A Lightweight Semantic- and Graph-Guided Network for Advanced Optical Remote Sensing Image Salient Object Detection by Jie Liu, Jinpeng He, Huaixin Chen, Ruoyu Yang, Ying Huang

“…To further efficiently aggregate multi-level features and preserve the integrity and complexity of overall object shape, we introduce a Graph-Based Region Awareness Module (GRAM). …”
Get full text

Arrears behavior prediction of power users based on BP neural network and multi-scale feature learning: a refined risk assessment framework by Liang Yu, Yuanshen Hong, Hua Lin, Xu Jiang, Ziming Song

“…Abstract This study aims to develop an efficient model to predict the arrears behavior of electricity users by integrating multi-scale feature learning with a backpropagation (BP) neural network. …”
Get full text

INFORMATION TECHNOLOGY FOR RECOGNITION OF ROAD SIGNS USING A NEURAL NETWORK by Elena Yashina, Roman Artiukh, Nikolai Рan, Andrei Zelensky

“…The recognition process takes place by constructing a convolutional neural network. Features of the layers of the roller network are considered.  Schematically illustrated script recognition. …”
Get full text

Assessing the performance and explainability of an avalanche danger forecast model by C. Pérez-Guillén, F. Techel, M. Volpi, A. van Herwijnen

“…While avalanche forecasting has traditionally relied exclusively on human expertise, avalanche warning services increasingly integrate data-driven models to support the forecasting process. …”
Get full text

Mathematical Model of the On-Board Antenna of Reentry Spacecraft Taking into Account Surface Waves by V. F. Mikhailov, I. V. Mazhnik

“…When passing through dense layers of the atmosphere, they are exposed to aerodynamic heating, for protection from which a heat-resistant radio-transparent thermal protection is used. …”
Get full text

Attention-enhanced StrongSORT for robust vehicle tracking in complex environments by Wei Xu, Xiaodong Du, Ruochen Li, Bingjie Li, Yuhu Jiao, Lei Xing

“…Abstract While multi-object tracking is critical for autonomous driving systems, traditional algorithms exhibit three fundamental limitations in complex scenarios: (1) blurred feature representation under occlusion and re-identification scenarios causing identity switches, (2) insufficient sensitivity to scale-variant targets due to fixed geometric constraints in conventional IoU-based loss functions, and (3) gradient degradation in deep convolutional layers hindering discriminative feature learning. …”
Get full text

An Interpretable Method for Asphalt Pavement Skid Resistance Performance Evaluation Under Sand-Accumulated Conditions Based on Multi-Scale Fractals by Yuhan Weng, Zhaoyun Sun, Huiying Liu, Yingbin Gu

“…Existing research using only wavelet transforms or fractal theory to study the pavement surface texture-skid resistance relationship has limitations. This paper integrates a wavelet transform and fractal theory to extract the multi-scale fractal features of pavement texture. …”
Get full text

On the effectiveness of neural operators at zero-shot weather downscaling by Saumya Sinha, Brandon Benton, Patrick Emami

“…We find that this Swin-Transformer-based approach mostly outperforms models with neural operator layers in terms of average error metrics, whereas an Enhanced Super-Resolution Generative Adversarial Network-based approach is better than most models in terms of capturing the physics of the ground truth data. …”
Get full text

Hybrid Method for Point Cloud Classification by Abdurrahman Hazer, Remzi Yildirim

“…In this study, we introduce a novel hybrid ResPOL method that integrates a bidirectional architecture with a newly developed Patch-Offset Lambda (POL) mechanism for feature extraction from point cloud data. …”
Get full text

Tip of the Spear: Developing Predictive Military Planning Tools Using Hidden Markov Models by Matthew Litvinas

“…Military planners’ success is in their ability to develop synergy through layering effects of a complex system at a decisive point on the battlefield. …”
Get full text

PaleAle 6.0: Prediction of Protein Relative Solvent Accessibility by Leveraging Pre-Trained Language Models (PLMs) by Wafa Alanazi, Di Meng, Gianluca Pollastri

“…In particular, recent breakthroughs in deep learning—driven by the integration of natural language processing (NLP) algorithms—have significantly advanced the field of protein research. …”
Get full text

