Search

The use of Artificial Intelligence (AI) to preserve and promote cultural heritage has experienced significant growth in recent years. Among the various areas of cultural heritage, numismatics have emerged as a particularly promising field where we can develop AI solutions. Numismatics refers to the study of coins, tokens, paper money, and medals, which play a critical role in understanding human history and culture. However, there are still limited resources available to help researchers and collectors in the identification of coins. This is due to the vast number of coins in circulation, which presents a significant challenge in developing smart tools for classification tasks. This paper aims to provide a contribution to this setting. In particular, we start by creating a new dataset called EURO-Coin, which consists of images showing the side of coins with reliefs and is designed to facilitate the training and testing of AI models for euro coin classification. Then, we propose two approaches that leverage Convolutional Neural Networks and self-attention layers to classify the country and value of the coins. In our experiments, we obtain an accuracy of 86.9% for country classification and an accuracy of 96.4% for value classification. Finally, we conduct an ablation study to evaluate the impact of the preprocessing activities and attention layers in our approaches. [ABSTRACT FROM AUTHOR]

This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The image forming method called the rising paper chromatography is utilized in preparing the images of Memecik varieties of green olives for CNN. In the rising chromatography method, 20, 30, and 40% sample concentrations were determined as the suitable concentrations for both organic and conventional olives. The concentrations of AgNO3 and FeSO4 were determined as 0.25, 0.5, 0.75 and 1% for both conventional and organic samples. The visual differences used for differentiation of different types of Memecik green olives are usually determined according to the regional color differences, the vivid color occurrence, the width and the frequency of bowl occurrence, the thin line, and the picks at drop zone by the expert assessors. The testing results in this study verified the effectiveness of the CNN methodology in differentiating between the organically and conventionally cultivated Memecik green olives. The newly designed neural network achieved 100% accuracy. Furthermore, this high accuracy achieved by CNN might suggest that it can be effectively used in place of the expert assessors. [ABSTRACT FROM AUTHOR]

Brain–computer interfacing (BCI) research, fueled by deep learning, integrates insights from diverse domains. A notable focus is on steady-state visual evoked potential (SSVEP) in BCI applications, requiring in-depth assessment through deep learning. EEG research frequently employs SSVEPs, which are regarded as normal brain responses to visual stimuli, particularly in investigations of visual perception and attention. This paper tries to give an in-depth analysis of the implications of deep learning for SSVEP-adapted BCI. A systematic search across four stable databases (Web of Science, PubMed, ScienceDirect, and IEEE) was developed to assemble a vast reservoir of relevant theoretical and scientific knowledge. A comprehensive search yielded 177 papers that appeared between 2010 and 2023. Thence a strict screening method from predetermined inclusion criteria finally generated 39 records. These selected works were the basis of the study, presenting alternate views, obstacles, limitations and interesting ideas. By providing a systematic presentation of the material, it has made a key scholarly contribution. It focuses on the technical aspects of SSVEP-based BCI, EEG technologies and complex applications of deep learning technology in these areas. The study delivers more penetrating reporting on the latest deep learning pattern recognition techniques than its predecessors, together with progress in data acquisition and recording means suitable for SSVEP-based BCI devices. Especially in the realms of deep learning technology orchestration, pattern recognition techniques, and EEG data collection, it has effectively closed four important research gaps. To increase the accessibility of this critical material, the results of the study take the form of easy-to-read tables just generated. Applying deep learning techniques in SSVEP-based BCI applications, as the research shows, also has its downsides. The study concludes that a radical framework will be presented which, includes intelligent decision-making tools for evaluation and benchmarking. Rather than just finding a comparable or similar analogy, this framework is intended to help guide future research and pragmatic applications, and to determine which SSVEP-based BCI applications have succeeded at responsibility for what they set out with. [ABSTRACT FROM AUTHOR]

Blockchain technology has unlocked the doors of building decentralized applications, where security plays a vital role. Any transaction ever created in a blockchain is recorded permanently. With the increasing usage of social media modalities today, many non-reputable sources create and publish fake and luring news. Due to the easy availability of the internet and excessive use of social media, fake news can spread like a flash. It causes the need to eliminate fake news posted on social media platforms. The main motive of the paper is to develop an ensemble model that assists in the automated identification of fake news. This paper addresses the identified gaps in detecting multi-modal fake news. We propose Fake News Network (FNNet) as a novel secure blockchain-based deep learning model to detect fake news. It uses blockchain and deep learning to assure data integrity and learn data representations, respectively. The proposed model consists of four layers: the node layer, the deep learning layer, the blockchain layer, and the network layer. This is an ensemble deep-learning model that leverages Bi-LSTM and CNN models, where the Bi-LSTM model captures the sequential data in both directions, and CNN captures the hidden features. We use Pheme, CrisisLexT6, and ISOT datasets to train the model. FNNet achieves an average accuracy of 86.93%, 92.22%, and 98.53% on Pheme, CrisisLexT9, and ISOT datasets, respectively. Our results show that the proposed model is robust and applicable to real-time datasets and social media networks to detect fake news effectively. [ABSTRACT FROM AUTHOR]

Forest fire is a severe natural disaster, which leads to the destruction of forest ecology. At present, fire detection technology represented by convolutional neural network is widely used in forest resource protection, which can realize rapid analysis. However, in forest flame and smoke detection tasks, due to continuous expansion of the target range, a better detection effect cannot be achieved. This paper proposes an improved YOLOX method for multi-scale forest fire detection. This method proposes a novel feature pyramid model to reduce the information loss of high-level forest fire feature maps and enhance the representation ability of feature pyramids. Moreover, the method applies a small object data augmentation strategy to enrich the forest fire dataset, making it more suitable for the actual forest fire scene. According to the experimental results, the mAP of the model proposed in this paper reaches 79.64%, which is about 4.89% higher than the baseline network YOLOX. The method improves the accuracy of forest fire detection, reduces false alarms, and is suitable for real scenarios of forest fires. [ABSTRACT FROM AUTHOR]

The increasing availability of hydrological and physiographic spatiotemporal data has boosted machine learning's role in rapid flood mapping. Yet, data scarcity, especially high-resolution DEMs, challenges regions with limited access. This paper examines how DEM type and resolution affect flood prediction accuracy, utilizing a cutting-edge deep learning (DL) method called 1D convolutional neural network (CNN). It utilizes synthetic hydrographs as training input and water depth data obtained from LISFLOOD-FP, a 2D hydrodynamic model, as target data. This study investigates digital surface models (DSMs) and digital terrain models (DTMs) derived from a 1 m LIDAR-based DTM, with resolutions from 15 to 30 m. The methodology is applied and assessed in a established benchmark, city of Carlisle, UK. The models' performance is then evaluated and compared against an observed flood event using RMSE, Bias, and Fit indices. Leveraging the insights gained from this region, the paper discusses the applicability of the methodology to address the challenges encountered in a data-scarce flood-prone region, exemplified by Pakistan. Results indicated that utilizing a 30 m DTM outperformed a 30 m DSM in terms of flood depth prediction accuracy by about 21% during the flood peak stage, highlighting the superior performance of DTM at lower resolutions. Increasing the resolution of DTM to 15 m resulted in a minimum 50% increase in RMSE and a 20% increase in fit index across all flood stages. The findings emphasize that while a coarser resolution DEM may impact the accuracy of machine learning models, it remains a viable option for rapid flood prediction. However, even a slight improvement in data resolution in data-scarce regions would provide significant added value, ultimately enhancing flood risk management. [ABSTRACT FROM AUTHOR]

