Explainable Artificial Intelligence(XAI)has an advanced feature to enhance the decision-making feature and improve the rule-based technique by using more advanced Machine Learning(ML)and Deep Learning(DL)based algorit...Explainable Artificial Intelligence(XAI)has an advanced feature to enhance the decision-making feature and improve the rule-based technique by using more advanced Machine Learning(ML)and Deep Learning(DL)based algorithms.In this paper,we chose e-healthcare systems for efficient decision-making and data classification,especially in data security,data handling,diagnostics,laboratories,and decision-making.Federated Machine Learning(FML)is a new and advanced technology that helps to maintain privacy for Personal Health Records(PHR)and handle a large amount of medical data effectively.In this context,XAI,along with FML,increases efficiency and improves the security of e-healthcare systems.The experiments show efficient system performance by implementing a federated averaging algorithm on an open-source Federated Learning(FL)platform.The experimental evaluation demonstrates the accuracy rate by taking epochs size 5,batch size 16,and the number of clients 5,which shows a higher accuracy rate(19,104).We conclude the paper by discussing the existing gaps and future work in an e-healthcare system.展开更多
BACKGROUND Nutritional support for patients hospitalized in the intensive care unit(ICU)is an important part of clinical treatment and care,but there are significant implementation difficulties.AIM To introduce a modi...BACKGROUND Nutritional support for patients hospitalized in the intensive care unit(ICU)is an important part of clinical treatment and care,but there are significant implementation difficulties.AIM To introduce a modified nutritional support management system for ICU patients based on closed-loop information management and psychological counseling.METHODS The division of functions,personnel training,system construction,development of an intelligent decision-making software system,quality control,and improvement of the whole process were carried out to systematically manage nutritional support for ICU patients.RESULTS Following the implementation of the whole process management system,the scores of ICU medical staff’s knowledge,attitudes/beliefs,and practices regarding nutritional support were comprehensively enhanced.The proportion of hospital bed-days of total enteral nutrition(EN)in ICU patients increased from 5.58%to 11.46%,and the proportion of EN plus parenteral nutrition increased from 42.71%to 47.07%.The rate of EN initiation within 48 h of ICU admission increased from 37.50%to 48.28%,and the EN compliance rate within 72 h elevated from 20.59%to 31.72%.After the implementation of the project,the Self-rating Anxiety Scale score decreased from 61.07±9.91 points to 52.03±9.02 points,the Self-rating Depression Scale score reduced from 62.47±10.50 points to 56.34±9.83 points,and the ICU stay decreased from 5.76±2.77 d to 5.10±2.12 d.CONCLUSION The nutritional support management system based on closed-loop information management and psychological counseling achieved remarkable results in clinical applications in ICU patients.展开更多
Rapid increase in the large quantity of industrial data,Industry 4.0/5.0 poses several challenging issues such as heterogeneous data generation,data sensing and collection,real-time data processing,and high request ar...Rapid increase in the large quantity of industrial data,Industry 4.0/5.0 poses several challenging issues such as heterogeneous data generation,data sensing and collection,real-time data processing,and high request arrival rates.The classical intrusion detection system(IDS)is not a practical solution to the Industry 4.0 environment owing to the resource limitations and complexity.To resolve these issues,this paper designs a new Chaotic Cuckoo Search Optimiza-tion Algorithm(CCSOA)with optimal wavelet kernel extreme learning machine(OWKELM)named CCSOA-OWKELM technique for IDS on the Industry 4.0 platform.The CCSOA-OWKELM technique focuses on the design of feature selection with classification approach to achieve minimum computation complex-ity and maximum detection accuracy.The CCSOA-OWKELM technique involves the design of CCSOA based feature selection technique,which incorpo-rates the concepts of chaotic maps with CSOA.Besides,the OWKELM technique is applied for the intrusion detection and classification process.In addition,the OWKELM technique is derived by the hyperparameter tuning of the WKELM technique by the use of sunflower optimization(SFO)algorithm.The utilization of CCSOA for feature subset selection and SFO algorithm based hyperparameter tuning leads to better performance.In order to guarantee the supreme performance of the CCSOA-OWKELM technique,a wide range of experiments take place on two benchmark datasets and the experimental outcomes demonstrate the promis-ing performance of the CCSOA-OWKELM technique over the recent state of art techniques.展开更多
In the context of both the Virtual Power Plant (VPP) and microgrid(MG), the Energy Management System (EMS) is a key decision-maker forintegrating Distributed renewable Energy Resources (DERs) efficiently. TheEMS is re...In the context of both the Virtual Power Plant (VPP) and microgrid(MG), the Energy Management System (EMS) is a key decision-maker forintegrating Distributed renewable Energy Resources (DERs) efficiently. TheEMS is regarded as a strong enabler of providing the optimized schedulingcontrol in operation and management of usage of disperse DERs and RenewableEnergy reSources (RES) such as a small-size wind-turbine (WT) andphotovoltaic (PV) energies. The main objective to be pursued by the EMSis the minimization of the overall operating cost of the MG integrated VPPnetwork. However, the minimization of the power peaks is a new objective andopen issue to a well-functional EMS, along with the maximization of profitin the energy market. Thus, both objectives have to be taken into accountat the same time. Thus, this paper proposes the EMS application incorporatingpower offering strategy applying a nature-inspired algorithm such asParticle Swarm Optimization (PSO) algorithm, in order to find the optimalsolution of the objective function in the context of the overall operating cost,the coordination of DERs, and the energy losses in a MG integrated VPPnetwork. For a fair DERs coordination with minimized power fluctuationsin the power flow, the power offering strategies with an active power controland re-distribution are proposed. Simulation results show that the proposedMG integrated VPP model with PSO-based EMS employing EgalitarianreDistribution (ED) power offering strategy is most feasible option for theoverall operating cost of VPP revenue. The total operating cost of the proposedEMS with ED strategy is 40.98$ compared to 432.8$ of MGs only withoutEMS. It is concluded that each MGs in the proposed VPP model intelligentlyparticipates in energy trading market compliant with the objective function,to minimize the overall cost and the power fluctuation.展开更多
