Optimization algorithms are crucial for solving NP-hard problems in engineering and computational sciences.Metaheuristic algorithms,in particular,have proven highly effective in complex optimization scenarios characte...Optimization algorithms are crucial for solving NP-hard problems in engineering and computational sciences.Metaheuristic algorithms,in particular,have proven highly effective in complex optimization scenarios characterized by high dimensionality and intricate variable relationships.The Mountain Gazelle Optimizer(MGO)is notably effective but struggles to balance local search refinement and global space exploration,often leading to premature convergence and entrapment in local optima.This paper presents the Improved MGO(IMGO),which integrates three synergistic enhancements:dynamic chaos mapping using piecewise chaotic sequences to boost explo-ration diversity;Opposition-Based Learning(OBL)with adaptive,diversity-driven activation to speed up convergence;and structural refinements to the position update mechanisms to enhance exploitation.The IMGO underwent a comprehensive evaluation using 52 standardised benchmark functions and seven engineering optimization problems.Benchmark evaluations showed that IMGO achieved the highest rank in best solution quality for 31 functions,the highest rank in mean performance for 18 functions,and the highest rank in worst-case performance for 14 functions among 11 competing algorithms.Statistical validation using Wilcoxon signed-rank tests confirmed that IMGO outperformed individual competitors across 16 to 50 functions,depending on the algorithm.At the same time,Friedman ranking analysis placed IMGO with an average rank of 4.15,compared to the baseline MGO’s 4.38,establishing the best overall performance.The evaluation of engineering problems revealed consistent improvements,including an optimal cost of 1.6896 for the welded beam design vs.MGO’s 1.7249,a minimum cost of 5885.33 for the pressure vessel design vs.MGO’s 6300,and a minimum weight of 2964.52 kg for the speed reducer design vs.MGO’s 2990.00 kg.Ablation studies identified OBL as the strongest individual contributor,whereas complete integration achieved superior performance through synergistic interactions among components.Computational complexity analysis established an O(T×N×5×f(P))time complexity,representing a 1.25×increase in fitness evaluation relative to the baseline MGO,validating the favorable accuracy-efficiency trade-offs for practical optimization applications.展开更多
Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional comp...Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.展开更多
Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learni...Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learning 2-based approach for detecting Parkinson’s disease before any of the overt symptoms develop during their prodromal stage.We used 5 publicly accessible datasets,including UCI Parkinson’s Voice,Spiral Drawings,PaHaW,NewHandPD,and PPMI,and implemented a dual stream CNN–BiLSTM architecture with Fisher-weighted feature merging and SHAP-based explanation.The findings reveal that the model’s performance was superior and achieved 98.2%,a F1-score of 0.981,and AUC of 0.991 on the UCI Voice dataset.The model’s performance on the remaining datasets was also comparable,with up to a 2–7 percent betterment in accuracy compared to existing strong models such as CNN–RNN–MLP,ILN–GNet,and CASENet.Across the evidence,the findings back the diagnostic promise of micro-tremor assessment and demonstrate that combining temporal and spatial features with a scatter-based segment for a multi-modal approach can be an effective and scalable platform for an“early,”interpretable PD screening system.展开更多
The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EIS...The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EISA)framework for 6G unmanned aerial vehicle(UAV)-assisted Internet of vehicles(IoV)networks that integrates task-driven semantic communication,deep reinforcement learning(DRL)-based edge intelligence,and blockchain-based semantic validation across 6G terahertz(THz)links.UAVs in the proposed architecture serve as adaptive edge nodes that receive semantically vital information about the vehicle at any given stage,optimize aggregation and transmission parameters dynamically,and guarantee data integrity through a structured,lightweight consortium blockchain that signs semantically detailed representations rather than raw packets.Simulation results from a hybrid NS-3,MATLAB,and Python environment indicate that the proposed framework can achieve up to 45%reduction in end-to-end latency,an approximately 70%increase in throughput,and semantic efficiency with blockchain verification delays of less than 20 ms(more than 98%).These findings support the effectiveness of the proposed co-design for achieving context-aware,energy-efficient,and reliable communication under heavy-traffic conditions.The proposed framework provides a flexible and scalable foundation for next-generation 6G-enabled automotive networks,with subsequent growth toward federated learning-based collaborative intelligence,digital-twinassisted traffic modeling,and quantum-safe blockchain mechanisms to enhance scalability,intelligence,and long-term security.展开更多
The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigm...The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigms have fundamental issues in data privacy,regulatory compliance,and ownership silo alongside the scaled limitations of the real-life application.The concept of Federated Deep Learning(FDL)is a privacy-by-design method that will enable the distributed training of machine learning models among distributed clients without sharing raw data and is suitable in heterogeneous urban settings.It is an overview of the privacy-preserving developments in FDL as of 2018-2025 with a narrow scope on its usage in smart cities(traffic prediction,environmental monitoring,energy grids),smart homes/buildings/IoT(non-intrusive load monitoring,HVAC optimization,anomaly detection)and the healthcare application(medical imaging,Electronic Health Records(EHR)analysis,remote monitoring).It gives coherent taxonomy,domain pipelines,comparative analyses of privacy mechanisms(differential privacy,secure aggregation,Homomorphic Encryption(HE),Trusted Execution Environments(TEEs),blockchain enhanced and hybrids),system structures,security/robustness defense,deployment/Machine Learning Operation(MLOps)issues,and the longstanding challenges(non-IID heterogeneity,communication efficiency,fairness,and sustainability).Some of the contributions made are structured comparisons of privacy threats,practical design advice on urban areas,recognition of open problems,and a research roadmap into the future up to 2035.The paper brings out the transformational worth of FDL in building credible,scalable,and sustainable intelligent urban ecosystems and the need to do further interdisciplinary research in standardization,real-world testbeds,and ethical governance.展开更多
The planning of teaching for a course that belongs to an undergraduate program usually begins with the definition of its contents,which are derived from syllabus of a political-pedagogical project.The contents listed ...The planning of teaching for a course that belongs to an undergraduate program usually begins with the definition of its contents,which are derived from syllabus of a political-pedagogical project.The contents listed are organized in a sequence considered logical.A set of actions is planned,such as lectures,laboratories,among others,through which content will be developed.The previous training of the student is considered,the concurrent and subsequent courses,the context of the course inside the program,the specific and general objectives of the program.A set of assessments is also defined as part of this planning,the associated methodologies,techniques and teaching objectives.In this context,this paper focuses on the aspect of the sequencing of content,methodologies and teaching techniques in a course.For this purpose,the Bloom's Taxonomy of Educational Objectives is applied,which provides a hierarchical structure for the cognitive process.The importance of this hierarchy of knowledge is greater awareness of the teacher about the ways to be adopted in the teaching process.展开更多
