Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using d...Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.展开更多
As legal cases grow in complexity and volume worldwide,integrating machine learning and artificial intelligence into judicial systems has become a pivotal research focus.This study introduces a comprehensive framework...As legal cases grow in complexity and volume worldwide,integrating machine learning and artificial intelligence into judicial systems has become a pivotal research focus.This study introduces a comprehensive framework for verdict recommendation that synergizes rule-based methods with deep learning techniques specifically tailored to the legal domain.The proposed framework comprises three core modules:legal feature extraction,semantic similarity assessment,and verdict recommendation.For legal feature extraction,a rule-based approach leverages Black’s Law Dictionary and WordNet Synsets to construct feature vectors from judicial texts.Semantic similarity between cases is evaluated using a hybrid method that combines rule-based logic with an LSTM model,analyzing the feature vectors of query cases against a legal knowledge base.Verdicts are then recommended through a rule-based retrieval system,enhanced by predefined legal statutes and regulations.By merging rule-based methodologies with deep learning,this framework addresses the interpretability challenges often associated with contemporary AImodels,thereby enhancing both transparency and generalizability across diverse legal contexts.The system was rigorously tested using a legal corpus of 43,000 case laws across six categories:Criminal,Revenue,Service,Corporate,Constitutional,and Civil law,ensuring its adaptability across a wide range of judicial scenarios.Performance evaluation showed that the feature extraction module achieved an average accuracy of 91.6%with an F-Score of 95%.The semantic similarity module,tested using Manhattan,Euclidean,and Cosine distance metrics,achieved 88%accuracy and a 93%F-Score for short queries(Manhattan),89%accuracy and a 93.7%F-Score for medium-length queries(Euclidean),and 87%accuracy with a 92.5%F-Score for longer queries(Cosine).The verdict recommendation module outperformed existing methods,achieving 90%accuracy and a 93.75%F-Score.This study highlights the potential of hybrid AI frameworks to improve judicial decision-making and streamline legal processes,offering a robust,interpretable,and adaptable solution for the evolving demands of modern legal systems.展开更多
Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;...Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;however,its accu-racy is limited by operator dependency and interobserver variability.Advance-ments in deep learning,particularly convolutional neural networks(CNNs),show great potential for enhancing GI disease detection and classification.This review explores the application of CNNs in endoscopic imaging,focusing on polyp and tumor detection,disease classification,endoscopic ultrasound,and capsule endo-scopy analysis.We discuss the performance of CNN models with traditional dia-gnostic methods,highlighting their advantages in accuracy and real-time decision support.Despite promising results,challenges remain,including data availability,model interpretability,and clinical integration.Future directions include impro-ving model generalization,enhancing explainability,and conducting large-scale clinical trials.With continued advancements,CNN-powered artificial intelligence systems could revolutionize GI endoscopy by enhancing early disease detection,reducing diagnostic errors,and improving patient outcomes.展开更多
Electric vehicles(EVs)are gradually being deployed in the transportation sector.Although they have a high impact on reducing greenhouse gas emissions,their penetration is challenged by their random energy demand and d...Electric vehicles(EVs)are gradually being deployed in the transportation sector.Although they have a high impact on reducing greenhouse gas emissions,their penetration is challenged by their random energy demand and difficult scheduling of their optimal charging.To cope with these problems,this paper presents a novel approach for photovoltaic grid-connected microgrid EV charging station energy demand forecasting.The present study is part of a comprehensive framework involving emerging technologies such as drones and artificial intelligence designed to support the EVs’charging scheduling task.By using predictive algorithms for solar generation and load demand estimation,this approach aimed at ensuring dynamic and efficient energy flow between the solar energy source,the grid and the electric vehicles.The main contribution of this paper lies in developing an intelligent approach based on deep recurrent neural networks to forecast the energy demand using only its previous records.Therefore,various forecasters based on Long Short-term Memory,Gated Recurrent Unit,and their bi-directional and stacked variants were investigated using a real dataset collected from an EV charging station located at Trieste University(Italy).The developed forecasters have been evaluated and compared according to different metrics,including R,RMSE,MAE,and MAPE.We found that the obtained R values for both PV power generation and energy demand ranged between 97%and 98%.These study findings can be used for reliable and efficient decision-making on the management side of the optimal scheduling of the charging operations.展开更多
Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susce...Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susceptibility to backdoors maliciously injected by adversaries.This vulnerability arises due to the intricate architecture and opacity of DNNs,resulting in numerous redundant neurons embedded within the models.Adversaries exploit these vulnerabilities to conceal malicious backdoor information within DNNs,thereby causing erroneous outputs and posing substantial threats to the efficacy of DNN-based applications.This article presents a comprehensive survey of backdoor attacks against DNNs and the countermeasure methods employed to mitigate them.Initially,we trace the evolution of the concept from traditional backdoor attacks to backdoor attacks against DNNs,highlighting the feasibility and practicality of generating backdoor attacks against DNNs.Subsequently,we provide an overview of notable works encompassing various attack and defense strategies,facilitating a comparative analysis of their approaches.Through these discussions,we offer constructive insights aimed at refining these techniques.Finally,we extend our research perspective to the domain of large language models(LLMs)and synthesize the characteristics and developmental trends of backdoor attacks and defense methods targeting LLMs.Through a systematic review of existing studies on backdoor vulnerabilities in LLMs,we identify critical open challenges in this field and propose actionable directions for future research.展开更多
Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves,blood vessels,retinal health,and the impact of diabetes on the optic nerves.Fundus disorders are a major global health concern,affec...Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves,blood vessels,retinal health,and the impact of diabetes on the optic nerves.Fundus disorders are a major global health concern,affecting millions of people worldwide due to their widespread occurrence.Fundus photography generates machine-based eye images that assist in diagnosing and treating ocular diseases such as diabetic retinopathy.As a result,accurate fundus detection is essential for early diagnosis and effective treatment,helping to prevent severe complications and improve patient outcomes.To address this need,this article introduces a Derivative Model for Fundus Detection using Deep NeuralNetworks(DMFD-DNN)to enhance diagnostic precision.Thismethod selects key features for fundus detection using the least derivative,which identifies features correlating with stored fundus images.Feature filtering relies on the minimum derivative,determined by extracting both similar and varying textures.In this research,the DNN model was integrated with the derivative model.Fundus images were segmented,features were extracted,and the DNN was iteratively trained to identify fundus regions reliably.The goal was to improve the precision of fundoscopic diagnosis by training the DNN incrementally,taking into account the least possible derivative across iterations,and using outputs from previous cycles.The hidden layer of the neural network operates on the most significant derivative,which may reduce precision across iterations.These derivatives are treated as inaccurate,and the model is subsequently trained using selective features and their corresponding extractions.The proposed model outperforms previous techniques in detecting fundus regions,achieving 94.98%accuracy and 91.57%sensitivity,with a minimal error rate of 5.43%.It significantly reduces feature extraction time to 1.462 s and minimizes computational overhead,thereby improving operational efficiency and scalability.Ultimately,the proposed model enhances diagnostic precision and reduces errors,leading to more effective fundus dysfunction diagnosis and treatment.展开更多
Underwater wireless sensor networks(UWSNs)have emerged as a new paradigm of real-time organized systems,which are utilized in a diverse array of scenarios to manage the underwater environment surrounding them.One of t...Underwater wireless sensor networks(UWSNs)have emerged as a new paradigm of real-time organized systems,which are utilized in a diverse array of scenarios to manage the underwater environment surrounding them.One of the major challenges that these systems confront is topology control via clustering,which reduces the overload of wireless communications within a network and ensures low energy consumption and good scalability.This study aimed to present a clustering technique in which the clustering process and cluster head(CH)selection are performed based on the Markov decision process and deep reinforcement learning(DRL).DRL algorithm selects the CH by maximizing the defined reward function.Subsequently,the sensed data are collected by the CHs and then sent to the autonomous underwater vehicles.In the final phase,the consumed energy by each sensor is calculated,and its residual energy is updated.Then,the autonomous underwater vehicle performs all clustering and CH selection operations.This procedure persists until the point of cessation when the sensor’s power has been reduced to such an extent that no node can become a CH.Through analysis of the findings from this investigation and their comparison with alternative frameworks,the implementation of this method can be used to control the cluster size and the number of CHs,which ultimately augments the energy usage of nodes and prolongs the lifespan of the network.Our simulation results illustrate that the suggested methodology surpasses the conventional low-energy adaptive clustering hierarchy,the distance-and energy-constrained K-means clustering scheme,and the vector-based forward protocol and is viable for deployment in an actual operational environment.展开更多
Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers t...Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers to techniques that increase the amount of image data.Common operations for image augmentation include changes in illumination,rotation,contrast,size,viewing angle,and others.Recently,Generative Adversarial Networks(GANs)have been employed for image generation.However,like image augmentation methods,GAN approaches can only generate images that are similar to the original images.Therefore,they also cannot generate new classes of data.Texture images presentmore challenges than general images,and generating textures is more complex than creating other types of images.This study proposes a gradient-based deep neural network method that generates a new class of texture.It is possible to rapidly generate new classes of textures using different kernels from pre-trained deep networks.After generating new textures for each class,the number of textures increases through image augmentation.During this process,several techniques are proposed to automatically remove incomplete and similar textures that are created.The proposed method is faster than some well-known generative networks by around 4 to 10 times.In addition,the quality of the generated textures surpasses that of these networks.The proposed method can generate textures that surpass those of someGANs and parametric models in certain image qualitymetrics.It can provide a big texture dataset to train deep networks.A new big texture dataset is created artificially using the proposed method.This dataset is approximately 2 GB in size and comprises 30,000 textures,each 150×150 pixels in size,organized into 600 classes.It is uploaded to the Kaggle site and Google Drive.This dataset is called BigTex.Compared to other texture datasets,the proposed dataset is the largest and can serve as a comprehensive texture dataset for training more powerful deep neural networks and mitigating overfitting.展开更多
With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from h...With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.展开更多
Social media has emerged as one of the most transformative developments on the internet,revolu-tionizing the way people communicate and interact.However,alongside its benefits,social media has also given rise to signi...Social media has emerged as one of the most transformative developments on the internet,revolu-tionizing the way people communicate and interact.However,alongside its benefits,social media has also given rise to significant challenges,one of the most pressing being cyberbullying.This issue has become a major concern in modern society,particularly due to its profound negative impacts on the mental health and well-being of its victims.In the Arab world,where social media usage is exceptionblly high,cyberbullying has become increasingly prevalent,necessitating urgent attention.Early detection of harmful online behavior is critical to fostering safer digital environments and mitigating the adverse efcts of cyberbullying.This underscores the importance of developing advanced tools and systems to identify and address such behavior efectively.This paper investigates the development of a robust cyberbullying detection and classifcation system tailored for Arabic comments on YouTube.The study explores the efectiveness of various deep learning models,including Bi-LSTM(Bidirectional Long Short Term Memory),LSTM(Long Short-Term Memory),CNN(Convolutional Neural Networks),and a hybrid CNN-LSTM,in classifying Arabic comments into binary classes(bullying or not)and multiclass categories.A comprehensive dataset of 20,000 Arabic YouTube comments was collected,preprocessed,and labeled to support these tasks.The results revealed that the CNN and hybrid CNN-LSTM models achieved the highest accuracy in binary classification,reaching an impressive 91.9%.For multiclass dlassification,the LSTM and Bi-LSTM models outperformed others,achieving an accuracy of 89.5%.These findings highlight the efctiveness of deep learning approaches in the mitigation of cyberbullying within Arabic online communities.展开更多
Physiological signals such as electroencephalogram(EEG)signals are often corrupted by artifacts during the acquisition and processing.Some of these artifacts may deteriorate the essential properties of the signal that...Physiological signals such as electroencephalogram(EEG)signals are often corrupted by artifacts during the acquisition and processing.Some of these artifacts may deteriorate the essential properties of the signal that pertains to meaningful information.Most of these artifacts occur due to the involuntary movements or actions the human does during the acquisition process.So,it is recommended to eliminate these artifacts with signal processing approaches.This paper presents two mechanisms of classification and elimination of artifacts.In the first step,a customized deep network is employed to classify clean EEG signals and artifact-included signals.The classification is performed at the feature level,where common space pattern features are extracted with convolutional layers,and these features are later classified with a support vector machine classifier.In the second stage of the work,the artifact signals are decomposed with empirical mode decomposition,and they are then eliminated with the proposed adaptive thresholding mechanism where the threshold value changes for every intrinsic mode decomposition in the iterative mechanism.展开更多
Digital content such as games,extended reality(XR),and movies has been widely and easily distributed over wireless networks.As a result,unauthorized access,copyright infringement by third parties or eavesdroppers,and ...Digital content such as games,extended reality(XR),and movies has been widely and easily distributed over wireless networks.As a result,unauthorized access,copyright infringement by third parties or eavesdroppers,and cyberattacks over these networks have become pressing concerns.Therefore,protecting copyrighted content and preventing illegal distribution in wireless communications has garnered significant attention.The Intelligent Reflecting Surface(IRS)is regarded as a promising technology for future wireless and mobile networks due to its ability to reconfigure the radio propagation environment.This study investigates the security performance of an uplink Non-Orthogonal Multiple Access(NOMA)system integrated with an IRS and employing Fountain Codes(FCs).Specifically,two users send signals to the base station at separate distances.A relay receives the signal from the nearby user first and then relays it to the base station.The IRS receives the signal from the distant user and reflects it to the relay,which then sends the reflected signal to the base station.Furthermore,a malevolent eavesdropper intercepts both user and relay communications.We construct mathematical equations for Outage Probability(OP),throughput,diversity evaluation,and Interception Probability(IP),offering quantitative insights to assess system security and performance.Additionally,OP and IP are analyzed using a Deep Neural Network(DNN)model.A deeper comprehension of the security performance of the IRS-assisted NOMA systemin signal transmission is provided by Monte Carlo simulations,which are also carried out to confirm the theoretical conclusions.