academic literature and public opinions on Twitter, providing a unique and comprehensive view of the industry from both academic and public perspectives. The academic-view dataset was created from the Scopus database and contains 156,759 research articles from 2000 to 2022, which were modelled to identify 33 distinct parameters in 4 categories: Tourism Types, Planning, Challenges, and Media & Technologies. A Twitter dataset of 485,813 tweets was collected over 18 months starting March 2021 to August 2022 to showcase public perception of tourism in Saudi Arabia, which was modelled to reveal 13 parameters categorized into two broader sets: Tourist Attractions and Tourism Services. Discovering system parameters are re-quired to embed autonomous capabilities in systems and for decision-making and problem-solving during system design and operations. The proposed approach improves AI-based information discovery by extending the use of scientific literature, Twitter, and other sources for autonomous, dynamic optimizations of systems, promoting novel research in the tourism sector and contributing to the development of smart and sustainable societies. The paper also presents a comprehensive knowledge structure and literature review of the tourism sector based on over 250 research articles.

As the adoption of deep learning models continues to surge across various applications, the need for efficient deployment architectures becomes increasingly critical. This paper presents a novel approach to enhance the deployment of deep learning models by leveraging serverless architecture. Serverless computing has been popular for its auto-scaling, cost-effectiveness, and simplified management characteristics. However, the intense resource demands of deep learning models pose challenges in maintaining low response times and effective load balancing within serverless environments. The proposed architecture addresses these challenges by integrating principles from both deep learning model optimization and serverless computing. Through systematic experimentation and analysis, we demonstrate that by appropriately designing and tuning the deployment architecture, significant improvements in response time, performance, resource utilization, and load distribution can be achieved.

Mobile health technologies enable continuous, quantitative assessment of mobility and gait in real-world environments, facilitating early diagnosis of gait disorders, disease progression monitoring, and prediction of adverse events like falls. Traditionally, mobile gait assessment predominantly relied on body-fixed sensors positioned at the feet or lower trunk. Here, we investigate the potential of an algorithm utilizing an ear-worn motion sensor for spatiotemporal segmentation of gait patterns. We collected 3D acceleration profiles from the ear-worn sensor during varied walking speeds in 53 healthy adults. Temporal convolutional networks were trained to detect stepping sequences and predict spatial relations between steps. The resulting algorithm, mEar, accurately detects initial and final ground contacts (F1 score of 99% and 91%, respectively). It enables determination of temporal and spatial gait cycle characteristics (among others stride time and stride length) with good to excellent validity at a precision sufficient to monitor clinically relevant changes in walking speed, stride-to-stride variability, and side asymmetry. This study highlights the ear as a viable site for monitoring gait and proposes its potential integration with in-ear vital sign monitoring. Such integration offers a practical approach to comprehensive health monitoring and telemedical applications, by integrating multiple sensors in a single anatomical location.

Groundnut is an oil seed cash crop, that can be consumed directly by humans and animals. It is also used as an intelligence in the industrial production of butter and other products. However, Groundnut seeds can become infected with fungi, viruses, pests, physical damage, and high heat, which can negatively impact crop yield, quality, and economic value, and pose health hazards. To address these challenges, computer vision technology detects and classifies defects. This study introduced an ensemble deep learning defected classification model that combines VGG16 and InceptionV3 using seed images. To enhance model performance, collected images are preprocessed using novel techniques tailored to different image types. Preprocessing techniques are chosen based on image-quality evaluation metrics. Watershed segmentation is applied followed by detecting the region of interest in the image using YOLOv3. The image dataset is augmented and balanced using a Generative Adversarial Network (GAN). The model development involves a combination of classical and deep-based features, comparing features extracted with (HOG and GLCM) to those extracted with InceptionV3 and VGG16. The ensemble model achieves an accuracy of 96.25% with a split ratio of 10% for testing, 10% for validation, and 80% for training set. This research benefits farmers looking to improve yield, consumers of groundnut products, and researchers studying seed defects. The work provides valid insights for future researchers regarding dataset creation, augmentation, methods, and feature selection for modeling. However, the model experienced misclassifications due to the similar appearance of sample images in different classes. Future researchers should address these challenges and consider factors such as oil content and defect grading.