In this paper,the Web-based integration methodology and framework have been developed to facilitate collabora-tive and concurrent engineering design in distributed manufacturing environments.The distributed concurrent...In this paper,the Web-based integration methodology and framework have been developed to facilitate collabora-tive and concurrent engineering design in distributed manufacturing environments.The distributed concurrent engineering and co-design are discussed as key components in the mechanism.The related integration system is presented,which includes four function-al modules:co-design,Web-based visualization,manufacturing analysis and look-up service.It can be used for a design team geo-graphically distributed to organize a collaborative and concurrent engineering design effectively.In particular,the collaborative mechanism incorporated with Java-based and Internet-enabled technologies can generate extended strategies for design and planning.Thus,the proposed integration architecture enables the system to be generic,open and scalable.Finally,for the trend of global manufacturing,a case study of Internet-enabled collaborative optimization is introduced and a discussion on teamwork capability is made.展开更多
The Intelligent Internet of Things(IIoT)involves real-world things that communicate or interact with each other through networking technologies by collecting data from these“things”and using intelligent approaches,s...The Intelligent Internet of Things(IIoT)involves real-world things that communicate or interact with each other through networking technologies by collecting data from these“things”and using intelligent approaches,such as Artificial Intelligence(AI)and machine learning,to make accurate decisions.Data science is the science of dealing with data and its relationships through intelligent approaches.Most state-of-the-art research focuses independently on either data science or IIoT,rather than exploring their integration.Therefore,to address the gap,this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT)system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics.The paper analyzes the data science or big data security and privacy features,including network architecture,data protection,and continuous monitoring of data,which face challenges in various IoT-based systems.Extensive insights into IoT data security,privacy,and challenges are visualized in the context of data science for IoT.In addition,this study reveals the current opportunities to enhance data science and IoT market development.The current gap and challenges faced in the integration of data science and IoT are comprehensively presented,followed by the future outlook and possible solutions.展开更多
Time series are an important object of study in sciences, engineering and business, especially in cases where it is expected to know, predict and optimize behaviors. In this context, we intend to show the feasibility ...Time series are an important object of study in sciences, engineering and business, especially in cases where it is expected to know, predict and optimize behaviors. In this context, we intend to show the feasibility of using artificial neural networks in the study of several time series in an engineering course, especially those that have no overt behavior or are not able to be modeled mathematically in a simple way and have direct application in the education of future engineers.展开更多
Accurate estimation of evapotranspiration(ET)is crucial for efficient water resource management,particularly in the face of climate change and increasing water scarcity.This study performs a bibliometric analysis of 3...Accurate estimation of evapotranspiration(ET)is crucial for efficient water resource management,particularly in the face of climate change and increasing water scarcity.This study performs a bibliometric analysis of 352 articles and a systematic review of 35 peer-reviewed papers,selected according to PRISMA guidelines,to evaluate the performance of Hybrid Artificial Neural Networks(HANNs)in ET estimation.The findings demonstrate that HANNs,particularly those combining Multilayer Perceptrons(MLPs),Recurrent Neural Networks(RNNs),and Convolutional Neural Networks(CNNs),are highly effective in capturing the complex nonlinear relationships and tem-poral dependencies characteristic of hydrological processes.These hybrid models,often integrated with optimization algorithms and fuzzy logic frameworks,significantly improve the predictive accuracy and generalization capabilities of ET estimation.The growing adoption of advanced evaluation metrics,such as Kling-Gupta Efficiency(KGE)and Taylor Diagrams,highlights the increasing demand for more robust performance assessments beyond traditional methods.Despite the promising results,challenges remain,particularly regarding model interpretability,computational efficiency,and data scarcity.Future research should prioritize the integration of interpretability techniques,such as attention mechanisms,Local Interpretable Model-Agnostic Explanations(LIME),and feature importance analysis,to enhance model transparency and foster stakeholder trust.Additionally,improving HANN models’scalability and computational efficiency is crucial,especially for large-scale,real-world applications.Approaches such as transfer learning,parallel processing,and hyperparameter optimization will be essential in overcoming these challenges.This study underscores the transformative potential of HANN models for precise ET estimation,particularly in water-scarce and climate-vulnerable regions.By integrating CNNs for automatic feature extraction and leveraging hybrid architectures,HANNs offer considerable advantages for optimizing water management,particularly agriculture.Addressing challenges related to interpretability and scalability will be vital to ensuring the widespread deployment and operational success of HANNs in global water resource management.展开更多
Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify sp...Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
Over the past few years,the application and usage of Machine Learning(ML)techniques have increased exponentially due to continuously increasing the size of data and computing capacity.Despite the popularity of ML tech...Over the past few years,the application and usage of Machine Learning(ML)techniques have increased exponentially due to continuously increasing the size of data and computing capacity.Despite the popularity of ML techniques,only a few research studies have focused on the application of ML especially supervised learning techniques in Requirement Engineering(RE)activities to solve the problems that occur in RE activities.The authors focus on the systematic mapping of past work to investigate those studies that focused on the application of supervised learning techniques in RE activities between the period of 2002–2023.The authors aim to investigate the research trends,main RE activities,ML algorithms,and data sources that were studied during this period.Forty-five research studies were selected based on our exclusion and inclusion criteria.The results show that the scientific community used 57 algorithms.Among those algorithms,researchers mostly used the five following ML algorithms in RE activities:Decision Tree,Support Vector Machine,Naïve Bayes,K-nearest neighbour Classifier,and Random Forest.The results show that researchers used these algorithms in eight major RE activities.Those activities are requirements analysis,failure prediction,effort estimation,quality,traceability,business rules identification,content classification,and detection of problems in requirements written in natural language.Our selected research studies used 32 private and 41 public data sources.The most popular data sources that were detected in selected studies are the Metric Data Programme from NASA,Predictor Models in Software Engineering,and iTrust Electronic Health Care System.展开更多