Recently,researchers have shown increasing interest in combining more than one programming model into systems running on high performance computing systems(HPCs)to achieve exascale by applying parallelism at multiple ...Recently,researchers have shown increasing interest in combining more than one programming model into systems running on high performance computing systems(HPCs)to achieve exascale by applying parallelism at multiple levels.Combining different programming paradigms,such as Message Passing Interface(MPI),Open Multiple Processing(OpenMP),and Open Accelerators(OpenACC),can increase computation speed and improve performance.During the integration of multiple models,the probability of runtime errors increases,making their detection difficult,especially in the absence of testing techniques that can detect these errors.Numerous studies have been conducted to identify these errors,but no technique exists for detecting errors in three-level programming models.Despite the increasing research that integrates the three programming models,MPI,OpenMP,and OpenACC,a testing technology to detect runtime errors,such as deadlocks and race conditions,which can arise from this integration has not been developed.Therefore,this paper begins with a definition and explanation of runtime errors that result fromintegrating the three programming models that compilers cannot detect.For the first time,this paper presents a classification of operational errors that can result from the integration of the three models.This paper also proposes a parallel hybrid testing technique for detecting runtime errors in systems built in the C++programming language that uses the triple programming models MPI,OpenMP,and OpenACC.This hybrid technology combines static technology and dynamic technology,given that some errors can be detected using static techniques,whereas others can be detected using dynamic technology.The hybrid technique can detect more errors because it combines two distinct technologies.The proposed static technology detects a wide range of error types in less time,whereas a portion of the potential errors that may or may not occur depending on the 4502 CMC,2023,vol.74,no.2 operating environment are left to the dynamic technology,which completes the validation.展开更多
Vehicle-to-grid technology is an emerging field that allows unused power from Electric Vehicles(EVs)to be used by the smart grid through the central aggregator.Since the central aggregator is connected to the smart gr...Vehicle-to-grid technology is an emerging field that allows unused power from Electric Vehicles(EVs)to be used by the smart grid through the central aggregator.Since the central aggregator is connected to the smart grid through a wireless network,it is prone to cyber-attacks that can be detected and mitigated using an intrusion detection system.However,existing intrusion detection systems cannot be used in the vehicle-to-grid network because of the special requirements and characteristics of the vehicle-to-grid network.In this paper,the effect of denial-of-service attacks of malicious electric vehicles on the central aggregator of the vehicle-to-grid network is investigated and an intrusion detection system for the vehicle-to-grid network is proposed.The proposed system,central aggregator–intrusion detection system(CA-IDS),works as a security gateway for EVs to analyze andmonitor incoming traffic for possible DoS attacks.EVs are registered with a Central Aggregator(CAG)to exchange authenticated messages,and malicious EVs are added to a blacklist for violating a set of predefined policies to limit their interaction with the CAG.A denial of service(DoS)attack is simulated at CAG in a vehicle-to-grid(V2G)network manipulating various network parameters such as transmission overhead,receiving capacity of destination,average packet size,and channel availability.The proposed system is compared with existing intrusion detection systems using different parameters such as throughput,jitter,and accuracy.The analysis shows that the proposed system has a higher throughput,lower jitter,and higher accuracy as compared to the existing schemes.展开更多
Biometrics,which has become integrated with our daily lives,could fall prey to falsification attacks,leading to security concerns.In our paper,we use Transient Evoked Otoacoustic Emissions(TEOAE)that are generated by ...Biometrics,which has become integrated with our daily lives,could fall prey to falsification attacks,leading to security concerns.In our paper,we use Transient Evoked Otoacoustic Emissions(TEOAE)that are generated by the human cochlea in response to an external sound stimulus,as a biometric modality.TEOAE are robust to falsification attacks,as the uniqueness of an individual’s inner ear cannot be impersonated.In this study,we use both the raw 1D TEOAE signals,as well as the 2D time-frequency representation of the signal using Continuous Wavelet Transform(CWT).We use 1D and 2D Convolutional Neural Networks(CNN)for the former and latter,respectively,to derive the feature maps.The corresponding lower-dimensional feature maps are obtained using principal component analysis,which is then used as features to build classifiers using machine learning techniques for the task of person identification.T-SNE plots of these feature maps show that they discriminate well among the subjects.Among the various architectures explored,we achieve a best-performing accuracy of 98.95%and 100%using the feature maps of the 1D-CNN and 2D-CNN,respectively,with the latter performance being an improvement over all the earlier works.This performance makes the TEOAE based person identification systems deployable in real-world situations,along with the added advantage of robustness to falsification attacks.展开更多
Image encryption has attracted much interest as a robust security solution for preventing unauthorized access to critical image data.Medical picture encryption is a crucial step in many cloud-based and healthcare appl...Image encryption has attracted much interest as a robust security solution for preventing unauthorized access to critical image data.Medical picture encryption is a crucial step in many cloud-based and healthcare applications.In this study,a strong cryptosystem based on a 2D chaotic map and Jigsaw transformation is presented for the encryption of medical photos in private Internet of Medical Things(IoMT)and cloud storage.A disorganized three-dimensional map is the foundation of the proposed cipher.The dispersion of pixel values and the permutation of their places in this map are accomplished using a nonlinear encoding process.The suggested cryptosystem enhances the security of the delivered medical images by performing many operations.To validate the efficiency of the recommended cryptosystem,various medical image kinds are used,each with its unique characteristics.Several measures are used to evaluate the proposed cryptosystem,which all support its robust security.The simulation results confirm the supplied cryptosystem’s secrecy.Furthermore,it provides strong robustness and suggested protection standards for cloud service applications,healthcare,and IoMT.It is seen that the proposed 3D chaotic cryptosystem obtains an average entropy of 7.9998,which is near its most excellent value of 8,and a typical NPCR value of 99.62%,which is also near its extreme value of 99.60%.Moreover,the recommended cryptosystem outperforms conventional security systems across the test assessment criteria.展开更多
The present study suggests that series voltage injection is more effective than parallel current injection to improve voltage quality on the load side.The line voltage can be accurately symmetrized at the connection p...The present study suggests that series voltage injection is more effective than parallel current injection to improve voltage quality on the load side.The line voltage can be accurately symmetrized at the connection point by creating and controlling a series voltage component in each phase.This is more reliable and effective than parallel current injection.A dynamic voltage restorer(DVR)and a distribution static synchronous compensator(DSTATCOM)were utilized to provide the required power.The DVR is an effective andmodern device utilized in parallel within the grid and can protect sensitive loads from voltage problems in the grid by injecting voltage.The DVR and D-STATCOM were used to improve voltage stability in faults.A standard 13-bus system was studied in the presence of a wind farm.The simulation results demonstrated that single and three-phase overloads dramatically altered the voltage of the system,making it necessary to use compensators to improve voltage stability.The DVR and D-STATCOM showed similar performance under normal conditions and somewhat improved grid voltage unbalance.However,the DVR outperformed D-STATCOM under asymmetric faults conditions and led to lower voltage variations.展开更多
