Array最新文献

筛选
英文 中文
IoT-driven real-time weather measurement and forecasting mobile application with machine learning integration 物联网驱动的实时天气测量和预报移动应用程序与机器学习集成
IF 4.5
Array Pub Date : 2025-08-07 DOI: 10.1016/j.array.2025.100474
Jul Jalal Al-Mamur Sayor , Nishat Tasnim Shishir , Bitta Boibhov Barmon , Sumon Ahemed , Md. Moshiur Rahman
{"title":"IoT-driven real-time weather measurement and forecasting mobile application with machine learning integration","authors":"Jul Jalal Al-Mamur Sayor ,&nbsp;Nishat Tasnim Shishir ,&nbsp;Bitta Boibhov Barmon ,&nbsp;Sumon Ahemed ,&nbsp;Md. Moshiur Rahman","doi":"10.1016/j.array.2025.100474","DOIUrl":"10.1016/j.array.2025.100474","url":null,"abstract":"<div><div>The importance of accurate and timely weather information cannot be overstated, as it is crucial for daily activities, safety, and decision-making across various sectors. Existing weather forecasting systems often lack the precision required for localized conditions, relying on data from distant weather stations and limited environmental parameters. This paper introduces a real-time weather forecasting mobile application that integrates machine learning and IoT technology to address these challenges effectively. The system incorporates a mobile application designed to provide users with real-time weather updates through an intuitive and easy-to-use platform. It utilizes IoT sensors to collect comprehensive environmental data, including temperature, humidity, wind speed, barometric pressure, and rainfall, which are strategically deployed to ensure the collection of localized, high-resolution weather data in real-time. Additionally, the system leverages LoRa technology for robust long-range data transmission. It employs an Incremental Learning model that continuously adapts to new environmental inputs, thereby enhancing forecasting precision and efficiency. APIs (Application Programming Interface) enable efficient data input and retrieval, guaranteeing smooth connection and integration between the sensors and the forecasting algorithms. Moreover, we analyze forecasts from Google and systematically compare them with our localized predictions to highlight the advantages of site-specific deployment for achieving superior localized outcomes. This creative method offers a scalable and flexible solution that can be expanded to cover larger geographic areas in addition to providing precise weather forecasts. The project addresses the limitations of existing weather applications by delivering precise local weather conditions and an intuitive user experience. The initial implementation in Gazipur, Bangladesh, demonstrates the system’s effectiveness and potential for wider application nationwide.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100474"},"PeriodicalIF":4.5,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827668","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
Attack surface analysis and mitigation for near-field communication networks and devices in smart grids 智能电网中近场通信网络和设备的攻击面分析与缓解
IF 4.5
Array Pub Date : 2025-08-05 DOI: 10.1016/j.array.2025.100447
Jing Guo, Zhimin Gu, Haitao Jiang, Yan Li, Daohua Zhu
{"title":"Attack surface analysis and mitigation for near-field communication networks and devices in smart grids","authors":"Jing Guo,&nbsp;Zhimin Gu,&nbsp;Haitao Jiang,&nbsp;Yan Li,&nbsp;Daohua Zhu","doi":"10.1016/j.array.2025.100447","DOIUrl":"10.1016/j.array.2025.100447","url":null,"abstract":"<div><div>With growing demand and increasing concern for energy sustainability, smart grids (SGs) have emerged as a promising solution by integrating information and communication technologies to enhance the efficiency, reliability, and flexibility of power systems. While SGs enable real-time monitoring, they also introduce new security risks, particularly for endpoint and edge devices such as smart meters and inverters. Although earlier attacks primarily targeted centralized systems, recent studies have highlighted vulnerabilities on the consumer side, especially in the context of MadIoT-style attacks (MadIoT, short for Manipulation of Demand via IoT, refers to a class of coordinated attacks exploiting high-wattage IoT devices to destabilize power grids). This paper analyzes the attack surfaces of near-field communication network (NFN) protocols and devices within SGs, with a focus on widely adopted public protocols. We propose mitigation strategies to address these risks, including a reverse engineering-based edge device firmware emulation and execution method, a large language model-based protocol analysis approach, and a fuzzing-based malicious behavior simulation technique in a NFN. In our experiments, the proposed AFL-Netzob framework discovered 6 vulnerabilities across 3 firmware samples and achieved up to a 2× improvement in fuzzing efficiency compared to Boofuzz. These results demonstrate the practical effectiveness and general applicability of our framework in real-world smart grid scenarios.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100447"},"PeriodicalIF":4.5,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828728","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
