IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100500

Mohammad Ashiqur Noor , Samia Binta Hassan , Md. Sakib Bin Alam , Aiman Lameesa , Md Anonno Rahman Siddique

{"title":"A privacy-preserving federated learning framework with graph neural networks for enhanced heart attack risk prediction","authors":"Mohammad Ashiqur Noor , Samia Binta Hassan , Md. Sakib Bin Alam , Aiman Lameesa , Md Anonno Rahman Siddique","doi":"10.1016/j.array.2025.100500","DOIUrl":"10.1016/j.array.2025.100500","url":null,"abstract":"<div><div>Cardiovascular disease, a predominant global cause of death, underlines the critical need for sophisticated and privacy-conserving predictive systems for early risk assessment. This paper introduces a novel federated learning (FL) architecture that incorporates graph neural networks (GNNs) to facilitate secure and efficient heart attack risk prediction utilizing decentralized healthcare data. Our methodology generates graph-structured representations from preprocessed client data, dispersed among three clients to maintain data locality and safeguard patient privacy. The GNN models are trained locally, with only the acquired weights transmitted to a central server for secure aggregation. The proposed framework attains a classification accuracy of 96.79 % through comprehensive ablation studies and hyperparameter optimization, exceeding baseline models such as Graph Attention Networks (GAT), 1D Convolutional Neural Networks (1D-CNN), conventional machine learning, and ensemble techniques. Additional validation using an external dataset supports the model's robustness, with an accuracy of 98.77 %. Furthermore, trials conducted on a consolidated dataset demonstrate consistent performance, hence strengthening the framework's generalizability. These findings illustrate the potential of integrating GNNs with federated learning for privacy-preserving, high-performance prediction of heart attack risk in practical healthcare contexts.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100500"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144921761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing spinal cord lesion segmentation using hierarchical classification and U-NET based segmentation model 基于层次分类和U-NET分割模型的脊髓损伤分割优化

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100495

David Cahyadi , Yosi Kristian , Edwin Pramana , I. Gusti Lanang Ngurah Agung Artha Wiguna , Maria Florencia Deslivia , Yuliana Melita Pranoto , Ivan Alexander Liando , Rudi Limantara

{"title":"Optimizing spinal cord lesion segmentation using hierarchical classification and U-NET based segmentation model","authors":"David Cahyadi , Yosi Kristian , Edwin Pramana , I. Gusti Lanang Ngurah Agung Artha Wiguna , Maria Florencia Deslivia , Yuliana Melita Pranoto , Ivan Alexander Liando , Rudi Limantara","doi":"10.1016/j.array.2025.100495","DOIUrl":"10.1016/j.array.2025.100495","url":null,"abstract":"<div><div>Rapid and accurate identification of spinal cord lesions is crucial in emergency medical care; however, current automated analysis systems face significant challenges in terms of processing speed and accuracy. This study presents a novel approach that combines hierarchical classification with segmentation models for automated spinal cord lesion analysis that can operate without human intervention, from image selection to lesion segmentation. We developed and evaluated a multistage classification system utilizing state-of-the-art efficient vision models, including EfficientVit, MobileNetV4, and RepVit, and compared it with a ResNet baseline. We incorporated a transfer learning strategy for lesion segmentation, leveraging pre-trained models to improve lesion boundary delineation. In addition, we introduced a synthetic lesion augmentation framework to address data scarcity and improve the generalization of the model. The system was trained and validated using six public datasets, including RadImageNet (1.4M images), and two private hospital datasets comprising 351 patients with spinal MRI scans. Our hierarchical classification approach achieved an end-to-end F1 score of 0.8357 using EfficientVit, whereas our optimized U-Net segmentation model attained a mean Dice score of 0.7527, surpassing previous approaches. Notably, the system achieved a ninefold increase in processing speed, reducing the lesion segmentation analysis time from 9.86 to 1.04 s per series and achieving a classification inference speed of 11.47 ms per image. Our findings suggest that this approach may support efficient automated spinal cord lesion analysis in resource-constrained clinical settings, potentially aiding diagnosis in emergency care, supporting radiologist workflow, and increasing the accessibility of spinal cord lesion analysis.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100495"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144921762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A robust and adaptive driver identification framework for intelligent transportation systems 面向智能交通系统的鲁棒自适应驾驶员识别框架