Biometric security is a growing trend,as it supports the authentication of persons using confidential biometric data.Most of the transmitted data in multi-media systems are susceptible to attacks,which affect the secur...Biometric security is a growing trend,as it supports the authentication of persons using confidential biometric data.Most of the transmitted data in multi-media systems are susceptible to attacks,which affect the security of these sys-tems.Biometric systems provide sufficient protection and privacy for users.The recently-introduced cancellable biometric recognition systems have not been investigated in the presence of different types of attacks.In addition,they have not been studied on different and large biometric datasets.Another point that deserves consideration is the hardware implementation of cancellable biometric recognition systems.This paper presents a suggested hybrid cancellable biometric recognition system based on a 3D chaotic cryptosystem.The rationale behind the utilization of the 3D chaotic cryptosystem is to guarantee strong encryption of biometric templates,and hence enhance the security and privacy of users.The suggested cryptosystem adds significant permutation and diffusion to the encrypted biometric templates.We introduce some sort of attack analysis in this paper to prove the robustness of the proposed cryptosystem against attacks.In addition,a Field Programmable Gate Array(FPGA)implementation of the pro-posed system is introduced.The obtained results with the proposed cryptosystem are compared with those of the traditional encryption schemes,such as Double Random Phase Encoding(DRPE)to reveal superiority,and hence high recogni-tion performance of the proposed cancellable biometric recognition system.The obtained results prove that the proposed cryptosystem enhances the security and leads to better efficiency of the cancellable biometric recognition system in the presence of different types of attacks.展开更多
A comprehensive understanding of human intelligence is still an ongoing process,i.e.,human and information security are not yet perfectly matched.By understanding cognitive processes,designers can design humanized cog...A comprehensive understanding of human intelligence is still an ongoing process,i.e.,human and information security are not yet perfectly matched.By understanding cognitive processes,designers can design humanized cognitive information systems(CIS).The need for this research is justified because today’s business decision makers are faced with questions they cannot answer in a given amount of time without the use of cognitive information systems.The researchers aim to better strengthen cognitive information systems with more pronounced cognitive thresholds by demonstrating the resilience of cognitive resonant frequencies to reveal possible responses to improve the efficiency of human-computer interaction(HCI).Apractice-oriented research approach included research analysis and a review of existing articles to pursue a comparative research model;thereafter,amodel development paradigm was used to observe and monitor the progression of CIS during HCI.The scope of our research provides a broader perspective on how different disciplines affect HCI and how human cognitive models can be enhanced to enrich complements.We have identified a significant gap in the current literature on mental processing resulting from a wide range of theory and practice.展开更多
To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to imp...To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to improve its information management and increase the availability of accurate, real-time data for disaster and humanitarian response teams, significant gaps persist. There are inefficiencies in the emergency management of data at every stage of its lifecycle: collection, processing, analysis, distribution, storage, and retrieval. Disaster risk reduction and disaster risk management are the two main tenets of the United Nations’ worldwide plan for disaster management. Information systems are crucial because of the crucial roles they play in capturing, processing, and transmitting data. The management of information is seldom discussed in published works. The goal of this study is to employ qualitative research methods to provide insight by facilitating an expanded comprehension of relevant contexts, phenomena, and individual experiences. Humanitarian workers and OCHA staffers will take part in the research. The study subjects will be chosen using a random selection procedure. Online surveys with both closed- and open-ended questions will be used to compile the data. UN OCHA offers a structure for the handling of information via which all humanitarian actors may contribute to the overall response. This research will enable the UN Office for OCHA better gather, process, analyze, disseminate, store, and retrieve data in the event of a catastrophe or humanitarian crisis.展开更多
Vocational education can effectively improve the vocational skills of employees,improve people’s traditional concept of vocational education,and focus on the training of vocational skills for students by using new ed...Vocational education can effectively improve the vocational skills of employees,improve people’s traditional concept of vocational education,and focus on the training of vocational skills for students by using new educational methods and concepts,so that they can master key vocational skills and develop key abilities.In this paper,three different learning models,Deep Knowledge Tracing(DKT),Dynamic Key-Value Memory Networks(DKVMN)and Double Deep Q-network(DDQN),are used to evaluate the indicators in the vocational education system.On the one hand,the influence of learning degree on the performance of the model is compared,on the other hand,the performance evaluation of three models under the same learning effect is compared,so as to obtain the best learning model applied to the field of skill training.In order to accurately evaluate the learning status of students,the loss function curves under three models are compared.Finally,the error rate of students in vocational skills education tends to be zero,and the learning process of intensive learning effectively improves students’mastery of skills and key abilities.展开更多
Image steganography is a technique of concealing confidential information within an image without dramatically changing its outside look.Whereas vehicular ad hoc networks(VANETs),which enable vehicles to communicate w...Image steganography is a technique of concealing confidential information within an image without dramatically changing its outside look.Whereas vehicular ad hoc networks(VANETs),which enable vehicles to communicate with one another and with roadside infrastructure to enhance safety and traffic flow provide a range of value-added services,as they are an essential component of modern smart transportation systems.VANETs steganography has been suggested by many authors for secure,reliable message transfer between terminal/hope to terminal/hope and also to secure it from attack for privacy protection.This paper aims to determine whether using steganography is possible to improve data security and secrecy in VANET applications and to analyze effective steganography techniques for incorporating data into images while minimizing visual quality loss.According to simulations in literature and real-world studies,Image steganography proved to be an effectivemethod for secure communication on VANETs,even in difficult network conditions.In this research,we also explore a variety of steganography approaches for vehicular ad-hoc network transportation systems like vector embedding,statistics,spatial domain(SD),transform domain(TD),distortion,masking,and filtering.This study possibly shall help researchers to improve vehicle networks’ability to communicate securely and lay the door for innovative steganography methods.展开更多
Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep lear...Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.展开更多
BACKGROUND Radiomics is a promising tool that may increase the value of magnetic resonance imaging(MRI)for different tasks related to the management of patients with hepatocellular carcinoma(HCC).However,its implement...BACKGROUND Radiomics is a promising tool that may increase the value of magnetic resonance imaging(MRI)for different tasks related to the management of patients with hepatocellular carcinoma(HCC).However,its implementation in clinical practice is still far,with many issues related to the methodological quality of radiomic studies.AIM To systematically review the current status of MRI radiomic studies concerning HCC using the Radiomics Quality Score(RQS).METHODS A systematic literature search of PubMed,Google Scholar,and Web of Science databases was performed to identify original articles focusing on the use of MRI radiomics for HCC management published between 2017 and 2023.The methodological quality of radiomic studies was assessed using the RQS tool.Spearman’s correlation(ρ)analysis was performed to explore if RQS was correlated with journal metrics and characteristics of the studies.The level of statistical significance was set at P<0.05.RESULTS One hundred and twenty-seven articles were included,of which 43 focused on HCC prognosis,39 on prediction of pathological findings,16 on prediction of the expression of molecular markers outcomes,18 had a diagnostic purpose,and 11 had multiple purposes.The mean RQS was 8±6.22,and the corresponding percentage was 24.15%±15.25%(ranging from 0.0% to 58.33%).RQS was positively correlated with journal impact factor(IF;ρ=0.36,P=2.98×10^(-5)),5-years IF(ρ=0.33,P=1.56×10^(-4)),number of patients included in the study(ρ=0.51,P<9.37×10^(-10))and number of radiomics features extracted in the study(ρ=0.59,P<4.59×10^(-13)),and time of publication(ρ=-0.23,P<0.0072).CONCLUSION Although MRI radiomics in HCC represents a promising tool to develop adequate personalized treatment as a noninvasive approach in HCC patients,our study revealed that studies in this field still lack the quality required to allow its introduction into clinical practice.展开更多
Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wa...Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.展开更多
The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and...The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and access information.Among the many smartphones available,those operating on the Android platform dominate,being the most widely used type.This widespread adoption of the Android OS has significantly contributed to increased malware attacks targeting the Android ecosystem in recent years.Therefore,there is an urgent need to develop new methods for detecting Android malware.The literature contains numerous works related to Android malware detection.As far as our understanding extends,we are the first ones to identify dangerous combinations of permissions and system calls to uncover malicious behavior in Android applications.We introduce a novel methodology that pairs permissions and system calls to distinguish between benign and malicious samples.This approach combines the advantages of static and dynamic analysis,offering a more comprehensive understanding of an application’s behavior.We establish covalent bonds between permissions and system calls to assess their combined impact.We introduce a novel technique to determine these pairs’Covalent Bond Strength Score.Each pair is assigned two scores,one for malicious behavior and another for benign behavior.These scores serve as the basis for classifying applications as benign or malicious.By correlating permissions with system calls,the study enables a detailed examination of how an app utilizes its requested permissions,aiding in differentiating legitimate and potentially harmful actions.This comprehensive analysis provides a robust framework for Android malware detection,marking a significant contribution to the field.The results of our experiments demonstrate a remarkable overall accuracy of 97.5%,surpassing various state-of-the-art detection techniques proposed in the current literature.展开更多
Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,w...Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.展开更多
Social media(SM)based surveillance systems,combined with machine learning(ML)and deep learning(DL)techniques,have shown potential for early detection of epidemic outbreaks.This review discusses the current state of SM...Social media(SM)based surveillance systems,combined with machine learning(ML)and deep learning(DL)techniques,have shown potential for early detection of epidemic outbreaks.This review discusses the current state of SM-based surveillance methods for early epidemic outbreaks and the role of ML and DL in enhancing their performance.Since,every year,a large amount of data related to epidemic outbreaks,particularly Twitter data is generated by SM.This paper outlines the theme of SM analysis for tracking health-related issues and detecting epidemic outbreaks in SM,along with the ML and DL techniques that have been configured for the detection of epidemic outbreaks.DL has emerged as a promising ML technique that adaptsmultiple layers of representations or features of the data and yields state-of-the-art extrapolation results.In recent years,along with the success of ML and DL in many other application domains,both ML and DL are also popularly used in SM analysis.This paper aims to provide an overview of epidemic outbreaks in SM and then outlines a comprehensive analysis of ML and DL approaches and their existing applications in SM analysis.Finally,this review serves the purpose of offering suggestions,ideas,and proposals,along with highlighting the ongoing challenges in the field of early outbreak detection that still need to be addressed.展开更多
文摘Explainable Artificial Intelligence(XAI)has an advanced feature to enhance the decision-making feature and improve the rule-based technique by using more advanced Machine Learning(ML)and Deep Learning(DL)based algorithms.In this paper,we chose e-healthcare systems for efficient decision-making and data classification,especially in data security,data handling,diagnostics,laboratories,and decision-making.Federated Machine Learning(FML)is a new and advanced technology that helps to maintain privacy for Personal Health Records(PHR)and handle a large amount of medical data effectively.In this context,XAI,along with FML,increases efficiency and improves the security of e-healthcare systems.The experiments show efficient system performance by implementing a federated averaging algorithm on an open-source Federated Learning(FL)platform.The experimental evaluation demonstrates the accuracy rate by taking epochs size 5,batch size 16,and the number of clients 5,which shows a higher accuracy rate(19,104).We conclude the paper by discussing the existing gaps and future work in an e-healthcare system.