Study on dynamic strength criterion of sandstone under the coupling influence of confining pressure, bedding angle and impact pressure by Wenbing Fan, Junwen Zhang, Yang Yang, Jiaqi Wang, Lin Mao, Shaokang Wu, Yang Zhang, Xukai Dong, Yifan Huang, Chuanzhong Jiang

“…Building on these results, enhanced strength criteria were proposed to explicitly integrate the coupling effects of confining pressure, bedding angle, and impact pressure. …”
Get full text

Drafting the "15th Five-Year Plan" of Chinese Libraries: Constructing the Strategic Goals and Systems Based on Environmental Scanning and Demand Analysis by KE Ping, LI Xiaoying, SUN Xuan, LIU Yue

“…We should consistently integrate the above three key priorities throughout the four modern systems.…”
Get full text

Illumination-adaptative granularity progressive multimodal image fusion method by Chuanyun WANG, Dongdong SUN, Mingqi ZHOU, Tian WANG, Qian GAO, Zhaokui LI

“…This integration allows the fusion network to adjust its behavior according to contextual lighting conditions, resulting in more accurate image fusion. …”
Get full text

Autonomous Vehicle Security: Hybrid Threat Modeling Approach by Amal Yousseef, Yu-Zheng Lin, Shalaka Satam, Banafsheh Saber Latibari, Jesus Pacheco, Soheil Salehi, Salim Hariri, Pratik Satam

“…Applied to a generic multi-layered AV architecture, our findings show that intra-vehicle networks, especially CAN bus spoofing and fuzzing attacks, and suspension attacks, represent the most critical vulnerabilities due to their high exploitability and systemic impact. …”
Get full text

Constant High-Voltage Triboelectric Nanogenerator with Stable AC for Sustainable Energy Harvesting by Aso Ali Abdalmohammed Shateri, Salar K. Fatah, Fengling Zhuo, Nazifi Sani Shuaibu, Chuanrui Chen, Rui Wan, Xiaozhi Wang

“…This study presents an innovative approach to sustainable energy generation by integrating horizontal motion harvesting with rotational energy conversion. …”
Get full text

Diet Engine: A real-time food nutrition assistant system for personalized dietary guidance by Asim Moin Saad, Md. Raihanul Haque Rahi, Md. Manirul Islam, Gulam Rabbani

“…The system employs a client-server architecture, using advanced deep learning techniques like YOLOv8 (You Only Look Once version 8) and Convolutional Neural Networks (CNNs) optimized for real-time object detection with 295 layers, for training and processing image requests. …”
Get full text

Exploring the miscibility challenges of bio-based PLA/PBAT backbones in aluminium feedstock for metal material extrusion (MMEX) by Vahid Momeni, Zahra Shahroodi, Joamin Gonzalez-Gutierrez, Ivica Duretek, Stephan Schuschnigg, Thomas Grießer, Christian Kukla, Clemens Holzer

“…However, solvent debinding tests using cyclohexane showed that parts with higher PBAT content maintained structural integrity, while higher PLA content led to increased crack formation, particularly in the outer layers. …”
Get full text

Applying nanocarbon prepared from coal as an anode in lithium-ion batteries by Huong Do Tra, Van Tu Nguyen, Linh Ha Xuan, Hien Lan Nguyen Thi, Dung Nguyen Quoc, Nhuong Chu Manh, Long Nguyen Khanh, Vuong Truong Xuan, Tran Thi Kim Ngan

“…Carbon materials is a commonly used electrode material because of its low cost, good conductivity, and structure that allows lithium ions to intercalate between layers in the carbon network. In this article, carbon nanomaterials (CP) have been successfully manufactured from Vietnamese coal. …”
Get full text

A method for detecting the rate of tobacco leaf loosening in tobacco leaf sorting scenarios by Yansong Wang, Yansong Wang, Chunjie Zhang, Chunjie Zhang, Mingjie Wu, Mingjie Wu, Ruilin Luo, Lin Lu, Zaiqing Chen, Zaiqing Chen, Lijun Yun, Lijun Yun

“…This was achieved by adding layers for detecting smaller objects and integrating a weighted bi-directional feature pyramid structure to reconstruct the feature fusion network. …”
Get full text