Multi-task deep learning for simultaneous prediction of steel purity and carbon capture rate using membrane separation technology in integrated steelmaking processes 综合炼钢过程中膜分离技术的多任务深度学习同时预测钢纯度和碳捕集率
IF 4.5
Array Pub Date : 2025-08-05 DOI: 10.1016/j.array.2025.100485
Somboon Sukpancharoen , Pakon Sakdee , Natacha Phetyim , Rinlada Sirisangsawang , Chayut Sungsook
{"title":"Multi-task deep learning for simultaneous prediction of steel purity and carbon capture rate using membrane separation technology in integrated steelmaking processes","authors":"Somboon Sukpancharoen ,&nbsp;Pakon Sakdee ,&nbsp;Natacha Phetyim ,&nbsp;Rinlada Sirisangsawang ,&nbsp;Chayut Sungsook","doi":"10.1016/j.array.2025.100485","DOIUrl":"10.1016/j.array.2025.100485","url":null,"abstract":"<div><div>Steel production significantly contributes to global CO<sub>2</sub> emissions, demanding simultaneous optimization of product quality and environmental performance. Current prediction models address steel purity and carbon capture separately, missing opportunities for integrated process optimization. This work presents the first comparison of single-task learning (STL) versus multi-task learning (MTL) for simultaneous prediction of iron purity classification and carbon capture rates in membrane-integrated steelmaking processes. Deep neural networks (DNNs) were trained on 1,473 validated simulation data points with 30 input features covering raw materials, operating conditions, and membrane specifications. The MTL architecture employed shared hidden layers with task-specific output branches, utilizing ReLU activation functions and Adam optimization. STL achieved 97.62% accuracy with perfect recall for iron purity classification, while MTL demonstrated superior carbon capture prediction (R<sup>2</sup> = 0.9948 vs 0.9902), representing 30% improvement through shared process learning. Feature importance analysis revealed air flow rate as the dominant factor for iron purity, while membrane feed pressure controlled carbon capture performance. Results demonstrate strategic model selection for steel optimization: STL for critical quality control requiring zero false negatives; MTL for integrated processes leveraging parameter interactions. This framework enables simultaneous steel quality and environmental enhancement, advancing sustainable steelmaking and multi-objective optimization in process industries.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100485"},"PeriodicalIF":4.5,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144810583","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
Impact of surrogate model accuracy on performance and model management strategy in surrogate-assisted evolutionary algorithms 代理模型精度对代理辅助进化算法性能和模型管理策略的影响
IF 4.5
Array Pub Date : 2025-08-05 DOI: 10.1016/j.array.2025.100461
Yuki Hanawa , Tomohiro Harada , Yukiya Miura
{"title":"Impact of surrogate model accuracy on performance and model management strategy in surrogate-assisted evolutionary algorithms","authors":"Yuki Hanawa ,&nbsp;Tomohiro Harada ,&nbsp;Yukiya Miura","doi":"10.1016/j.array.2025.100461","DOIUrl":"10.1016/j.array.2025.100461","url":null,"abstract":"<div><div>Surrogate-assisted evolutionary algorithms (SAEAs) are widely used to solve expensive optimization problems where evaluating candidate solutions is computationally intensive. To reduce this cost, SAEAs employ surrogate models—machine learning models that approximate expensive evaluation functions. While previous studies have investigated how surrogate model prediction accuracy affects SAEA performance, they are limited in two key ways: (1) lacking a comprehensive analysis of commonly used model management strategies, and (2) comparing these strategies under inconsistent surrogate accuracy settings. To address these limitations, we construct a pseudo-surrogate model with adjustable prediction accuracy, enabling fair comparisons across different strategies. We evaluate three representative strategies — pre-selection (PS), individual-based (IB), and generation-based (GB) — using a common pseudo-surrogate model on six benchmark problems in 10 and 30 dimensions from the CEC2015 competition. Results show that although higher surrogate accuracy generally enhances search performance, the impact varies by strategy. PS exhibits steady improvement with increasing accuracy, while IB and GB maintain robust performance beyond a certain threshold. Notably, SAEAs with accuracy above 0.6 consistently outperform the baseline without surrogates. In strategy comparisons, GB performs best across a wide accuracy range, IB excels at lower accuracies, and PS at higher ones. These findings support developing guidelines for selecting model management strategies based on surrogate accuracy.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100461"},"PeriodicalIF":4.5,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144781268","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
