Array最新文献

{"title":"GPAT: Enhancing point cloud registration with local-global Integration and Geo-positional awareness","authors":"Zijian Wang,&nbsp;Zhenbao Wang,&nbsp;Xin Liu,&nbsp;Xinxi Xu,&nbsp;Chen Su,&nbsp;Xiuguo Zhao","doi":"10.1016/j.array.2025.100660","DOIUrl":"10.1016/j.array.2025.100660","url":null,"abstract":"<div><div>Point cloud registration, essential for applications like autonomous driving and 3D reconstruction, remains challenging in scenarios with low overlap and incomplete data. Although learning-based methods have shown promise, existing keypoint-based and coarse-to-fine approaches can struggle with ambiguous matching due to similar local patches in non-overlapping regions, particularly under low overlap conditions. This study introduces GPAT(Geometric-Positional Attention and Local-Global Transformer Networks), a novel hierarchical deep learning framework designed to address these limitations by effectively integrating local geometric and positional information with global structural awareness. By leveraging a novel positional encoding and attention mechanisms, GPAT captures the intricate interplay between geometric structures and spatial configurations, enriching the distinctiveness of local features. Simultaneously, it incorporates global geometric consistency to establish robust correspondences, effectively bridging the gap between local and global contexts. The framework further refines these correspondences into dense point matches, ensuring precise registration even under challenging conditions. Extensive experiments on benchmark datasets, including 3DMatch, ModelNet, and KITTI, demonstrate GPAT's competitive performance, especially in low-overlap situations, demonstrating its capability to extract discriminative features and achieve accurate transformations with high robustness.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100660"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146034355","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":"Benchmarking the adversarial resilience of machine learning models for DDoS detection","authors":"Harsh Dadhwal ,&nbsp;Mateus de Abreu ,&nbsp;Nazanin Parvizi ,&nbsp;Sajal Saha","doi":"10.1016/j.array.2025.100664","DOIUrl":"10.1016/j.array.2025.100664","url":null,"abstract":"<div><div>Distributed Denial of Service (DDoS) attacks continue to grow in scale and sophistication, making timely and reliable detection increasingly challenging. Machine learning (ML) models have demonstrated promise in identifying malicious traffic patterns. However, their vulnerability to adversarial manipulation remains a critical security concern. This study benchmarks the adversarial robustness of several standalone ML models trained on clean traffic from the CIC-IDS2017 dataset. Adversarial perturbations are generated using the Fast Gradient Sign Method (FGSM). Baseline robustness is assessed by evaluating each model on FGSM adversarial samples generated at <span><math><mrow><mi>ϵ</mi><mo>=</mo><mn>0</mn><mo>.</mo><mn>1</mn></mrow></math></span>. Adversarial training is then performed by augmenting the clean dataset with FGSM-generated samples, after which models are evaluated across multiple perturbation strengths (<span><math><mrow><mi>ϵ</mi><mo>=</mo><mn>0</mn><mo>.</mo><mn>1</mn></mrow></math></span> to <span><math><mrow><mn>3</mn><mo>.</mo><mn>0</mn></mrow></math></span>). Experimental findings show that boosting-based models, particularly XGBoost and LightGBM, demonstrate the highest resilience under adversarial stress. In contrast, models such as Logistic Regression and MLP experience significant performance degradation, even after adversarial training. Despite this, adversarial training substantially improves robustness across all models, highlighting its effectiveness in mitigating FGSM-induced decision boundary shifts. This benchmarking study underscores the importance of adversarial training and model selection when deploying ML-based intrusion detection systems. Boosting ensembles consistently provide superior robustness, while linear and neural models remain more susceptible to perturbations.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100664"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146073846","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":"Performance analysis of Convolutional Neural Networks on edge devices for Computer Vision tasks","authors":"Andrea Bricola,&nbsp;Nicoletta Noceti,&nbsp;Daniele D’Agostino","doi":"10.1016/j.array.2026.100692","DOIUrl":"10.1016/j.array.2026.100692","url":null,"abstract":"<div><div>Computer vision is currently applied in an increasing number of technological systems and devices. In many cases, security and privacy constraints, or the need for real-time decision-making, require these tasks to be executed at the edge, where images are acquired. When high performance targets must be met, Convolutional Neural Networks (CNNs) remain the gold standard since, if compared to more