Array最新文献

{"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}

{"title":"LDAM: A lightweight dual attention module for optimizing automotive malware classification","authors":"Jiahui Chen,&nbsp;Mingrui Wu,&nbsp;Huiwu Huang","doi":"10.1016/j.array.2025.100396","DOIUrl":"10.1016/j.array.2025.100396","url":null,"abstract":"<div><div>In recent years, electric vehicles have become prime targets for cyberattacks, with attackers exploiting public charging stations, USB ports, and other entry points to implant malware. This can lead to network outages and power disruptions. Traditional rule-based classification methods struggle against malware due to advanced encryption and obfuscation techniques. Thus, innovative classification approaches are urgently needed. Previous research often focused on converting malware binary files into RGB images for family classification, but overlooked the importance of runtime memory data. Inspired by earlier work, this study introduces a new deep neural network feature extraction module, the Lightweight Dual Attention Module (LDAM), for malware image classification. LDAM leverages attention mechanisms to capture both global and detailed features and uses feature fusion to balance these scales. This approach allows the neural network to effectively classify both raw binary and memory images of malware, while maintaining a low number of trainable parameters. By integrating LDAM into EfficientNet, the model achieves classification accuracies of 96.7% on the Malvis dataset and 98.1% on the Dumpware10 dataset, making it suitable for classifying malware on vehicle systems.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100396"},"PeriodicalIF":2.3,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821375","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":"Meta-learning based softmax average of convolutional neural networks using multi-layer perceptron for brain tumour classification","authors":"Irwan Budi Santoso,&nbsp;Shoffin Nahwa Utama,&nbsp;Supriyono","doi":"10.1016/j.array.2025.100398","DOIUrl":"10.1016/j.array.2025.100398","url":null,"abstract":"<div><div>Brain tumour classification using Magnetic Resonance Imaging (MRI) is crucial for medical decision-making. The variability in tumour shape, size, and position poses challenges to classification methods. Convolutional Neural Networks (CNNs) are commonly used due to their proven performance, but their effectiveness diminishes with the high variability of tumour characteristics. This study proposes a meta-learning approach, leveraging the softmax average of multiple CNN models with a Multi-Layer Perceptron (MLP) as the meta-learner. The base-learner models include MobileNetV2, InceptionV3, Xception, DenseNet201, and ResNet50. This approach combines the softmax outputs of these CNN models, capturing their strengths to handle diverse tumour characteristics. The averaged outputs are fed into the MLP for increased classification performance. To evaluate the proposed method, we used several brain MRI image datasets, including Dataset 1 (Thomas Dubail Dataset), Dataset 2 (Mesoud Nickparcar Dataset), and Dataset 3 (Fernando Feltrin Dataset). The test results showed the proposed method's effectiveness in improving classification performance. For Dataset 1, the MLP with one hidden layer (128 neurons) achieved 97.47 % accuracy, improving the base learners' performance by 1.94 %–7.42 %. On Dataset 2, the MLP with 64 neurons reached 99.54 % accuracy, with a 0 %–2.44 % improvement. For Dataset 3, an MLP with two hidden layers (256 and 125 neurons) achieved 98.87 % accuracy, enhancing performance by 0.46 %–5.67 %.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100398"},"PeriodicalIF":2.3,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821373","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 for algorithmic trading: A systematic review of predictive models and optimization strategies","authors":"MD Shahriar Mahmud Bhuiyan ,&nbsp;MD AL Rafi ,&nbsp;Gourab Nicholas Rodrigues ,&nbsp;MD Nazmul Hossain Mir ,&nbsp;Adit Ishraq ,&nbsp;M.F. Mridha ,&nbsp;Jungpil Shin","doi":"10.1016/j.array.2025.100390","DOIUrl":"10.1016/j.array.2025.100390","url":null,"abstract":"<div><div>Algorithmic trading has revolutionized financial markets, offering rapid and efficient trade execution. The integration of deep learning (DL) into these systems has further enhanced predictive capabilities, providing sophisticated models that capture complex, non-linear market patterns. This systematic literature review explores recent advancements in the application of DL algorithms to algorithmic trading with a focus on optimizing financial market predictions. We analyze and synthesize the key DL architectures, such as recurrent neural networks (RNN), long short-term memory (LSTM), convolutional neural networks (CNN), and hybrid models, to evaluate their performance in predicting stock prices, volatility, and market trends. The review highlights current challenges, such as data noise, overfitting, and interpretability, while discussing emerging solutions and future research directions. Our findings provide a comprehensive understanding of how DL reshapes algorithmic trading and its potential to improve decision-making processes in volatile financial environments.