Multimodal Fall Detection Using Spatial–Temporal Attention and Bi-LSTM-Based Feature Fusion by Jungpil Shin, Abu Saleh Musa Miah, Rei Egawa, Najmul Hassan, Koki Hirooka, Yoichi Tomioka

“…The GSTCAN model uses AlphaPose for skeleton extraction, calculates motion between consecutive frames, and applies a graph convolutional network (GCN) with a CA mechanism to focus on relevant features while suppressing noise. …”
Get full text

A Transformer-Based Multiscale Difference Enhancement Network for Change Detection by Mengyang Pan, Hang Yang, Chengkang Yu, Mingqing Li, Anping Deng

“…Despite the progress made by convolutional neural networks and Transformer architectures in visual analysis, challenges remain in achieving robust feature representation and global contextual understanding. …”
Get full text

Evaluation of machine learning algorithm capability for Bosten Lake Wetland classification based on multi-temporal Sentinel-2 data by Feiying Xia, Guanghui Lv

Get full text

Panchromatic and Hyperspectral Image Fusion Using Ratio Residual Attention Networks by Fengxiang Xu, Nan Zhang, Zhenxiang Chen, Peiran Peng, Tingfa Xu

“…Hyperspectral remote sensing images provide rich spectral information about land surface features and are widely used in fields such as environmental monitoring, disaster assessment, and land classification. …”
Get full text

Progressive multi-scale attention neural network for pneumonia classification in chest X-rays by Mohammad Reza Mahdiani

“…We propose a novel Progressive Multi-Scale Attention Network (PMSAN) with an integrated Edge-Aware Loss function for improved pneumonia classification in chest X-rays. …”
Get full text

MAHGA: Multi-Aspect Heterogeneous Graph Analysis for Harmful Speech Detection on Social Networks by Ryo Yoshida, Soh Yoshida, Mitsuji Muneyasu

“…Deep neural networks demonstrate high accuracy in detecting harmful social media posts; however, conventional text-based methods often overlook critical contextual relationships among posts, users, and shared information. …”
Get full text

Recognizing Mixing Patterns of Urban Agglomeration Based on Complex Network Assortativity Coefficient: A Case Study in China by Kaiqi Zhang, Lujin Jia, Sheng Xu

“…Based on multi-source data (Baidu index data, investment data of listed companies, high-speed rail operation data, and highway network data) from 2017 to 2019 across seven national-level urban agglomerations, this study introduces complex network assortativity coefficients to analyze the mechanisms of urban relationship formation from two dimensions, structural features and socioeconomic attributes, to evaluate how these features shape urban agglomeration networks and reveal the distribution of network assortativity coefficients across urban agglomerations to classify diverse developmental patterns. …”
Get full text

Damage identification based on the inner product matrix and parallel convolution neural network for frame structure by Yingying He, Ji Feng, Baogang Sun, Feixue Wang, Likai Zhang, Jidi Jiang

“…This unique combination leverages the strengths of both 1D and 2D CNNs to capture temporal and modal features of the signal effectively. To validate the effectiveness and superiority of the proposed method, a five-story steel frame model is used as the research object, and five comparative methods are evaluated under the same experimental conditions. …”
Get full text

DGNMDA: Dual Heterogeneous Graph Neural Network Encoder for miRNA-Disease Association Prediction by Daying Lu, Qi Zhang, Chunhou Zheng, Jian Li, Zhe Yin

“…Additionally, we develop a specialized fine-grained multi-layer feature interaction gating mechanism to integrate outputs from the neural network encoders to identify novel associations connecting miRNAs with diseases. …”
Get full text

Enhancing Kármán Vortex Street Detection via Auxiliary Networks Incorporating Key Atmospheric Parameters by Yihan Zhang, Zhi Zhang, Qiao Su, Chaoyue Wu, Yuqi Zhang, Daoyi Chen

“…Utilizing reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF-ERA5), representative atmospheric features are extracted and subjected to feature permutation importance (PFI) analysis to quantitatively evaluate the influence of each parameter on the detection task. …”
Get full text

A stacked ensemble approach to detect cyber attacks based on feature selection techniques by Wahida Ferdose Urmi, Mohammed Nasir Uddin, Md Ashraf Uddin, Md. Alamin Talukder, Md. Rahat Hasan, Souvik Paul, Moumita Chanda, John Ayoade, Ansam Khraisat, Rakib Hossen, Faisal Imran