Ultra Wideband radar-based gait analysis for gender classification using artificial intelligence 基于超宽带雷达的人工智能性别分类步态分析
IF 4.5
Array Pub Date : 2025-08-04 DOI: 10.1016/j.array.2025.100477
Adil Ali Saleem , Hafeez Ur Rehman Siddiqui , Muhammad Amjad Raza , Sandra Dudley , Julio César Martínez Espinosa , Luis Alonso Dzul López , Isabel de la Torre Díez
{"title":"Ultra Wideband radar-based gait analysis for gender classification using artificial intelligence","authors":"Adil Ali Saleem ,&nbsp;Hafeez Ur Rehman Siddiqui ,&nbsp;Muhammad Amjad Raza ,&nbsp;Sandra Dudley ,&nbsp;Julio César Martínez Espinosa ,&nbsp;Luis Alonso Dzul López ,&nbsp;Isabel de la Torre Díez","doi":"10.1016/j.array.2025.100477","DOIUrl":"10.1016/j.array.2025.100477","url":null,"abstract":"<div><div>Gender classification plays a vital role in various applications, particularly in security and healthcare. While several biometric methods such as facial recognition, voice analysis, activity monitoring, and gait recognition are commonly used, their accuracy and reliability often suffer due to challenges like body part occlusion, high computational costs, and recognition errors. This study investigates gender classification using gait data captured by Ultra-Wideband radar, offering a non-intrusive and occlusion-resilient alternative to traditional biometric methods. A dataset comprising 163 participants was collected, and the radar signals underwent preprocessing, including clutter suppression and peak detection, to isolate meaningful gait cycles. Spectral features extracted from these cycles were transformed using a novel integration of Feedforward Artificial Neural Networks and Random Forests , enhancing discriminative power. Among the models evaluated, the Random Forest classifier demonstrated superior performance, achieving 94.68% accuracy and a cross-validation score of 0.93. The study highlights the effectiveness of Ultra-wideband radar and the proposed transformation framework in advancing robust gender classification.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100477"},"PeriodicalIF":4.5,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144766643","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
Impact of software quality on organizational performance 软件质量对组织绩效的影响
IF 4.5
Array Pub Date : 2025-07-31 DOI: 10.1016/j.array.2025.100476
Ahmad Nabot , Ahmad Al-Qerem
{"title":"Impact of software quality on organizational performance","authors":"Ahmad Nabot ,&nbsp;Ahmad Al-Qerem","doi":"10.1016/j.array.2025.100476","DOIUrl":"10.1016/j.array.2025.100476","url":null,"abstract":"<div><div>Software has emerged as a critical strategic asset that drives organizational success and competitive advantage. In today’s software-centric economy, businesses manage their software resources to enhance organizational performance effectively. However, low-quality software systems can significantly hinder this goal. This study investigates the impact of information quality (IQ), quality of service (QoS), and software quality (SQ) on organizational performance (OP). A quantitative research approach was employed, involving a survey of 360 participants. Data analysis techniques, including exploratory factor analysis (EFA), confirmatory factor analysis (CFA), and structural equation modeling (SEM), were utilized to test the proposed hypotheses. The findings reveal a significant positive correlation between information system quality and organizational performance. These results underscore the importance of prioritizing the quality of software systems, the quality of information, and the quality of service to achieve superior organizational performance. The implications of these findings for managers are discussed, highlighting the need to invest in software quality initiatives and to continuously monitor and improve information and service quality to drive business success.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100476"},"PeriodicalIF":4.5,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144756873","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
Hybrid bio-inspired optimization based routing protocol for enhancing data transmission in clustered network 基于混合生物优化的路由协议增强集群网络中的数据传输
IF 4.5
Array Pub Date : 2025-07-30 DOI: 10.1016/j.array.2025.100481
Kirandeep Kaur, Satinder Kaur
