A5030514354- Smart Agriculture and AI
- Remote Sensing and Land Use
- Spectroscopy and Chemometric Analyses
- Inertial Sensor and Navigation
- EEG and Brain-Computer Interfaces
- Target Tracking and Data Fusion in Sensor Networks
- Geophysics and Gravity Measurements
- Robotic Path Planning Algorithms
- Indoor and Outdoor Localization Technologies
- Stroke Rehabilitation and Recovery
- Advanced Algorithms and Applications
- Functional Brain Connectivity Studies
- Muscle activation and electromyography studies
- Tree Root and Stability Studies
- Emotion and Mood Recognition
- Robotics and Sensor-Based Localization
- Advanced Chemical Sensor Technologies
- Leaf Properties and Growth Measurement
- Advanced Measurement and Detection Methods
- Reinforcement Learning in Robotics
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Olfactory and Sensory Function Studies
- Robot Manipulation and Learning
- Visual Attention and Saliency Detection
Changzhou University
2016-2025
Beijing Jiaotong University
2021
Jilin Medical University
2016
Jilin University
2016
Jiangsu University
2010-2012
Shanghai University of Finance and Economics
2012
Shanghai University of Sport
2007
East China University of Political Science and Law
2004
Abstract In order to achieve collision-free path planning in complex environment, Munchausen deep Q-learning network (M-DQN) is applied mobile robot learn the best decision. On basis of Soft-DQN, M-DQN adds scaled log-policy immediate reward. The method allows agent do more exploration. However, algorithm has problem slow convergence. A new and improved (DM-DQN) proposed paper address problem. First, its structure was on by decomposing into a value function an advantage function, thus...
Research on emotion recognition based electroencephalogram (EEG) signals is important for human detection and improvements in mental health. However, the importance of EEG from different brain regions frequency bands different. For this problem, paper proposes Capsule–Transformer method multi-region multi-band recognition. First, features are extracted combined into feature vectors which input fully connected network dimension alignment. Then, inputted Transformer calculating self-attention...
Abstract Fruit images collected by picking robots in natural environments have problems such as uneven lighting, complex backgrounds, occlusion of branches and leaves, overlapping fruits vegetables, which greatly increases the difficulty for to accurately identify target vegetables. Meanwhile, most vegetables similar‐color backgrounds. Compared with ones different colors background, backgrounds are similar their leaves surrounding weeds, identification. Therefore, realizing accurate...
Motor imagery-based brain-computer interfaces (MI-BCIs) hold significant promise for upper limb rehabilitation in stroke patients. However, traditional MI paradigm primarily involves various limbs and fails to effectively address unilateral needs. In addition, compared decoding MI-EEG signals from different limbs, same faces more challenges. We introduced a novel tri-class fine motor imagery (FMI) collected electroencephalogram (EEG) data 20 healthy subjects research. Furthermore, we...
Patients with inflammatory bowel disease (IBD) often suffer from mood disorders and cognitive decline, which has prompted research into abnormalities in emotional brain regions their functional analysis. However, most IBD studies only focus on single-modality neuroimaging technologies. Due to a limited spatiotemporal resolution, it is unfeasible fully explore deep source activities accurately evaluate the connectivity. Therefore, we propose an electroencephalography (EEG)-functional magnetic...
Magnetic and inertial measurement units (MIMUs) are promising tools for attitude tracking of moving bodies without location restriction. An extended Kalman filter (EKF) is a commonly used algorithm MIMUs, its gain usually regulated according to the measurements accelerometer best integrated performance, i.e., performance both when carrier motionless moving. A hidden Markov model (HMM) introduced, then trained using static accelerometer. Once body has movement, match probability between...
<p>Current research confirms abnormalities in resting-state electroencephalogram (EEG) power and functional connectivity (FC) patterns specific brain regions of individuals with depression. To study changes the flow information between cortical patients depression, we used 64-channel EEG to record neural oscillatory activity 68 relevant 22 depressed healthy adolescents using source-space EEG. The direction strength was investigated directional phase transfer entropy (PTE). Compared...
Magnetic and inertial measurement units (MIMU) are currently being explored as a promising tool for attitude tracking of moving object, such human body parts. The function calculation is realized by using algorithms. overall performance these algorithms seriously influenced linear acceleration the object. Therefore, there requirement to find solutions this problem. In paper, new algorithm MIMU known REQUEST introduced. then revised in order be suitable MIMU. A representation object...
The vision system of apple harvesting robot was researched and designed to make it possible for realizing automatic apple. model is studied. by two aspects, including hardware composition soft architecture. VFW method employed realize the real-time image acquisition. recognition developed using combination regional growth algorithm color characteristics. preliminary orientation target calculated finding its centroid. At last, performance this version evaluated. results showed that...