In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equi...In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equipment lifespan,reducing maintenance costs,and improving production quality and safety.This research focuses on utilizing Bayesian search-based machine learning and deep learning approaches for the condition monitoring of industrial equipment.The study aims to enhance predictive maintenance for industrial equipment by forecasting vibration values based on domain-specific feature engineering.Early prediction of vibration enables proactive interventions to minimize downtime and extend the lifespan of critical assets.A data set of load information and vibration values from a heavy-duty industrial slip ring induction motor(4600 kW)and gearbox equipped with vibration sensors is used as a case study.The study implements and compares six machine learning models with the proposed Bayesian-optimized stacked Long Short-Term Memory(LSTM)model.The hyperparameters used in the implementation of models are selected based on the Bayesian optimization technique.Comparative analysis reveals that the proposed Bayesian optimized stacked LSTM outperforms other models,showcasing its capability to learn temporal features as well as long-term dependencies in time series information.The implemented machine learning models:Linear Regression(LR),RandomForest(RF),Gradient Boosting Regressor(GBR),ExtremeGradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Support Vector Regressor(SVR)displayed a mean squared error of 0.9515,0.4654,0.1849,0.0295,0.2127 and 0.0273,respectively.The proposed model predicts the future vibration characteristics with a mean squared error of 0.0019 on the dataset containing motor load information and vibration characteristics.The results demonstrate that the proposed model outperforms other models in terms of other evaluation metrics with a mean absolute error of 0.0263 and 0.882 as a coefficient of determination.Current research not only contributes to the comparative performance of machine learning models in condition monitoring but also showcases the practical implications of employing these techniques.By transitioning fromreactive to proactive maintenance strategies,industries canminimize downtime,reduce costs,and prolong the lifespan of crucial assets.This study demonstrates the practical advantages of transitioning from reactive to proactive maintenance strategies using ML-based condition monitoring.展开更多
A Distributed Denial-of-Service(DDoS)attack poses a significant challenge in the digital age,disrupting online services with operational and financial consequences.Detecting such attacks requires innovative and effect...A Distributed Denial-of-Service(DDoS)attack poses a significant challenge in the digital age,disrupting online services with operational and financial consequences.Detecting such attacks requires innovative and effective solutions.The primary challenge lies in selecting the best among several DDoS detection models.This study presents a framework that combines several DDoS detection models and Multiple-Criteria Decision-Making(MCDM)techniques to compare and select the most effective models.The framework integrates a decision matrix from training several models on the CiC-DDOS2019 dataset with Fuzzy Weighted Zero Inconsistency Criterion(FWZIC)and MultiAttribute Boundary Approximation Area Comparison(MABAC)methodologies.FWZIC assigns weights to evaluate criteria,while MABAC compares detection models based on the assessed criteria.The results indicate that the FWZIC approach assigns weights to criteria reliably,with time complexity receiving the highest weight(0.2585)and F1 score receiving the lowest weight(0.14644).Among the models evaluated using the MABAC approach,the Support Vector Machine(SVM)ranked first with a score of 0.0444,making it the most suitable for this work.In contrast,Naive Bayes(NB)ranked lowest with a score of 0.0018.Objective validation and sensitivity analysis proved the reliability of the framework.This study provides a practical approach and insights for cybersecurity practitioners and researchers to evaluate DDoS detection models.展开更多
Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques...Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques to detect defects,as traditional methods are often prone to human error,and this issue is also addressed through image processing(IP).In addition to IP,automated,accurate,and real-time detection of structural defects,such as cracks,corrosion,and material degradation that conventional inspection techniques may miss,is made possible by Artificial Intelligence(AI)technologies like Machine Learning(ML)and Deep Learning(DL).This review examines the integration of computer vision and AI techniques in Structural Health Monitoring(SHM),investigating their effectiveness in detecting various forms of structural deterioration.Also,it evaluates ML and DL models in SHM for their accuracy in identifying and assessing structural damage,ultimately enhancing safety,durability,and maintenance practices in the field.Key findings reveal that AI-powered approaches,especially those utilizing IP and DL models like CNNs,significantly improve detection efficiency and accuracy,with reported accuracies in various SHM tasks.However,significant research gaps remain,including challenges with the consistency,quality,and environmental resilience of image data,a notable lack of standardized models and datasets for training across diverse structures,and concerns regarding computational costs,model interpretability,and seamless integration with existing systems.Future work should focus on developing more robust models through data augmentation,transfer learning,and hybrid approaches,standardizing protocols,and fostering interdisciplinary collaboration to overcome these limitations and achieve more reliable,scalable,and affordable SHM systems.展开更多
The identification of defect types and their reduction values is the most crucial step in coffee grading.In Ethiopia,the current coffee defect investigation techniques rely on manual screening,which requires substanti...The identification of defect types and their reduction values is the most crucial step in coffee grading.In Ethiopia,the current coffee defect investigation techniques rely on manual screening,which requires substantial human resources,time-consuming,and prone to errors.Recently,the deep learning driven object detection has shown promising results in coffee defect identification and grading tasks.In this study,we propose KN-YOLOv8,a modified You Only Look Once version-8(YOLOv8)model optimized for real-time detection of coffee bean defects.This lightweight network incorporates effective feature fusion techniques to accurately detect and locate defects,even among overlapping beans.We have compiled a custom dataset of 562 images comprising thirteen distinct types of defects.The model achieved exceptional performance,with training dataset metrics of 97% recall,100% precision,and 98% mean average precision(mAP).On the test dataset,it maintained outstanding results with 99% recall,100% precision,and 98.9% mAP.The model outperforms existing approaches by achieving a 97.7%m AP for all classes at a 0.5 threshold,while maintaining an optimal precision-recall balance.The model outperforms new approaches by achieving a balance between precision and recall,achieving a mean average precision of 97.7% for all classes.This solution significantly reduces reliance on labor-intensivemanual inspection while improving accuracy.Its lightweight design and high speed make it suitable for real-time industrial applications,transforming coffee quality inspection.展开更多