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100506

Wenze Shi , Ao Guo , Xufei Chu , Siyu Yang , Zilin Huang , Lin Lu

{"title":"A robust and adaptive driver identification framework for intelligent transportation systems","authors":"Wenze Shi , Ao Guo , Xufei Chu , Siyu Yang , Zilin Huang , Lin Lu","doi":"10.1016/j.array.2025.100506","DOIUrl":"10.1016/j.array.2025.100506","url":null,"abstract":"<div><div>Driver identification via behavioral characterization is a popular topic of intelligent transportation systems, yet existing methods often struggle with varying trip segmentation and vehicle type situations. This study proposes a refined deep learning framework to improve model robustness and adaptability under limited driving behavioral signal conditions. Our approach partitions driving trips into fixed-length identification windows, each with overlapping dynamic segments to allow the capture of temporal dependencies of driving patterns. Then, a deep neural network structure that combines a residual sequential autoencoder with an attention mechanism is incorporated to enhance the model identification performance through adaptive regularization. The framework is validated on two real-world datasets comprising 5 truck drivers and 5 sedan drivers through conventional train-validation-test. Our models achieve up to 91% accuracy for sedan drivers and 75% for truck drivers, significantly outperforming the baseline models. Notably, our approach maintains consistent performance across varying segment lengths, with an accuracy difference of only about 4% when the window length changes from 60 to 180 s. Experimental results demonstrate that our framework achieves strong segmentation-variability robustness and cross-vehicle adaptability.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100506"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TCP DCERL+: Improving congestion control in mobile ad hoc networks TCP DCERL+：改进移动自组织网络中的拥塞控制

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100472

Srutha Keerthi Varala, Hosam El-Ocla, Vikram Singh

引用次数: 0

Challenge-response PIN authentication system to withstand shoulder surfing and recording attacks 挑战-响应PIN认证系统，以抵御肩冲浪和记录攻击

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100505

Farid Binbeshr , Lip Yee Por , Muhammad Imam , M.L. Mat Kiah , Mohammad Hammoudeh

{"title":"Challenge-response PIN authentication system to withstand shoulder surfing and recording attacks","authors":"Farid Binbeshr , Lip Yee Por , Muhammad Imam , M.L. Mat Kiah , Mohammad Hammoudeh","doi":"10.1016/j.array.2025.100505","DOIUrl":"10.1016/j.array.2025.100505","url":null,"abstract":"<div><div>Personal Identification Number (PIN) authentication remains widely used despite its vulnerability to shoulder surfing and recording attacks, due to the repeated exposure of static PINs in traditional systems. To address this, we propose a novel visual challenge-response PIN authentication system that generates a one-time PIN (OTP) for each session using a lightweight addition modulo 10 operation. Unlike prior approaches, our system requires no extra hardware, completes authentication in a single round, and maintains compatibility with regular PIN entry. We evaluate two design variants, TablePIN and RegularPIN, in a controlled user study with 30 participants. The results show 100% resistance to shoulder surfing attacks and over 80% resistance to recording attacks for hard PINs, with usability metrics including average login times under 15 s and success rates above 90%. User feedback indicates a strong preference for using the system in high-security contexts. We also introduce a PIN strength checker, which complements the system by helping prevent the use of weak, easily guessable PINs. Overall, the proposed system achieves a strong balance between usability and enhanced security, making it a viable alternative to traditional PIN authentication methods.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100505"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of mixture of experts models for the recognition of pests and diseases in maize 混合专家模型在玉米病虫害识别中的应用

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100502

Luis Enrique Raya-González , Víctor Alfonso Alcántar-Camarena , Jonathan Cepeda-Negrete , Antonio Bustos-Gaytán , Ma del Rosario Abraham-Juárez , Noé Saldaña-Robles

{"title":"Application of mixture of experts models for the recognition of pests and diseases in maize","authors":"Luis Enrique Raya-González , Víctor Alfonso Alcántar-Camarena , Jonathan Cepeda-Negrete , Antonio Bustos-Gaytán , Ma del Rosario Abraham-Juárez , Noé Saldaña-Robles","doi":"10.1016/j.array.2025.100502","DOIUrl":"10.1016/j.array.2025.100502","url":null,"abstract":"<div><div>Manual monitoring of pests and diseases in maize crops requires considerable time and resources, significantly increasing production costs. Artificial intelligence (AI)-based studies have explored their automated detection, primarily through transfer learning architectures, although with limited success. This study evaluated and compared four AI approaches: convolutional neural networks (CNN), a hybrid CNN with support vector machines (CNN-SVM), mixture of experts (MoE) models, and transfer learning architectures. Eighteen CNN models were developed and optimized using a factorial design, and the best-performing model was used as the foundation for constructing the hybrid CNN-SVM and CNN-SVM-MoE models. The CNN-SVM-MoE model achieved the highest accuracy (99.14 %) and demonstrated strong generalization capabilities, even with data collected under field conditions. In contrast, transfer learning architectures showed lower performance. Statistical analysis revealed significant differences among the models, highlighting the superiority of the CNN-SVM-MoE approach. The results confirm that MoE models enhance performance in classifying maize pests and diseases and offer strong potential for integration into mobile or embedded devices, enabling their direct application in the field.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100502"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144987918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

