Array最新文献 - Book学术

Multimodal transformers predict cancer therapy response from tumor mechanics. 多模态变压器从肿瘤力学预测癌症治疗反应。

IF 5.3

Array Pub Date : 2026-09-01 DOI: 10.1016/j.array.2026.101168

Styliana Georgiou, Triantafyllos Stylianopoulos, Chrysovalantis Voutouri

{"title":"Multimodal transformers predict cancer therapy response from tumor mechanics.","authors":"Styliana Georgiou, Triantafyllos Stylianopoulos, Chrysovalantis Voutouri","doi":"10.1016/j.array.2026.101168","DOIUrl":"10.1016/j.array.2026.101168","url":null,"abstract":"<p><p>Precise prediction of cancer therapy response remains challenging because conventional biomarkers capture molecular features but overlook the physical state of tumors. We developed a multimodal deep-learning framework integrating ultrasound shear wave elastography (SWE) images with quantitative stiffness measurements (elastic modulus, kPa) to predict treatment outcomes in preclinical murine tumors. Each image-stiffness pair is tokenized within a transformer that learns interactions between local elastographic texture and global rigidity. A lightweight convolutional encoder extracts image features, the modulus is embedded as a numeric token, and self-attention fuses both modalities for classification. Trained on 1578 baseline SWE images from five syngeneic tumor models, the model classified tumors as responders, stable, or non-responders. Across five random seeds, it achieved 92.4% ± 1.3% accuracy, macro-F1 0.92, and ROC-AUC 0.99 on a held-out test set, with well-calibrated probabilities. Matched-split ablations-image-only, stiffness-token-removed, stiffness-shuffled, late-fusion, and stiffness-only-showed that performance reflected genuine cross-modal learning rather than scalar stiffness alone; shuffling image-stiffness pairings significantly reduced accuracy (all corrected p < 0.01). Leave-one-tumor-model-out analysis demonstrated generalization to unseen tumor types, with 95.5% ± 1.5% accuracy (range 93.9-97.9%) across five held-out models. Lower baseline stiffness correlated with better response, supporting the hypothesis that mechanically normalized tumors respond more effectively. These preclinical proof-of-concept findings establish tumor mechanics as candidate predictive biomarkers and transformer-based multimodal learning as a scalable approach to biomechanically informed response prediction, while requiring validation in human cohorts.</p>","PeriodicalId":8417,"journal":{"name":"Array","volume":"31 ","pages":"None"},"PeriodicalIF":5.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13614918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149057264","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}

引用次数: 0

FairFlow: A transparency-first framework for verifiable and reproducible bioinformatics. FairFlow：透明优先的可验证和可复制生物信息学框架。

IF 5.3

Array Pub Date : 2026-09-01 DOI: 10.1016/j.array.2026.101150

Agata D'Onofrio, Eliseo Martelli, Maurizio Alessandri, Sebastian Bucatariu, Sandro Gepiro Contaldo, Maria Luisa Ratto, Jianli Tao, Beatrice Nuvolari, Isabella Castellano, Andrea Loiacono, Sara Bianchi, Maddalena Arigoni, Alessandro Bertero, Elisa Balmas, Roberto Chiarle, Luca Alessandri

{"title":"FairFlow: A transparency-first framework for verifiable and reproducible bioinformatics.","authors":"Agata D'Onofrio, Eliseo Martelli, Maurizio Alessandri, Sebastian Bucatariu, Sandro Gepiro Contaldo, Maria Luisa Ratto, Jianli Tao, Beatrice Nuvolari, Isabella Castellano, Andrea Loiacono, Sara Bianchi, Maddalena Arigoni, Alessandro Bertero, Elisa Balmas, Roberto Chiarle, Luca Alessandri","doi":"10.1016/j.array.2026.101150","DOIUrl":"10.1016/j.array.2026.101150","url":null,"abstract":"<p><p>Bioinformatics analyses depend on external software that itself relies on further programs, or dependencies, each with its own release cycle. Because tools are updated to fix bugs and add features, identical code can produce different results depending on which versions are installed, and incomplete documentation of dependencies and versions therefore undermines reproducibility. Containerization packages software with all its dependencies, but demands technical expertise and lacks a standard operating procedure. Existing workflow managers and container tools have improved reproducibility, yet each works differently and requires specialized knowledge, forcing developers to rebuild equivalent solutions from scratch. Here we present FairFlow, a framework that makes rigorous, reproducible analysis accessible without specialized technical knowledge. Developers describe a pipeline once in a declarative, INI-style specification file written in Baryon, and FairFlow automatically generates ready-to-run interfaces for R, Python, Bash, Galaxy, Nextflow and StreamFlow, each executing the analysis inside a version-locked container. The generated interfaces are self-contained: end users need only Docker and their preferred language. As a proof of concept we reanalyzed a published study in two ways: following the original protocol, which does not account for dependency installation, and with a FairFlow-based script. The first yielded only ∼21% concordance with the original findings, traced to an unspecified sequence-alignment tool version, whereas the FairFlow-based reanalysis achieved 98.8-100% concordance across operating systems and reduced setup from months of troubleshooting to a single Docker installation.</p>","PeriodicalId":8417,"journal":{"name":"Array","volume":"31 ","pages":"None"},"PeriodicalIF":5.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13614917/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149057314","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}