The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These in...The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These infrastructures are very effective in providing a fast response to the respective queries of the requesting modules, but their distributed nature has introduced other problems such as security and privacy. To address these problems, various security-assisted communication mechanisms have been developed to safeguard every active module, i.e., devices and edges, from every possible vulnerability in the IoT. However, these methodologies have neglected one of the critical issues, which is the prediction of fraudulent devices, i.e., adversaries, preferably as early as possible in the IoT. In this paper, a hybrid communication mechanism is presented where the Hidden Markov Model (HMM) predicts the legitimacy of the requesting device (both source and destination), and the Advanced Encryption Standard (AES) safeguards the reliability of the transmitted data over a shared communication medium, preferably through a secret shared key, i.e., , and timestamp information. A device becomes trusted if it has passed both evaluation levels, i.e., HMM and message decryption, within a stipulated time interval. The proposed hybrid, along with existing state-of-the-art approaches, has been simulated in the realistic environment of the IoT to verify the security measures. These evaluations were carried out in the presence of intruders capable of launching various attacks simultaneously, such as man-in-the-middle, device impersonations, and masquerading attacks. Moreover, the proposed approach has been proven to be more effective than existing state-of-the-art approaches due to its exceptional performance in communication, processing, and storage overheads, i.e., 13%, 19%, and 16%, respectively. Finally, the proposed hybrid approach is pruned against well-known security attacks in the IoT.展开更多
Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prev...Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prevent vision loss.This study aims to develop a deep-learning approach for the early and precise diagnosis of DR,asmanual detection can be time-consuming,costly,and prone to human error.The classification task is divided into two groups for binary classification:patients with DR(diagnoses 1–4)and those without DR(diagnosis 0).For multi-class classification,the categories are no DR,mild DR,moderate DR,severe DR,and proliferative diabetic retinopathy(PDR).To achieve this,the proposed model utilizes two pre-trained convolutional neural networks(CNNs),specifically ResNet50 and DenseNet-121.Both models were trained and evaluated on fundus images sourced from the widely recognized APTOS dataset,a publicly available resource.,and achieved impressive training and testing accuracies.For binary classification,DenseNet-121 achieved an accuracy of 98.1%,while ResNet50 attained an accuracy of 97.4%.Inmulti-class classification forDR,DenseNet-121 achieved an accuracy of 82.0%,and ResNet50 reached an accuracy of 80.8%.The results are promising and comparable to state-of-the-art techniques in the literature for both binary and multi-label classification of DR.展开更多
Sentiment Analysis,a significant domain within Natural Language Processing(NLP),focuses on extracting and interpreting subjective information-such as emotions,opinions,and attitudes-from textual data.With the increasi...Sentiment Analysis,a significant domain within Natural Language Processing(NLP),focuses on extracting and interpreting subjective information-such as emotions,opinions,and attitudes-from textual data.With the increasing volume of user-generated content on social media and digital platforms,sentiment analysis has become essential for deriving actionable insights across various sectors.This study presents a systematic literature review of sentiment analysis methodologies,encompassing traditional machine learning algorithms,lexicon-based approaches,and recent advancements in deep learning techniques.The review follows a structured protocol comprising three phases:planning,execution,and analysis/reporting.During the execution phase,67 peer-reviewed articles were initially retrieved,with 25 meeting predefined inclusion and exclusion criteria.The analysis phase involved a detailed examination of each study’s methodology,experimental setup,and key contributions.Among the deep learning models evaluated,Long Short-Term Memory(LSTM)networks were identified as the most frequently adopted architecture for sentiment classification tasks.This review highlights current trends,technical challenges,and emerging opportunities in the field,providing valuable guidance for future research and development in applications such as market analysis,public health monitoring,financial forecasting,and crisis management.展开更多
文摘Optimization algorithms are crucial for solving NP-hard problems in engineering and computational sciences.Metaheuristic algorithms,in particular,have proven highly effective in complex optimization scenarios characterized by high dimensionality and intricate variable relationships.The Mountain Gazelle Optimizer(MGO)is notably effective but struggles to balance local search refinement and global space exploration,often leading to premature convergence and entrapment in local optima.This paper presents the Improved MGO(IMGO),which integrates three synergistic enhancements:dynamic chaos mapping using piecewise chaotic sequences to boost explo-ration diversity;Opposition-Based Learning(OBL)with adaptive,diversity-driven activation to speed up convergence;and structural refinements to the position update mechanisms to enhance exploitation.The IMGO underwent a comprehensive evaluation using 52 standardised benchmark functions and seven engineering optimization problems.Benchmark evaluations showed that IMGO achieved the highest rank in best solution quality for 31 functions,the highest rank in mean performance for 18 functions,and the highest rank in worst-case performance for 14 functions among 11 competing algorithms.Statistical validation using Wilcoxon signed-rank tests confirmed that IMGO outperformed individual competitors across 16 to 50 functions,depending on the algorithm.At the same time,Friedman ranking analysis placed IMGO with an average rank of 4.15,compared to the baseline MGO’s 4.38,establishing the best overall performance.The evaluation of engineering problems revealed consistent improvements,including an optimal cost of 1.6896 for the welded beam design vs.MGO’s 1.7249,a minimum cost of 5885.33 for the pressure vessel design vs.MGO’s 6300,and a minimum weight of 2964.52 kg for the speed reducer design vs.MGO’s 2990.00 kg.Ablation studies identified OBL as the strongest individual contributor,whereas complete integration achieved superior performance through synergistic interactions among components.Computational complexity analysis established an O(T×N×5×f(P))time complexity,representing a 1.25×increase in fitness evaluation relative to the baseline MGO,validating the favorable accuracy-efficiency trade-offs for practical optimization applications.
