Array最新文献

{"title":"A comparative study of machine learning and deep learning models in binary and multiclass classification for intrusion detection systems","authors":"Ayesha Alharthi,&nbsp;Meera Alaryani,&nbsp;Sanaa Kaddoura","doi":"10.1016/j.array.2025.100406","DOIUrl":"10.1016/j.array.2025.100406","url":null,"abstract":"<div><div>Network infrastructure evolution has significantly expanded the attack surface, leading to increasingly complex and sophisticated cybersecurity threats. Traditional rule-based intrusion detection systems (IDS) often fail to detect emerging attack vectors, prompting the need for intelligent, data-driven approaches. This study evaluates and compares the performance of machine learning (ML) and deep learning (DL) models for network intrusion detection. Two publicly available datasets were utilized: a binary-labeled software-defined networking (SDN) dataset and a multiclass industrial control system dataset based on the IEC 60870-5-104 protocol. Preprocessing steps included normalization, label encoding, and a 70:10:20 train-validation-test split. Seven models, Random Forest, Decision Tree, K-Nearest Neighbors, XGBoost, Convolutional Neural Network, Gated Recurrent Unit, and Long Short-Term Memory, were trained and evaluated using precision, recall, and F1-score. The Random Forest model achieved the highest F1-score of 93.57 % on the IEC 60870-5-104 dataset, while XGBoost attained a near-perfect F1-score of 99.97 % on the SDN dataset. These results outperform comparable models in the literature and offer practical insights for selecting effective IDS solutions based on classification type and dataset structure.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100406"},"PeriodicalIF":2.3,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947120","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}

{"title":"Risk assessment and physical hazard detection in elderly living environments using multi-scale infrared and visible imagery fusion","authors":"Peng Gao ,&nbsp;Naji Alhusaini ,&nbsp;Jinjun Liu ,&nbsp;Liang Zhao ,&nbsp;Yiwen Zhang","doi":"10.1016/j.array.2025.100403","DOIUrl":"10.1016/j.array.2025.100403","url":null,"abstract":"<div><div>With the rapid growth of the elderly population, smart elderly care has become a crucial solution to address this societal challenge, with safety concerns being paramount. Existing research often focuses on fall detection and localization, but overlooks the comprehensive identification of hazards in home environments. This work proposes a preventive hazard detection and safety assessment paradigm based on infrared visible dual-mode fusion, aiming to identify various potential hazards, including the risk of falling, and achieve a paradigm shift from “post response” to “pre prevention”. The model is designed with a channel space dual attention Transformer and a multi-scale adaptive fusion module, which improves the accuracy of hazard detection under different lighting conditions. Experimental results show a 15% improvement in detection accuracy over single-modality images on a custom-collected dataset. Compared to state-of-the-art methods such as DATFuse, IPLF, and Res2Fusion, our approach improves the mean Average Precision by 10%, with higher precision and recall in complex environments. Additionally, a Bayesian-optimized lightweight CNN achieves a 30% reduction in model size while maintaining high accuracy, making it suitable for deployment on resource-constrained devices. This study provides a robust tool for enhancing elderly safety in home environments and establishes a solid foundation for future research in smart elderly care.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100403"},"PeriodicalIF":2.3,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106305","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}

{"title":"Emotion recognition with a Randomized CNN-multihead-attention hybrid model optimized by evolutionary intelligence algorithm","authors":"Syed Muhammad Salman Bukhari ,&nbsp;Muhammad Hamza Zafar ,&nbsp;Syed Kumayl Raza Moosavi ,&nbsp;Filippo Sanfilippo","doi":"10.1016/j.array.2025.100401","DOIUrl":"10.1016/j.array.2025.100401","url":null,"abstract":"<div><div>Emotion recognition systems are vital for various applications, yet existing models often face limitations in computational efficiency and accuracy, especially when handling complex emotional expressions in sequential data. To address these challenges, we propose an innovative emotion recognition framework that integrates a Randomised Convolutional Neural Network (RCNN) with a Multi-Head Attention model, further optimized by the Football Team Training Algorithm (FTTA) metaheuristic to enhance network parameters effectively. The RCNN, characterized by fixed random weights in its convolutional layers, efficiently extracts features from facial landmarks, enabling robust and diverse feature extraction while reducing computational load. This structure is complemented by a multi-head attention mechanism that processes temporal dynamics in emotion data, with both components optimized through FTTA to balance exploration and exploitation. Our hybrid model undergoes rigorous testing on a widely recognized emotion recognition dataset, outperforming conventional fully trainable models and alternative architectures. The results indicate a substantial improvement in classification accuracy, with an overall accuracy of 99%, and a significant reduction in computational demands, achieving a 65% faster training time on average compared to state-of-the-art models. These enhancements confirm the model’s efficiency and robustness across various emotional classifications. The synergy between the RCNN’s fixed-weight feature extraction and FTTA’s optimization capabilities demonstrates a powerful solution for emotion recognition systems. The combination of accuracy and efficiency renders our model suitable for real-world applications, particularly in fields like healthcare and mental health monitoring, where real-time emotion detection can have significant impacts.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100401"},"PeriodicalIF":2.3,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936546","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}

