A5101760958- Control Systems and Identification
- Image and Signal Denoising Methods
- Structural Health Monitoring Techniques
- Advanced Computational Techniques and Applications
- Protein Structure and Dynamics
- RNA and protein synthesis mechanisms
- Visual Attention and Saliency Detection
- Advanced Neural Network Applications
- Advanced Algorithms and Applications
- Service-Oriented Architecture and Web Services
- Embedded Systems and FPGA Design
- Blind Source Separation Techniques
- Cognitive Computing and Networks
- Computational Drug Discovery Methods
- Advanced Image and Video Retrieval Techniques
Suzhou University of Science and Technology
2023
PLA Information Engineering University
2020
University of Illinois Urbana-Champaign
2000
Motorola (United States)
2000
Embedded and mobile smart devices face problems related to limited computing power excessive consumption. To address these problems, we propose Mixed YOLOv3-LITE, a lightweight real-time object detection network that can be used with non-graphics processing unit (GPU) devices. Based on YOLO-LITE as the backbone network, YOLOv3-LITE supplements residual block (ResBlocks) parallel high-to-low resolution subnetworks, fully utilizes shallow characteristics while increasing depth, uses "shallow...
An analytical framework is developed that permits the input-output representations of discrete-time linear time-varying (LTV) systems in terms biorthogonal bases on compact time intervals. Using these representations, companion paper, Part II develops computational procedures for rapid identification fast nonsmooth LTV based short data records. One proposed also used H. Zhao and J. Bentsman, “Block Diagram Reduction Interconnected Linear Time-Varying Systems Time Frequency Domain,” accepted...
The present work proposes a new class of algorithms for identification fast linear time-varying systems on short time intervals, based the biorthogonal function decomposition. When certain features system dynamics are known priori, admit their embedding into procedure through choice matching bases, yielding rapidly convergent laws. speed-up is attained via utilizing both and frequency localized permitting fewer coefficients without noticeable loss accuracy. Simulation shows that resulting...
The present work proposes a rigorous general framework and rapidly convergent identification algorithm for high speed of fast linear time-varying systems in short time intervals. speed-up is attained via utilizing both frequency localized bases. This feature permits fewer coefficients without noticeable loss accuracy the results. Under an assumption that inputs outputs plants considered belong to l/sup p/ spaces, where p=2 or p=/spl infin/, their impulse responses are shown Banach spaces....