With the rapid development of Intelligent Transportation Systems (ITS), vehicle type classification, as a key link in Automatic Toll Collection systems (ATC), is of great significance in improving traffic efficiency and reducing economic losses. This study proposes an intelligent vehicle classification system based on deep learning and multi-sensor data fusion to address the accuracy issues existing in vehicle classification methods based on optical sensors (OS) and human observers. The system significantly improves the accuracy and robustness of vehicle classification by combining deep Convolutional Neural Networks (CNN), LiDAR sensors, and machine learning algorithms. We first constructed a large-scale annotated dataset containing multiple vehicle types and complex traffic scenes to improve our model's capability to identify different vehicle characteristics. Next, CNN models based on different architectures were designed to extract global and local features of the vehicle, respectively. In addition, the LiDAR sensor was used to achieve the spatial structure architectures of the vehicle and combined with the output of the CNN model to improve classification performance under occlusion and complex scenes.

Accurate forecasting of available energy portion that corresponds to the reservoir inflow of the month(s) ahead provides important decision support for the hydropower plants in energy pro-duction planning for revenue maximization, as well as for the environmental impact prevention, and flood control at the upstream and downstream of a basin. Therefore, a reliable forecasting tool or model is deemed necessary and crucial. Considering the fluctuation and nonlinearity of data which significantly influence the forecasting results, this study develops an effective hybrid model by integrating Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) called “PSO-ANN” model based on the hydrological and meteorological data pre-processed by cross-correlation function (CCF), autocorrelation function (AFC), and normalization techniques for predicting the available energy portion corresponding to the reservoir inflow mentioned above for a case study hydropower plant in Laos namely, Theun-Hinboun hydropower plant (THHP). The model was evaluated by using correlation coefficient (r), relative error (RE), root mean square error (RMSE), and Taylor diagram plots in comparison with the popular single algorithm approaches such as ANN, and NARX models. Results demonstrated the superiority of the proposed PSO-ANN approach over the other two models.

Amidst the escalating demands for efficient Intelligent Transportation Systems (ITS) management, the significance of accurate Origin-Destination (OD) data prediction has emerged as a paramount concern, given its indispensable role in the ITS domain. This paper introduces a groundbreaking integrated model, creatively fusing the unique strengths of Graph Convolutional Network (GCN), Residual Neural Network (ResNet), and Long Short-Term Memory Network (LSTM) into a single architecture, which we name GraphResLSTM, to exploit road segment average speed data for OD prediction. Compared with conventional road segment traffic volume data, average speed data is more readily available, significantly reducing the data accessibility barrier for OD prediction. We underscore the critical role of selection of key road segments and employs a combination of Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to identify 41 representative road segments from the experimental road network. In the experimental phase, we simulate 86400000 seconds of traffic conditions, generating a total of 1440000 data records. Utilizing these simulated data, we design and conduct comparative experiments between models as well as data types. The results demonstrate that both the GraphResLSTM model and road segment average speed data outperform other models and data types notably in OD prediction tasks.

Early disease detection is crucial for maximizingcrop yields and minimizing financial losses in agriculture. Inorder to categorise leaf diseases in pepper, tomato, and potato plants, this study suggests a revolutionary CNN design. The algorithm collects disease-specific features from input photos by using data augmentation techniques to artificially enlarge the training dataset. ReLU-activated convolutional layers gradually capture features at different levels, from low to high, while max pooling layers minimise spatial dimensionality. After thecharacteristics are extracted, a fully-connected layers with a softmax activation function classify them into illness groups. A well chosen dataset containing labelled healthy and sick leaves is used to train and validate the model. Generalizability to untesteddata is ensured via performance evaluation on an independent testing set. The field of deep learning for agricultural applications benefits from this research. This strategy has the ability to rev- olutionise agricultural practices by enabling automated disease identification. This might result in early interventions, better crop health, and eventually sustainable agricultural production.

Deep learning has increasingly been employed to identify minerals. However, deep learning can only be used to identify minerals in the distribution of the training set, while any mineral outside the spectrum of the training set is inevitably categorized erroneously within a predetermined class from the training set. To solve this problem, the study introduces the approach that amalgamates One-Class Support Vector Machines (OCSVM) with the ResNet architecture for the out-of-distribution mineral detection. Initially, ResNet undergoes training using a training set comprising well-defined minerals. Subsequently, the earlier layers of the trained ResNet are employed to extract the discriminative features of the mineral under consideration. These extracted mineral features then become the input for OCSVM. When OCSVM discerns the mineral in the training set's distribution, it triggers the subsequent layers within the trained ResNet, facilitating the accurate classification of the mineral into one of the predefined categories encompassing the known minerals. In the event OCSVM identifies the mineral out of the training set's distribution, it is unequivocally categorized as an unclassified or 'unknown' mineral. Empirical results substantiate the method's capability to identify out-of-distribution minerals while concurrently maintaining a commendably high accuracy rate for the classification of the 36 in-distribution minerals.