引用次数: 0

XQE-Net: A deep learning framework with integrated feature fusion and optimization for cervical cancer screening XQE-Net：一种集成特征融合与优化的宫颈癌筛查深度学习框架

IF 5.3

Array Pub Date : 2026-09-01 Epub Date: 2026-07-20 DOI: 10.1016/j.array.2026.101102

Bhawna Swarnkar, Nilay Khare, Manasi Gyanchandani, Nitin Kumar

{"title":"XQE-Net: A deep learning framework with integrated feature fusion and optimization for cervical cancer screening","authors":"Bhawna Swarnkar, Nilay Khare, Manasi Gyanchandani, Nitin Kumar","doi":"10.1016/j.array.2026.101102","DOIUrl":"10.1016/j.array.2026.101102","url":null,"abstract":"<div><div>Cervical cancer remains a critical global health concern requiring accurate and efficient automated screening solutions. This paper presents XQE-Net, a Computer-Aided Diagnosis framework built upon a heterogeneous ensemble of three CNN architectures — Xception, SqueezeNet, and EfficientNet B7 — each selected for its distinct architectural design. XQE-Net extracts hierarchical deep features from three layers of each CNN — fully connected, pooling, and convolutional — yielding nine independent feature sets that collectively capture a comprehensive diagnostic representation of cervical cell morphology. A Discrete Wavelet Transform using a Haar basis function at six decomposition levels is applied exclusively to convolutional layer features, compressing raw dimensionality by up to 98.9% while preserving discriminative spectral characteristics prior to fusion. Subsequently, mRMR-based feature selection reduces the fused feature space by up to 91.6%, yielding a deployment-ready classifier requiring as little as 1.56 KB memory per sample. XQE-Net process Pap smear images without requiring segmentation or image enhancement, simplifying the diagnostic pipeline for clinical deployment. Validated through five-fold cross-validation on two benchmark datasets, XQE-Net achieves 98.5% accuracy on SIPaKMeD and 100% on Mendeley LBC, outperforming existing methods by 3.77% and 1.22% respectively, confirming its diagnostic reliability and cross-dataset generalizability.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"31 ","pages":"Article 101102"},"PeriodicalIF":5.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148934802","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}

引用次数: 0

Review on different band selection approaches for classification of hyperspectral images 高光谱图像分类中不同波段选择方法的综述

IF 5.3

Array Pub Date : 2026-09-01 Epub Date: 2026-09-25 DOI: 10.1016/j.array.2026.100993

M. PrabuKumar, R. Satheeshkumar

{"title":"Review on different band selection approaches for classification of hyperspectral images","authors":"M. PrabuKumar, R. Satheeshkumar","doi":"10.1016/j.array.2026.100993","DOIUrl":"10.1016/j.array.2026.100993","url":null,"abstract":"<div><div>Hyperspectral Imaging (HSI) has become a very necessary technology in remote sensing, agriculture, medical diagnostics, and environmental studies because of the imaging ability of hundreds of narrow spectral bands. Hyperspectral data is high dimensional, which causes spectral redundancy, expense of computation and Hughes phenomenon, where classification performance decreases as the number of features increases greatly relative to the available training samples. The given paper is a systematic literature review (SLR) of the hyperspectral band selection methods published in 2023-2025 that were retrieved through IEEE Xplore, ScienceDirect, Scopus, ACM Digital Library, and SpringerLink. The methods reviewed are classified into four methodological paradigms namely filter-based, wrapper-based, embedded and hybrid methods. Synthesis of 72% peer-reviewed works was done. Hybrid and deep-learning-enhanced designs, such as reinforcement learning (RL), multi-objective optimization (MOO), and transformer-based selection, are more accurate (OA ≥ 97%) and have competitive computational power (<300 ms). Benchmark analysis of the data of Indian Pines, Salinas, Pavia University, and Kennedy Space Centre (KSC) shows that Proximal Policy Optimization (PPO)-based RL has the largest OA (97.9%), and Discrete Wavelet Transform (DWT)-based fusion has the lowest cost-accuracy ratio. The areas of critical research gaps in the adaptive online selection, edge-deployable lightweight models, domain-specific spectral optimization, and explainability of deep-learning selectors remain. The research needs to focus its future efforts on interpretable, real-time and cross-domain adaptive band selection frameworks to enable hyperspectral imaging to be deployed to practice.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"31 ","pages":"Article 100993"},"PeriodicalIF":5.3,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149043978","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}