文摘Breast cancer screening programs rely heavily on mammography for early detection;however,diagnostic performance is strongly affected by inter-reader variability,breast density,and the limitations of conven-tional computer-aided detection systems.Recent advances in deep learning have enabled more robust and scalable solutions for large-scale screening,yet a systematic comparison of modern object detection architectures on nationally representative datasets remains limited.This study presents a comprehensive quantitative comparison of prominent deep learning–based object detection architectures for Artificial Intelligence-assisted mammography analysis using the MammosighTR dataset,developed within the Turkish National Breast Cancer Screening Program.The dataset comprises 12,740 patient cases collected between 2016 and 2022,annotated with BI-RADS categories,breast density levels,and lesion localization labels.A total of 31 models were evaluated,including One-Stage,Two-Stage,and Transformer-based architectures,under a unified experimental framework at both patient and breast levels.The results demonstrate that Two-Stage architectures consistently outperform One-Stage models,achieving approximately 2%–4%higher Macro F1-Scores and more balanced precision–recall trade-offs,with Double-Head R-CNN and Dynamic R-CNN yielding the highest overall performance(Macro F1≈0.84–0.86).This advantage is primarily attributed to the region proposal mechanism and improved class balance inherent to Two-Stage designs.One-Stage detectors exhibited higher sensitivity and faster inference,reaching Recall values above 0.88,but experienced minor reductions in Precision and overall accuracy(≈1%–2%)compared with Two-Stage models.Among Transformer-based architectures,Deformable DEtection TRansformer demonstrated strong robustness and consistency across datasets,achieving Macro F1-Scores comparable to CNN-based detectors(≈0.83–0.85)while exhibiting minimal performance degradation under distributional shifts.Breast density–based analysis revealed increased misclassification rates in medium-density categories(types B and C),whereas Transformer-based architectures maintained more stable performance in high-density type D tissue.These findings quantitatively confirm that both architectural design and tissue characteristics play a decisive role in diagnostic accuracy.Overall,the study provides a reproducible benchmark and highlights the potential of hybrid approaches that combine the accuracy of Two-Stage detectors with the contextual modeling capability of Transformer architectures for clinically reliable breast cancer screening systems.
基金supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2025/03/32440).
文摘Parkinson’s disease remains a major clinical issue in terms of early detection,especially during its prodromal stage when symptoms are not evident or not distinct.To address this problem,we proposed a new deep learning 2-based approach for detecting Parkinson’s disease before any of the overt symptoms develop during their prodromal stage.We used 5 publicly accessible datasets,including UCI Parkinson’s Voice,Spiral Drawings,PaHaW,NewHandPD,and PPMI,and implemented a dual stream CNN–BiLSTM architecture with Fisher-weighted feature merging and SHAP-based explanation.The findings reveal that the model’s performance was superior and achieved 98.2%,a F1-score of 0.981,and AUC of 0.991 on the UCI Voice dataset.The model’s performance on the remaining datasets was also comparable,with up to a 2–7 percent betterment in accuracy compared to existing strong models such as CNN–RNN–MLP,ILN–GNet,and CASENet.Across the evidence,the findings back the diagnostic promise of micro-tremor assessment and demonstrate that combining temporal and spatial features with a scatter-based segment for a multi-modal approach can be an effective and scalable platform for an“early,”interpretable PD screening system.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)-Information Technology Research Center(ITRC)under Grant No.IITP-2025-RS-2023-00259004the Basic Science Research Program through the National Research Foundation of Korea(NRF)under Grant No.RS-2025-25434261.
文摘The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EISA)framework for 6G unmanned aerial vehicle(UAV)-assisted Internet of vehicles(IoV)networks that integrates task-driven semantic communication,deep reinforcement learning(DRL)-based edge intelligence,and blockchain-based semantic validation across 6G terahertz(THz)links.UAVs in the proposed architecture serve as adaptive edge nodes that receive semantically vital information about the vehicle at any given stage,optimize aggregation and transmission parameters dynamically,and guarantee data integrity through a structured,lightweight consortium blockchain that signs semantically detailed representations rather than raw packets.Simulation results from a hybrid NS-3,MATLAB,and Python environment indicate that the proposed framework can achieve up to 45%reduction in end-to-end latency,an approximately 70%increase in throughput,and semantic efficiency with blockchain verification delays of less than 20 ms(more than 98%).These findings support the effectiveness of the proposed co-design for achieving context-aware,energy-efficient,and reliable communication under heavy-traffic conditions.The proposed framework provides a flexible and scalable foundation for next-generation 6G-enabled automotive networks,with subsequent growth toward federated learning-based collaborative intelligence,digital-twinassisted traffic modeling,and quantum-safe blockchain mechanisms to enhance scalability,intelligence,and long-term security.
文摘The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigms have fundamental issues in data privacy,regulatory compliance,and ownership silo alongside the scaled limitations of the real-life application.The concept of Federated Deep Learning(FDL)is a privacy-by-design method that will enable the distributed training of machine learning models among distributed clients without sharing raw data and is suitable in heterogeneous urban settings.It is an overview of the privacy-preserving developments in FDL as of 2018-2025 with a narrow scope on its usage in smart cities(traffic prediction,environmental monitoring,energy grids),smart homes/buildings/IoT(non-intrusive load monitoring,HVAC optimization,anomaly detection)and the healthcare application(medical imaging,Electronic Health Records(EHR)analysis,remote monitoring).It gives coherent taxonomy,domain pipelines,comparative analyses of privacy mechanisms(differential privacy,secure aggregation,Homomorphic Encryption(HE),Trusted Execution Environments(TEEs),blockchain enhanced and hybrids),system structures,security/robustness defense,deployment/Machine Learning Operation(MLOps)issues,and the longstanding challenges(non-IID heterogeneity,communication efficiency,fairness,and sustainability).Some of the contributions made are structured comparisons of privacy threats,practical design advice on urban areas,recognition of open problems,and a research roadmap into the future up to 2035.The paper brings out the transformational worth of FDL in building credible,scalable,and sustainable intelligent urban ecosystems and the need to do further interdisciplinary research in standardization,real-world testbeds,and ethical governance.
