Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection by Xueqi Zhang

“…The new system adopts an optimized convolutional kernel design to improve the accuracy of feature extraction. It incorporates batch normalization techniques to mitigate the occurrence of overfitting and utilizes multi-scale feature fusion technology to enhance the ability to recognize book images. …”
Get full text

Enhancing diabetes risk prediction through focal active learning and machine learning models. by Wangyouchen Zhang, Zhenhua Xia, Guoqing Cai, Junhao Wang, Xutao Dong

“…The method integrates SHAP (SHapley Additive Explanations) to quantify feature importance and applies attention mechanisms to dynamically adjust feature weights, enhancing model interpretability and performance in predicting diabetes risk. …”
Get full text

Robust two stages federated learning for sensor based human activity recognition with label noise by Haifeng Sun, Junping Yao, Xiaojun Li, Yanfei Liu, Hongyang Gu

“…To overcome these challenges of complex label noise and feature drift, this paper proposes LN-FHAR, a two-stage federated learning framework with label noise robustness. …”
Get full text

Accurate Extraction of Rural Residential Buildings in Alpine Mountainous Areas by Combining Shadow Processing with FF-SwinT by Guize Luan, Jinxuan Luo, Zuyu Gao, Fei Zhao

“…Building upon this, the Feature Fusion Swin Transformer (FF-SwinT) model was constructed by optimizing the data processing, loss function, and multi-view feature fusion. …”
Get full text

Recent progress on machine learning with limited materials data: Using tools from data science and domain knowledge by Bangtan Zong, Jinshan Li, Tinghuan Yuan, Jun Wang, Ruihao Yuan

“…The enhancement of data quality and amount via data augmentation and feature engineering is first summarized and discussed. …”
Get full text

EMI-EMC Qualification of the NASA SWOT Mission Using High Fidelity Modeling by Nacer E. Chahat, Edward Gonzales, Emmanuel Decrossas, Amy Stevens, Matthew Keyawa, Pablo S. Narvaez

“…Surface Water and Ocean Topography (SWOT) is a complex satellite with multiple high-power transmitters and highly sensitive receivers. A pivotal feature is the Ka-band interferometer, operating at 2000 Watts, which significantly amplifies the satellite's qualification challenges. …”
Get full text

Coseismic Landslide Mapping Based on Trans-UNet and Transfer Learning by Tianhe Ren, Wenping Gong, Jun Chen, Liang Gao, Jiahao Wu, Xuyang Xiang

“…The Trans-UNet model integrates a UNet-like encoder–decoder structure with a Transformer module to enhance global context extraction, a U-shaped full-scale feature extraction module to preserve multiscale spatial details, and a convolutional decoder for effective feature fusion and resolution restoration. …”
Get full text

Longitudinal shear behavior of composite slabs with recycled coarse and fine aggregate concrete by Jiongzhuo Bai, Yue Geng, Yu-Yin Wang, Charles K.S. Moy, Huan Zhang

Get full text

Machine Learning-Enabled Attacks on Anti-Phishing Blacklists by Wenhao Li, Shams Ul Arfeen Laghari, Selvakumar Manickam, Yung-Wey Chong, Binyong Li

“…The results emphasize the need for APEs to implement more robust and adaptive defenses and propose mitigation strategies to enhance the resilience of the anti-phishing ecosystem.…”
Get full text

An Inverted Transformer Framework for Aviation Trajectory Prediction with Multi-Flight Mode Fusion by Gaoyong Lu, Yang Ou, Wei Li, Xinyu Zeng, Ziyang Zhang, Dongcheng Huang, Igor Kotenko

“…This imbalance poses significant challenges to flight punctuality and operational efficiency. To mitigate these issues, existing models often rely solely on individual flight data, which restricts the breadth and depth of feature learning. …”
Get full text

WTI-SLAM: a novel thermal infrared visual SLAM algorithm for weak texture thermal infrared images by Sen Li, Xiaofei Ma, Rui He, Yuanrui Shen, He Guan, Hezhao Liu, Fei Li

“…The research introduces a new infrared visual odometry that integrates feature-based methods with optical flow techniques, enhancing image processing capabilities to mitigate the issues of high time overhead and cumulative errors in traditional feature-based odometry. …”
Get full text