Unmanned Underwater Vehicles (UUVs) are pivotal in ocean exploration, research, and various industrial activities such as marine mining and offshore engineering. However, traditional methods of navigating these vehicles face significant challenges, mainly due to the inefficacy of electromagnetic waves in water, leading to signal loss. To address these limitations, researchers are increasingly turned learning, an artificial intelligence technique capable of learning from data-enhancing underwater navigation, mainly through visual Simultaneous Localization and Mapping (SLAM). This paper explores integrating deep learning methodologies and sensor technologies to revolutionize underwater navigation for UUVs. Proprioceptive sensors, along with exteroceptive sensors, are crucial in accurately measuring and comprehending the underwater environment. Additionally, the paper provides detailed insights into the processes of underwater SLAM, camera-based underwater positioning systems, sonar systems for underwater navigation, and the utilization of Lidar in underwater navigation. Furthermore, it delves into applying deep learning techniques in underwater SLAM, offering a comprehensive understanding of the innovative processes driving advancements in underwater vehicle navigation. By leveraging these advancements, this research aims to improve underwater navigation systems' precision, reliability, and adaptability, thereby unlocking new frontiers in ocean exploration and industrial applications for UUVs.

All types of sports are potential application scenarios for automatic and real-time visual object and event detection. In rink hockey, the popular roller quad skate variant of hockey team sports, it is of great interest to automatically track player’s movements and positions, player’s sticks and, also, making other judgments, such as being able to locate the ball. In this work, we introduce a real-time pipeline composed by an object detection model, created specifically for rink hockey games, followed by a knowledge-based event detection module. Even in the presence of occlusions and quick motions, our deep learning object detection model effectively identifies and tracks, in real-time, important visual elements such as: ball; players; sticks; referees; crowd; goalkeeper; and goal. Using a curated dataset composed by a collection of videos of rink hockey, comprising 2525 annotated frames, we trained and evaluated the algorithm performance and compare it to state of the art object detection techniques. Our object detection model, based on YOLOv7, presents a global accuracy of 80%, and presents a good performance in terms of accuracy and speed, according to our results, making it a good choice for rink hockey applications. In our initial tests, the event detection module successfully detected one important event type in rink hockey games, the occurrence of penalties.

The accurate state of health (SOH) estimation of lithium-ion batteries (LIBs) during operation is crucial to ensure optimal performance, prolonging battery life and preventing unexpected failure or safety hazards. This work presents a storage and performance optimised deep learning approach to predict the capacity based SOH of LIBs using raw sensor data from partial charging curves under constant current condition. The proposed model is based on a combination of a 1-dimensional convolutional and long-short term memory neural network and processes time, voltage and incremental capacity of partial charging curves as time series. The model is cross-validated on different aging scenarios reaching an overall MAE = 0.418% and RMSE = 0.531%, promising an accurate SOH estimation of LIBs under varying usage and environmental conditions in a real world application.

The importance of detecting and diagnosing the imminence of aneurysm rupture before it occurs cannot be overstated. However, this process is often time-consuming and challenging, with variability in conclusions not uncommon among experts. Furthermore, current state-of-the-art models in medical image segmentation suffer from limited availability of large annotated datasets for training, exacerbated by an immense data imbalance. In most segmentation tasks, 3D segmentation is preferred due to its capacity to leverage more contextual information. However, these models require more data, which is constrained by the aforementioned issues. In the realm of current diagnosis models, those lacking geographic context are notably ineffective. To address these issues, the aim is to develop a model pipeline to accurately detect cerebral intracranial aneurysms and diagnose rupture imminence through 3D magnetic resonance angiography (MRA) and tabular input, augmented with the implementation of neuro-symbolic ai. The utilization of data fusion to tackle the lack of context in tabular models is proposed, leveraging extracted geographical features from a segmentation model. To enhance segmentation results and tackle the data imbalance in aneurysm segmentation, a two-stage model pipeline that extracts contextual geographic features before aneurysm segmentation is suggested. Segmentation results are additionally improved through ensemble techniques and novel preprocessing techniques. Finally, a neuro-symbolic aspect is introduced to enhance model diagnosis, interpretability and performance. The multi-step Integrated Neuro-Symbolic Analysis Pipeline for Cerebral Aneurysm Rupture Diagnosis is introduced.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