{"title":"Predicting traffic flow with federated learning and graph neural with asynchronous computations network","authors":"Muhammad Yaqub ,&nbsp;Shahzad Ahmad ,&nbsp;Malik Abdul Manan ,&nbsp;Muhammad Salman Pathan ,&nbsp;Lan He","doi":"10.1016/j.array.2025.100411","DOIUrl":"10.1016/j.array.2025.100411","url":null,"abstract":"<div><div>Real-time traffic flow prediction holds significant importance within the domain of Intelligent Transportation Systems (ITS). The task of achieving a balance between prediction precision and computational efficiency presents a significant challenge. In this article, we present a novel deep-learning method called Federated Learning and Asynchronous Graph Convolutional Network (FLAGCN). Our framework incorporates the principles of asynchronous graph convolutional networks with federated learning to enhance the accuracy and efficiency of real-time traffic flow prediction. The FLAGCN model employs a spatial-temporal graph convolution technique to asynchronously address spatio-temporal dependencies within traffic data effectively. To efficiently handle the computational requirements associated with this deep learning model, this study used a graph federated learning technique known as GraphFL. This approach is designed to facilitate the training process. The experimental results obtained from conducting tests on two distinct traffic datasets demonstrate that the utilization of FLAGCN leads to the optimization of both training and inference durations while maintaining a high level of prediction accuracy. FLAGCN outperforms existing models with significant improvements by achieving up to approximately 6.85 % reduction in RMSE, 20.45 % reduction in MAPE, compared to the best-performing existing models.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100411"},"PeriodicalIF":2.3,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143924573","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}

{"title":"Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing","authors":"Jinwoo Kim ,&nbsp;Jaewan Baek ,&nbsp;Mingi Choi","doi":"10.1016/j.array.2025.100407","DOIUrl":"10.1016/j.array.2025.100407","url":null,"abstract":"<div><div>The protonic ceramic fuel cell (PCFC) is currently attracting attention as a promising energy-conversion device capable of generating electricity from hydrogen with high efficiency. However, when developing high-performance PCFCs, a wide range of material properties and manufacturing processes must be optimized, necessitating tremendous time and manpower investments as well as a high cost. To address these issues, this study proposes a method by which to analyze the effects of certain materials and manufacturing processes on the fabrication of PCFCs, assisted by machine learning (ML). Based on data from earlier work, we first evaluate the performance-predicting capabilities of 6 ML models, showing the best-predicting performance with XGBoost model. Based on the selected model of XGBoost, we also conduct the feature analysis using Shapley additive explanations, which successfully determine the factors contributing most to the PCFC performance in terms of the materials and manufacturing processes for the anode, cathode, and electrolyte in each case. These results can give us guidelines for the efficient manufacturing of the PCFC.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100407"},"PeriodicalIF":2.3,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936061","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}

{"title":"UDGS-SLAM: UniDepth Assisted Gaussian Splatting for Monocular SLAM","authors":"Mostafa Mansour ,&nbsp;Ahmed Abdelsalam ,&nbsp;Ari Happonen ,&nbsp;Jari Porras ,&nbsp;Esa Rahtu","doi":"10.1016/j.array.2025.100400","DOIUrl":"10.1016/j.array.2025.100400","url":null,"abstract":"<div><div>Recent advancements in monocular neural depth estimation, particularly those achieved by the UniDepth network, have prompted the investigation of integrating UniDepth within a Gaussian splatting framework for monocular SLAM. This study presents UDGS-SLAM, a novel approach that eliminates the necessity of RGB-D sensors for depth estimation within Gaussian splatting framework. UDGS-SLAM employs statistical filtering to ensure local consistency of the estimated depth and jointly optimizes camera trajectory and Gaussian scene representation parameters. The proposed method achieves high-fidelity rendered images and low ATE-RMSE of the camera trajectory. The performance of UDGS-SLAM is rigorously evaluated using the TUM RGB-D dataset and benchmarked against several baseline methods, demonstrating superior performance across various scenarios. Additionally, an ablation study is conducted to validate design choices and investigate the impact of different network backbone encoders on system performance.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100400"},"PeriodicalIF":2.3,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143890783","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}