In order to explore the application of neural networks in the intelligent protection of digital music copyrights, this paper initially investigates the key aspects of digital music-related supply chain management (SCM). Subsequently, this paper introduces a fuzzy, comprehensive evaluation-based method for authenticating digital music infringement. Furthermore, it employs a convolutional neural network to analyze digital music's source components. Within this context, an attention mechanism and an adaptive gate model are meticulously designed. Moreover, a selective adaptive cascade is implemented to optimize the structure of the multi-resolution coder–decoder. Through fuzzy authentication, it becomes feasible to accurately and reliably track and verify copyright information pertaining to digital music, thus providing an effective protective mechanism for the digital music industry. Experimental results reveal that in comparison with the SHN-4 series models, the network model embedded with the channel space (CS) attention module achieves improvements of up to 0.04 dB in terms of performance metrics for human voice and accompaniment sources. Furthermore, it outperforms these models by up to 0.19 dB in music source separation metrics. The incorporation of the adaptive attention mechanism profoundly enhances the model's performance in audio source separation tasks, benefiting both vocal and accompaniment sources. This improvement is evident in the form of a 0.44 SDR enhancement for vocal sources and a 0.18 SDR enhancement for accompaniment sources. Additionally, the proposed two-stage music separation-gate self-attention model surpasses the two-stage music separation-gate model in metrics associated with human voice and accompaniment sources. This outcome convincingly underscores the enhanced effectiveness achieved by integrating CS, self-attention, and adaptive connection in network performance, as well as the adaptive gate structure for music copyright protection. This approach heightens the model's autonomous selectivity, minimizes outliers, stabilizes waveform characteristics, and significantly contributes to the safeguarding of digital content. [ABSTRACT FROM AUTHOR]

Advancements in Machine Learning (ML) and Computer Vision have led to notable improvements in the detection of breast cancer. However, the accuracy of the classifier is limited due to imbalanced datasets that cause overfitting. Thus, additional images are needed to improve the classifier's performance. Generative Adversarial Networks (GAN) are used for image augmentation. Still, its limitations, such as the random use of different types of GAN, can lead to a too-good discriminator, causing generator training to fail due to vanishing gradients. Therefore, selecting the appropriate GAN model for the given scenario is crucial for optimal performance. This paper proposes a novel Smart Generative Adversarial Network (Smart GAN) architecture to develop an efficient and computational classification model for a limited imbalanced dataset. Smart GAN uses a three-fold approach. Different types of GAN augment the dataset in the first phase of experimental work, and their evaluation metrics are calculated. In the second phase, the metric scores are used as rewards for the Reinforcement learning model (Q-learning approach). The best augmentation is chosen based on the best Q-values for each metric score. It compares three different Convolutional Neural Networks (CNN) and selects the best-suited network to classify the augmented datasets. The proposed Smart GAN architecture outperforms other existing approaches by giving a better accuracy of 89.62% and 89.91% on Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM) augmented datasets, respectively, representing an approximately 10% increment in detection rate compared to non-augmented datasets. [ABSTRACT FROM AUTHOR]

This paper presents ConvStabNet, a convolutional neural network designed to predict optimal stabilization parameters for each cell in the Streamline Upwind Petrov Galerkin (SUPG) stabilization scheme. ConvStabNet employs a shared parameter approach, allowing the network to understand the relationships between cell characteristics and their corresponding stabilization parameters while efficiently handling the parameter space. Comparative analyses with state-of-the-art neural network solvers based on variational formulations highlight the superior performance of ConvStabNet. To improve the accuracy of SUPG in solving partial differential equations (PDEs) with interior and boundary layers, ConvStabNet incorporates a loss function that combines a strong residual component with a cross-wind derivative term. The findings confirm ConvStabNet as a promising method for accurately predicting stabilization parameters in SUPG, thereby marking it as an advancement over neural network-based PDE solvers. [ABSTRACT FROM AUTHOR]

Scene recognition has been the foundation of research in computer vision fields. Because scene images typically are composed of specific regions distributed in some layout, so modeling layouts of various scenes is a key clue for scene recognition. Existing methods usually require an additional stream to detect regions for subsequent modeling, which accumulate errors and may miss important information. Meanwhile, they use manual features to model relations between regions, which weakens the representation ability of layouts. In this paper, we propose a single-stream adaptive scene layout modeling approach based on a layout modeling module (LMM), which constructs layouts without additional detection streams and adaptively captures the relations to take advantage of graph attention network. LMM is directly concatenated to a convolutional neural network, where each pixel of the activation maps of the last convolutional layer is defined as a region that is the initial input node of the LMM. LMM first models the layout of each region, and then uses all regions with layout information to model the entire scene. Layout relations are encoded as edges, which are automatically analyzed according to region co-occurrence and relative position. Our work can be understood as optimizing features of the activation maps from a scene layout modeling perspective for scene recognition. Experimental results on MIT67, SUN397, and Places365 show that our single-stream model achieves competitive performance. [ABSTRACT FROM AUTHOR]

By exploring the current block-based lossy video coding process and compressed videos, this paper finds two unique characteristics namely quality fluctuation and pixel deficiency. And we use 3D convolutional neural network (3D-CNN) to make full use of the limited temporal and spatial information in compressed video and build compressed video quality enhancement network (CVQENet) to improve the compressed video quality. The experimental results show that compared with the videos encoded by High Efficiency Video Coding (HEVC/H.265), the mean value of the Peak Signal-to-Noise Ratio (PSNR) of enhanced videos has been improved by 0.4652 dB under Low Delay (LD) configuration with Quantization Parameter (QP) is set to 37. [ABSTRACT FROM AUTHOR]

Underwater segmentation technology achieves effective monitoring of fish biological information through accurate identification of fish species and precise estimation of their quantities. It serves as an effective approach to enhance the informatization level of aquaculture and promote intelligent management in fisheries. However, the complex and diverse underwater environment, coupled with poor visibility, results in blurry and lower-quality underwater fish images. The current image segmentation methods, when applied to fish segmentation, exhibit low accuracy and inadequate generalization capabilities. This paper proposes an image segmentation model based on Atrous Spatial Pyramid Pooling (ASPP) to address these challenges. The model aims to improve fish feature extraction and enhance the segmentation precision of fish images in complex underwater environments, thereby enhancing the accuracy and generalization capabilities of existing fish segmentation models. First, a multiscale feature extraction module (triangular atrous spatial pyramid multifeature fusion) based on dilated convolutional spatial pyramid pooling, which enhances the extraction of high-level semantic features of images through the triangular combination of multilayer dilated convolutional pyramid pooling and the adaptive channel attention module, is proposed. Second, a spatial attention module based on strip pooling (atrous strip pooling) is proposed, which further expands the receptive field of the attention mechanism by combining different expansion rates, enhances the correlations between pixels, and effectively captures spatial information. Finally, a decoder module based on multilayer semantic feature fusion is proposed. Through the processing and fusion of medium-, low-, and high-level semantic features, the model understands image content and performs accurate pixel-level segmentation. The proposed model is evaluated using a VOC-compliant dataset created from underwater fish images and validated against public and specific underwater fish datasets. The results demonstrate the successful application of the feature extraction and feature fusion modules in underwater fish image segmentation, achieving an average Intersection over Union (MIoU) of 85.49% in segmentation tasks. Compared to conventional segmentation models, the proposed model shows significant improvements, with an average increase of 3.8% in MIoU and 2.5% in balanced F-score (F1-score). The accurate segmentation of underwater fish images and extraction of vital biological information by this model provide a solid foundation for intelligent monitoring, including fish length measurement, weight estimation, and analysis of growth and health status. Moreover, the model offers a scientific framework for decision-making in aquaculture, driving advancements in precision and intelligent management practices in the field. [ABSTRACT FROM AUTHOR]

