A5008714566- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Neural dynamics and brain function
- Logic, Reasoning, and Knowledge
- Embedded Systems and FPGA Design
- Motor Control and Adaptation
- Phonetics and Phonology Research
- Speech and dialogue systems
- Multi-Agent Systems and Negotiation
- ECG Monitoring and Analysis
- IoT-based Smart Home Systems
- Gaze Tracking and Assistive Technology
- Transportation and Mobility Innovations
- Electric and Hybrid Vehicle Technologies
- Advanced Memory and Neural Computing
- Blind Source Separation Techniques
- Wireless Sensor Networks and IoT
- Speech Recognition and Synthesis
- Electric Vehicles and Infrastructure
- Semantic Web and Ontologies
- Infrared Target Detection Methodologies
Zhejiang University
2004-2024
Human-Computer Interface (HCI) has become an important area of research and development for the disabled. A portable wireless eye movement-controlled which can be used disabled who have motor paralysis cannot speak in multiple applications (such as communication aid smart home applications) is described here. This consists four major parts: (1) surface electrodes, (2) a two-channel amplifier, (3) laptop (or micro-processor), (4) ZigBee module. Horizontal vertical Electro-Oculography (EOG)...
This technical report presents the 1st winning model for UG2+, a task in CVPR 2024 UAV Tracking and Pose-Estimation Challenge. challenge faces difficulties drone detection, UAV-type classification 2D/3D trajectory estimation extreme weather conditions with multi-modal sensor information, including stereo vision, various Lidars, Radars, audio arrays. Leveraging this we propose classification, 3D tracking method accurate tracking. A novel pipeline which incorporates sequence fusion, region of...
Real-time computation, portability and flexibility are crucial for practical brain-machine interface (BMI) applications. In this work, we proposed Hardware Processing Modules (HPMs) as a method accelerating BMI computation. Two HPMs have been developed. One is the field-programmable gate array (FPGA) implementation of spike sorting based on probabilistic neural network (PNN), other FPGA ensemble decoding Kalman filter (KF). These two modules were configured under same framework tested with...
In this paper, a control model is developed to automate the process of navigation in rat-robot-a new type bio-robot based on BCI (Brain-Computer Interface) technique. Because particular difficulties rat-robot control, we design novel `learn' and `imitate' behavior human guidance. General Regression Neural Network (GRNN) used analyze commands made by operators, with locomotion information recorded analyzed video-based experimental system. The results shows that could be well understood...
In this paper, radial basis function (RBF) network is applied to achieve the discrimination of ratpsilas behavior by encoding and decoding motor cortical activity. Firstly, brain neuronal action potentials during extending flexing behaviors ratspsila forearms are recorded. Secondly, classified based on principal component analysis (PCA) K-means cluster methods. Thirdly, firing frequency each neuron calculated. Lastly, ensembles model characterized RBF. We use as input RBF network, will give...
A brain computer interface (BCI) builds an additional pathway between the and external devices. This paper introduces a BCI system combined with virtual reality (VR) technology that allows users to navigate in apartment by motor imagery. Since performance online sessions is sometimes found decrease due non-stationarity of electroencephalogram (EEG) signals, we proposed method based on adaptive probabilistic neural network (APNN) overcome this phenomenon. Online experiments were carried out...
According to new specifications of Knowledge Query and Manipulation Language (KQML) special requirements brought with real application domains, a serial KQML realization algorithms according for agent communication are proposed, relative comprehensive translator is developed, it used in the "intelligent fusion system intercept information" successfully.
Traditional automatic navigation methods for bio-robots are constrained to configured environments and thus can't be applied tasks in unknown environments. With no consideration of bio-robot's own innate living ability treating the same way as mechanical robots, those neglect intelligence behavior animals. This paper proposes a novel ratbot method using only reward stimulation distance measurement. By utilizing rat's habit thigmotaxis its reward-seeking behavior, this is able incorporate...
Although EEG classification for schizophrenia has shown promising results on individual datasets, the cross-dataset generalizability of such remains unknown. This study aimed to assess this through transfer learning at segment and levels, by employing spectral convolutional neural network (CNN-S) two distinct datasets classification. While direct cross-decoding only obtained baseline accuracies 54.72% ± 2.77% 47.78% 3.62% fine-tuned CNN-S achieved average 76.46% 1.17% 56.71% 5.76,...
Abstract Reaching to grasp movement is thought rely upon two independent brain pathways. The dorsomedial one involved in reaching while the dorsolateral dealing with grasping. However, some recent evidences suggested that pathway might participate movement. Therefore, it important investigate whether PMd planning, and if participating, what kind of role played planning. In this study, macaques monkeys were trained same object by instructing or freely choosing grips, power grip hook grip. A...