KPN-anonymity: Extension of K-anonymity for user anonymity evaluation on web applications kpn -匿名：对k -匿名的扩展，用于web应用的用户匿名性评估

IF 4.5

Array Pub Date : 2025-09-01 DOI: 10.1016/j.array.2025.100499

Ángel Merino , Ángel Cuevas , Rubén Cuevas

{"title":"KPN-anonymity: Extension of K-anonymity for user anonymity evaluation on web applications","authors":"Ángel Merino , Ángel Cuevas , Rubén Cuevas","doi":"10.1016/j.array.2025.100499","DOIUrl":"10.1016/j.array.2025.100499","url":null,"abstract":"<div><div>User data powers much of the Internet nowadays. Beyond personally identifiable information (PII), online systems routinely collect several non-PII user attributes. In world-scale datasets, users may share their combination of attribute values with only a few others, or even be the sole individual matching a specific combination. This makes evaluating and comparing general anonymity across systems challenging, as classical K-anonymity would often be one. We introduce a general methodology to assess user anonymity in general datasets, addressing this issue. Our approach adapts the concept of K-anonymity to focus on most users rather than the least anonymous ones, proposing the metric <span><math><msubsup><mrow><mi>K</mi></mrow><mrow><mi>P</mi></mrow><mrow><mi>N</mi></mrow></msubsup></math></span>: the minimum anonymity (K) among the most anonymous P% of users defined by N attributes. This metric enables the comparison of anonymity levels across systems, helping to identify risks and evaluate the impact of changes such as attribute granularity redesign.</div><div>We demonstrate the applicability of this metric through a case study involving three digital platforms: Meta, LinkedIn, and Twitter (X), leveraging audience data from their advertising systems. We define three common attributes and one platform-specific attribute to reflect each platform’s unique segmentation capabilities. By examining all possible combinations and applying our metric, we demonstrate that Twitter provides the highest levels of anonymity, while Meta yields the lowest. We also study how a specific change in the age attribute cardinality can increase anonymity by more than 10 times on Meta. This case illustrates the utility of our metric in assessing and comparing anonymity risks in real-world data systems.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100499"},"PeriodicalIF":4.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145018628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CST-AFNet: A dual attention-based deep learning framework for intrusion detection in IoT networks CST-AFNet：用于物联网网络入侵检测的基于双注意力的深度学习框架

IF 4.5

Array Pub Date : 2025-08-28 DOI: 10.1016/j.array.2025.100501

Waqas Ishtiaq , Ashrafun Zannat , A.H.M. Shahariar Parvez , Md. Alamgir Hossain , Muntasir Hasan Kanchan , Muhammad Masud Tarek

{"title":"CST-AFNet: A dual attention-based deep learning framework for intrusion detection in IoT networks","authors":"Waqas Ishtiaq , Ashrafun Zannat , A.H.M. Shahariar Parvez , Md. Alamgir Hossain , Muntasir Hasan Kanchan , Muhammad Masud Tarek","doi":"10.1016/j.array.2025.100501","DOIUrl":"10.1016/j.array.2025.100501","url":null,"abstract":"<div><div>The rapid expansion of the Internet of Things (IoT) has revolutionized modern industries by enabling smart automation and real-time connectivity. However, this evolution has also introduced complex cybersecurity challenges due to the heterogeneous, resource-constrained, and distributed nature of these environments. To address these challenges, this research presents CST-AFNet, a novel dual attention-based deep learning framework specifically designed for robust intrusion detection in IoT networks. The model integrates multi-scale Convolutional Neural Networks (CNNs) for spatial feature extraction, Bidirectional Gated Recurrent Units (BiGRUs) for capturing temporal dependencies, and a dual attention mechanism, channel and temporal attention to enhance focus on critical patterns in the data. The proposed method was trained and evaluated on the Edge-IIoTset dataset, a comprehensive and realistic benchmark containing over 2.2 million labeled instances spanning 15 attack types and benign traffic, collected from a seven-layer industrial testbed. Our proposed model achieves an outstanding accuracy with 15 attack types and benign traffic. CST-AFNet model achieves 99.97 % accuracy. Moreover, this model demonstrates an exceptional accuracy with macro-averaged precision, recall, and F1-score all above 99.3 %. Experimental results demonstrate that CST-AFNet achieves superior detection accuracy, significantly outperforming traditional deep learning models. The findings confirm that CST-AFNet is a powerful and scalable solution for real-time cyber threat detection in complex IoT/IIoT environments, paving the way for more secure, intelligent, and adaptive cyber-physical systems.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100501"},"PeriodicalIF":4.5,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ensemble approach assisted grade capacitance prediction of biomass-derived electrode materials: New insights and implications for high performance supercapacitors 集成方法辅助生物质衍生电极材料的等级电容预测：高性能超级电容器的新见解和意义

