A5061215289- Tensor decomposition and applications
- Advanced Neural Network Applications
- Advanced Memory and Neural Computing
- Human Pose and Action Recognition
- Advanced Neuroimaging Techniques and Applications
- Vehicle Dynamics and Control Systems
- Computational Physics and Python Applications
- Ferroelectric and Negative Capacitance Devices
- Neural Networks and Reservoir Computing
- Parallel Computing and Optimization Techniques
- Integrated Energy Systems Optimization
- Neural Networks and Applications
- Energy Load and Power Forecasting
- Sparse and Compressive Sensing Techniques
- Generative Adversarial Networks and Image Synthesis
- Simulation and Modeling Applications
- Neural dynamics and brain function
- Advanced Image and Video Retrieval Techniques
- Domain Adaptation and Few-Shot Learning
- Neuroscience and Neural Engineering
- Mechanical Engineering and Vibrations Research
- Advanced Data Compression Techniques
- Power Systems and Renewable Energy
- Medical Image Segmentation Techniques
- Hydraulic and Pneumatic Systems
Northwest Institute of Mechanical and Electrical Engineering
2022-2024
Xi'an Jiaotong University
2019-2023
How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse non-uniform have μs temporal resolution, is of great value has various real-life applications. Spiking neural network (SNN), as one brain-inspired event-triggered computing models, potential extract effective features from streams. However, when aggregating individual into frames a new higher existing SNN models do not attach importance that serial different signal-to-noise...
Abstract By mimicking the neurons and synapses of human brain employing spiking neural networks on neuromorphic chips, computing offers a promising energy-efficient machine intelligence. How to borrow high-level dynamic mechanisms help achieve energy advantages is fundamental issue. This work presents an application-oriented algorithm-software-hardware co-designed system for this First, we design fabricate asynchronous chip called “Speck”, sensing-computing chip. With low processor resting...
Abstract Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, even general field artificial intelligence. It has great fundamental importance strong industrial needs, particularly modern deep neural networks (DNNs) some brain-inspired methodologies, have largely boosted performance on many concrete tasks, with help large amounts training data new powerful computation resources. Although accuracy usually first concern for...
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition. However, because modern RNNs have complex topologies expensive space/computation complexity, compressing them becomes a hot promising topic recent years. Among plenty of compression methods, tensor decomposition, e.g., train (TT), block term (BT), ring (TR), hierarchical Tucker (HT), appears be most amazing approach very high ratio might obtained....
It is essential and forward-thinking to investigate the personalized use of four-wheel driving steering wire-controlled unmanned chassis. This paper introduces a path-tracking approach designed adapt vehicle’s control system human-like characteristics, enhancing fit maximizing potential chassis’ multi-directional capabilities. By modifying classic vehicle motion controller design, this aligns with individual habits, significantly improving upon traditional methods that rely solely on...
Tensor completion, which recovers missing entries of multiway data, plays an important role in many applications such as image processing, computer vision, machine learning, et al. There into, most the current methods exploit this technology for completion based on tensor train (TT) decomposition, is able to capture hidden information from tensors benefit by its well-balanced multiple matricization scheme. In order seek a highly accurate solution comparing with traditional linear TT...
Abstract The field of trajectory tracking control for ground vehicles has problems such as unknown object manipulation characteristics, missing dynamic digital models, and susceptibility to distortion upper-layer algorithms. This paper first proposes a method identifying the chassis forward/inverse dynamics model based on vehicle-level state variables variable methods solve these issues. Secondly, characteristics fitting are obtained specific electric drive-tracked chassis. Thirdly, linear...
Abstract The increase in the penetration rate of renewable energy such as wind power and photovoltaics has brought challenges to stable dispatch safe operation system. Therefore, based on short-time fast Fourier transform method, this paper constructs a long-short-term memory neural network model, proposes new volatility clustering algorithm for intermittent energy. On basis, open source data set RTS-GMLC published by National Renewable Energy Laboratory (NREL), experimental simulations were...