recent and complex architectures, they provide a simpler structure that allows for easier implementation and compatibility with different hardware platforms. This paper presents a comparative analysis of the performance of several state-of-the-art CNNs on two edge computing architectures, specifically Jetson Nano and OAK-D-CM4. We considered also the Coral Edge TPU, even if it seems discontinued. The objective is to evaluate the achievable performance and identify the limitations inherent in the available software libraries and hardware. Particular attention is given to the trade-off between high accuracy and fast inference. To this end, two use cases targeting classical Computer Vision tasks, i.e. object detection and face recognition, will be discussed.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100692"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146073848","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":"IoT node for monitoring and traceability of live plants in maritime transport","authors":"Blanca Méndez,&nbsp;Paula Lamo","doi":"10.1016/j.array.2025.100621","DOIUrl":"10.1016/j.array.2025.100621","url":null,"abstract":"<div><div>The work presents an Internet of Things (IoT) monitoring node designed to convert shipping containers into smart greenhouses, thereby optimizing the transportation of live plants over long distances. This node utilizes specialized sensors to measure ambient temperature, soil temperature, relative humidity, soil moisture, and luminosity. Communication is via LoRa for local transmission and a low-Earth orbit (LEO) satellite infrastructure to ensure global connectivity. The collected data is stored and verified on the IOTA Tangle, ensuring traceability and immutability. Field tests in controlled environments demonstrated measurement accuracy, operational stability under varying environmental conditions, and optimized energy consumption. Additionally, the system is accessible through the Blynk platform, which provides real-time monitoring and customizable alert configurations. The paper also analyzes system costs, scalability, and specific conditions for installation on ships and containers. Limitations, such as dependence on satellite connectivity and structural barriers in maritime environments, are discussed. Finally, future lines of research focused on integrating artificial intelligence, energy optimization and connection with global logistics chains are identified.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100621"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921256","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":"Improve semantic similarity based on statistical approach and LLM based transformer model for extractive summarization","authors":"Sutriawan ,&nbsp;Supriadi Rustad ,&nbsp;Guruh Fajar Shidik ,&nbsp;Pujiono","doi":"10.1016/j.array.2025.100671","DOIUrl":"10.1016/j.array.2025.100671","url":null,"abstract":"<div><div>This study addresses the need for effective extractive text summarization methods specifically designed for Indonesian news texts, driven by the increasing volume of digital information and persistent challenges related to semantic drift and coherence instability. A key challenge in extractive summarization lies in maintaining semantic fidelity while preserving informative content and ensuring computational efficiency, particularly for morphologically complex languages such as Indonesian. To address this issue, this research proposes a hybrid extractive summarization approach that integrates statistical methods, namely Term Frequency–Inverse Document Frequency (TF-IDF) and Latent Semantic Analysis (LSA), with Indonesian-specific transformer models, including IndoBERT and GPT, to enhance semantic similarity measurement during sentence selection. The proposed framework employs a weighted hybrid formulation (α·TF-IDF + β·LSA + γ·IndoBERT + δ·GPT), combined with cosine similarity computation and diversity-aware sentence selection. The approach is evaluated under a consistent experimental setting using the Indonesian subset of the XL-Sum dataset, with experiments conducted on TPU V2-8 infrastructure. Experimental results demonstrate competitive performance across the evaluated baseline components. The TF-IDF + LSA model achieved the highest ROUGE-1 score of 63.76 %, while the TF-IDF + Cosine Similarity model showed balanced performance across ROUGE metrics with a cosine similarity score of 0.8538. IndoBERT + Cosine Similarity and GPT + Cosine Similarity achieved higher semantic similarity scores, with GPT reaching 0.8677. Overall, the proposed approach demonstrates substantial improvements over Indonesian extractive summarization baselines under the same dataset and evaluation protocol, highlighting the effectiveness of hybrid statistical-transformer integration for low-resource language summarization.