展开更多
The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the ...The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.展开更多
The Wireless Sensor Networks(WSN)are vulnerable to assaults due to the fact that the devices connected to them have a reliable connection to the inter-net.A malicious node acts as the controller and uses a grey hole a...The Wireless Sensor Networks(WSN)are vulnerable to assaults due to the fact that the devices connected to them have a reliable connection to the inter-net.A malicious node acts as the controller and uses a grey hole attack to get the data from all of the other nodes in the network.Additionally,the nodes are dis-carding and modifying the data packets according to the requirements of the sys-tem.The assault modifies the fundamental concept of the WSNs,which is that different devices should communicate with one another.In the proposed system,there is a fuzzy idea offered for the purpose of preventing the grey hole attack from making effective communication among the WSN devices.The currently available model is unable to recognise the myriad of different kinds of attacks.The fuzzy engine identified suspicious actions by utilising the rules that were gen-erated to make a prediction about the malicious node that would halt the process.Experiments conducted using simulation are used to determine delay,accuracy,energy consumption,throughput,and the ratio of packets successfully delivered.It stands in contrast to the model that was suggested,as well as the methodologies that are currently being used,and analogue behavioural modelling.In comparison to the existing method,the proposed model achieves an accuracy rate of 45 per-cent,a packet delivery ratio of 79 percent,and a reduction in energy usage of around 35.6 percent.These results from the simulation demonstrate that the fuzzy grey detection technique that was presented has the potential to increase the net-work’s capability of detecting grey hole assaults.展开更多
In the ‘‘Internet Plus" era, space-based information services require effective and fast image satellite scheduling. Most existing studies consider image satellite scheduling to be an optimization problem to so...In the ‘‘Internet Plus" era, space-based information services require effective and fast image satellite scheduling. Most existing studies consider image satellite scheduling to be an optimization problem to solve with searching algorithms in a batch-wise manner. No real-time speed method for satellite scheduling exists. In this paper, with the idea of building a real-time speed method, satellite scheduling is remodeled based on a Dynamic and Stochastic Knapsack Problem(DSKP), and the objective is to maximize the total expected profit. No existing algorithm could be able to solve this novel scheduling problem properly. With inspiration from the recent achievements in Deep Reinforcement Learning(DRL) in video games, AlphaGo and dynamic controlling,a novel DRL-based method is applied to training a neural network to schedule tasks. The numerical results show that the method proposed in this paper can achieve relatively good performance with real-time speed and immediate respond style.展开更多
The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks ...The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.展开更多
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金The work described in this paper was fully supported by a grant from Hong Kong Metropolitan University(RIF/2021/05).
文摘Parkinson’s disease(PD)is a debilitating neurological disorder affecting over 10 million people worldwide.PD classification models using voice signals as input are common in the literature.It is believed that using deep learning algorithms further enhances performance;nevertheless,it is challenging due to the nature of small-scale and imbalanced PD datasets.This paper proposed a convolutional neural network-based deep support vector machine(CNN-DSVM)to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets.A customized kernel function reduces the impact of biased classification towards the majority class(healthy candidates in our consideration).An improved generative adversarial network(IGAN)was designed to generate additional training data to enhance the model’s performance.For performance evaluation,the proposed algorithm achieves a sensitivity of 97.6%and a specificity of 97.3%.The performance comparison is evaluated from five perspectives,including comparisons with different data generation algorithms,feature extraction techniques,kernel functions,and existing works.Results reveal the effectiveness of the IGAN algorithm,which improves the sensitivity and specificity by 4.05%–4.72%and 4.96%–5.86%,respectively;and the effectiveness of the CNN-DSVM algorithm,which improves the sensitivity by 1.24%–57.4%and specificity by 1.04%–163%and reduces biased detection towards the majority class.The ablation experiments confirm the effectiveness of individual components.Two future research directions have also been suggested.