文摘The planning of teaching for a course that belongs to an undergraduate program usually begins with the definition of its contents,which are derived from syllabus of a political-pedagogical project.The contents listed are organized in a sequence considered logical.A set of actions is planned,such as lectures,laboratories,among others,through which content will be developed.The previous training of the student is considered,the concurrent and subsequent courses,the context of the course inside the program,the specific and general objectives of the program.A set of assessments is also defined as part of this planning,the associated methodologies,techniques and teaching objectives.In this context,this paper focuses on the aspect of the sequencing of content,methodologies and teaching techniques in a course.For this purpose,the Bloom's Taxonomy of Educational Objectives is applied,which provides a hierarchical structure for the cognitive process.The importance of this hierarchy of knowledge is greater awareness of the teacher about the ways to be adopted in the teaching process.
文摘In this paper,the Web-based integration methodology and framework have been developed to facilitate collabora-tive and concurrent engineering design in distributed manufacturing environments.The distributed concurrent engineering and co-design are discussed as key components in the mechanism.The related integration system is presented,which includes four function-al modules:co-design,Web-based visualization,manufacturing analysis and look-up service.It can be used for a design team geo-graphically distributed to organize a collaborative and concurrent engineering design effectively.In particular,the collaborative mechanism incorporated with Java-based and Internet-enabled technologies can generate extended strategies for design and planning.Thus,the proposed integration architecture enables the system to be generic,open and scalable.Finally,for the trend of global manufacturing,a case study of Internet-enabled collaborative optimization is introduced and a discussion on teamwork capability is made.
基金supported in part by the National Natural Science Foundation of China under Grant 62371181in part by the Changzhou Science and Technology International Cooperation Program under Grant CZ20230029+1 种基金supported by a National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(2021R1A2B5B02087169)supported under the framework of international cooperation program managed by the National Research Foundation of Korea(2022K2A9A1A01098051)。
文摘The Intelligent Internet of Things(IIoT)involves real-world things that communicate or interact with each other through networking technologies by collecting data from these“things”and using intelligent approaches,such as Artificial Intelligence(AI)and machine learning,to make accurate decisions.Data science is the science of dealing with data and its relationships through intelligent approaches.Most state-of-the-art research focuses independently on either data science or IIoT,rather than exploring their integration.Therefore,to address the gap,this article provides a comprehensive survey on the advances and integration of data science with the Intelligent IoT(IIoT)system by classifying the existing IoT-based data science techniques and presenting a summary of various characteristics.The paper analyzes the data science or big data security and privacy features,including network architecture,data protection,and continuous monitoring of data,which face challenges in various IoT-based systems.Extensive insights into IoT data security,privacy,and challenges are visualized in the context of data science for IoT.In addition,this study reveals the current opportunities to enhance data science and IoT market development.The current gap and challenges faced in the integration of data science and IoT are comprehensively presented,followed by the future outlook and possible solutions.
文摘Time series are an important object of study in sciences, engineering and business, especially in cases where it is expected to know, predict and optimize behaviors. In this context, we intend to show the feasibility of using artificial neural networks in the study of several time series in an engineering course, especially those that have no overt behavior or are not able to be modeled mathematically in a simple way and have direct application in the education of future engineers.
文摘Accurate estimation of evapotranspiration(ET)is crucial for efficient water resource management,particularly in the face of climate change and increasing water scarcity.This study performs a bibliometric analysis of 352 articles and a systematic review of 35 peer-reviewed papers,selected according to PRISMA guidelines,to evaluate the performance of Hybrid Artificial Neural Networks(HANNs)in ET estimation.The findings demonstrate that HANNs,particularly those combining Multilayer Perceptrons(MLPs),Recurrent Neural Networks(RNNs),and Convolutional Neural Networks(CNNs),are highly effective in capturing the complex nonlinear relationships and tem-poral dependencies characteristic of hydrological processes.These hybrid models,often integrated with optimization algorithms and fuzzy logic frameworks,significantly improve the predictive accuracy and generalization capabilities of ET estimation.The growing adoption of advanced evaluation metrics,such as Kling-Gupta Efficiency(KGE)and Taylor Diagrams,highlights the increasing demand for more robust performance assessments beyond traditional methods.Despite the promising results,challenges remain,particularly regarding model interpretability,computational efficiency,and data scarcity.Future research should prioritize the integration of interpretability techniques,such as attention mechanisms,Local Interpretable Model-Agnostic Explanations(LIME),and feature importance analysis,to enhance model transparency and foster stakeholder trust.Additionally,improving HANN models’scalability and computational efficiency is crucial,especially for large-scale,real-world applications.Approaches such as transfer learning,parallel processing,and hyperparameter optimization will be essential in overcoming these challenges.This study underscores the transformative potential of HANN models for precise ET estimation,particularly in water-scarce and climate-vulnerable regions.By integrating CNNs for automatic feature extraction and leveraging hybrid architectures,HANNs offer considerable advantages for optimizing water management,particularly agriculture.Addressing challenges related to interpretability and scalability will be vital to ensuring the widespread deployment and operational success of HANNs in global water resource management.
基金the Deanship of Scientifc Research at King Khalid University for funding this work through large group Research Project under grant number RGP2/421/45supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2024/R/1446)+1 种基金supported by theResearchers Supporting Project Number(UM-DSR-IG-2023-07)Almaarefa University,Riyadh,Saudi Arabia.supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2021R1F1A1055408).