基金Supported by Research Project of Zhejiang Provincial Department of Education,No.Y202045115.
文摘BACKGROUND Nutritional support for patients hospitalized in the intensive care unit(ICU)is an important part of clinical treatment and care,but there are significant implementation difficulties.AIM To introduce a modified nutritional support management system for ICU patients based on closed-loop information management and psychological counseling.METHODS The division of functions,personnel training,system construction,development of an intelligent decision-making software system,quality control,and improvement of the whole process were carried out to systematically manage nutritional support for ICU patients.RESULTS Following the implementation of the whole process management system,the scores of ICU medical staff’s knowledge,attitudes/beliefs,and practices regarding nutritional support were comprehensively enhanced.The proportion of hospital bed-days of total enteral nutrition(EN)in ICU patients increased from 5.58%to 11.46%,and the proportion of EN plus parenteral nutrition increased from 42.71%to 47.07%.The rate of EN initiation within 48 h of ICU admission increased from 37.50%to 48.28%,and the EN compliance rate within 72 h elevated from 20.59%to 31.72%.After the implementation of the project,the Self-rating Anxiety Scale score decreased from 61.07±9.91 points to 52.03±9.02 points,the Self-rating Depression Scale score reduced from 62.47±10.50 points to 56.34±9.83 points,and the ICU stay decreased from 5.76±2.77 d to 5.10±2.12 d.CONCLUSION The nutritional support management system based on closed-loop information management and psychological counseling achieved remarkable results in clinical applications in ICU patients.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under grant number(RGP1/338/40)Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R237)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Rapid increase in the large quantity of industrial data,Industry 4.0/5.0 poses several challenging issues such as heterogeneous data generation,data sensing and collection,real-time data processing,and high request arrival rates.The classical intrusion detection system(IDS)is not a practical solution to the Industry 4.0 environment owing to the resource limitations and complexity.To resolve these issues,this paper designs a new Chaotic Cuckoo Search Optimiza-tion Algorithm(CCSOA)with optimal wavelet kernel extreme learning machine(OWKELM)named CCSOA-OWKELM technique for IDS on the Industry 4.0 platform.The CCSOA-OWKELM technique focuses on the design of feature selection with classification approach to achieve minimum computation complex-ity and maximum detection accuracy.The CCSOA-OWKELM technique involves the design of CCSOA based feature selection technique,which incorpo-rates the concepts of chaotic maps with CSOA.Besides,the OWKELM technique is applied for the intrusion detection and classification process.In addition,the OWKELM technique is derived by the hyperparameter tuning of the WKELM technique by the use of sunflower optimization(SFO)algorithm.The utilization of CCSOA for feature subset selection and SFO algorithm based hyperparameter tuning leads to better performance.In order to guarantee the supreme performance of the CCSOA-OWKELM technique,a wide range of experiments take place on two benchmark datasets and the experimental outcomes demonstrate the promis-ing performance of the CCSOA-OWKELM technique over the recent state of art techniques.
文摘In the context of both the Virtual Power Plant (VPP) and microgrid(MG), the Energy Management System (EMS) is a key decision-maker forintegrating Distributed renewable Energy Resources (DERs) efficiently. TheEMS is regarded as a strong enabler of providing the optimized schedulingcontrol in operation and management of usage of disperse DERs and RenewableEnergy reSources (RES) such as a small-size wind-turbine (WT) andphotovoltaic (PV) energies. The main objective to be pursued by the EMSis the minimization of the overall operating cost of the MG integrated VPPnetwork. However, the minimization of the power peaks is a new objective andopen issue to a well-functional EMS, along with the maximization of profitin the energy market. Thus, both objectives have to be taken into accountat the same time. Thus, this paper proposes the EMS application incorporatingpower offering strategy applying a nature-inspired algorithm such asParticle Swarm Optimization (PSO) algorithm, in order to find the optimalsolution of the objective function in the context of the overall operating cost,the coordination of DERs, and the energy losses in a MG integrated VPPnetwork. For a fair DERs coordination with minimized power fluctuationsin the power flow, the power offering strategies with an active power controland re-distribution are proposed. Simulation results show that the proposedMG integrated VPP model with PSO-based EMS employing EgalitarianreDistribution (ED) power offering strategy is most feasible option for theoverall operating cost of VPP revenue. The total operating cost of the proposedEMS with ED strategy is 40.98$ compared to 432.8$ of MGs only withoutEMS. It is concluded that each MGs in the proposed VPP model intelligentlyparticipates in energy trading market compliant with the objective function,to minimize the overall cost and the power fluctuation.
基金[King Abdulaziz University][Deanship of Scientific Research]Grant Number[KEP-PHD-20-611-42].