基金funded by the Deanship of Scientific Research at Jouf University under Grant number DSR-2022-RG-0101。
文摘As legal cases grow in complexity and volume worldwide,integrating machine learning and artificial intelligence into judicial systems has become a pivotal research focus.This study introduces a comprehensive framework for verdict recommendation that synergizes rule-based methods with deep learning techniques specifically tailored to the legal domain.The proposed framework comprises three core modules:legal feature extraction,semantic similarity assessment,and verdict recommendation.For legal feature extraction,a rule-based approach leverages Black’s Law Dictionary and WordNet Synsets to construct feature vectors from judicial texts.Semantic similarity between cases is evaluated using a hybrid method that combines rule-based logic with an LSTM model,analyzing the feature vectors of query cases against a legal knowledge base.Verdicts are then recommended through a rule-based retrieval system,enhanced by predefined legal statutes and regulations.By merging rule-based methodologies with deep learning,this framework addresses the interpretability challenges often associated with contemporary AImodels,thereby enhancing both transparency and generalizability across diverse legal contexts.The system was rigorously tested using a legal corpus of 43,000 case laws across six categories:Criminal,Revenue,Service,Corporate,Constitutional,and Civil law,ensuring its adaptability across a wide range of judicial scenarios.Performance evaluation showed that the feature extraction module achieved an average accuracy of 91.6%with an F-Score of 95%.The semantic similarity module,tested using Manhattan,Euclidean,and Cosine distance metrics,achieved 88%accuracy and a 93%F-Score for short queries(Manhattan),89%accuracy and a 93.7%F-Score for medium-length queries(Euclidean),and 87%accuracy with a 92.5%F-Score for longer queries(Cosine).The verdict recommendation module outperformed existing methods,achieving 90%accuracy and a 93.75%F-Score.This study highlights the potential of hybrid AI frameworks to improve judicial decision-making and streamline legal processes,offering a robust,interpretable,and adaptable solution for the evolving demands of modern legal systems.
基金Supported by Open Funds for Shaanxi Provincial Key Laboratory of Infection and Immune Diseases,No.2023-KFMS-1.
文摘Gastrointestinal(GI)diseases,including gastric and colorectal cancers,signi-ficantly impact global health,necessitating accurate and efficient diagnostic me-thods.Endoscopic examination is the primary diagnostic tool;however,its accu-racy is limited by operator dependency and interobserver variability.Advance-ments in deep learning,particularly convolutional neural networks(CNNs),show great potential for enhancing GI disease detection and classification.This review explores the application of CNNs in endoscopic imaging,focusing on polyp and tumor detection,disease classification,endoscopic ultrasound,and capsule endo-scopy analysis.We discuss the performance of CNN models with traditional dia-gnostic methods,highlighting their advantages in accuracy and real-time decision support.Despite promising results,challenges remain,including data availability,model interpretability,and clinical integration.Future directions include impro-ving model generalization,enhancing explainability,and conducting large-scale clinical trials.With continued advancements,CNN-powered artificial intelligence systems could revolutionize GI endoscopy by enhancing early disease detection,reducing diagnostic errors,and improving patient outcomes.
基金University of Jeddah,Jeddah,Saudi Arabia,grant No.(UJ-23-SRP-10).
文摘Electric vehicles(EVs)are gradually being deployed in the transportation sector.Although they have a high impact on reducing greenhouse gas emissions,their penetration is challenged by their random energy demand and difficult scheduling of their optimal charging.To cope with these problems,this paper presents a novel approach for photovoltaic grid-connected microgrid EV charging station energy demand forecasting.The present study is part of a comprehensive framework involving emerging technologies such as drones and artificial intelligence designed to support the EVs’charging scheduling task.By using predictive algorithms for solar generation and load demand estimation,this approach aimed at ensuring dynamic and efficient energy flow between the solar energy source,the grid and the electric vehicles.The main contribution of this paper lies in developing an intelligent approach based on deep recurrent neural networks to forecast the energy demand using only its previous records.Therefore,various forecasters based on Long Short-term Memory,Gated Recurrent Unit,and their bi-directional and stacked variants were investigated using a real dataset collected from an EV charging station located at Trieste University(Italy).The developed forecasters have been evaluated and compared according to different metrics,including R,RMSE,MAE,and MAPE.We found that the obtained R values for both PV power generation and energy demand ranged between 97%and 98%.These study findings can be used for reliable and efficient decision-making on the management side of the optimal scheduling of the charging operations.
基金supported in part by the National Natural Science Foundation of China under Grants No.62372087 and No.62072076the Research Fund of State Key Laboratory of Processors under Grant No.CLQ202310the CSC scholarship.