To equip convolutional neural networks (CNNs) with explainability, it is essential to interpret how opaque models make specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in the classifiers. This paper introduces ADVISE, a new explainability method that quantifies and leverages the relevance of each unit of the feature map to provide better visual explanations. To this end, we propose using adaptive bandwidth kernel density estimation to assign a relevance score to each unit of the feature map with respect to the predicted class. We also propose an evaluation protocol to quantitatively assess the visual explainability of CNN models. Our extensive evaluation of ADVISE in image classification tasks using pretrained AlexNet, VGG16, ResNet50, and Xception models on ImageNet shows that our method outperforms other visual explainable methods in quantifying feature-relevance and visual explainability while maintaining competitive time complexity. Our experiments further show that ADVISE fulfils the sensitivity and implementation independence axioms while passing the sanity checks. The implementation is accessible for reproducibility purposes on https://github.com/dehshibi/ADVISE. [ABSTRACT FROM AUTHOR]

Recently, learned image compression (LIC) has shown significant research potential. Most existing LIC methods are CNN-based or transformer-based or mixed. However, these LIC methods suffer from a certain degree of degradation in global attention performance, as CNN has limited-sized convolution kernels while window partitioning is applied to reduce computational complexity in transformer. This gives rise to the following two issues: (1) The main autoencoder (AE) and hyper AE exhibit limited transformation capabilities due to insufficient global modeling, making it challenging to improve the accuracy of coarse-grained entropy model. (2) The fine-grained entropy model struggles to adaptively utilize a larger range of contexts, because of weaker global modeling capability. In this paper, we propose the LIC with joint enhanced swin transformer (SwinT) and CNN to improve the entropy modeling accuracy. The key in the proposed method is that we enhance the global modeling ability of SwinT by introducing neighborhood window attention while maintaining an acceptable computational complexity and combines the local modeling ability of CNN to form the enhanced SwinT and CNN block (ESTCB). Specifically, we reconstruct the main AE and hyper AE of LIC based on ESTCB, enhancing their global transformation capabilities and resulting in a more accurate coarse-grained entropy model. Besides, we combine ESTCB with the checkerboard mask and the channel autoregressive model to develop a spatial then channel fine-grained entropy model, expanding the scope of LIC adaptive reference contexts. Comprehensive experiments demonstrate that our proposed method achieves state-of-the-art rate-distortion performance compared to existing LIC models. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural network (CNN) and transformer based on hyperspectral image super-resolution methods have achieved superior performance. Nevertheless, this is still an important problem how to effectively extract local and global features and improve spectral representation of hyperspectral image. In this paper, we propose a hybrid CNN and transformer network (HCT) for hyperspectral image super-resolution, which consists of a transformer module with local–global spatial attention mechanism (LSMSAformer) and a convolution module with 3D convolution (3DDWTC) to process high and low frequency information, respectively. Specifically, in the transformer branch, the introduced attention mechanism module (LSMSA) is used to extract local–global spatial features at different scales. In the convolution branch, 3DDWTC is proposed to learn local spatial information and preserve the spectral features, which can enhance the representation of the network. Extensive experimental results show that the proposed method can obtain better results than some state-of-the-art hyperspectral image super-resolution methods. [ABSTRACT FROM AUTHOR]

Chemical molecular structures are a direct and convenient means of expressing chemical knowledge, playing a vital role in academic communication. In chemistry, hand drawing is a common task for students and researchers. If we can convert hand-drawn chemical molecular structures into machine-readable formats, like SMILES encoding, computers can efficiently process and analyze these structures, significantly enhancing the efficiency of chemical research. Furthermore, with the progress of educational technology, automated grading is gaining popularity. When machines automatically recognize chemical molecular structures and assess the correctness of the drawings, it offers great convenience to teachers. We created ChemReco, a tool designed to identify chemical molecular structures involving three atoms: C, H, and O, providing convenience for chemical researchers. Currently, there are limited studies on hand-drawn chemical molecular structures. Therefore, the primary focus of this paper is constructing datasets. We propose a synthetic image method to rapidly generate images resembling hand-drawn chemical molecular structures, enhancing dataset acquisition efficiency. Regarding model selection, the hand-drawn chemical molecule structural recognition model developed in this article achieves a final recognition accuracy of 96.90%. This model employs the encoder-decoder architecture of EfficientNet + Transformer, demonstrating superior performance compared to other encoder-decoder combinations. [ABSTRACT FROM AUTHOR]

It is important to establish a real-time and accurate tool wear monitoring system for improving machining quality, tool utilization, and reducing cost. In this paper, an end-to-end tool wear condition monitoring algorithm is proposed by combining 1D convolutional neural network (1DCNN) with residual block and Transformer. Firstly, the original sensor signal is processed directly by one-dimensional convolution, the local features of the signal are extracted and the dimensionality of the signal is reduced. Then, Transformer is applied to model the sequence and capture the global feature relationship. After threefold cross-validation, the average index of the presented method: accuracy, F1 score, precision, and recall rate on the PHM2010 milling dataset were 97.41%, 97.4%, 97.43%, and 97.4%, respectively. It can be seen that the proposed algorithm can complete the task of tool wear classification and also showed a strong generalization ability on each validation set. [ABSTRACT FROM AUTHOR]

During their life cycle, buildings are subjected to damage that reduces their performance and can pose a significant threat to structural safety. This paper presents the results of research into the creation of a model for predicting damage intensity of buildings located in mining terrains. The basis for the research was a database of technical and mining impact data for 185 masonry residential buildings. The intensity of damage to buildings was negligible and ranged from 0 to 6%. The Convolutional Neural Network (CNN) methodology was used to create the model. The Support Vector Machine (SVM) methodology, which is commonly used for analysis of this type of issue, was used for comparisons. The resulting models were evaluated by comparing parameters such as accuracy, precision, recall, and F1 score. The comparisons revealed only minor differences between the models. Despite the small range of damage intensity, the models created were able to achieve prediction results of around 80%. The SVM model had better results for training set accuracy, while the CNN model achieved higher values for F1 score and average precision for the test set. The results obtained justify the adoption of the CNN methodology as effective in the context of predicting the damage intensity of masonry residential buildings located in mining terrains. [ABSTRACT FROM AUTHOR]