{"title":"Hybrid bio-inspired optimization based routing protocol for enhancing data transmission in clustered network","authors":"Kirandeep Kaur,&nbsp;Satinder Kaur","doi":"10.1016/j.array.2025.100481","DOIUrl":"10.1016/j.array.2025.100481","url":null,"abstract":"<div><div>The Internet of Things (IoT) incorporates Wireless Sensor Networks (WSNs) to gather data in real time for a range of applications, including smart homes and healthcare. Energy efficiency is an essential concern considering sensor nodes have limited energy resources. Early node failures, network segmentation, and reduced quality of service (QoS) are driven by constant and uneven energy consumption among sensor nodes, particularly during data transmission and cluster head (CH) processes. For addressing this issue, the current study proposes a hybrid optimization approach for a clustering protocol that mitigates transmission latency and optimises energy efficiency by integrating bi-objective Tabu Search and Ant Colony Optimization (ACO). The primary goals include to extend the network lifetime via efficient data transmission and the most optimal possible cluster head (CH) selection. In two deployment scenarios, the protocol is simulated in MATLAB and assessed based on residual energy, transmission delay, network stability, and lifetime. Results indicate a 73 % lifetime increase, a 25 % improvement in network stability, and a 36 % decrease in delivery latency when compared to GWO, ESO, GECR, and LEACH. The proposed protocol surpasses other protocols in extending WSN capabilities in Internet of Things systems.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100481"},"PeriodicalIF":4.5,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144756874","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
An optimal weighting-based hybrid classifier for Children's congenital heart diseases signal processing 儿童先天性心脏病信号处理的最优加权混合分类器
IF 4.5
Array Pub Date : 2025-07-28 DOI: 10.1016/j.array.2025.100479
Morteza Ebrahimpour , Mehdi Khashei
{"title":"An optimal weighting-based hybrid classifier for Children's congenital heart diseases signal processing","authors":"Morteza Ebrahimpour ,&nbsp;Mehdi Khashei","doi":"10.1016/j.array.2025.100479","DOIUrl":"10.1016/j.array.2025.100479","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Classification is one of the most prominent modeling approaches that can be successfully applied in model-based medical support systems to make more accurate diagnostic decisions. The classification literature indicates that numerous classifiers with different characteristics have been developed and frequently applied across a wide range of medical diagnostic processes. Several features of a classifier, such as accuracy, reliability, and complexity, can be considered when choosing the most appropriate classifier for modeling purposes in a medical decision support system. Among these features, classification accuracy is one of the most critical due to its significant impact on the quality and precision of medical diagnoses. However, achieving accurate results, especially in the medical domain which often contains complex and mixed patterns, is still a commonly difficult task. Hybridization is among the most popular techniques frequently used in the classification literature to enhance accuracy. In this paper, a hybrid classifier incorporating Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) is proposed and applied to diagnose congenital heart disease in children. The most distinguishing feature of the proposed hybrid classifier compared to existing ones is its optimal weighting algorithm. In this study, an optimal weighting algorithm is developed which, unlike previously proposed algorithms, can guarantee that the best accuracy will be achieved. The main objective of the proposed optimal weighting-based CNN-LSTM-SVM (OCLS) hybrid classifier is to simultaneously leverage the unique advantages of CNN in feature extraction from input signals, LSTM in modeling the sequential patterns of signals, SVM in classifying regular patterns, and especially the proposed weighting algorithm to optimally integrate the outputs of these components. Experimental findings based on the Children's Congenital Heart Disease benchmark dataset demonstrate that the proposed hybrid classification model outperforms its individual base classifiers. Furthermore, it delivers superior accuracy compared to several recently introduced hybrid models in the existing literature. Notably, the proposed method also outperforms CNN-LSTM-SVM combinations that use conventional weighting strategies such as Simple Average (SA), Majority Voting (MV), and metaheuristic optimization algorithms. Numerical results illustrate that the proposed hybrid classifier can, on average, improve the classification rate and diagnostic capability by 7.09 %, 13.60 %, 5.52 %, and 6.84 % compared to its individual components, other single shallow or deep statistical or intelligent classifiers, other weighting-based parallel hybrid classifiers, and other recently developed classifiers for congenital heart disease diagnosis, respectively. In addition, these improvements are not limited to the classification rate. The obtained results indicate that the prop","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100479"},"PeriodicalIF":4.5,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750448","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