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100671"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921317","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":"Trans-ADENet: Transformer-based Attention-guided Deep Ensemble Network for high-dimensional data classification","authors":"Venkaiah Chowdary Bhimineni,&nbsp;Rajiv Senapati","doi":"10.1016/j.array.2025.100659","DOIUrl":"10.1016/j.array.2025.100659","url":null,"abstract":"<div><div>High-dimensional (HD) biomedical data, such as gene expression profiles and ECG signals, pose significant challenges for machine learning (ML) due to limited sample size, feature redundancy, and noisy distributions. Conventional models tend to overfit, whereas boosting and ensemble approaches struggle with irrelevant features. Deep autoencoders (DAE) reduce nonlinear dimensionality but miss complex dependencies, whereas transformers require large datasets to model long-range relationships through self-attention mechanisms. We propose a Transformer-based Attention-guided Deep Ensemble Network (Trans-ADENet) that integrates dimensionality reduction, attention-driven feature learning, and meta-level ensemble fusion in an end-to-end framework. A deep autoencoder compresses HD inputs into compact latent representations, refined by a Transformer Encoder with multi-head self-attention. Refined features are fed to diverse base classifiers (CatBoost, Support Vector Machine (SVM), TabNet, and Generalized Multi-Layer Perceptron (GMLP)), and their outputs are fused by a meta-MLP, which learns adaptive weights to yield robust predictions. Experiments on breast, leukemia, INCART2 and Thyroid-RNA datasets achieved 96.3%, 94.1%, 92.7% and 94.6% accuracy, surpassing state-of-the-art models in terms of accuracy, F1, precision, recall, and AUC. By combining representation learning, attention, and adaptive fusion, Trans-ADENet delivers accurate, interpretable classification for biomedical tasks.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100659"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921394","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":"An explainable comparative study of statistical, machine learning, deep learning, and hybrid models for CO2 emissions forecasting in Australia","authors":"Safa Ghannam","doi":"10.1016/j.array.2025.100639","DOIUrl":"10.1016/j.array.2025.100639","url":null,"abstract":"<div><div>Accurate forecasting of national CO₂ emissions is critical for evidence-based climate policy and for meeting commitments such as Australia's 2050 net-zero target and the United Nations Sustainable Development Goal 13 (Climate Action). This study implements and evaluates thirteen forecasting approaches, including statistical models (ARIMA), machine learning methods (random forest, XGBoost, SVR), kernel methods (GPR), hybrid approaches (ELM, ISSA-ELM), deep learning networks (MLP, LSTM, GRU, RNN), and two ensemble models (stacking regressor and enhanced stacking regressor), using annual Australian data from 1982 to 2022 within a reproducible pipeline. Thirty random seeds ensured robustness for stochastic learners. Ensemble tree methods delivered the most accurate and stable predictions: Random Forest achieved mean cross-validation R² ≈ 0.989 ± 0.003 and RMSE ≈0.018 ± 0.002 and generalized well to unseen 2016–2022 data (R² ≈ 0.96; RMSE ≈ 2.43 Mt CO₂). Pairwise significance testing confirmed that Random Forest and stacking significantly outperformed most individual learners (p &lt; 0.01). SHAP analysis identified energy productivity, total GHG excluding land-use change, total energy consumption, and population as dominant drivers. Scenario experiments show that deterministic adjustments yield only modest 2050 reductions (−0.49 % to −2.68 %), with population shifts treated as exogenous sensitivities, underscoring the need for system-level action to achieve net-zero. Limitations include reliance on annual data and exclusion of policy and trade factors. Future work could extend this framework through causal inference and hybrid physics-informed machine learning. Building on global advances in emissions forecasting, this study contributes a localized, interpretable comparative framework tailored to Australia's emissions profile, addressing a notable gap in national-level forecasting research. This transparent and reproducible approach provides evidence-based guidance for model selection and supports policy-relevant discussions on national CO₂ forecasting.