A5100603319- Anomaly Detection Techniques and Applications
- Video Analysis and Summarization
- Multimodal Machine Learning Applications
- Opportunistic and Delay-Tolerant Networks
- Data Mining Algorithms and Applications
- Mobile Ad Hoc Networks
- Advanced Image and Video Retrieval Techniques
- Digital Storytelling and Education
- Video Surveillance and Tracking Methods
- Advanced Clustering Algorithms Research
- Network Security and Intrusion Detection
- Caching and Content Delivery
- Domain Adaptation and Few-Shot Learning
- Risk and Safety Analysis
- Retinal Imaging and Analysis
- Data Management and Algorithms
- Brain Tumor Detection and Classification
- Collaboration in agile enterprises
- COVID-19 diagnosis using AI
- Time Series Analysis and Forecasting
- Bayesian Modeling and Causal Inference
- Medical Image Segmentation Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Neural Network Applications
- Green IT and Sustainability
Northwestern Polytechnical University
2025
Zhengzhou University
2025
China Agricultural University
2018-2024
Shanxi Agricultural University
2024
Nanjing Normal University
2024
Macau University of Science and Technology
2024
Emily Griffith Technical College
2023
Zhejiang University
2023
Southeast University
2023
University of Science and Technology
2022
Map symbols play a crucial role in cartographic representation. Among these symbols, icons are particularly valued for their vivid and intuitive designs, making them widely utilized tourist maps. However, the diversity complexity of present significant challenges to workflows. Icon design often relies on manual drawing, which is not only time-consuming but also heavily dependent specialized skills. Automating extraction from existing maps could greatly enhance map symbol database, offering...
Traffic light detection technology can assist drivers in making decisions and has potential applications autonomous driving to reduce loss of life property. However, the traffic objects is challenging due light’s small size complex backgrounds, it difficult for current meet real-time high accuracy requirements. In this work, we identify that inappropriate feature integration static parameters during detector training limit model efficiency. Specifically, using same criteria all object sizes...
Despite the utility of gaze gestures as an input method, there is a lack guidelines available regarding how to design gestures, what algorithms use for gesture recognition, and these compare in terms performance. To facilitate development applications that leverage we have evaluated performance combination template-based data-driven on two custom sets can map user actions. Template-based had consistently high accuracies but slowest runtimes, making them best small or accuracy-critical...
Accessing multiple carrier networks (T-Mobile, Sprint, AT&T, and so on) offers a promising paradigm for smartphones to boost its mobile network quality. However, the current practice does not achieve full potential of this approach because it has utilized fine-grained, cellular-specific domain knowledge. Our experiments code analysis discover three implementation-independent issues: 1) may trigger anticipated switch when serving is poor; 2) takes much longer time than needed; 3) device fails...
Abstract This paper presents a secure communication application called DiscoverFriends. Its purpose is to securely communicate group of online friends while bypassing their respective social networking servers under mobile ad hoc network environment. DiscoverFriends leverages Bloom filters and hybrid encryption technique with self‐organized public‐key management scheme identify provide authentication. Additionally, enables anonymous location check‐ins by utilizing new cryptographic primitive...
The assessment of muscle activity and contraction is significant in biomechanical research clinical applications. Such information commonly measured characterized by electromyography, ultrasound imaging, laser Doppler. In this paper, we propose a new method Video Myography (VMG) that can be used to obtain information. proposed VMG produces two results measure contraction: the Myogram (VMM) strength contraction, Muscle Activity Vector-Field (MAV-F) describe two-dimensional displacement field...
With the continuous improvement of broiler production performance, frequent occurrence leg problems has caused serious economic losses in many factories. In order to more efficiently detect and prevent diseases, we propose an auxiliary detection system for diseases based on deep learning. The is divided into two parts. First, a digital radiography (DR) image taken through industrial computed tomography (CT), then improved deep-learning network Tibia-YOLO used tibia; detected results are...