文摘Recently,researchers have shown increasing interest in combining more than one programming model into systems running on high performance computing systems(HPCs)to achieve exascale by applying parallelism at multiple levels.Combining different programming paradigms,such as Message Passing Interface(MPI),Open Multiple Processing(OpenMP),and Open Accelerators(OpenACC),can increase computation speed and improve performance.During the integration of multiple models,the probability of runtime errors increases,making their detection difficult,especially in the absence of testing techniques that can detect these errors.Numerous studies have been conducted to identify these errors,but no technique exists for detecting errors in three-level programming models.Despite the increasing research that integrates the three programming models,MPI,OpenMP,and OpenACC,a testing technology to detect runtime errors,such as deadlocks and race conditions,which can arise from this integration has not been developed.Therefore,this paper begins with a definition and explanation of runtime errors that result fromintegrating the three programming models that compilers cannot detect.For the first time,this paper presents a classification of operational errors that can result from the integration of the three models.This paper also proposes a parallel hybrid testing technique for detecting runtime errors in systems built in the C++programming language that uses the triple programming models MPI,OpenMP,and OpenACC.This hybrid technology combines static technology and dynamic technology,given that some errors can be detected using static techniques,whereas others can be detected using dynamic technology.The hybrid technique can detect more errors because it combines two distinct technologies.The proposed static technology detects a wide range of error types in less time,whereas a portion of the potential errors that may or may not occur depending on the 4502 CMC,2023,vol.74,no.2 operating environment are left to the dynamic technology,which completes the validation.
基金Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2021R1A6A1A03039493).
文摘Vehicle-to-grid technology is an emerging field that allows unused power from Electric Vehicles(EVs)to be used by the smart grid through the central aggregator.Since the central aggregator is connected to the smart grid through a wireless network,it is prone to cyber-attacks that can be detected and mitigated using an intrusion detection system.However,existing intrusion detection systems cannot be used in the vehicle-to-grid network because of the special requirements and characteristics of the vehicle-to-grid network.In this paper,the effect of denial-of-service attacks of malicious electric vehicles on the central aggregator of the vehicle-to-grid network is investigated and an intrusion detection system for the vehicle-to-grid network is proposed.The proposed system,central aggregator–intrusion detection system(CA-IDS),works as a security gateway for EVs to analyze andmonitor incoming traffic for possible DoS attacks.EVs are registered with a Central Aggregator(CAG)to exchange authenticated messages,and malicious EVs are added to a blacklist for violating a set of predefined policies to limit their interaction with the CAG.A denial of service(DoS)attack is simulated at CAG in a vehicle-to-grid(V2G)network manipulating various network parameters such as transmission overhead,receiving capacity of destination,average packet size,and channel availability.The proposed system is compared with existing intrusion detection systems using different parameters such as throughput,jitter,and accuracy.The analysis shows that the proposed system has a higher throughput,lower jitter,and higher accuracy as compared to the existing schemes.
基金The authors would like to thank the Biometrics Security Laboratory of the University of Toronto for providing the Transient Evoked Otoacoustic Emissions(TEOAE)dataset.
文摘Biometrics,which has become integrated with our daily lives,could fall prey to falsification attacks,leading to security concerns.In our paper,we use Transient Evoked Otoacoustic Emissions(TEOAE)that are generated by the human cochlea in response to an external sound stimulus,as a biometric modality.TEOAE are robust to falsification attacks,as the uniqueness of an individual’s inner ear cannot be impersonated.In this study,we use both the raw 1D TEOAE signals,as well as the 2D time-frequency representation of the signal using Continuous Wavelet Transform(CWT).We use 1D and 2D Convolutional Neural Networks(CNN)for the former and latter,respectively,to derive the feature maps.The corresponding lower-dimensional feature maps are obtained using principal component analysis,which is then used as features to build classifiers using machine learning techniques for the task of person identification.T-SNE plots of these feature maps show that they discriminate well among the subjects.Among the various architectures explored,we achieve a best-performing accuracy of 98.95%and 100%using the feature maps of the 1D-CNN and 2D-CNN,respectively,with the latter performance being an improvement over all the earlier works.This performance makes the TEOAE based person identification systems deployable in real-world situations,along with the added advantage of robustness to falsification attacks.
基金The authors are thankful to the Deanship of Scientific Research at Najran University for funding this work under the Research Groups Funding program grant code(NU/RC/SERC/11/5).
文摘Image encryption has attracted much interest as a robust security solution for preventing unauthorized access to critical image data.Medical picture encryption is a crucial step in many cloud-based and healthcare applications.In this study,a strong cryptosystem based on a 2D chaotic map and Jigsaw transformation is presented for the encryption of medical photos in private Internet of Medical Things(IoMT)and cloud storage.A disorganized three-dimensional map is the foundation of the proposed cipher.The dispersion of pixel values and the permutation of their places in this map are accomplished using a nonlinear encoding process.The suggested cryptosystem enhances the security of the delivered medical images by performing many operations.To validate the efficiency of the recommended cryptosystem,various medical image kinds are used,each with its unique characteristics.Several measures are used to evaluate the proposed cryptosystem,which all support its robust security.The simulation results confirm the supplied cryptosystem’s secrecy.Furthermore,it provides strong robustness and suggested protection standards for cloud service applications,healthcare,and IoMT.It is seen that the proposed 3D chaotic cryptosystem obtains an average entropy of 7.9998,which is near its most excellent value of 8,and a typical NPCR value of 99.62%,which is also near its extreme value of 99.60%.Moreover,the recommended cryptosystem outperforms conventional security systems across the test assessment criteria.