This paper discussed an efficient technique to detect near-duplicate images with higher accuracy. The proposed method improved the existing accuracy of near-duplicate image detection and classification using Haar wavelet feature extraction and classification algorithm. Due to advancements in digital image acquisition and image editing software, near-duplicate image counterfeiting has become predictable. This expanding problem needs the creation of sophisticated detection algorithms capable of effectively preventing the spread of near-duplicate image deception. Support vector machine (SVM) and K-near neighbor (KNN) classifiers are used in the classification stage of a modified deep learning model with a convolutional neural network (CNN). The classification model finds the better result on the Imperial College London dataset, with 99.12% using CNN with KNN classifier and 98.63% for CNN with SVM classifier. The classification model also gives better results on the Nanyang Technological University dataset, with 98.36% using CNN with the KNN classifier and 97.85% for CNN with the SVM classifier. The model is tested using publicly available images to find the results. According to the comparison results, this model performed significantly better result than the previous model. As a result, digital image forensics has become more critical, particularly in identifying image duplication. [ABSTRACT FROM AUTHOR]

With the development of cloud computing, more and more resource constrained data owners tend to store their images in the cloud and rely on image retrieval services to get back images they want. However, this process raises huge privacy leakage risks. Privacy-preserving image retrieval (PPIR) can prevent privacy leakage during the retrieval process. Using convolutional neural networks for image feature extraction can significantly improve retrieval accuracy and has become a common trend in PPIR, but it also brings a new problem of network model parameter leakage, which is often ignored by most PPIR schemes. Besides, existing PPIR schemes often adopt centralized image retrieval service, which typically require frequent interactions between the cloud server and users during the retrieval process, resulting in excessive computational overhead for resource-limited users. Aiming to solve these problems, a distributed privacy-preserving image retrieval scheme is proposed in this paper. Three collaborative cloud servers utilize three neural network models split and outsourced by the data owner to extract features of the query image and perform subsequent retrieval tasks. A new secure Euclidean distance calculation protocol is designed for cloud servers to measure feature similarity, and secure sort pair protocol, secure sorting protocol, secure search protocol are utilized to achieve secure image retrieval. Additionally, a hierarchical index tree is employed to narrow down the search scope and improve search efficiency. This approach avoids the problem of network model parameter leakage caused by using neural networks to extract image features at the users' side, reduces the computational burden on users, and improves the accuracy and the efficiency of the retrieval process while ensuring retrieval security. Security analysis and experimental results demonstrate the security and retrieval performance of the proposed scheme. [ABSTRACT FROM AUTHOR]

In recent years, vector-to-vector mapping-based raw waveform biosignal enhancement methods have gained significant attention in remote health monitoring system. In this paper, a novel end-to-end convolutional encoder–decoder (CED) model with stacked gated recurrent unit (SGRU) is proposed to learn sequential information of biosignal for signal enhancement. The proposed model CED-SGRU employs convolutional neural network to capture the spatial features and SGRU to capture temporal distributions of the biosignal layer by layer which increases the robustness of the proposed model. This work applies mean absolute error as a loss function for CED-SGRU-based vector-to-vector model. The proposed method has been evaluated on three foremost required biosignals, namely electrocardiogram, photoplethysmography and heart rate signals for diagnosing cardiovascular diseases. Experimental result shows outstanding denoising capability of the proposed CED-SGRU model on three biosignals which yields significantly higher reconstruction signal-to-noise ratio value and lower average absolute error, root mean square error and percent root mean square difference values when compared with state-of-the-art-methods. Moreover, the simple architecture of SGRU lowers the complexity of the model; thereby, reducing the inference time for denoising and restoring compressed biosignal tasks is fairly compared with baseline models, namely recurrent neural network model and long short-term memory model. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD), the predominant form of dementia, is a growing global challenge, emphasizing the urgent need for accurate and early diagnosis. Current clinical diagnoses rely on radiologist expert interpretation, which is prone to human error. Deep learning has thus far shown promise for early AD diagnosis. However, existing methods often overlook focal structural atrophy critical for enhanced understanding of the cerebral cortex neurodegeneration. This paper proposes a deep learning framework that includes a novel structure-focused neurodegeneration CNN architecture named SNeurodCNN and an image brightness enhancement preprocessor using gamma correction. The SNeurodCNN architecture takes as input the focal structural atrophy features resulting from segmentation of brain structures captured through magnetic resonance imaging (MRI). As a result, the architecture considers only necessary CNN components, which comprises of two downsampling convolutional blocks and two fully connected layers, for achieving the desired classification task, and utilises regularisation techniques to regularise learnable parameters. Leveraging mid-sagittal and para-sagittal brain image viewpoints from the Alzheimer's disease neuroimaging initiative (ADNI) dataset, our framework demonstrated exceptional performance. The para-sagittal viewpoint achieved 97.8% accuracy, 97.0% specificity, and 98.5% sensitivity, while the mid-sagittal viewpoint offered deeper insights with 98.1% accuracy, 97.2% specificity, and 99.0% sensitivity. Model analysis revealed the ability of SNeurodCNN to capture the structural dynamics of mild cognitive impairment (MCI) and AD in the frontal lobe, occipital lobe, cerebellum, temporal, and parietal lobe, suggesting its potential as a brain structural change digi-biomarker for early AD diagnosis. This work can be reproduced using code we made available on GitHub. [ABSTRACT FROM AUTHOR]

The brain-computer interface (BCI) is a direct pathway of communication between the electrical activity of the brain and an external device. The present paper was aimed to investigate directed connectivity between different areas of the brain during motor imagery (MI)-based BCI. For this purpose, two methods were implemented including, Limited Penetrable Horizontal Visibility Graph (LPHVG) and Direct Lingam. The visibility graph (VG) is a robust algorithm for analyzing complex systems such as the brain. Direct Lingam uses a non-Gaussian model to extract causal links which is appropriate for analyzing large-scale connectivity. First, LPHVG map MI-EEG (electroencephalogram) signals into networks. After extracting the topological features of the networks, a support vector machine classifier was applied to categorize multi-classes MI. The network of all classes was found to be different from one another, and the kappa value of classification was 0.68. The degree sequence of LPHVG was calculated for each channel in order to obtain the direction of brain information flow. Transfer entropy (TE) is used to compute the relations of the channel degree sequence. Therefore, the directed graph between channels was formed. This method is called LPHVG_TE directed graph. The Bayesian network, also known as the Direct LiNGAM model, was implemented for the second method. Finally, images of the LPHVG and Direct Lingam were classified by convolutional neural network (CNN). In this study, Data sets 2a of BCI competition IV was used. The outcomes reveal that the brain network developed by LPHVG (92.7%) might be more effective to distinguish 4 classes of MI than the Direct Lingam (90.6%) and it was shown that graph theory has the potential to get better efficiency of BCI. [ABSTRACT FROM AUTHOR]