IF 4.5

Array Pub Date : 2025-08-26 DOI: 10.1016/j.array.2025.100497

Richa Dubey , Ravi Prakash Dwivedi , Nilanjan Tewari , Velmathi Guruviah

{"title":"Ensemble approach assisted grade capacitance prediction of biomass-derived electrode materials: New insights and implications for high performance supercapacitors","authors":"Richa Dubey , Ravi Prakash Dwivedi , Nilanjan Tewari , Velmathi Guruviah","doi":"10.1016/j.array.2025.100497","DOIUrl":"10.1016/j.array.2025.100497","url":null,"abstract":"<div><div>Biomass derived carbon precursors have emerged as the promising candidates for electrode materials in supercapacitors. Beyond structural diversity, biomass-based materials offer various advantages of sustainability, biodegradability, heteroatom abundance, hierarchical structure along with eco friendliness. Activated carbon electrode synthesis and operational parameters play significant role in affecting the electrochemical performance of biomass-based supercapacitors.</div><div>In the current research, grade prediction of specific capacitance for biomass derived activated carbon (BDAC) supercapacitor was performed using ten ensemble approaches. Proposed models M2, M9 and M10 showed highest kappa values of 0.996, 0.977 and 0.981 respectively and lowest RMSE values of 0.179, 0.212 and 0.201 respectively by selecting 14 top rank features on the basis of chemical activation, electrode preparation procedures, structural parameters and electrode operational parameters. Further, sensitivity and specificity parameters were evaluated to provide effectiveness in predicting the actual capacitance values. Ensemble approach facilitated to improve the overall prediction accuracy by capturing a more explicit understanding of the considered dataset. Principal Component Analysis and Attribute polarization analysis showed prominent effect of activation ratio, conductive material ratio and the gas adsorption parameters (V<sub>0.1</sub>-V<sub>0.9</sub>) on biomass-based supercapacitors. This multi-data approach supported in attaining cognizance of biomass derived materials contributing to electrode fabrication for achieving higher capacitance.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100497"},"PeriodicalIF":4.5,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144912865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving test suite generation quality through machine learning-driven boundary value analysis 通过机器学习驱动的边界值分析提高测试套件生成质量

IF 4.5

Array Pub Date : 2025-08-26 DOI: 10.1016/j.array.2025.100496

Xiujing Guo , Hiroyuki Okamura , Tadashi Dohi

{"title":"Improving test suite generation quality through machine learning-driven boundary value analysis","authors":"Xiujing Guo , Hiroyuki Okamura , Tadashi Dohi","doi":"10.1016/j.array.2025.100496","DOIUrl":"10.1016/j.array.2025.100496","url":null,"abstract":"<div><div>Boundary value analysis (BVA) is a widely used method in software testing to identify errors at the boundaries of input domains. However, traditional BVA is resource intensive and often impractical for complex systems with expansive input spaces. Recent advances in machine learning offer potential for automating BVA, improving efficiency and fault detection capabilities. This paper introduces a machine learning based approach for the automatic generation of boundary test inputs. The research focuses on addressing the automation of BVA processes, with a particular emphasis on white-box testing scenarios. The proposed methodology consists of two main steps. First, a ML-based discriminator is trained to identify the existence of a boundary between two test inputs. Based on the discriminator’s output, we calculate the boundary density using two proposed methods: “pointDensity” and “pairDensity.” In the second step, Markov Chain Monte Carlo (MCMC) techniques are applied to generate test inputs guided by the calculated boundary densities. Experiments were conducted to evaluate the fault detection capabilities of the ML-based approach compared to concolic testing and manual boundary analysis. The results show that our proposed method surpasses manual boundary analysis in five of the eight programs and outperforms concolic testing in four out of eight programs.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100496"},"PeriodicalIF":4.5,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Array最新文献