基金International Research Partnership“Electrical Engineering-Thai French Research Center(EE-TFRC)”under the project framework of the Lorraine Universitéd’Excellence(LUE)in cooperation between Universitéde Lorraine and King Mongkut’s University of Technology North Bangkok and in part by the National Research Council of Thailand(NRCT)under Senior Research Scholar Program under Grant No.N42A640328National Science,Research and Innovation Fund(NSRF)under King Mongkut’s University of Technology North Bangkok under Grant No.KMUTNB-FF-65-20.
文摘The present study suggests that series voltage injection is more effective than parallel current injection to improve voltage quality on the load side.The line voltage can be accurately symmetrized at the connection point by creating and controlling a series voltage component in each phase.This is more reliable and effective than parallel current injection.A dynamic voltage restorer(DVR)and a distribution static synchronous compensator(DSTATCOM)were utilized to provide the required power.The DVR is an effective andmodern device utilized in parallel within the grid and can protect sensitive loads from voltage problems in the grid by injecting voltage.The DVR and D-STATCOM were used to improve voltage stability in faults.A standard 13-bus system was studied in the presence of a wind farm.The simulation results demonstrated that single and three-phase overloads dramatically altered the voltage of the system,making it necessary to use compensators to improve voltage stability.The DVR and D-STATCOM showed similar performance under normal conditions and somewhat improved grid voltage unbalance.However,the DVR outperformed D-STATCOM under asymmetric faults conditions and led to lower voltage variations.
文摘Biometric security is a growing trend,as it supports the authentication of persons using confidential biometric data.Most of the transmitted data in multi-media systems are susceptible to attacks,which affect the security of these sys-tems.Biometric systems provide sufficient protection and privacy for users.The recently-introduced cancellable biometric recognition systems have not been investigated in the presence of different types of attacks.In addition,they have not been studied on different and large biometric datasets.Another point that deserves consideration is the hardware implementation of cancellable biometric recognition systems.This paper presents a suggested hybrid cancellable biometric recognition system based on a 3D chaotic cryptosystem.The rationale behind the utilization of the 3D chaotic cryptosystem is to guarantee strong encryption of biometric templates,and hence enhance the security and privacy of users.The suggested cryptosystem adds significant permutation and diffusion to the encrypted biometric templates.We introduce some sort of attack analysis in this paper to prove the robustness of the proposed cryptosystem against attacks.In addition,a Field Programmable Gate Array(FPGA)implementation of the pro-posed system is introduced.The obtained results with the proposed cryptosystem are compared with those of the traditional encryption schemes,such as Double Random Phase Encoding(DRPE)to reveal superiority,and hence high recogni-tion performance of the proposed cancellable biometric recognition system.The obtained results prove that the proposed cryptosystem enhances the security and leads to better efficiency of the cancellable biometric recognition system in the presence of different types of attacks.
基金This work was supported by King Saud University through Researchers Supporting Project Number(RSP2022R426),King Saud University,Riyadh,Saudi Arabia.
文摘A comprehensive understanding of human intelligence is still an ongoing process,i.e.,human and information security are not yet perfectly matched.By understanding cognitive processes,designers can design humanized cognitive information systems(CIS).The need for this research is justified because today’s business decision makers are faced with questions they cannot answer in a given amount of time without the use of cognitive information systems.The researchers aim to better strengthen cognitive information systems with more pronounced cognitive thresholds by demonstrating the resilience of cognitive resonant frequencies to reveal possible responses to improve the efficiency of human-computer interaction(HCI).Apractice-oriented research approach included research analysis and a review of existing articles to pursue a comparative research model;thereafter,amodel development paradigm was used to observe and monitor the progression of CIS during HCI.The scope of our research provides a broader perspective on how different disciplines affect HCI and how human cognitive models can be enhanced to enrich complements.We have identified a significant gap in the current literature on mental processing resulting from a wide range of theory and practice.
文摘To guarantee a unified response to disasters, humanitarian organizations work together via the United Nations Office for the Coordination of Humanitarian Affairs (OCHA). Although the OCHA has made great strides to improve its information management and increase the availability of accurate, real-time data for disaster and humanitarian response teams, significant gaps persist. There are inefficiencies in the emergency management of data at every stage of its lifecycle: collection, processing, analysis, distribution, storage, and retrieval. Disaster risk reduction and disaster risk management are the two main tenets of the United Nations’ worldwide plan for disaster management. Information systems are crucial because of the crucial roles they play in capturing, processing, and transmitting data. The management of information is seldom discussed in published works. The goal of this study is to employ qualitative research methods to provide insight by facilitating an expanded comprehension of relevant contexts, phenomena, and individual experiences. Humanitarian workers and OCHA staffers will take part in the research. The study subjects will be chosen using a random selection procedure. Online surveys with both closed- and open-ended questions will be used to compile the data. UN OCHA offers a structure for the handling of information via which all humanitarian actors may contribute to the overall response. This research will enable the UN Office for OCHA better gather, process, analyze, disseminate, store, and retrieve data in the event of a catastrophe or humanitarian crisis.
文摘Vocational education can effectively improve the vocational skills of employees,improve people’s traditional concept of vocational education,and focus on the training of vocational skills for students by using new educational methods and concepts,so that they can master key vocational skills and develop key abilities.In this paper,three different learning models,Deep Knowledge Tracing(DKT),Dynamic Key-Value Memory Networks(DKVMN)and Double Deep Q-network(DDQN),are used to evaluate the indicators in the vocational education system.On the one hand,the influence of learning degree on the performance of the model is compared,on the other hand,the performance evaluation of three models under the same learning effect is compared,so as to obtain the best learning model applied to the field of skill training.In order to accurately evaluate the learning status of students,the loss function curves under three models are compared.Finally,the error rate of students in vocational skills education tends to be zero,and the learning process of intensive learning effectively improves students’mastery of skills and key abilities.
基金Dr.Arshiya Sajid Ansari would like to thank the Deanship of Scientific Research at Majmaah University for supporting this work under Project No.R-2023-910.