文摘Machine learning(ML)is increasingly applied for medical image processing with appropriate learning paradigms.These applications include analyzing images of various organs,such as the brain,lung,eye,etc.,to identify specific flaws/diseases for diagnosis.The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification.Most of the extracted image features are irrelevant and lead to an increase in computation time.Therefore,this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features.This process trains the learning paradigm using similarity and correlation-based features over different textural intensities and pixel distributions.The similarity between the pixels over the various distribution patterns with high indexes is recommended for disease diagnosis.Later,the correlation based on intensity and distribution is analyzed to improve the feature selection congruency.Therefore,the more congruent pixels are sorted in the descending order of the selection,which identifies better regions than the distribution.Now,the learning paradigm is trained using intensity and region-based similarity to maximize the chances of selection.Therefore,the probability of feature selection,regardless of the textures and medical image patterns,is improved.This process enhances the performance of ML applications for different medical image processing.The proposed method improves the accuracy,precision,and training rate by 13.19%,10.69%,and 11.06%,respectively,compared to other models for the selected dataset.The mean error and selection time is also reduced by 12.56%and 13.56%,respectively,compared to the same models and dataset.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金Research Center of the College of Computer and Information Sciences,King Saud University,Grant/Award Number:RSPD2024R947King Saud University。
文摘Over the past few years,the application and usage of Machine Learning(ML)techniques have increased exponentially due to continuously increasing the size of data and computing capacity.Despite the popularity of ML techniques,only a few research studies have focused on the application of ML especially supervised learning techniques in Requirement Engineering(RE)activities to solve the problems that occur in RE activities.The authors focus on the systematic mapping of past work to investigate those studies that focused on the application of supervised learning techniques in RE activities between the period of 2002–2023.The authors aim to investigate the research trends,main RE activities,ML algorithms,and data sources that were studied during this period.Forty-five research studies were selected based on our exclusion and inclusion criteria.The results show that the scientific community used 57 algorithms.Among those algorithms,researchers mostly used the five following ML algorithms in RE activities:Decision Tree,Support Vector Machine,Naïve Bayes,K-nearest neighbour Classifier,and Random Forest.The results show that researchers used these algorithms in eight major RE activities.Those activities are requirements analysis,failure prediction,effort estimation,quality,traceability,business rules identification,content classification,and detection of problems in requirements written in natural language.Our selected research studies used 32 private and 41 public data sources.The most popular data sources that were detected in selected studies are the Metric Data Programme from NASA,Predictor Models in Software Engineering,and iTrust Electronic Health Care System.
文摘In the era of Industry 4.0,conditionmonitoring has emerged as an effective solution for process industries to optimize their operational efficiency.Condition monitoring helps minimize unplanned downtime,extending equipment lifespan,reducing maintenance costs,and improving production quality and safety.This research focuses on utilizing Bayesian search-based machine learning and deep learning approaches for the condition monitoring of industrial equipment.The study aims to enhance predictive maintenance for industrial equipment by forecasting vibration values based on domain-specific feature engineering.Early prediction of vibration enables proactive interventions to minimize downtime and extend the lifespan of critical assets.A data set of load information and vibration values from a heavy-duty industrial slip ring induction motor(4600 kW)and gearbox equipped with vibration sensors is used as a case study.The study implements and compares six machine learning models with the proposed Bayesian-optimized stacked Long Short-Term Memory(LSTM)model.The hyperparameters used in the implementation of models are selected based on the Bayesian optimization technique.Comparative analysis reveals that the proposed Bayesian optimized stacked LSTM outperforms other models,showcasing its capability to learn temporal features as well as long-term dependencies in time series information.The implemented machine learning models:Linear Regression(LR),RandomForest(RF),Gradient Boosting Regressor(GBR),ExtremeGradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Support Vector Regressor(SVR)displayed a mean squared error of 0.9515,0.4654,0.1849,0.0295,0.2127 and 0.0273,respectively.The proposed model predicts the future vibration characteristics with a mean squared error of 0.0019 on the dataset containing motor load information and vibration characteristics.The results demonstrate that the proposed model outperforms other models in terms of other evaluation metrics with a mean absolute error of 0.0263 and 0.882 as a coefficient of determination.Current research not only contributes to the comparative performance of machine learning models in condition monitoring but also showcases the practical implications of employing these techniques.By transitioning fromreactive to proactive maintenance strategies,industries canminimize downtime,reduce costs,and prolong the lifespan of crucial assets.This study demonstrates the practical advantages of transitioning from reactive to proactive maintenance strategies using ML-based condition monitoring.
文摘A Distributed Denial-of-Service(DDoS)attack poses a significant challenge in the digital age,disrupting online services with operational and financial consequences.Detecting such attacks requires innovative and effective solutions.The primary challenge lies in selecting the best among several DDoS detection models.This study presents a framework that combines several DDoS detection models and Multiple-Criteria Decision-Making(MCDM)techniques to compare and select the most effective models.The framework integrates a decision matrix from training several models on the CiC-DDOS2019 dataset with Fuzzy Weighted Zero Inconsistency Criterion(FWZIC)and MultiAttribute Boundary Approximation Area Comparison(MABAC)methodologies.FWZIC assigns weights to evaluate criteria,while MABAC compares detection models based on the assessed criteria.The results indicate that the FWZIC approach assigns weights to criteria reliably,with time complexity receiving the highest weight(0.2585)and F1 score receiving the lowest weight(0.14644).Among the models evaluated using the MABAC approach,the Support Vector Machine(SVM)ranked first with a score of 0.0444,making it the most suitable for this work.In contrast,Naive Bayes(NB)ranked lowest with a score of 0.0018.Objective validation and sensitivity analysis proved the reliability of the framework.This study provides a practical approach and insights for cybersecurity practitioners and researchers to evaluate DDoS detection models.