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100639"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788382","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":"Mobile phone image-based framework for anti-copy pattern detection and classification","authors":"Joseph Smith ,&nbsp;Zheming Zuo ,&nbsp;Jonathan Stonehouse ,&nbsp;Boguslaw Obara","doi":"10.1016/j.array.2025.100643","DOIUrl":"10.1016/j.array.2025.100643","url":null,"abstract":"<div><div>The proliferation of high-quality printing and reproduction technologies has exacerbated product counterfeiting. Manufacturers have employed anti-copy patterns to prevent unauthorised duplication, yet their effectiveness relies on the robustness of image processing systems. This paper presents, to the best of our knowledge, the first comprehensive <em>mobile phone image-based framework</em> for detecting and classifying anti-copy patterns in real-world industrial scenarios. Unlike prior studies that address segmentation, quality control, or feature extraction in isolation, our contribution lies in the <em>non-trivial integration</em> of these modules into a validated, end-to-end system. The framework combines the Segment Anything Model with an adaptive-angle cropping mechanism for precise segmentation, incorporates no-reference image quality assessment to filter unreliable inputs, and unifies spatial and frequency-domain features for robust representation. Dimensionality reduction and clustering then manage the feature pool efficiently. Validated on a real-world dataset of over 980 annotated samples, the system achieves 99.49% classification accuracy under varied imaging conditions, demonstrating both the feasibility and industrial applicability of an integrated pipeline for combating counterfeiting.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100643"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788385","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":"Neuro-cognitive AI-driven system for preventing road accidents through driver drowsiness alerts","authors":"Chitaranjan Mahapatra ,&nbsp;Shuvendra Kumar Tripathy ,&nbsp;Mrunmayee Tripathy","doi":"10.1016/j.array.2025.100631","DOIUrl":"10.1016/j.array.2025.100631","url":null,"abstract":"<div><div>The increasing integration of smart city technologies has underscored the need for intelligent transportation systems that prioritize road safety. This study presents a neuro-cognitive artificial intelligence (AI)-driven system designed to detect driver drowsiness in real time and proposes a framework for future accident detection. The system combines computer vision and machine learning to monitor driver alertness and issue timely warnings. Facial expressions and eye movements are analyzed using a hybrid architecture that integrates convolutional neural networks (CNNs) for spatial feature extraction and gated recurrent units (GRUs) for temporal modeling. When signs of fatigue are detected—such as sustained low eye aspect ratio (EAR)—the system triggers visual and auditory alerts to re-engage the driver. Operating within a smart city infrastructure, the system is designed to communicate with traffic management platforms and emergency services for enhanced coordination. While the drowsiness detection module has been fully implemented and evaluated, the accident detection component remains a proposed feature for future development. This research contributes to the advancement of proactive road safety solutions and lays the groundwork for scalable, multimodal AI systems in intelligent transportation networks.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100631"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145788381","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":"Artificial intelligence-based image interpretation system: Unlocking a new dimension of artwork analysis","authors":"Lijun Huang ,&nbsp;Shizheng Sun ,&nbsp;Yunhan Liu ,&nbsp;Pinxian Mao ,&nbsp;Xiaoyu Zhou","doi":"10.1016/j.array.2025.100670","DOIUrl":"10.1016/j.array.2025.100670","url":null,"abstract":"<div><div>This paper presents an artificial intelligence-based image interpretation system for automated, multi-perspective analysis of visual artworks. The system integrates a multimodal perception-generation pipeline that combines visual feature encoding with structured knowledge retrieval to enable context-aware art understanding. Specifically, the system employs a graph retrieval-augmented generation (GRAG) framework built upon an art context knowledge graph (ACKG). This framework not only models the relationships among artists, styles, historical periods, and cultural symbols, but also performs graph-based entity retrieval and subgraph reasoning to efficiently extract semantically relevant contextual knowledge. Subsequently, this knowledge is integrated with visual representations to generate high-quality textual interpretations. We evaluate the system on two public painting datasets, SemArt and Artpedia, and compare it with several state-of-the-art methods. Experimental results demonstrate that our approach significantly outperforms baseline models in both descriptive accuracy and richness of artistic context, while also achieving higher scores in human evaluations. These findings provide a new technological pathway and practical reference for applications in art education, intelligent museum guidance, and public art appreciation.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100670"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146184697","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}