{"title":"Smart system for real time monitoring and diagnosis of dengue surfaces in Bangladesh","authors":"Md. Shahriar Hossain Apu,&nbsp;Samsuddin Ahmed,&nbsp;Md. Toukir Ahmed","doi":"10.1016/j.array.2025.100389","DOIUrl":"10.1016/j.array.2025.100389","url":null,"abstract":"<div><div>Efficient vector management techniques hold great importance according to the World Health Organization (WHO) as a foundation to reduce and maintain the decline of vector-born diseases. Health surveillance teams operating in malaria and dengue and Zika and Chikungunya endemic areas can effectively use drone or unmanned aerial vehicles (UAVs) as technology to detect and eradicate mosquito breeding sites. UAVs enable users to obtain detailed aerial photographs and monitor locations throughout time and geographic areas. The process of vector control intervention analysis through manual image inspection requires extensive labor efforts and takes significant amounts of time. This research presents a methodology to automatically detect mosquito breeding areas in aerial drone images. Leveraging a CBAM-enhanced YOLOv9 object detection framework, we present a UAV-based strategy for dengue surface monitoring, achieving an impressive mean Average Precision (mAP) of 99.5% for mAP50, 86.4% for mAP50-95, 94% for Intersection over Union (IoU), 45 FPS, 98% precision, and 90% recall. The integration of the Convolutional Block Attention Module (CBAM) enhances the model’s feature extraction capabilities, improving its focus on critical regions in the images. Robust performance was ensured by the consistent achievement of these outcomes in a variety of operational and environmental contexts, including urban and rural locations. To confirm the model’s practicality, more tests under various circumstances will be carried out. This deep learning approach facilitates targeted and timely vector control interventions, leveraging drone-based surveillance to combat the spread of vector-borne diseases efficiently.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100389"},"PeriodicalIF":2.3,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823929","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}

{"title":"DGTM: Deriving Graph from transformer with Mamba for panoptic scene graph generation","authors":"Youxuan Sun,&nbsp;Yunliang Chen ,&nbsp;Xiaohui Huang ,&nbsp;Yuewei Wang,&nbsp;Shaoqian Chen,&nbsp;Kangfei Yao,&nbsp;Ao Yang","doi":"10.1016/j.array.2025.100394","DOIUrl":"10.1016/j.array.2025.100394","url":null,"abstract":"<div><div>Scene Graph Generation (SGG) transforms images into structured graph representations that encapsulate the objects, attributes, and relationships present within objects. Graph models boost visual content understanding and reasoning for image captioning, question answering, and HCI. Panoptic Scene Graph Generation (PSG) enhances the object detection task within scene graph generation by incorporating panoptic segmentation, thereby imposing greater demands on the model’s capacity to comprehend images. Existing approaches often rely on intricate modeling techniques to predict relationships between objects, while neglecting the inherent connections among object queries that are learned through multi-head self-attention in object detectors. This oversight not only leads to a significant increase in parameter count but also complicates model design and hinders transferability. This paper proposes a new single-stage panoptic scene graph generator called DGTM (Deriving Graph from transformer with Mamba). DGTM utilizes the by-products of multi-head self-attention layers in transformers, treats queries and keys as subjects and objects respectively to extract relationship information between objects. By introducing the Mamba module, multi-level and multi-scale feature information is integrated efficiently, empowering the model to better grasp intricate relationships. In addition, a Kolmogorov–Arnold Network (KAN) is incorporated to help the model better distinguish between subjects and objects, enriching feature representation. Experimental results show that DGTM achieves at least 25%, 15%, and 15% improvements in mR@20, mR@50, and mR@100 compared to the baseline, demonstrating notable enhancements in the precision and comprehensiveness of PSG.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100394"},"PeriodicalIF":2.3,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835246","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}

