PercepWeldNet: A Novel Perception-Guided Deep Model for Welding Defect Detection by Xingxing Zhang

“…In this study, we introduce PercepWeldNet, a deep architecture designed for visual perception in welding defect detection, addressing the challenge of identifying semantically significant features within complex welding scenes. …”
Get full text

Quantification and Flow Simulation of Ecosystem Service Supply and Demand in the Yellow River Delta High-Efficiency Eco-Economic Zone by Wenjun Liu, Xiangyi Ma, Qian Sun, Wei Qi, Xinyang Yu

“…This study selected the Yellow River Delta High-Efficiency Eco-Economic Zone in China as the case study area and assessed the habitat quality and carbon sequestration services for 2000, 2010, and 2020. …”
Get full text

FastADnet: Fast Anomaly Detection via Core-Feature Centered Cluster Reconstruction Network by Daeyeob Na, Youngjoon Yoo

“…In recent works in this field, there are trade-offs between computational complexity and anomaly detection accuracy for effective deployment. …”
Get full text

DECISION SUPPORT SYSTEM IN PLANNING INVESTMENT PROJECTS by Viktor Kosenko

“…The following tasks were solved in the article: the model of complex planning was studied and the investment project was implemented, the method of selecting an optimal variant of investment project implementation was developed, the elements of the decision support system to select the investment method were specified. …”
Get full text

MRC-DETR: A High-Precision Detection Model for Electrical Equipment Protection in Power Operations by Shenwang Li, Yuyang Zhou, Minjie Wang, Li Liu, Thomas Wu

“…This paper introduces MRC-DETR (Multi-Scale Re-calibration Detection Transformer), a novel framework for detecting Power Engineering Personal Protective Equipment (PEPPE) in complex electrical operating environments. …”
Get full text

An Improved Lithium-Ion Battery Fire and Smoke Detection Method Based on the YOLOv8 Algorithm by Li Deng, Di Kang, Quanyi Liu

“…This paper introduces a novel algorithm—YOLOv8 (You Only Look Once version 8) + FRMHead (a multi-branch feature refinement head) + Slimneck (a lightweight bottleneck module), abbreviated as YFSNet—for lithium-ion battery fire and smoke detection in complex backgrounds. By integrating advanced modules for richer feature extraction and streamlined architecture, YFSNet significantly enhances detection precision and real-time performance. …”
Get full text

Multimodal AI-driven object detection with uncertainty quantification for cardiovascular risk assessment in autistic patients by Ling Tang, Chengchao Shen

“…IntroductionArtificial Intelligence (AI) has transformed medical diagnostics, offering enhanced precision and efficiency in detecting cardiovascular risks. However, traditional diagnostic approaches for cardiovascular risk assessment in autistic patients remain limited due to the complexity of medical data, inter-individual variability, and the challenges of integrating multi-modal clinical information. …”
Get full text

Liveness Detection in Computer Vision: Transformer-Based Self-Supervised Learning for Face Anti-Spoofing by Arman Keresh, Pakizar Shamoi

“…We compared the performance of the proposed fine-tuned ViT model using the DINO framework against traditional models, including CNN Model EfficientNet b2, EfficientNet b2 (Noisy Student), and Mobile ViT on the face anti-spoofing task. …”
Get full text

Beyond the Grid: GLRT-Based TomoSAR Fast Detection for Retrieving Height and Thermal Dilation by Nabil Haddad, Karima Hadj-Rabah, Alessandra Budillon, Gilda Schirinzi

“…While effective, these methods face two primary limitations: high computational complexity and the off-grid problem caused by the discretization of the search space. …”
Get full text

The application of natural language processing technology in hospital network information management systems: Potential for improving diagnostic accuracy and efficiency by Shiyong Wang, Hong Luo

“…To overcome this difficulty, the complex interactions among natural language processing (NLP), optical character recognition (OCR) and image preprocessing was used. …”
Get full text

Adaptive AI-enhanced computation offloading with machine learning for QoE optimization and energy-efficient mobile edge systems by Dinesh Kumar Nishad, Vandna Rani Verma, Pushkar Rajput, Sandeep Gupta, Anurag Dwivedi, Dharti Raj Shah

“…Abstract Mobile Edge Computing (MEC) systems face critical challenges in optimizing computation offloading decisions while maintaining quality of experience (QoE) and energy efficiency, particularly in dynamic multi-user environments. …”
Get full text

Delamination Detection in CFRP Stringers with A₀-Mode Lamb Wave Curvature by Gaozheng Zhao, Yike Zeng, Zhenyang Yu, Kaihua Sun, Jian Chen

“…Ultrasonic detection of delamination in stringer-stiffened panels made of carbon fiber-reinforced plastics (CFRPs) presents a critical challenge due to their complex geometry, complicated properties and large size. …”
Get full text

A Multimodal Parallel Transformer Framework for Apple Disease Detection and Severity Classification with Lightweight Optimization by Chuhuang Zhou, Xinjin Ge, Yihe Chang, Mingfei Wang, Zhongtian Shi, Mengxue Ji, Tianxing Wu, Chunli Lv

“…To address the impact of complex disease characteristics and diverse environmental factors on detection accuracy, this study proposes a multimodal parallel transformer-based approach for apple disease detection and classification. …”
Get full text

Detection of Q235 Mild Steel Resistance Spot Welding Defects Based on EMD-SVM by Yuxin Wu, Xiangdong Gao, Dongfang Zhang, Perry Gao

“…Real-time detection of welding defects in resistance spot welding is a complex challenge. …”
Get full text

An Attention-Enhanced 3D-CNN Framework for Spectrogram-Based EEG Analysis in Epilepsy Detection by Ziaullah Khan, Aakanksha Dayal, Hee-Cheol Kim

Get full text

Supervised Anomaly Detection in Univariate Time-Series Using 1D Convolutional Siamese Networks by Ayan Chatterjee, Vajira Thambawita, Michael A. Riegler, Pal Halvorsen

“…Anomalies can compromise data quality and operational efficiency. The complexity of time-series data, with its temporal dependencies and potential non-stationarity, makes anomaly detection challenging but essential. …”
Get full text

AH-YOLO: An Improved YOLOv8-Based Lightweight Model for Fire Detection in Aircraft Hangars by Li Deng, Zhuoyu Wang, Quanyi Liu

“…First, the MobileOne module is integrated to reduce the network complexity and improve the computational efficiency. …”
Get full text

Effects of Broken Rotor Bars on Three-Phase Induction Machines and Detection Methods – State of Arts by Boudmane Bilal, Rachid Aziz, Mortabit Idriss, Errifai Nidale

“…Identifying and addressing rotor bar issues promptly is crucial for maintaining operational reliability and minimizing unplanned maintenance activities. Detecting broken rotor bars presents challenges due to the subtle nature of early-stage faults and the complexity of motor operating conditions. …”
Get full text

A Hybrid Graph-Based Risk Assessment and Attack Path Detection Model for IoT Systems by Ferhat Arat, Sedat Akleylek, Zaliha Yuce Tok

“…Our proposed approach targets high-vulnerability components within the system through risk-weighted backtracking, thereby facilitating more efficient attack path detection and filtering. The developed method is evaluated in a border security case scenario, with comparisons made in terms of algorithmic and asymptotic complexity. …”
Get full text

On Robustness of the Explanatory Power of Machine Learning Models: Insights From a New Explainable AI Approach Using Sensitivity Analysis by Banamali Panigrahi, Saman Razavi, Lorne E. Doig, Blanchard Cordell, Hoshin V. Gupta, Karsten Liber

Get full text