文摘Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susceptibility to backdoors maliciously injected by adversaries.This vulnerability arises due to the intricate architecture and opacity of DNNs,resulting in numerous redundant neurons embedded within the models.Adversaries exploit these vulnerabilities to conceal malicious backdoor information within DNNs,thereby causing erroneous outputs and posing substantial threats to the efficacy of DNN-based applications.This article presents a comprehensive survey of backdoor attacks against DNNs and the countermeasure methods employed to mitigate them.Initially,we trace the evolution of the concept from traditional backdoor attacks to backdoor attacks against DNNs,highlighting the feasibility and practicality of generating backdoor attacks against DNNs.Subsequently,we provide an overview of notable works encompassing various attack and defense strategies,facilitating a comparative analysis of their approaches.Through these discussions,we offer constructive insights aimed at refining these techniques.Finally,we extend our research perspective to the domain of large language models(LLMs)and synthesize the characteristics and developmental trends of backdoor attacks and defense methods targeting LLMs.Through a systematic review of existing studies on backdoor vulnerabilities in LLMs,we identify critical open challenges in this field and propose actionable directions for future research.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2021R1F1A1055408)supported by the Researchers Supporting Project Number(MHIRSP2024005)Almaarefa University,Riyadh,Saudi Arabia.
文摘Fundoscopic diagnosis involves assessing the proper functioning of the eye’s nerves,blood vessels,retinal health,and the impact of diabetes on the optic nerves.Fundus disorders are a major global health concern,affecting millions of people worldwide due to their widespread occurrence.Fundus photography generates machine-based eye images that assist in diagnosing and treating ocular diseases such as diabetic retinopathy.As a result,accurate fundus detection is essential for early diagnosis and effective treatment,helping to prevent severe complications and improve patient outcomes.To address this need,this article introduces a Derivative Model for Fundus Detection using Deep NeuralNetworks(DMFD-DNN)to enhance diagnostic precision.Thismethod selects key features for fundus detection using the least derivative,which identifies features correlating with stored fundus images.Feature filtering relies on the minimum derivative,determined by extracting both similar and varying textures.In this research,the DNN model was integrated with the derivative model.Fundus images were segmented,features were extracted,and the DNN was iteratively trained to identify fundus regions reliably.The goal was to improve the precision of fundoscopic diagnosis by training the DNN incrementally,taking into account the least possible derivative across iterations,and using outputs from previous cycles.The hidden layer of the neural network operates on the most significant derivative,which may reduce precision across iterations.These derivatives are treated as inaccurate,and the model is subsequently trained using selective features and their corresponding extractions.The proposed model outperforms previous techniques in detecting fundus regions,achieving 94.98%accuracy and 91.57%sensitivity,with a minimal error rate of 5.43%.It significantly reduces feature extraction time to 1.462 s and minimizes computational overhead,thereby improving operational efficiency and scalability.Ultimately,the proposed model enhances diagnostic precision and reduces errors,leading to more effective fundus dysfunction diagnosis and treatment.
文摘Underwater wireless sensor networks(UWSNs)have emerged as a new paradigm of real-time organized systems,which are utilized in a diverse array of scenarios to manage the underwater environment surrounding them.One of the major challenges that these systems confront is topology control via clustering,which reduces the overload of wireless communications within a network and ensures low energy consumption and good scalability.This study aimed to present a clustering technique in which the clustering process and cluster head(CH)selection are performed based on the Markov decision process and deep reinforcement learning(DRL).DRL algorithm selects the CH by maximizing the defined reward function.Subsequently,the sensed data are collected by the CHs and then sent to the autonomous underwater vehicles.In the final phase,the consumed energy by each sensor is calculated,and its residual energy is updated.Then,the autonomous underwater vehicle performs all clustering and CH selection operations.This procedure persists until the point of cessation when the sensor’s power has been reduced to such an extent that no node can become a CH.Through analysis of the findings from this investigation and their comparison with alternative frameworks,the implementation of this method can be used to control the cluster size and the number of CHs,which ultimately augments the energy usage of nodes and prolongs the lifespan of the network.Our simulation results illustrate that the suggested methodology surpasses the conventional low-energy adaptive clustering hierarchy,the distance-and energy-constrained K-means clustering scheme,and the vector-based forward protocol and is viable for deployment in an actual operational environment.
基金supported via funding from Prince Sattam bin Abdulaziz University(PSAU/2025/R/1446)Princess Nourah bint Abdulrahman University(PNURSP2025R300)Prince Sultan University.