“…However, the effectiveness of CADS is highly dependent on selecting pertinent features. This research evaluates the impact of three feature selection techniques—Recursive Feature Elimination (RFE), Mutual Information (MI), and Lasso Feature Selection (LFS)—on CADS performance. …”
Get full text

WDM-UNet: A Wavelet-Deformable Gated Fusion Network for Multi-Scale Retinal Vessel Segmentation by Xinlong Li, Hang Zhou

Get full text

A Multi-Scale attention network for building extraction from high-resolution remote sensing images by Jing Chang, Xiaohui He, Dingjun Song, Panle Li, Mengjia Qiao, Xijie Cheng

“…Then, in the decoding phase, channel grouping shuffle and dual attention mechanisms are synergistically integrated to exploit the interrelations and global dependencies of building features. Finally, a hybrid loss function is devised to address the class imbalance and thereby ensure more stable network training. …”
Get full text

PC3D-YOLO: An Enhanced Multi-Scale Network for Crack Detection in Precast Concrete Components by Zichun Kang, Kedi Gu, Andrew Yin Hu, Haonan Du, Qingyang Gu, Yang Jiang, Wenxia Gan

“…Our methodology involves three key innovations: (1) the Multi-Dilation Spatial-Channel Fusion with Shuffling (MSFS) module, employing dilated convolutions and channel shuffling to enable global feature fusion, replaces the C3K2 bottleneck module to enhance long-distance dependency capture; (2) the AIFI_M2SA module substitutes the conventional SPPF to mitigate its restricted receptive field and information loss, incorporating multi-scale attention for improved near-far contextual integration; (3) a redesigned neck network (MSCD-Net) preserves rich contextual information across all feature scales. …”
Get full text

Enhancing Power Grid Reliability With Machine Learning and Auxiliary Classifier Generative Adversarial Networks: A Study on Fault Detection Using the Georgia Electric System Load D... by Hafeez Ur Rehman Siddiqui, Robert Brown, Adil Ali Saleem, Muhammad Amjad Raza, Sandra Dudley

“…Power networks are vital to society, yet service outages and faults can have devastating consequences. …”
Get full text

SpikeMOT: Event-Based Multi-Object Tracking With Sparse Motion Features by Song Wang, Zhu Wang, Can Li, Xiaojuan Qi, Hayden Kwok-Hay So

“…To address these limitations, we introduce SpikeMOT, an innovative event-based MOT framework employing spiking neural networks (SNNs) within a Siamese architecture. SpikeMOT extracts and associates sparse spatiotemporal features from event streams, enabling high-frequency object motion inference while preserving object identities. …”
Get full text

Resilient Topology Reconfiguration for Industrial Internet of Things: A Feature-Driven Approach Against Heterogeneous Attacks by Tianyu Wang, Dong Li, Bowen Zhang, Xianda Liu, Wenli Shang

“…This paper proposes a feature-driven topology reconfiguration framework to enhance the resilience of Industrial Internet of Things (IIoT) systems against heterogeneous attacks. …”
Get full text

Examining the Impact of Content Features on Customer Engagement in Social Media: A Data Mining Approach on Instagram by Azade Shekari, Mohammad Mehdi Poursaeed, Saeed Dehyadegari

“…Then, the Clementine data mining toolkit, along with three methods—Association Rules, Apriori Algorithm, and Decision Tree—were used to identify features affecting customer engagement in terms of likes, comments, and conversations, and to evaluate their effectiveness.   …”
Get full text

Hybrid Feature Selection and Classifying Stages through Electrocardiogram (ECG) Signal for Heart Disease Prediction by Babu Kumar, Radhakrishnan Soundararajan, Kanimozhi Natesan, Roobini Maridhas Santhi

“…This approach involves many rounds of data sorting for decreasing noise, thresholding an ECG difference signal by examining the time interval between QRS, and then comparing relative magnitudes to identify the area of interval processing to evaluate accuracy results. In order to choose the best features, a modified chicken swarm optimization algorithm (MCSO) was proposed. …”
Get full text

SCM-DL: Split-Combine-Merge Deep Learning Model Integrated With Feature Selection in Sports for Talent Identification by Didem Abidin, Muhammed G. Erdem

Get full text