{"title":"Deep learning-based detection and classification of acute lymphoblastic leukemia with explainable AI techniques","authors":"Debendra Muduli ,&nbsp;Sourav Parija ,&nbsp;Suhani Kumari ,&nbsp;Asmaul Hassan ,&nbsp;Harendra S. Jangwan ,&nbsp;Abu Taha Zamani ,&nbsp;Sk. Mohammed Gouse ,&nbsp;Banshidhar Majhi ,&nbsp;Nikhat Parveen","doi":"10.1016/j.array.2025.100397","DOIUrl":"10.1016/j.array.2025.100397","url":null,"abstract":"<div><div>Leukemia is identified by an excess of immature white blood cells (WBC) being formed in the bone marrow, leading to cancer. It is divided into two main types: acute, which stems from early cell growth ab- normalities and involves rapid immature cell proliferation, and chronic, which progresses more slowly due to a blockage in the later stages of the cell life cycle. Detecting acute lymphoblastic leukemia (ALL) at an early stage is critical to reducing its associated mortality rate. This study presents an empirical analysis of various pre-trained deep learning models, including VGG16, VGG19, ResNet50, Xception, ResNet152, EfficientNet- B0, NASNetMobile, DenseNet169, DenseNet121, and EfficientNetV2B0, for the detection and classification of ALL. A comprehensive evaluation highlights the effectiveness of deep learning in distinguishing different types of ALL, demonstrating its potential as a reliable diagnostic tool in medical imaging. Additionally, we evaluated the performance of these models using different optimization techniques, including Adadelta, SGD, RMSprop, and Adam, to determine the most effective optimization strategy for improving classifica-tion accuracy. Our results demonstrate that EfficientNet-B0 achieved a classification accuracy of 72 %, while NASNetMobile attained 81 %. Notably, DenseNet121 outperformed these models with an accuracy of 99 %. Furthermore, the remaining seven models VGG16, VGG19, ResNet50, Xception, ResNet152, DenseNet169, and EfficientNetV2B achieved a perfect classification accuracy of 100 %, highlighting their robustness and effectiveness in our experimental setup. To improve the interpretability of the leukemia detection process, explainable AI techniques, including Grad-CAM, Score-CAM, and Grad-CAM++, were integrated to vi-sualize critical regions influencing model predictions. These techniques enhance transparency by providing visual explanations of classification decisions. A detailed comparative analysis was conducted, examining key parameters such as learning rate, optimization algorithms, and the number of training epochs to determine the most effective approach. The study leveraged a publicly available acute lymphoblastic leukemia dataset to ensure comprehensive model evaluation. By offering insights into model performance and interpretability.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100397"},"PeriodicalIF":2.3,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821374","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}

{"title":"KA-GCN: Kernel-Attentive Graph Convolutional Network for 3D face analysis","authors":"Francesco Agnelli,&nbsp;Giuseppe Facchi,&nbsp;Giuliano Grossi,&nbsp;Raffaella Lanzarotti","doi":"10.1016/j.array.2025.100392","DOIUrl":"10.1016/j.array.2025.100392","url":null,"abstract":"<div><div>Graph Structure Learning (GSL) methods address the limitations of real-world graphs by refining their structure and representation. This allows Graph Neural Networks (GNNs) to be applied to broader unstructured domains such as 3D face analysis. GSL can be considered as the dynamic learning of connection weights within a layer of message passing in a GNN, and particularly in a Graph Convolutional Network (GCN). A significant challenge for GSL methods arises in scenarios with limited availability of large datasets, a common issue in 3D face analysis, particularly in medical applications. This constraint limits the applicability of data-intensive GNN models, such as Graph Transformers, which, despite their effectiveness, require large amounts of training data. To address this limitation, we propose the Kernel-Attentive Graph Convolutional Network (KA-GCN). Our key finding is that integrating kernel-based and attention-based mechanisms to dynamically refine distances and learn the adjacency matrix within a Graph Structure Learning (GSL) framework enhances the model’s adaptability, making it particularly effective for 3D face analysis tasks and delivering strong performance in data-scarce scenarios. Comprehensive experiments on the Facescape, Headspace, and Florence datasets, evaluating age, sexual dimorphism, and emotion, demonstrate that our approach outperforms state-of-the-art models in both effectiveness and robustness, achieving an average accuracy improvement of 2%. The project page is available on GitHub <span><span>¹</span></span>.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100392"},"PeriodicalIF":2.3,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143807798","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}