文摘Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques to detect defects,as traditional methods are often prone to human error,and this issue is also addressed through image processing(IP).In addition to IP,automated,accurate,and real-time detection of structural defects,such as cracks,corrosion,and material degradation that conventional inspection techniques may miss,is made possible by Artificial Intelligence(AI)technologies like Machine Learning(ML)and Deep Learning(DL).This review examines the integration of computer vision and AI techniques in Structural Health Monitoring(SHM),investigating their effectiveness in detecting various forms of structural deterioration.Also,it evaluates ML and DL models in SHM for their accuracy in identifying and assessing structural damage,ultimately enhancing safety,durability,and maintenance practices in the field.Key findings reveal that AI-powered approaches,especially those utilizing IP and DL models like CNNs,significantly improve detection efficiency and accuracy,with reported accuracies in various SHM tasks.However,significant research gaps remain,including challenges with the consistency,quality,and environmental resilience of image data,a notable lack of standardized models and datasets for training across diverse structures,and concerns regarding computational costs,model interpretability,and seamless integration with existing systems.Future work should focus on developing more robust models through data augmentation,transfer learning,and hybrid approaches,standardizing protocols,and fostering interdisciplinary collaboration to overcome these limitations and achieve more reliable,scalable,and affordable SHM systems.
文摘The identification of defect types and their reduction values is the most crucial step in coffee grading.In Ethiopia,the current coffee defect investigation techniques rely on manual screening,which requires substantial human resources,time-consuming,and prone to errors.Recently,the deep learning driven object detection has shown promising results in coffee defect identification and grading tasks.In this study,we propose KN-YOLOv8,a modified You Only Look Once version-8(YOLOv8)model optimized for real-time detection of coffee bean defects.This lightweight network incorporates effective feature fusion techniques to accurately detect and locate defects,even among overlapping beans.We have compiled a custom dataset of 562 images comprising thirteen distinct types of defects.The model achieved exceptional performance,with training dataset metrics of 97% recall,100% precision,and 98% mean average precision(mAP).On the test dataset,it maintained outstanding results with 99% recall,100% precision,and 98.9% mAP.The model outperforms existing approaches by achieving a 97.7%m AP for all classes at a 0.5 threshold,while maintaining an optimal precision-recall balance.The model outperforms new approaches by achieving a balance between precision and recall,achieving a mean average precision of 97.7% for all classes.This solution significantly reduces reliance on labor-intensivemanual inspection while improving accuracy.Its lightweight design and high speed make it suitable for real-time industrial applications,transforming coffee quality inspection.
基金supported by the Deanship of Graduate Studies and Scientific Research at Qassim University via Grant No.(QU-APC-2025).
文摘The Internet of Things (IoT) and edge-assisted networking infrastructures are capable of bringing data processing and accessibility services locally at the respective edge rather than at a centralized module. These infrastructures are very effective in providing a fast response to the respective queries of the requesting modules, but their distributed nature has introduced other problems such as security and privacy. To address these problems, various security-assisted communication mechanisms have been developed to safeguard every active module, i.e., devices and edges, from every possible vulnerability in the IoT. However, these methodologies have neglected one of the critical issues, which is the prediction of fraudulent devices, i.e., adversaries, preferably as early as possible in the IoT. In this paper, a hybrid communication mechanism is presented where the Hidden Markov Model (HMM) predicts the legitimacy of the requesting device (both source and destination), and the Advanced Encryption Standard (AES) safeguards the reliability of the transmitted data over a shared communication medium, preferably through a secret shared key, i.e., , and timestamp information. A device becomes trusted if it has passed both evaluation levels, i.e., HMM and message decryption, within a stipulated time interval. The proposed hybrid, along with existing state-of-the-art approaches, has been simulated in the realistic environment of the IoT to verify the security measures. These evaluations were carried out in the presence of intruders capable of launching various attacks simultaneously, such as man-in-the-middle, device impersonations, and masquerading attacks. Moreover, the proposed approach has been proven to be more effective than existing state-of-the-art approaches due to its exceptional performance in communication, processing, and storage overheads, i.e., 13%, 19%, and 16%, respectively. Finally, the proposed hybrid approach is pruned against well-known security attacks in the IoT.
文摘Diabetic retinopathy(DR)is a complication of diabetes that can lead to reduced vision or even blindness if left untreated.Therefore,early and accurate detection of this disease is crucial for diabetic patients to prevent vision loss.This study aims to develop a deep-learning approach for the early and precise diagnosis of DR,asmanual detection can be time-consuming,costly,and prone to human error.The classification task is divided into two groups for binary classification:patients with DR(diagnoses 1–4)and those without DR(diagnosis 0).For multi-class classification,the categories are no DR,mild DR,moderate DR,severe DR,and proliferative diabetic retinopathy(PDR).To achieve this,the proposed model utilizes two pre-trained convolutional neural networks(CNNs),specifically ResNet50 and DenseNet-121.Both models were trained and evaluated on fundus images sourced from the widely recognized APTOS dataset,a publicly available resource.,and achieved impressive training and testing accuracies.For binary classification,DenseNet-121 achieved an accuracy of 98.1%,while ResNet50 attained an accuracy of 97.4%.Inmulti-class classification forDR,DenseNet-121 achieved an accuracy of 82.0%,and ResNet50 reached an accuracy of 80.8%.The results are promising and comparable to state-of-the-art techniques in the literature for both binary and multi-label classification of DR.
基金supported by the“Technology Commercialization Collaboration Platform Construction”project of the Innopolis Foundation(Project Number:2710033536)the Competitive Research Fund of The University of Aizu,Japan.
文摘Sentiment Analysis,a significant domain within Natural Language Processing(NLP),focuses on extracting and interpreting subjective information-such as emotions,opinions,and attitudes-from textual data.With the increasing volume of user-generated content on social media and digital platforms,sentiment analysis has become essential for deriving actionable insights across various sectors.This study presents a systematic literature review of sentiment analysis methodologies,encompassing traditional machine learning algorithms,lexicon-based approaches,and recent advancements in deep learning techniques.The review follows a structured protocol comprising three phases:planning,execution,and analysis/reporting.During the execution phase,67 peer-reviewed articles were initially retrieved,with 25 meeting predefined inclusion and exclusion criteria.The analysis phase involved a detailed examination of each study’s methodology,experimental setup,and key contributions.Among the deep learning models evaluated,Long Short-Term Memory(LSTM)networks were identified as the most frequently adopted architecture for sentiment classification tasks.This review highlights current trends,technical challenges,and emerging opportunities in the field,providing valuable guidance for future research and development in applications such as market analysis,public health monitoring,financial forecasting,and crisis management.