文摘Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers to techniques that increase the amount of image data.Common operations for image augmentation include changes in illumination,rotation,contrast,size,viewing angle,and others.Recently,Generative Adversarial Networks(GANs)have been employed for image generation.However,like image augmentation methods,GAN approaches can only generate images that are similar to the original images.Therefore,they also cannot generate new classes of data.Texture images presentmore challenges than general images,and generating textures is more complex than creating other types of images.This study proposes a gradient-based deep neural network method that generates a new class of texture.It is possible to rapidly generate new classes of textures using different kernels from pre-trained deep networks.After generating new textures for each class,the number of textures increases through image augmentation.During this process,several techniques are proposed to automatically remove incomplete and similar textures that are created.The proposed method is faster than some well-known generative networks by around 4 to 10 times.In addition,the quality of the generated textures surpasses that of these networks.The proposed method can generate textures that surpass those of someGANs and parametric models in certain image qualitymetrics.It can provide a big texture dataset to train deep networks.A new big texture dataset is created artificially using the proposed method.This dataset is approximately 2 GB in size and comprises 30,000 textures,each 150×150 pixels in size,organized into 600 classes.It is uploaded to the Kaggle site and Google Drive.This dataset is called BigTex.Compared to other texture datasets,the proposed dataset is the largest and can serve as a comprehensive texture dataset for training more powerful deep neural networks and mitigating overfitting.
基金Project ZR2023MF111 supported by Shandong Provincial Natural Science Foundation。
文摘With the advancement of Vehicle-to-Everything(V2X)technology,efficient resource allocation in dynamic vehicular networks has become a critical challenge for achieving optimal performance.Existing methods suffer from high computational complexity and decision latency under high-density traffic and heterogeneous network conditions.To address these challenges,this study presents an innovative framework that combines Graph Neural Networks(GNNs)with a Double Deep Q-Network(DDQN),utilizing dynamic graph structures and reinforcement learning.An adaptive neighbor sampling mechanism is introduced to dynamically select the most relevant neighbors based on interference levels and network topology,thereby improving decision accuracy and efficiency.Meanwhile,the framework models communication links as nodes and interference relationships as edges,effectively capturing the direct impact of interference on resource allocation while reducing computational complexity and preserving critical interaction information.Employing an aggregation mechanism based on the Graph Attention Network(GAT),it dynamically adjusts the neighbor sampling scope and performs attention-weighted aggregation based on node importance,ensuring more efficient and adaptive resource management.This design ensures reliable Vehicle-to-Vehicle(V2V)communication while maintaining high Vehicle-to-Infrastructure(V2I)throughput.The framework retains the global feature learning capabilities of GNNs and supports distributed network deployment,allowing vehicles to extract low-dimensional graph embeddings from local observations for real-time resource decisions.Experimental results demonstrate that the proposed method significantly reduces computational overhead,mitigates latency,and improves resource utilization efficiency in vehicular networks under complex traffic scenarios.This research not only provides a novel solution to resource allocation challenges in V2X networks but also advances the application of DDQN in intelligent transportation systems,offering substantial theoretical significance and practical value.
基金financed by the European Union-NextGenerationEU,through the National Recowery and Resilience Plan of the Republic of Bulgaria,Project No.BG-RRP-2.013-0001-C01.
文摘Social media has emerged as one of the most transformative developments on the internet,revolu-tionizing the way people communicate and interact.However,alongside its benefits,social media has also given rise to significant challenges,one of the most pressing being cyberbullying.This issue has become a major concern in modern society,particularly due to its profound negative impacts on the mental health and well-being of its victims.In the Arab world,where social media usage is exceptionblly high,cyberbullying has become increasingly prevalent,necessitating urgent attention.Early detection of harmful online behavior is critical to fostering safer digital environments and mitigating the adverse efcts of cyberbullying.This underscores the importance of developing advanced tools and systems to identify and address such behavior efectively.This paper investigates the development of a robust cyberbullying detection and classifcation system tailored for Arabic comments on YouTube.The study explores the efectiveness of various deep learning models,including Bi-LSTM(Bidirectional Long Short Term Memory),LSTM(Long Short-Term Memory),CNN(Convolutional Neural Networks),and a hybrid CNN-LSTM,in classifying Arabic comments into binary classes(bullying or not)and multiclass categories.A comprehensive dataset of 20,000 Arabic YouTube comments was collected,preprocessed,and labeled to support these tasks.The results revealed that the CNN and hybrid CNN-LSTM models achieved the highest accuracy in binary classification,reaching an impressive 91.9%.For multiclass dlassification,the LSTM and Bi-LSTM models outperformed others,achieving an accuracy of 89.5%.These findings highlight the efctiveness of deep learning approaches in the mitigation of cyberbullying within Arabic online communities.
文摘Physiological signals such as electroencephalogram(EEG)signals are often corrupted by artifacts during the acquisition and processing.Some of these artifacts may deteriorate the essential properties of the signal that pertains to meaningful information.Most of these artifacts occur due to the involuntary movements or actions the human does during the acquisition process.So,it is recommended to eliminate these artifacts with signal processing approaches.This paper presents two mechanisms of classification and elimination of artifacts.In the first step,a customized deep network is employed to classify clean EEG signals and artifact-included signals.The classification is performed at the feature level,where common space pattern features are extracted with convolutional layers,and these features are later classified with a support vector machine classifier.In the second stage of the work,the artifact signals are decomposed with empirical mode decomposition,and they are then eliminated with the proposed adaptive thresholding mechanism where the threshold value changes for every intrinsic mode decomposition in the iterative mechanism.