Between machines and art: The impact of CNC technology on artistic creation 机器与艺术之间:数控技术对艺术创作的影响
IF 4.5
Array Pub Date : 2025-07-23 DOI: 10.1016/j.array.2025.100466
Marcelo Fraile-Narváez , Mihaela I. Chidean
{"title":"Between machines and art: The impact of CNC technology on artistic creation","authors":"Marcelo Fraile-Narváez ,&nbsp;Mihaela I. Chidean","doi":"10.1016/j.array.2025.100466","DOIUrl":"10.1016/j.array.2025.100466","url":null,"abstract":"<div><div>This study shows how a hybrid workflow based on a Style-GAN-3 (with 256 × 256 pixel resolution) together with a €185 open-hardware plotter reframes authorship by uniting algorithmic invention with material execution. Specifically, it focuses on the development of a low-cost CNC machine, named ‘Gorosito’, which includes various customisation elements, such as the ability to interchange drawing tools to suit the operator/artist. Experimental validation of Gorosito is performed using images generated with generative AI and also including a comparison of the results with those produced by a commercial CNC machine. Results reveal precision of <span><math><mrow><mn>0</mn><mo>.</mo><mn>045</mn></mrow></math></span> mm and a 34% cost saving comparing with other commercial solutions. Our findings also show that each artwork, derived from the same digital file, acquires a unique expression, which leads to a redefinition of authenticity in digital art and provides a renewed perspective on the interplay between technology, artistic creation and cultural perception. The study thus positions Gorosito as an open and reproducible framework that any creative-code laboratory can adopt, bridging machine learning research with low-cost digital fabrication.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100466"},"PeriodicalIF":4.5,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144724744","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
Discriminative local affine-hull clustering for high-dimensional data 高维数据的判别局部仿射-船体聚类
IF 2.3
Array Pub Date : 2025-07-23 DOI: 10.1016/j.array.2025.100465
Yu-Feng Yu , Jiali Luo , Xuanyi Chen , Yingchao Cheng , Yulin He , Joshua Zhexue Huang
{"title":"Discriminative local affine-hull clustering for high-dimensional data","authors":"Yu-Feng Yu ,&nbsp;Jiali Luo ,&nbsp;Xuanyi Chen ,&nbsp;Yingchao Cheng ,&nbsp;Yulin He ,&nbsp;Joshua Zhexue Huang","doi":"10.1016/j.array.2025.100465","DOIUrl":"10.1016/j.array.2025.100465","url":null,"abstract":"<div><div>Clustering high-dimensional data presents a critical technical challenge due to the curse of dimensionality, feature redundancy, and sensitivity to noise—issues that significantly degrade clustering accuracy in applications such as gene expression analysis, image recognition, and anomaly detection. Existing solutions often rely on dimensionality reduction techniques that risk discarding discriminative features, or on deep learning methods that require large-scale training data and suffer from poor interpretability. To address these limitations, this study proposes a novel discriminative subspace clustering algorithm that avoids traditional dimensionality reduction and instead operates directly in the high-dimensional space. Our method partitions the sample space into multiple local affine hulls and introduces a discriminative geometric distance metric that accounts for both relevant and irrelevant subspaces. Specifically, the model measures the ratio between a query sample’s proximity to its class-specific affine hull and its distance from unrelated class subspaces. This dual-space modeling improves both intra-class compactness and inter-class separation. To ensure computational efficiency, we reformulate distance calculations as matrix multiplications and leverage SVD for subspace projection, enabling scalable performance across large datasets. Extensive experiments on seven benchmark datasets demonstrate that the proposed method consistently outperforms state-of-the-art clustering algorithms. It achieves up to 92.60% accuracy on MNIST and maintains high robustness on sparse and noisy data, validating its effectiveness for high-dimensional clustering tasks. This work contributes a geometrically interpretable and computationally efficient framework that closes a long-standing gap in unsupervised learning under high-dimensional constraints.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"27 ","pages":"Article 100465"},"PeriodicalIF":2.3,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714345","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信