Thunderstorm gusts are a common form of severe convective weather in the warm season in North China, and it is of great importance to correctly forecast them. At present, the forecasting of thunderstorm gusts is mainly based on traditional subjective methods, which fails to achieve high-resolution and high-frequency gridded forecasts based on multiple observation sources. In this paper, we propose a deep learning method called Thunderstorm Gusts TransU-net (TG-TransUnet) to forecast thunderstorm gusts in North China based on multi-source gridded product data from the Institute of Urban Meteorology (IUM) with a lead time of 1 to 6 h. To determine the specific range of thunderstorm gusts, we combine three meteorological variables: radar reflectivity factor, lightning location, and 1-h maximum instantaneous wind speed from automatic weather stations (AWSs), and obtain a reasonable ground truth of thunderstorm gusts. Then, we transform the forecasting problem into an image-to-image problem in deep learning under the TG-TransUnet architecture, which is based on convolutional neural networks and a transformer. The analysis and forecast data of the enriched multi-source gridded comprehensive forecasting system for the period 2021–23 are then used as training, validation, and testing datasets. Finally, the performance of TG-TransUnet is compared with other methods. The results show that TG-TransUnet has the best prediction results at 1–6 h. The IUM is currently using this model to support the forecasting of thunderstorm gusts in North China. [ABSTRACT FROM AUTHOR]

Microscopic image analysis technology helps solve the inadvertences of artificial traditional methods in disease, wastewater treatment, and environmental change monitoring analysis. Convolutional neural network (CNN) play an important role in microscopic image analysis. Image segmentation, in which U-Net is increasingly applied in microscopic image segmentation, is a crucial step in detection, tracking, monitoring, feature extraction, modelling, and analysis. This paper comprehensively reviews the development history of U-Net, analyses several research results of various segmentation methods since the emergence of U-Net, and conducts a comprehensive review of related papers. This paper summarised the improved methods of U-Net and then listed the existing significance of image segmentation techniques and their improvements introduced over the years. Finally, focusing on the different improvement strategies of U-Net in different papers, the related work of each application target is reviewed according to detailed technical categories to facilitate future research. Researchers can see the dynamics of the transmission of technological development and keep up with future trends in this interdisciplinary field. [ABSTRACT FROM AUTHOR]

Deep neural networks are extensively used in text mining and Natural Language Processing is to enable computers to understand, analyze, and generate natural language data, such as text or speech, but semantic resources, such as taxonomies and ontologies, are not fully included in deep learning. In this paper, we use Deep Convolutional Neural Network (Deep CNN) to classify research papers using the Computer Science Ontology, an ontology of research areas in the field of computer science. It takes as input the abstract and keywords of a particular research paper and returns the relevant research topic. To evaluate our ontology, we used a gold standard dataset that includes research articles. To further improve text classification results, we propose to design a Deep CNN model. We then used ontology matching to reduce the classes and get better results. Experimental results show that the proposed approach outperforms the one with the highest precision, recall, and F1-score. [ABSTRACT FROM AUTHOR]

At present, in end-to-end network combined with deep learning in stereo matching, how to perceive ample image details within an acceptable range of computational cost, so as to improve the final matching accuracy, has become a hot research topic. In this paper, we design a cascaded disparity correction network based on DispNet, which can refine the initial disparity image by combining the process output results in the trunk network. The method proposed in this paper is named ETE–DC–CNN (end to end–disparity correction–convolutional neural network). In the trunk network, the mixed dilated convolution module is employed to extract the features of the original image, and the feature image is constructed into a 3D disparity space volume through depth-separable convolution, after which the initial disparity image can be obtained through 2D encoder–decoder module. In the correction network, the gradient information of the initial feature image is combined to reconstruct the modified matching cost body guided by the initial disparity image and then a smaller encoder–decoder module is trained and processed to make the final result at the sub-pixel level. The algorithm in this paper has been verified in SceneFlow and KITTI 2012/2015 data sets. The method proposed in this article achieves 3.46, 2.12, 1.19, and 0.6 results in the non-occluded area and 4.04, 2.55, 1.58, and 0.7 results in the global area on the Er (> 2 px), Er (> 3 px), Er (> 5 px), and Epe indicators in the KITTI 2012 test set, which are higher than those of the backbone network DispNet. [ABSTRACT FROM AUTHOR]

Phishing evolves rapidly nowadays, causing much damage to finance, brand reputation, and privacy. Various phishing detection methods have been proposed along with the rise of phishing, but there are still research issues. Phishing websites mainly steal users’ information through visual deception and deep learning methods have been proved very effective in computer vision applications but there is a lack in the research on visual analysis using deep learning algorithms. Moreover, most research use balanced datasets, which is not the case in a real Web environment. Therefore, this paper proposes a security indicator area (SIA) which contains most security indicators that are designed to help users identify phishing sites. The proposed method then takes screenshots of SIA and uses a convolutional neural network (CNN) as a classifier. To prove the efficiency of the proposed method, this paper carries out several comparative experiments on an unbalanced dataset with much fewer phishing sites, which increases detection difficulty but also makes the detection closer to reality. The results show that the proposed method achieves the highest F1-score among the compared methods, while providing advantages on detection efficiency and data expansibility in phishing detection. [ABSTRACT FROM AUTHOR]

The demand of sports video recognition simulation is increasing, but the traditional methods have some limitations in dealing with optical problems. Therefore, the purpose of this paper is to improve the effect of image optical processing by using convolutional neural networks. This paper first analyzes the structure of convolutional neural networks commonly used in computer vision applications, and discusses the improved method of convolutional neural networks to better understand and represent human motion in motion videos. Based on the process analysis of sports video recognition results, the concrete steps of image optical processing are completed. The advantages of convolutional neural network in image optical processing are demonstrated by simulation experiments on some sports videos and comparison with traditional methods. The experimental results show that the image optical processing based on convolutional neural network has a high recognition rate and can be used as an effective auxiliary means for sports training. By accurately analyzing and understanding human movements in sports videos, coaches and trainers can provide more effective training programs tailored to the needs of individual athletes. This can lead to improved performance results and better overall results. [ABSTRACT FROM AUTHOR]

Based on optical image enhancement, this paper uses convolutional neural network to detect key points of swimming posture. In swimming posture analysis, key point detection can provide information about posture accuracy and evaluation. However, due to the change of illumination conditions, the reduction of image quality and occlusion, the accuracy and stability of key point detection are limited. In order to solve this problem, an optical image enhancement method based on convolutional neural network is proposed in this paper. First, a specific convolutional neural network architecture is used to extract features from input images. Then optical image enhancement technology is used to preprocess the input image to improve the image quality. Next, the trained convolutional neural network model is used to detect key points. Experimental results show that the proposed method has good performance under different illumination conditions and image quality. Therefore, this study provides a new idea and method for the application of optical image enhancement in the detection of key points in swimming posture analysis. [ABSTRACT FROM AUTHOR]