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100390"},"PeriodicalIF":2.3,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sustainable AI for plant disease classification using ResNet18 in few-shot learning","authors":"Fareeha Naveed ,&nbsp;Adven Masih ,&nbsp;Jabar Mahmood ,&nbsp;Moeez Ahmed ,&nbsp;Aitizaz Ali ,&nbsp;Aysha Saddiqa ,&nbsp;Mohamed Shabbir Hamza Abdulnabi ,&nbsp;Ebenezer Agbozo","doi":"10.1016/j.array.2025.100395","DOIUrl":"10.1016/j.array.2025.100395","url":null,"abstract":"<div><div>Addressing the critical challenge of reduced crop production caused by plant diseases is essential to safeguard agricultural yield and quality. Conventional methods like visual inspection and laboratory testing are both time-consuming and costly. Although Modern AI-based deep learning techniques are promising, their potential in fields such as plant disease identification often remains unexplored due to the requirement of large and expert-labeled data. To mitigate these challenges, it is imperative to explore sustainable approaches that require minimal data while maintaining high accuracy in classification tasks. This research proposes a novel few-shot learning (FSL) framework employing a minimum sample size of 1 image and a maximum of 10 images per class for the accurate classification of plant diseases. The architecture incorporates a pre-training phase based on transfer learning as a feature extractor, followed by meta-learning using Prototypical Networks (ProtoNets) for class prototype computation and distance-based classification. The study evaluates the effectiveness of the proposed approach on the PlantVillage as well as rice disease datasets, performing comparative analyses among different transfer learning models such as ResNet18, ResNet50, and Vision Transformers in combination with Prototypical Networks under various N-way classification tasks (3-way, 5-way, and 10-way) and support sample (K-shot) settings (K=1, K=5, K=10). The experimental findings indicate that the proposed combination of pretraining through ResNet18 with Prototypical Networks achieved an impressive accuracy of 93% and 75% on PlantVillage. The proposed model’s performance was further evaluated on rice disease data where it achieves the average accuracy of 75%. Specifically, the proposed model demonstrated the ability to classify 10 distinct plant diseases with high accuracy when provided with a suitable sample size per class. The proposed framework offers a substantial advancement in sustainable AI for plant disease recognition by enhancing the model generalization, enabling accurate classification across numerous classes with minimal sample size, and addressing data scarcity in AI-driven agricultural solutions.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100395"},"PeriodicalIF":2.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Ensemble Learning Framework with Explainable AI for interpretable leaf disease detection","authors":"Mohammad Rifat Ahmmad Rashid,&nbsp;Md. AL Ehtesum Korim,&nbsp;Mahamudul Hasan,&nbsp;Md Sawkat Ali,&nbsp;Mohammad Manzurul Islam,&nbsp;Taskeed Jabid,&nbsp;Raihan Ul Islam,&nbsp;Maheen Islam","doi":"10.1016/j.array.2025.100386","DOIUrl":"10.1016/j.array.2025.100386","url":null,"abstract":"<div><div>The early and accurate detection of plant diseases is critical for sustainable agriculture, ensuring crop health, reducing losses, and supporting food security. To address this challenge, we present an Ensemble Learning Framework with Explainable AI (XAI) tailored to disease detection, using cucumber leaf diagnosis as a key use case. In this study, we experimented with a dataset comprising 6,400 images capturing six prevalent cucumber leaf diseases – Gummy Stem Blight, Downy Mildew, Anthracnose, Bacterial Wilt, Belly Rot, and Pythium Fruit Rot – alongside two healthy categories. Prior to training, the images underwent preprocessing steps such as resizing, rescaling, and data augmentation (through random rotations, flips, zooms, and contrast adjustments) to enhance model generalization. The proposed framework unites multiple architectures – CNN, DenseNet121, EfficientNetB0, InceptionV3, MobileNetV2, ResNet50, and Xception – into an ensemble that attained overall accuracy of 99%, alongside high recall and F1-scores. Individual models demonstrated accuracy ranging from 88.71% to 99%, underscoring the robustness of the ensemble. Integrating XAI methods further ensures interpretable outputs, granting valuable insights into the decision-making process and heightening transparency for researchers and agronomists. The findings confirm that transfer learning, model ensembling, and interpretability methods significantly enhance classification performance, especially in cases of limited data, offering a scalable solution for improved disease management in agriculture. Additionally, the framework is scalable for real-world deployment by enabling real-time disease monitoring on edge devices (e.g., Raspberry Pi, IoT systems), seamless integration with smart farming platforms, and continuous learning for adaptive crop management.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100386"},"PeriodicalIF":2.