基金supported in part by Vietnam National Foundation for Science and Technology Development(NAFOSTED)under Grant 102.04-2021.57in part by Culture,Sports and Tourism R&D Program through the Korea Creative Content Agency grant funded by the Ministry of Culture,Sports and Tourism in 2024(Project Name:Global Talent Training Program for Copyright Management Technology in Game Contents,Project Number:RS-2024-00396709,Contribution Rate:100%).
文摘Digital content such as games,extended reality(XR),and movies has been widely and easily distributed over wireless networks.As a result,unauthorized access,copyright infringement by third parties or eavesdroppers,and cyberattacks over these networks have become pressing concerns.Therefore,protecting copyrighted content and preventing illegal distribution in wireless communications has garnered significant attention.The Intelligent Reflecting Surface(IRS)is regarded as a promising technology for future wireless and mobile networks due to its ability to reconfigure the radio propagation environment.This study investigates the security performance of an uplink Non-Orthogonal Multiple Access(NOMA)system integrated with an IRS and employing Fountain Codes(FCs).Specifically,two users send signals to the base station at separate distances.A relay receives the signal from the nearby user first and then relays it to the base station.The IRS receives the signal from the distant user and reflects it to the relay,which then sends the reflected signal to the base station.Furthermore,a malevolent eavesdropper intercepts both user and relay communications.We construct mathematical equations for Outage Probability(OP),throughput,diversity evaluation,and Interception Probability(IP),offering quantitative insights to assess system security and performance.Additionally,OP and IP are analyzed using a Deep Neural Network(DNN)model.A deeper comprehension of the security performance of the IRS-assisted NOMA systemin signal transmission is provided by Monte Carlo simulations,which are also carried out to confirm the theoretical conclusions.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Funding Program,Grant No.(FRP-1443-15).
文摘The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.
文摘The Wireless Sensor Networks(WSN)are vulnerable to assaults due to the fact that the devices connected to them have a reliable connection to the inter-net.A malicious node acts as the controller and uses a grey hole attack to get the data from all of the other nodes in the network.Additionally,the nodes are dis-carding and modifying the data packets according to the requirements of the sys-tem.The assault modifies the fundamental concept of the WSNs,which is that different devices should communicate with one another.In the proposed system,there is a fuzzy idea offered for the purpose of preventing the grey hole attack from making effective communication among the WSN devices.The currently available model is unable to recognise the myriad of different kinds of attacks.The fuzzy engine identified suspicious actions by utilising the rules that were gen-erated to make a prediction about the malicious node that would halt the process.Experiments conducted using simulation are used to determine delay,accuracy,energy consumption,throughput,and the ratio of packets successfully delivered.It stands in contrast to the model that was suggested,as well as the methodologies that are currently being used,and analogue behavioural modelling.In comparison to the existing method,the proposed model achieves an accuracy rate of 45 per-cent,a packet delivery ratio of 79 percent,and a reduction in energy usage of around 35.6 percent.These results from the simulation demonstrate that the fuzzy grey detection technique that was presented has the potential to increase the net-work’s capability of detecting grey hole assaults.
基金co-supported by the Key Programs of the Chinese Academy of Sciences (No. ZDRW-KT-2016-2)the National High-tech Research and Development Program of China (No. 2015AA7013040)
文摘In the ‘‘Internet Plus" era, space-based information services require effective and fast image satellite scheduling. Most existing studies consider image satellite scheduling to be an optimization problem to solve with searching algorithms in a batch-wise manner. No real-time speed method for satellite scheduling exists. In this paper, with the idea of building a real-time speed method, satellite scheduling is remodeled based on a Dynamic and Stochastic Knapsack Problem(DSKP), and the objective is to maximize the total expected profit. No existing algorithm could be able to solve this novel scheduling problem properly. With inspiration from the recent achievements in Deep Reinforcement Learning(DRL) in video games, AlphaGo and dynamic controlling,a novel DRL-based method is applied to training a neural network to schedule tasks. The numerical results show that the method proposed in this paper can achieve relatively good performance with real-time speed and immediate respond style.
基金supported by the Center for Brains,Minds and Machines(CBMM),NSF STC award CCF(No.1231216),and ARO(No W911NF-15-1-0385)
文摘The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.