The emergence of data-driven analytics and intelligent monitoring systems is radically transforming the world of competitive sports. However, robust real-time activity recognition remains elusive for rapid-paced sports like table tennis due to the complexity of strokes and quick maneuvering. This paper tries to overcome this challenge through an innovative cloud-supported system integrating the Internet of Things (IoT), machine learning, and wearable sensors for automated analysis of table tennis gameplay. We strategically set up a multi-camera IoT system around a table tennis court to compile a rich labeled image dataset encapsulating over 15,000 frames. To improve model generalization, the images captured various playing styles, lighting conditions, and camera angles. We developed tailored SVM and CNN architectures optimized for table tennis activity classification. The models were trained on GPU-accelerated platforms using the curated dataset. After hyperparameter tuning and cross-validation, the CNN model achieved 96.2% accuracy, a precision value of 96.3%, a recall value of 95.2%, and an F1-score of 96.3% in classifying standard strokes and serves. Additionally, the models exhibited impressive processing speeds of 22–34 fps, enabling real-time utilization. Our proposed model outperformed the latest models in this field with higher accuracy, recall values, F1-score, and precision. While expanding the dataset diversity and testing variations of deep network architectures could further enhance performance, this paper demonstrates a crucial leap toward helping real-time analytics in table tennis using an AI-powered computer vision approach. The hybrid system combining IoT, wearables, and machine learning establishes a framework to transform data into actionable and timely insights for table tennis players and coaches. [ABSTRACT FROM AUTHOR]

This paper aims to craft adversarial queries for image retrieval, which uses image features for similarity measurement. Many commonly used methods are developed in the context of image classification. However, these methods, which attack prediction probabilities, only exert an indirect influence on the image features and are thus found less effective when being applied to the retrieval problem. In designing an attack method specifically for image retrieval, we introduce opposite-direction feature attack (ODFA), a white-box attack approach that directly attacks query image features to generate adversarial queries. As the name implies, the main idea underpinning ODFA is to impel the original image feature to the opposite direction, similar to a U-turn. This simple idea is experimentally evaluated on five retrieval datasets. We show that the adversarial queries generated by ODFA cause true matches no longer to be seen at the top ranks, and the attack success rate is consistently higher than classifier attack methods. In addition, our method of creating adversarial queries can be extended for multi-scale query inputs and is generalizable to other retrieval models without foreknowing their weights, i.e., the black-box setting. [ABSTRACT FROM AUTHOR]

This paper investigates the nuanced characteristics of the spectral envelope attributes due to vocal-tract resonance structure and fine-level excitation source features within short-term Fourier transform (STFT) magnitude spectra for the assessment of dysarthria. The single-channel convolutional neural network (CNN) employing time-frequency representations such as STFT spectrogram (STFT-SPEC) and Mel-spectrogram (MEL-SPEC) does not ensure capture of the source and system information simultaneously due to the filtering operation using a fixed-size filter. Building upon this observation, this study first explores the significance of convolution filter size in the context of the CNN-based automated dysarthric assessment system. An approach is then introduced to effectively capture resonance structure and fine-level features through a multi-channel CNN. In the proposed approach, the STFT-SPEC is decomposed using a one-level discrete wavelet transform (DWT) to separate the slow-varying spectral structure and fine-level features. The resulting decomposed coefficients in four directions are taken as the inputs to multi-channel CNN to capture the source and system features by employing different sizes of convolution filters. The experimental results conducted on the UA-speech corpus validate the efficacy of the proposed approach utilizing multi-channel CNN. The proposed approach demonstrates the notable enhancement in accuracy and F1 score (60.86% and 48.52%) compared to a single-channel CNN using STFT-SPEC (46.45% and 40.97%), MEL-SPEC (48.86% and 38.20%), and MEL-SPEC appended with delta and delta-delta coefficients (52.40% and 42.84%) for assessment of dysarthria in a speaker-independent and text-independent mode. [ABSTRACT FROM AUTHOR]

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

Deep learning has emerged as a highly effective and precise method for classifying images. The presence of plant diseases poses a significant threat to food security. However, accurately identifying these diseases in plants is challenging due to limited infrastructure and techniques. Fortunately, the recent advancements in deep learning within the field of computer vision have opened up new possibilities for diagnosing plant pathology. Detecting plant diseases at an early stage is crucial, and this research paper proposes a deep convolutional neural network model that can rapidly and accurately identify plant diseases. Given the minimal variation in image texture and color, deep learning techniques are essential for robust recognition. In this study, we introduce a deep, explainable neural architecture specifically designed for recognizing plant diseases. Fine-tuned deep convolutional neural network is designed by freezing the layers and adjusting the weights of learnable layers. By extracting deep features from a down sampled feature map of a fine-tuned neural network, we are able to classify these features using a customized K-Nearest Neighbors Algorithm. To train and validate our model, we utilize the largest standard plant village dataset, which consists of 38 classes. To evaluate the performance of our proposed system, we estimate specificity, sensitivity, accuracy, and AUC. The results demonstrate that our system achieves an impressive maximum validation accuracy of 99.95% and an AUC of 1, making it the most ideal and highest-performing approach compared to current state-of-the-art deep learning methods for automatically identifying plant diseases. [ABSTRACT FROM AUTHOR]

In this paper, a method based on transfer learning is proposed to recover the three-dimensional shape of cultural relics faces from a single old photo. It can simultaneously reconstruct the three-dimensional facial structure and align the texture of the cultural relics with fewer training samples. The UV position map is used to represent the three-dimensional shape in space and act as the output of the network. A convolutional neural network is used to reconstruct the UV position map from a single 2D image. In the training process, the human face data is used for pre-training, and then a small amount of artifact data is used for fine-tuning. A deep learning model with strong generalization ability is trained with fewer artifact data, and a three-dimensional model of the cultural relic face can be reconstructed from a single old photograph. The methods can train more complex deep networks without a large amount of cultural relic data, and no over-fitting phenomenon occurs, which effectively solves the problem of fewer cultural relic samples. The method is verified by restoring a Chinese Terracotta Warrior with facial cracks and a Buddha with a broken nose. Other applications can be used in the fields such as texture recovery, facial feature extraction, and three-dimensional model estimation of the damaged cultural relics or sculptures in the photos. [ABSTRACT FROM AUTHOR]

Over the past decades, the software industry has expanded to include all industries. Since stakeholders tend to use it to get their work done, software houses seek to estimate the cost of the software, which includes calculating the effort, time, and resources required. Although many researchers have worked to estimate it, the prediction accuracy results are still inaccurate and unstable. Estimating it requires a lot of effort. Therefore, there is an urgent need for modern techniques that contribute to cost estimation. This paper seeks to present a model based on deep learning and machine learning techniques by combining convolutional neural networks (CNN) and the particle swarm algorithm (PSO) in the context of time series forecasting, which enables feature extraction and automatic tuning of hyperparameters, which reduces the manual effort of selecting parameters and contributes to fine-tuning. The use of PSO also enhances the robustness and generalization ability of the CNN model and its iterative nature allows for efficient discovery of hyperparameter similarity. The model was trained and tested on 13 different benchmark datasets and evaluated through six metrics: mean absolute error (MAE), mean square error (MSE), mean magnitude relative error (MMRE), root mean square error (RMSE), median magnitude relative error (MdMRE), and prediction accuracy (PRED). Comparative results reveal that the performance of the proposed model is better than other methods for all datasets and evaluation criteria. The results were very promising for predicting software cost estimation. [ABSTRACT FROM AUTHOR]