Electromyography Signal Acquisition, Filtering, and Data Analysis for Exoskeleton Development by Jung-Hoon Sul, Lasitha Piyathilaka, Diluka Moratuwage, Sanura Dunu Arachchige, Amal Jayawardena, Gayan Kahandawa, D. M. G. Preethichandra

“…This review presents a comprehensive analysis of the EMG signal processing pipeline tailored to exoskeleton applications, spanning signal acquisition, noise mitigation, data preprocessing, feature extraction, and control strategies. …”
Get full text

Robust Photovoltaic Power Forecasting Model Under Complex Meteorological Conditions by Yuxiang Guo, Qiang Han, Tan Li, Huichu Fu, Meng Liang, Siwei Zhang

“…However, traditional PV power forecasting models designed for distributed PV power stations often struggle with accuracy due to unpredictable meteorological variations, data noise, non-stationary signals, and human-induced data collection errors. To effectively mitigate these limitations, this work proposes a dual-stage feature extraction method based on Variational Mode Decomposition (VMD) and Principal Component Analysis (PCA), enhancing multi-scale modeling and noise reduction capabilities. …”
Get full text

AI-Driven Boost in Detection Accuracy for Agricultural Fire Monitoring by Akmalbek Abdusalomov, Sabina Umirzakova, Komil Tashev, Jasur Sevinov, Zavqiddin Temirov, Bahodir Muminov, Abror Buriboev, Lola Safarova Ulmasovna, Cheolwon Lee

“…The proposed framework incorporates an optimized ConvNeXt backbone combined with a novel Feature Enhancement Block (FEB), specifically designed to refine spatial and contextual feature representation for improved detection performance. …”
Get full text

Computer-Vision-Aided Deflection Influences Line Identification of Concrete Bridge Enhanced by Edge Detection and Time-Domain Forward Inference by Jianfeng Chen, Long Zhao, Yuliang Feng, Zhiwei Chen

“…The methodology proposed in this research leverages computer vision technology with edge detection to surpass traditional contact-based measurement methods, greatly enhancing the operational efficiency and applicability of IL identification and, in particular, addressing the challenge of accurately measuring small deflections in concrete bridges. To mitigate the limitations of the Lucas–Kanade (LK) optical flow method, such as unclear feature points within the camera’s field of view and occasional point loss in certain video frames, an edge detection technique is employed to identify maximum values in the first-order derivatives of the image, creating virtual tracking points at the bridge edges through image processing. …”
Get full text

POI recommendation by deep neural matrix factorization integrated attention-aware meta-paths by Xiaoyan Li, Shenghua Xu, Hengxu Jin, Zhuolu Wang, Yu Ma, Xuan He

“…Attention networks are employed to aggregate node vectors across various relationships and serve as auxiliary information to mitigate the challenges of data sparsity. Subsequently, the internal embedding vectors of the users and POIs are extracted using feature embedding based on the user–POI interaction matrix. …”
Get full text

A sustainability trilogy approach for drought risk prevention: Case study in Indonesia by Ramli Akhmad, Sumarmi Sumarmi, I. Komang Astina, Satti Wagistina

“…Drought presents a major challenge to agriculture and rural livelihoods, particularly in countries like Indonesia, which feature diverse topography and unpredictable rainfall patterns. …”
Get full text

SFTA-Net: a self-supervised approach to detect copy-move and splicing forgery to leverage triplet loss, auxiliary loss, and spatial attention by Amerah Alabrah

“…The previously proposed studies focused on a single type of forgery detection utilizing block-based and key-point feature selection-based classical machine learning (ML) approaches. …”
Get full text

Artificial Intelligence in Healthcare: Innovation and Impact in Medical Practice by Amelia-Maria ISAC, Corina VERNIC

“…However, significant variability exists, particularly in smaller datasets (n < 500) and when suboptimal feature selection strategies are used. The analysis highlights the necessity of robust validation techniques, such as cross-validation and external dataset testing, to mitigate overfitting and improve model reliability across diverse clinical settings. …”
Get full text

The High-Granularity Timing Detector for ATLAS at HL-LHC by Joaquim Pinol

“…The High-Granularity Timing Detector (HGTD), featuring novel Low-Gain Avalanche Detector silicon technology, will provide pile-up mitigation and luminosity measurement capabilities, and augment the new all-silicon Inner Tracker in the pseudo-rapidity range from 2.4 to 4.0. …”
Get full text