引用次数: 0

Deep-fake Detection of Digital Misinformation Over social media: a comprehensive review 社交媒体上数字错误信息的深度虚假检测：全面审查

IF 5.3

Array Pub Date : 2026-07-13 DOI: 10.1016/j.array.2026.101086

Haiam Hamed Abuserea Abdelsalam, Hesham A. Hefny (Prof)

{"title":"Deep-fake Detection of Digital Misinformation Over social media: a comprehensive review","authors":"Haiam Hamed Abuserea Abdelsalam, Hesham A. Hefny (Prof)","doi":"10.1016/j.array.2026.101086","DOIUrl":"10.1016/j.array.2026.101086","url":null,"abstract":"<div><div>The proliferation of deepfake content across social media platforms has intensified the spread of digital misinformation, posing serious threats to public trust, democratic stability, and individual privacy. Existing deepfake detection methods, while technically advanced, face critical limitations in generalizability, real-time performance, and resilience against increasingly sophisticated generative techniques. This review highlights the urgent need for robust and adaptive detection frameworks capable of countering the evolving tactics used to fabricate and disseminate synthetic media.</div><div>We systematically examine current approaches, including machine learning algorithms, computer vision techniques, and adversarial training strategies, and evaluate their effectiveness based on dataset quality, modality coverage, and deployment feasibility. Our findings reveal that hybrid models integrating multiple detection modalities consistently outperform single-method systems in accuracy and robustness. The study underscores the importance of aligning technical innovation with social awareness, advocating for scalable solutions that can mitigate misinformation risks amplified by the viral nature of social media platforms.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"31 ","pages":"Article 101086"},"PeriodicalIF":5.3,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148501409","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}

引用次数: 0

Robust multi-scale LSTM for reliable and intelligent photovoltaic power forecasting 基于鲁棒多尺度LSTM的可靠智能光伏发电预测

IF 4.5

Array Pub Date : 2026-03-01 Epub Date: 2026-01-08 DOI: 10.1016/j.array.2026.100678

Chongchong Xu , Bin Zhao , Yujie Zhao

{"title":"Robust multi-scale LSTM for reliable and intelligent photovoltaic power forecasting","authors":"Chongchong Xu , Bin Zhao , Yujie Zhao","doi":"10.1016/j.array.2026.100678","DOIUrl":"10.1016/j.array.2026.100678","url":null,"abstract":"<div><div>Photovoltaic (PV) power generation, which playing a crucial role in promoting sustainable development and mitigating climate change, has become a key catalyst in the worldwide energy shift. However, its extensive integration into power grids presents issues for stability and efficient utilization, as PV output is highly dependent on meteorological conditions. The inherent variability and randomness of PV power time series often degrade forecasting performance. To address these challenges, a prediction approach based on a Robust Multi-scale Long Short-Term Memory Network (RMS-LSTM) is proposed in this study. We aim to construct a model which is able to capture both short-term and long-term trends. Specifically, we also employs correlation analysis and Robust Principal Component Analysis (RPCA) for feature selection and dimensionality reduction. On this basis, the refined training data inputs the multi-scale LSTM framework, aiming to derive the potential features. Then, we can employ the trained model to attain high-precision predictions of power output. The PV power data from Guoneng serves as a validation dataset to evaluate the performance of RMS-LSTM. It is shown that the Root Mean Square Error (RMSE) is 4.9482 and Mean Absolute Error (MAE) is 2.5246. Compared with benchmark methods, the proposed framework has advantages in prediction accuracy and robustness, verifying its effectiveness in PV power forecasting.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100678"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145973364","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

MambaSolar-Forcaster: A trustworthy photovoltaic ultra-short-term power forecasting method based on normalized optimization and multi-step forecasting mechanism MambaSolar-Forcaster：基于归一化优化和多步预测机制的可信赖的光伏超短期功率预测方法

IF 4.5

Array Pub Date : 2026-03-01 Epub Date: 2025-12-20 DOI: 10.1016/j.array.2025.100640