In the current era, remote sensing is a powerful platform for detecting and predicting landslides. Moreover, the advancement in computing technologies has proven significant in artificial intelligence (AI) research. Researchers have made significant attempts in the existing literature by introducing landslide detection procedures from remote sensing images (RSIs) through deep learning (DpLr) algorithms. This research work aims to survey those methods. Our database consists of 204 published research articles. In addition, 50% (approximately) of the papers are directly related to landslide information extraction from satellite and unmanned aerial vehicles (UAV) images exploiting DpLr models. The suggested methods have been categorized into seven parts based on the applied model. Further, the evaluation methods have been discussed. The quantitative results are based on the following parameters: (1) contributing nations, (2) key study locations, (3) data set distribution, and (4) model utilization. Lastly, challenges in the studies of DpLr algorithms and the opportunities in landslide detection problems are discussed to motivate future research. [ABSTRACT FROM AUTHOR]

The formation dip angle is an important characteristic parameter that reflects underground structures, and it is widely used in seismic exploration and geological interpretation. However, the routine dip angle calculation method suffers from the problems of artifact interference and insufficient accuracy, which restricts the development of fine exploration technology. More accurately obtaining the formation dip angle has become a general concern. To solve these problems, this paper proposes a method for calculating the formation dip angle using deep learning. The dip angle calculation is considered a regression problem. By establishing a database of synthetic seismic data and dip data tags, data-driven fitting of nonlinear functional relationships between the seismic data and dip angles are achieved, and intelligent dip calculations are realized. The method is verified using the synthetic sedimentary model and actual data and is compared with the mainstream dip angle calculation method in the industry. The results show that this method more realistically reflects the undulating characteristics of a structure with both high accuracy and anti-interference ability. [ABSTRACT FROM AUTHOR]

With the massive amount of data available on the Internet, many users face problems when they need access to the information and goods they need. Adapting information to user needs has become a complex and time-consuming process. Recommender systems are powerful tools for guiding users in electronic settings to information, services, and goods of interest. With the ability to identify users and predict their preferences, recommender systems can extract information likely to be of interest to users from vast amounts of data and save time and energy by providing them with relevant recommendations. Therefore, in this paper, a framework for a recommender system is proposed, which consists of four main phases. In the first phase, the preprocessing operation is performed. The purpose of this phase is to create an ontology model for products based on the convolutional neural network method. Data collection operations are carried out in the second phase. The purpose of this phase is to receive and store user information based on behavior and different criteria. The third phase is related to creating an ontology. The purpose of this phase is to create an ontology model for user behavior using OWL libraries. Finally, in the last phase, finding similarities and presented a proposal. The purpose of this phase is the necessary calculations of the proposed framework in the similarity finding section using ontology models. Simulation results show that the proposed framework measures MAE (more than 10 and 15%), RMSE (more than 12 and 16%), precision (less than 10 and 13%), recall (more than 25 and 28%), F1-score (higher than 25 and 30%) and Score of User (higher than 15 and 17%) outperform two related approaches, namely CF and CF+ Ontology, respectively. [ABSTRACT FROM AUTHOR]

Given a crowd image, there are two ways for human to approximate the counting number: exactly locating head points in each local region or directly estimating the total number of person based on the whole image. By imitating human visual perception, CNN and transformer are two mainstream models for solving crowd counting challenging, among which CNN has a strong ability to extract locality-oriented feature and transformer is suitable for modeling global dependencies. Based on the fact, in this paper, the proposed CLDE-Net is the first study that fulfills exact localization and direct estimation by designing the hybrid of CNN and transformer, to be specific, CNN searches all candidate head points in each local region and transformer learns the crowd density map with global receptive fields. Furthermore, we adopt two pipelines to further boost crowd counting performance: (1) cross-layer feature interaction module is employed to facilitate information transmission between two network branches of CNN and transformer and (2) dynamic factor generator is designed to adaptively fuse the result of head point localization and density map estimation. Extensive experiments show that the proposed CLDE-Net framework achieves the state-of-the-art performance on multiple data sets for crowd counting. [ABSTRACT FROM AUTHOR]

Re-ranking is a task of refining an initially ranked list of images obtained from an image retrieval technique for a given query image, with the goal of enhancing retrieval performance in an efficient manner. However, existing re-ranking methods suffer from high computational complexity, leading to slow and resource-intensive operations that render them to be impractical for real-life applications. This necessitates the development of a computationally efficient re-ranking approach that effectively improves the retrieval performance. In this paper, we propose a novel and computationally efficient re-ranking method for image retrieval, utilizing the speedy and proficient nature of image hashing techniques for image representation. Use of the hash code of an image using its DCT and DWT coefficients constitutes the basis of the proposed re-ranking technique. Three balanced binary search trees, one using the hash codes of the images corresponding to the DCT coefficients, and the other two using the most significant and the least significant bits of the hash codes corresponding to the DWT coefficients, are formed. Each balanced binary search tree is searched by comparing the hash code of the query image with those of the images in the tree starting from its root to form a set of the images that are comparable to the query image. Finally, the three sets of the images resulting from the three balanced binary search trees are used to obtain the final re-ranked list of retrieved images. Experimental results on the proposed retrieval scheme based on hashing-based re-ranking and various other image retrieval schemes using benchmark datasets demonstrate the superiority of our approach in terms of computational efficiency and retrieval performance. [ABSTRACT FROM AUTHOR]

Assessing the strength of complex networks is crucial for evaluating their functionality and monitoring system security. Two primary perspectives for measuring network robustness are connectivity and controllability, which quantify how well a network maintains connectivity and controllability after experiencing complete attacks. However, conventional robustness calculation methods that use simulation attacks can be impractical for large-scale networks. Recent research has explored the use of deep learning methods for network robustness prediction, including PCR (short for predictor of controllability robustness), which uses a VGG (short for visual geometry group)-based convolutional neural network (CNN) and a linear filter. However, PCR has limitations, including inaccurate edge importance differentiation and fluctuating output curves. This paper presents ATTRP, an attention-based robustness predictor, which addresses these limitations. ATTRP uses a novel convolutional neural network with channel and spatial attention mechanisms to improve prediction accuracy and a robustness filter based on Savitzky–Golay smoothing to rectify the robustness curve. Experimental studies demonstrate that ATTRP outperforms other predictors, with much lower errors, while its computational speed is far superior to that of traditional attacking simulation. Overall, our research provides a more effective and efficient means of predicting network robustness, with potential applications in monitoring system security. [ABSTRACT FROM AUTHOR]

Development of a reliable and intelligent traffic monitoring system is highly desired to improve the transportation safety and establish future transportation plans due to the fast growth of vehicle population. Vehicle classification is one of the most critical subsystems where existing ones suffer from privacy concerns, requirements of complicated systems, and high maintenance cost. This paper reports a novel vehicle classification method by utilizing a triboelectric sensor to accurately identify vehicles. Novelty of this method originates from using triboelectric sensor and machine learning method with important advantages over current alternatives by providing an easy installation, simple operation, noninvasive measurement, cost-effective manufacturing, and highly accurate classification. To make a classification, vehicle toys' signals were acquired from triboelectric sensor and then applied to a deep learning algorithm. The 1932 sensor output data were grouped into a set of seven vehicle toys with different wheelbases, and number of tires passing on are used to train and optimize 1D-CNN model. The utilized 1D-CNN model achieved accuracy, f1-score, precision, and recall as 96.38%, 0.9638, 0.9658, and 0.9637, respectively. [ABSTRACT FROM AUTHOR]