The new energy structure needs to balance energy security and dual carbon goals, which has brought major challenges to coal-fired power plants, the pollution reduction and carbon emissions reduction of coal-fired power plants will be a key task in the future. This article proposes an optimization operation of electrostatic precipitators(ESP), based on the working mechanism and historical data of ESP, voltage-current characteristic model and outlet dust concentration prediction model are constructed by deep learning algorithm, Particle Swarm Optimization(PSO) is used to achieve the optimal energy consumption while ensuring stable outlet dust concentration. By training with historical data collected on site, accurate prediction of secondary current and outlet dust concentration of ESP has been achieved, the Mean Absolute Percentage Error(MAPE) of secondary current is less than 1.5%, and the MAPE of outlet dust concentration of ESP on the test set is less than 5.2%. Finally, the optimization experiment is carried out in a 330MW coal-fired power plants, the results showed that the fluctuation of the outlet dust concentration is more stable, and the energy saving is about 43% after optimization, according to the annual operation of 300 days, the annual average carbon reduction is approximately 2621.34 tons. This method is effective and can be applied widely.

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.

Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, a great deal of mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks as well as their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain in-depth the building blocks to design deep learning models, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library.

Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and efficiency, primarily due to the high inspection demand from manufacturing industries with high production throughput. To solve this challenge, numerous computer-based alternatives have been developed, including Auto-mated Defect Recognition (ADR) using deep learning algorithms. At the core of training, these algorithms demand large volumes of data that should be representative of real-world cases. However, the availability of digital X-ray radiography data for open research is limited by non-disclosure contractual terms in the industry. This study presents a pipeline that is capable of modeling synthetic images based on statistical information acquired from X-ray intensity distribution from real digital X-ray radiography images. Through meticulous analysis of the intensity distribution in digital X-ray images, the unique statistical patterns associated with the exposure conditions used during image acquisition, type of component, thickness variations, beam divergence, anode heel effect, etc., are extracted. The realized synthetic images were utilized to train deep learning models, yielding an impressive model performance with mean intersection over union (IoU) of 0.93, and mean dice coefficient of 0.96, on real unseen digital X-ray radiography images. This methodology is scalable and adaptable, making it suitable for diverse industrial applications.

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN works best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features.

The escalation of climate change and the increasing frequency of extreme weather events have amplified the importance of precise and timely lightning prediction. This predictive capability is pivotal for the preservation of life, protection of property, and maintenance of crucial infrastructure safety. Recently, the rapid advancement and successful application of data-driven deep learning across diverse sectors, particularly in computer vision and spatio-temporal data analysis, have opened up innovative avenues for enhancing both the accuracy and efficiency of lightning prediction. This article presents a comprehensive review of the broad spectrum of existing lightning prediction methodologies. Starting from traditional numerical forecasting techniques, we traverse the path to the most recent breakthroughs in deep learning research. We encapsulate these diverse methods, shedding light on their progression and summarizing their capabilities, while also predicting their future development trajectories. This exploration is designed to enhance our understanding of these methodologies, allowing us to better utilize their strengths, navigate their limitations, and potentially integrate these techniques to create novel and powerful lightning prediction tools. Through such endeavors, our aim is to bolster our preparedness against the growing unpredictability of our climate and ensure a proactive stance towards lightning prediction.

AK is a common precancerous skin condition that requires effective detection and treatment monitoring. To improve the monitoring of AK burden in clinical settings with enhanced automation and precision, the present study evaluates the application of semantic segmentation based on the U-Net architecture (AKU-Net). AKU-Net employs transfer learning to compensate for the relatively small dataset of annotated images and integrates a recurrent process based on convLSTM to exploit contextual information and address the challenges related to low contrast and ambiguous boundaries of AK-affected skin regions. We used an annotated dataset of 569 clinical photographs from 115 patients with actinic keratosis to train and evaluate the model. From each photograph, patches of 512x512 pixels were extracted using translation lesion boxes that encompass lesions in different positions and capture different contexts of perilesional skin. In total, 16488 translation augmented crops were used for training the model, and 403 lesion center crops were used for testing. To demonstrate the improvements in AK detection, AKU-net was compared with plain U-Net and U-Net++ architectures. The experimental results highlighted the effectiveness of AKU-Net, improving both automation and precision over existing approaches, paving the way for more effective and reliable evaluation of actinic keratosis in clinical settings.