Li Ding , Xinyu Hu , Jian Deng , Weihua Zhu , Jiaming Hu

{"title":"MambaSolar-Forcaster: A trustworthy photovoltaic ultra-short-term power forecasting method based on normalized optimization and multi-step forecasting mechanism","authors":"Li Ding , Xinyu Hu , Jian Deng , Weihua Zhu , Jiaming Hu","doi":"10.1016/j.array.2025.100640","DOIUrl":"10.1016/j.array.2025.100640","url":null,"abstract":"<div><div>Against the backdrop of the global energy structure shifting towards clean and low-carbon, the high proportion of photovoltaic grid integration poses challenges to the safe and stable operation of the power system. The intermittency and volatility of photovoltaic output make high-precision and trustworthy ultra-short-term power prediction a key link in ensuring grid safety. Although deep learning models have shown potential in this field, traditional models such as RNN and Transformer have limitations in long-range dependencies and computational efficiency, and the uncertainty of their prediction results may lead to security decision risks. Therefore, this article proposes a new photovoltaic ultra short term power prediction model called MambaSolar-Forcaster. The core innovation of this study lies in introducing the Mamba architecture, a new generation state space model, into this field for the first time. By utilizing its selective state space mechanism, it efficiently captures long-range dependencies in photovoltaic power sequences while maintaining linear computational complexity, and generates more trustworthy prediction intervals. In addition, we have designed a normalization and multi-step prediction mechanism for photovoltaic data characteristics, and constructed a trustworthy AI evaluation system that integrates point prediction and interval prediction. Then, experiments were conducted on the PVDAQ dataset, and the results showed that MambaSolar-Forcaster significantly outperformed the comparison model in terms of prediction accuracy and interval prediction reliability. Its more compact and reliable prediction interval can provide stronger support for safe scheduling decisions in the power grid.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100640"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145921254","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

Tiny Machine Learning (TinyML): Research trends and future application opportunities 微型机器学习（TinyML）：研究趋势和未来应用机会

IF 4.5

Array Pub Date : 2026-03-01 Epub Date: 2026-01-03 DOI: 10.1016/j.array.2025.100674

Hui Han , Silvana Trimi , Sang M. Lee

引用次数: 0

Multi-rate real-time simulation: Techniques, models, frameworks, and challenges 多速率实时仿真：技术、模型、框架和挑战

IF 4.5

Array Pub Date : 2026-03-01 Epub Date: 2025-12-31 DOI: 10.1016/j.array.2025.100661

Hossein Taghizad, Michel Lemaire, Daniel Massicotte

引用次数: 0

Multilingual multimodal cyberbullying detection through adaptive and hierarchical fusion 基于自适应和分层融合的多语言多模式网络欺凌检测

IF 4.5

Array Pub Date : 2026-03-01 Epub Date: 2026-01-22 DOI: 10.1016/j.array.2026.100689

Walaa Saber Ismail , Hikmat Ullah , Muhammad Adnan , Farman Ullah

{"title":"Multilingual multimodal cyberbullying detection through adaptive and hierarchical fusion","authors":"Walaa Saber Ismail , Hikmat Ullah , Muhammad Adnan , Farman Ullah","doi":"10.1016/j.array.2026.100689","DOIUrl":"10.1016/j.array.2026.100689","url":null,"abstract":"<div><div>Detecting cyberbullying in multimodal content (such as memes) is challenging due to complex interactions between images and text, often involving sarcasm, multilingual usage, and other noisy real-world factors. This paper presents a multilingual multimodal cyberbullying detection framework that combines early fusion, late fusion, and hierarchical fusion strategies within a unified architecture. The framework introduces three key modules: Adaptive Cross-Modal Token Integration (ACTI) for iterative early fusion, Context-Adaptive Ensemble with Uncertainty-Aware Gating (CAE-UAG) for dynamic late fusion based on input reliability, and a Hierarchical Contextual Fusion Network (HCFN) that feeds early fused context back into later unimodal processing for refined predictions. Our system leverages state-of-the-art pretrained vision-language models (e.g., CLIP for images and XLM-RoBERTa for text) to learn subtle cross-modal representations (e.g., sarcasm or image–text irony) and uses uncertainty modeling to handle ambiguous or noisy inputs. We evaluate the approach on two benchmark datasets: the English-language Facebook Hateful Memes and the ArMeme dataset of Arabic memes. Experimental results show that our model outperforms multiple baselines (including single-modality models and a strong CLIP-based multimodal baseline), achieving high accuracy, F1-scores, and area under ROC (AUROC) across languages. Notably, it achieves state-of-the-art performance (e.g., 0.85 F1 and 0.88 AUROC on Hateful Memes), surpassing prior fusion methods. The proposed framework represents a significant step toward generalizable, culturally aware, and robust multimodal cyberbullying detection suitable for deployment across diverse social media contexts.</div></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"29 ","pages":"Article 100689"},"PeriodicalIF":4.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146073941","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