Manufacturers have traditionally relied on regular maintenance and inspections to ensure the proper functioning of all technical devices, machines, and components. In the era of Industry 4.0, these precautionary measures are supplemented and extended considerably by applying predictive maintenance. This form of maintenance is almost symbolic of Industry 4.0 and promises tremendous success. However, reliable data collection, integrating Industry 4.0 into the pre-existing manufacturing infrastructure, and analysing production machine status and production-related data present real challenges. A solution presented in this paper addressing these issues is an FPGA-based edge device development for data analysis and fault detection. In the proposed system, the MFCC method is implemented on a Pynq-Z2 board as pre-processing IP cores used to convert the vibration data collected to detect and diagnose machinery-bearing faults into 2D feature representations, which are then utilised for fault prediction based on optimised CNN network architecture. The Pynq-Z2 platform can be connected to the internet network directly through the Ethernet port and remotely controlled, making it perfect for IoT applications. We opted for the NCS2 accelerator from Intel to implement the proposed CNN network that will be connected to the Pynq-Z2 platform through the USB port. An experimental test through an IIoT application was carried out to validate the proposed system. The results showed that the system could perform pre-processing and prediction tasks in less than 40 ms. [ABSTRACT FROM AUTHOR]

In recent years, although significant progress has been made in infrared and visible image fusion, existing methods typically assume that the source images have been rigorously registered or aligned prior to image fusion. However, the difference in modalities of infrared and visible images poses a great challenge to achieve strict alignment automatically, affecting the quality of the subsequent fusion procedure. To address this problem, this paper proposes a deep learning framework for misaligned infrared and visible image fusion, aiming to free the fusion algorithm from strict registration. Technically, we design a convolutional neural network (CNN)-Transformer Hierarchical Interactive Embedding (CTHIE) module, which can combine the respective advantages of CNN and Transformer, to extract features from the source images. In addition, by characterizing the correlation between the features extracted from misaligned source images, a Dynamic Re-aggregation Feature Representation (DRFR) module is devised to align the features with a self-attention-based feature re-aggregation scheme. Finally, to effectively utilize the features at different levels of the network, a Fully Perceptual Forward Fusion (FPFF) module via interactive transmission of multi-modal features is introduced for feature fusion to reconstruct the fused image. Experimental results on both synthetic and real-world data demonstrate the effectiveness of the proposed method, verifying the feasibility of directly fusing infrared and visible images without strict registration. [ABSTRACT FROM AUTHOR]

The paper presents some methods of satellite data preprocessing for the elimination of atmospheric effects on the electromagnetic radiation detected by the target equipment of a satellite and subsequent detection of floods in the Amur River basin. The atmospheric correction algorithm that has been used for the preprocessing is based on the use of a lookup table obtained by applying the Second Simulation of a Satellite Signal in the Solar Spectrum, which is a model of atmosphere radiative transfer. The subsequent flood detection in the Amur River basin water bodies builds on a neural network algorithm, the core of which is the upgraded U-Net. The developed algorithms for atmospheric correction and subsequent flood detection make it possible to receive information in an automatic near-real-time mode for monitoring flood conditions. Some groundwork has been made for applying the algorithm to the data of the Russian satellite instruments for spacecraft planned for launch. [ABSTRACT FROM AUTHOR]

Identifying a target accurately in the presence of noise in synthetic aperture radar (SAR) images poses significant challenges considering various parameters, such as viewing angle and configuration changes. In this paper, SAR images are classified using the proposed convolutional neural network. The limitation of data concerning moving and stationary target acquisition and recognition (MSTAR) database led us to develop a primary network (learning network) by employing the proposed N-Sigmoid function and training it using eight different satellite databases with images more than MSTAR. We saved the best weights for the main network. Next, we replace the weights of the two fully connected (FC) layers of the ResNet-50 with the saved weights of the training network and employed the main network for classification. Our proposed method's primary contribution is twofold, based on the availability of additional information in heterogeneous SAR images and differences in intensity and clarity. First, we utilize the weights learned by the training network, and second, we keep negative neurons and neurons close to zero active instead of deactivating them to facilitate better training of the main network. Our proposed method outperformed other references in terms of sensitivity in all classes and achieved an accuracy of 98% for classification with good machine weight learning. [ABSTRACT FROM AUTHOR]

This paper presents an approach based on deep learning for accurate Electrocardiogram signal classification. The electrocardiogram is a significant signal in the realm of medical affairs, which gives vital information about the cardiovascular status of patients to heart specialists. Manually meticulous analysis of signals needs high and specific skills, and it is a time-consuming job too. The existence of noise, the inflexibility of signals, and the irregularity of heartbeats keep heart specialists in trouble. Cardiovascular diseases (CVDs) are the most important factor of fatality globally, which annually caused the deaths of 17.9 million people. Totally 31% of all death in the world are related to CVDs, which the age of 1/3 of patients that died because of CVDs is below 70 Because of the high percentage of mortality in cardiovascular patients, accurate diagnosis of this disease is an important matter. We present an approach to the analysis of electrocardiogram signals based on the convolutional neural network, discrete wavelet transformation with db2 mother wavelet, and synthetic minority over-sampling technique (SMOTE) on the MIT-BIH dataset according to the association for the advancement of medical instrumentation (AAMI) standards to increase the accuracy in electrocardiogram signal classifications. The evaluation results show this approach with 50 epoch training that the time of each epoch is 39 s, achieved 99.71% accuracy for category F, 98.69% accuracy for category N, 99.45% accuracy for category S, 99.33% accuracy for category V and 99.82% accuracy for category Q. It is worth mentioning that it can potentially be used as a clinical auxiliary diagnostic tool. The source code is available at https://gitlab.com/arminshoughi/ecg-classification-cnn. [ABSTRACT FROM AUTHOR]

To bring more intelligence to edge systems, Federated Learning (FL) is proposed to provide a privacy-preserving mechanism to train a globally shared model by utilizing a massive amount of user-generated data on devices. FL enables multiple clients collaboratively train a machine learning model while keeping the raw training data local. When the dataset is horizontally partitioned, existing FL algorithms can aggregate CNN models received from decentralized clients. But, it cannot be applied to the scenario where the dataset is vertically partitioned. This manuscript showcases the task of image classification in the vertical FL settings in which participants hold incomplete image pieces of all samples, individually. To this end, the paper discusses AdptVFedConv to tackle this issue and achieves the CNN models' aim for training without revealing raw data. Unlike conventional FL algorithms for sharing model parameters in every communication iteration, AdptVFedConv enables hidden feature representations. Each client fine-tunes a local feature extractor and transmits the extracted feature representations to the backend machine. A classifier model is trained with concatenated feature representations as input and ground truth labels as output at the server-side. Furthermore, we put forward the model transfer method and replication padding tricks to improve final performance. Extensive experiments demonstrate that the accuracy of AdptVFedConv is close to the centralized model. [ABSTRACT FROM AUTHOR]