Earthquakes pose significant risks to infrastructure and supply chains, making the timely and fair distribution of emergency relief materials crucial for reducing casualties and economic losses. This study addresses the challenge of optimizing emergency material dispatch under scenarios where distribution centers fail due to earthquake damage, with the aim of improving both the timeliness and fairness of resource allocation during post-disaster recovery. A multi-objective optimization model is developed, which integrates distribution center failures and the activation of backup centers. The model minimizes total dispatch time, maximizes fairness in supply distribution, and reduces unmet dema... More >

To address key challenges in post-harvest fruit grading—namely the difficulty of distinguishing visually similar varieties, the invisibility of internal quality, and mechanical damage during grasping—this study develops an intelligent robotic grading system that integrates advanced computer vision, Near-Infrared (NIR) spectroscopy, and flexible force-controlled grasping. First, an improved object detection algorithm, YOLOv11-TFE, is proposed to mitigate visual confusion between Qixia Fuji apples and Beijing Pinggu peaches and to handle the irregular geometry of Nanshui pears. By embedding the parameter-free SimAM attention mechanism into the backbone to explicitly enhance and decouple su... More >

Accurate traffic flow prediction is a crucial step in building an intelligent transportation system, and it is of great significance for alleviating urban traffic congestion and optimizing travel routes. Due to the complex spatial topology of the transportation network and the highly nonlinear temporal dynamic characteristics of the flow data, traditional prediction methods are difficult to fully capture the inherent spatio-temporal dependencies. Therefore, this paper proposes a traffic flow prediction model based on variant hybrid multi-hop graph convolution. Firstly, by introducing a multi-hop graph convolution operator, the model explicitly aggregates the spatial information of multiple-o... More >

This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches that empirically combine textual and numerical data without a formal understanding of their interaction mechanisms. We conceptualize a prompt-based LLM as a mathematically defined signal generator, capable of extracting directional market sentiment and an associated confidence score from financial news. These signals are then dynamically fused with structured historical price features through a noise-robust gating mechanism, enabling the Transformer to adapt... More >

Fatigue driving is widely recognized as one of the major factors contributing to traffic accidents, posing not only a serious threat to road safety but also potential risks to drivers’ health and public security. With the rapid development of modern transportation, how to efficiently and accurately detect and warn against driver fatigue has become a critical issue in the field of intelligent transportation. To effectively address this issue, this paper proposes a novel fatigue driving detection method based on a Multi-Head Transformer with Adaptive Weighted Loss. In the proposed framework, the YOLOv8 model is first employed to efficiently and accurately locate key facial regions of the dri... More >

Road safety has become an increasingly important concern and the integration of Advanced Rider Assistance Systems and Advanced Driver Assistance Systems plays a crucial role in preventing accidents. This work proposes a computer vision pipeline to automatically detect hazardous road anomalies—loose gravel, potholes, and puddles—from a motorcycle-mounted camera, targeting real-time operation on embedded edge devices. A hybrid dataset of 28764 annotated images was created by combining real-world photos, Blender-rendered synthetic scenes, and AI-generated images to improve diversity and coverage. Multiple state-of-the-art object detectors were trained and benchmarked, including the YOLOv5/7... More >

Defocus blur detection is essential for computational photography applications, but existing methods struggle with accurate blur localization and boundary preservation. We propose SemanticBlur, a deep learning framework which integrates semantic understanding with attention mechanisms for robust defocus blur detection. Our semantic-aware attention module combines channel attention, spatial attention, and semantic enhancement to leverage high-level features for low-level feature refinement. The architecture employs a modified ResNet-50 backbone with dilated convolutions that preserves spatial resolution while expanding receptive fields, coupled with a feature pyramid decoder using learnable f... More >

To address the challenge of traditional models in simultaneously capturing local fluctuations and global trends for air pollutant concentration prediction, this paper proposes a multimodal deep learning model named MLP-BiLSTM- MHAT. The model integrates static features via MLP, extracts temporal dependencies through bidirectional LSTM (BiLSTM), and employs a Multi-head Attention mechanism (MHAT) to fuse local and global features while enhancing interactions between static and temporal characteristics. An improved Adam algorithm dynamically optimizes learning rates to balance the influence of heterogenous features. Validated on multi-site air quality data from Beijing, experimental results de... More >