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards walkable footpath detection for the visually impaired on Bangladeshi roads with smartphones using deep edge intelligence","authors":"Md. Ishan Arefin Hossain,&nbsp;Jareen Anjom,&nbsp;Rashik Iram Chowdhury","doi":"10.1016/j.array.2025.100388","DOIUrl":"10.1016/j.array.2025.100388","url":null,"abstract":"<div><div>One of the ongoing prevalent issues is the challenge faced by visually impaired people when crossing footpaths, especially in a densely populated geographic location such as Dhaka city in Bangladesh, where numerous accidents take place that primarily result in the demise of the affected individuals. Visually impaired people find themselves in precarious situations while navigating through these footpaths. So, having an accessible edge device like a smartphone capable of predicting walkable footpaths by detecting obstacles in real-time is a blessing. However, little work has been done on efficient obstacle detection on footpaths and their corresponding distance prediction in real-time. To address this burning issue, a U-Net-based lightweight deep learning model called QPULM along with an obstacle distance measurement technique called SODD have been proposed in this research, which is utilized in an Android application to detect walkable footpath by avoiding the obstacles via the image captured and to broadcast the directions of the walkable paths using audio feedback. The proposed novel lightweight model at the Edge showed an excellent accuracy of 99.37% with a faster prediction time in milliseconds in real-time, which is significantly better and more efficient than the existing related solutions.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100388"},"PeriodicalIF":2.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SEAGET: Seasonal and active hours guided graph enhanced transformer for the next POI recommendation","authors":"Alif Al Hasan,&nbsp;Md. Musfique Anwar","doi":"10.1016/j.array.2025.100385","DOIUrl":"10.1016/j.array.2025.100385","url":null,"abstract":"<div><div>One of the most important challenges for improving personalized services in industries like tourism is predicting users’ near-future movements based on prior behavior and current circumstances. Next POI (Point of Interest) recommendation is essential for helping users and service providers by providing personalized recommendations. The intricacy of this work, however, stems from the requirement to take into consideration several variables at once, such as user preferences, time contexts, and geographic locations. POI selection is also greatly influenced by elements like a POI’s operational status during desired visit times, desirability for visiting during particular seasons, and its dynamic popularity over time. POI popularity is mostly determined by check-in frequency in recent studies, ignoring visitor volumes, operational constraints, and temporal dynamics. These restrictions result in recommendations that are less than ideal and do not take into account actual circumstances. We propose the Seasonal and Active hours-guided Graph-Enhanced Transformer (SEAGET) model as a solution to these problems. By integrating variations in the seasons, operational status, and temporal dynamics into a graph-enhanced transformer framework, SEAGET capitalizes on redefined POI popularity. This invention gives more accurate and context-aware next POI predictions, with potential applications for optimizing tourist experiences and enhancing location-based services in the tourism industry.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100385"},"PeriodicalIF":2.3,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"STATOS: A portable tool for secure malware analysis and sample acquisition in low resource environments","authors":"Alexander Cameron ,&nbsp;Abu Alam ,&nbsp;Nasreen Anjum ,&nbsp;Javed Ali Khan ,&nbsp;Alexios Mylonas","doi":"10.1016/j.array.2025.100391","DOIUrl":"10.1016/j.array.2025.100391","url":null,"abstract":"<div><div>Malware poses a significant security threat to organisations worldwide, particularly in environments with limited resources. Static analysis has emerged as a crucial technique for gaining insights into malware, but it often requires specialised hardware and software, which can be a barrier for organisations facing financial or supply constraints. To address these challenges, this study presents a Static-Analysis Operating System (StatOS), a portable Linux derivative operating system designed for static malware analysis. StatOS can be executed from a USB device, allowing organisations to perform efficient, user-friendly, and secure malware analysis even on underpowered hardware. This study contributes a practical solution to field analysis of malware within low-resource environments, providing a model and requirement data for future developments in portable cybersecurity tools. The tool was validated through a combination of expert feedback using the Delphi method and security assessments, including Monte-Carlo simulations and Common Vulnerabilities and Exposures (CVE) evaluations. Results indicate that StatOS meets and exceeds key performance requirements, with 100% of surveyed cyber specialists agreeing on its effectiveness, and 80% indicating they would use StatOS in forensic investigations.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"26 ","pages":"Article 100391"},"PeriodicalIF":2.3,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}