文摘Image steganography is a technique of concealing confidential information within an image without dramatically changing its outside look.Whereas vehicular ad hoc networks(VANETs),which enable vehicles to communicate with one another and with roadside infrastructure to enhance safety and traffic flow provide a range of value-added services,as they are an essential component of modern smart transportation systems.VANETs steganography has been suggested by many authors for secure,reliable message transfer between terminal/hope to terminal/hope and also to secure it from attack for privacy protection.This paper aims to determine whether using steganography is possible to improve data security and secrecy in VANET applications and to analyze effective steganography techniques for incorporating data into images while minimizing visual quality loss.According to simulations in literature and real-world studies,Image steganography proved to be an effectivemethod for secure communication on VANETs,even in difficult network conditions.In this research,we also explore a variety of steganography approaches for vehicular ad-hoc network transportation systems like vector embedding,statistics,spatial domain(SD),transform domain(TD),distortion,masking,and filtering.This study possibly shall help researchers to improve vehicle networks’ability to communicate securely and lay the door for innovative steganography methods.
基金funded by the Natural Science Foundation of Fujian Province,China (Grant No.2022J05291)Xiamen Scientific Research Funding for Overseas Chinese Scholars.
文摘Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.
基金Supported by the“Ricerca Corrente”Grant from Italian Ministry of Health,No.IRCCS SYNLAB SDN.
文摘BACKGROUND Radiomics is a promising tool that may increase the value of magnetic resonance imaging(MRI)for different tasks related to the management of patients with hepatocellular carcinoma(HCC).However,its implementation in clinical practice is still far,with many issues related to the methodological quality of radiomic studies.AIM To systematically review the current status of MRI radiomic studies concerning HCC using the Radiomics Quality Score(RQS).METHODS A systematic literature search of PubMed,Google Scholar,and Web of Science databases was performed to identify original articles focusing on the use of MRI radiomics for HCC management published between 2017 and 2023.The methodological quality of radiomic studies was assessed using the RQS tool.Spearman’s correlation(ρ)analysis was performed to explore if RQS was correlated with journal metrics and characteristics of the studies.The level of statistical significance was set at P<0.05.RESULTS One hundred and twenty-seven articles were included,of which 43 focused on HCC prognosis,39 on prediction of pathological findings,16 on prediction of the expression of molecular markers outcomes,18 had a diagnostic purpose,and 11 had multiple purposes.The mean RQS was 8±6.22,and the corresponding percentage was 24.15%±15.25%(ranging from 0.0% to 58.33%).RQS was positively correlated with journal impact factor(IF;ρ=0.36,P=2.98×10^(-5)),5-years IF(ρ=0.33,P=1.56×10^(-4)),number of patients included in the study(ρ=0.51,P<9.37×10^(-10))and number of radiomics features extracted in the study(ρ=0.59,P<4.59×10^(-13)),and time of publication(ρ=-0.23,P<0.0072).CONCLUSION Although MRI radiomics in HCC represents a promising tool to develop adequate personalized treatment as a noninvasive approach in HCC patients,our study revealed that studies in this field still lack the quality required to allow its introduction into clinical practice.
文摘Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.
文摘The prevalence of smartphones is deeply embedded in modern society,impacting various aspects of our lives.Their versatility and functionalities have fundamentally changed how we communicate,work,seek entertainment,and access information.Among the many smartphones available,those operating on the Android platform dominate,being the most widely used type.This widespread adoption of the Android OS has significantly contributed to increased malware attacks targeting the Android ecosystem in recent years.Therefore,there is an urgent need to develop new methods for detecting Android malware.The literature contains numerous works related to Android malware detection.As far as our understanding extends,we are the first ones to identify dangerous combinations of permissions and system calls to uncover malicious behavior in Android applications.We introduce a novel methodology that pairs permissions and system calls to distinguish between benign and malicious samples.This approach combines the advantages of static and dynamic analysis,offering a more comprehensive understanding of an application’s behavior.We establish covalent bonds between permissions and system calls to assess their combined impact.We introduce a novel technique to determine these pairs’Covalent Bond Strength Score.Each pair is assigned two scores,one for malicious behavior and another for benign behavior.These scores serve as the basis for classifying applications as benign or malicious.By correlating permissions with system calls,the study enables a detailed examination of how an app utilizes its requested permissions,aiding in differentiating legitimate and potentially harmful actions.This comprehensive analysis provides a robust framework for Android malware detection,marking a significant contribution to the field.The results of our experiments demonstrate a remarkable overall accuracy of 97.5%,surpassing various state-of-the-art detection techniques proposed in the current literature.
基金via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2023/R/1444).
文摘Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.
基金authors are thankful to the Deanship of Scientific Research at Najran University for funding this work,under the Research Groups Funding Program Grant Code(NU/RG/SERC/12/27).
文摘Social media(SM)based surveillance systems,combined with machine learning(ML)and deep learning(DL)techniques,have shown potential for early detection of epidemic outbreaks.This review discusses the current state of SM-based surveillance methods for early epidemic outbreaks and the role of ML and DL in enhancing their performance.Since,every year,a large amount of data related to epidemic outbreaks,particularly Twitter data is generated by SM.This paper outlines the theme of SM analysis for tracking health-related issues and detecting epidemic outbreaks in SM,along with the ML and DL techniques that have been configured for the detection of epidemic outbreaks.DL has emerged as a promising ML technique that adaptsmultiple layers of representations or features of the data and yields state-of-the-art extrapolation results.In recent years,along with the success of ML and DL in many other application domains,both ML and DL are also popularly used in SM analysis.This paper aims to provide an overview of epidemic outbreaks in SM and then outlines a comprehensive analysis of ML and DL approaches and their existing applications in SM analysis.Finally,this review serves the purpose of offering suggestions,ideas,and proposals,along with highlighting the ongoing challenges in the field of early outbreak detection that still need to be addressed.