A5065401986- Cell Image Analysis Techniques
- COVID-19 diagnosis using AI
- Brain Tumor Detection and Classification
- Advanced Neural Network Applications
- Autonomous Vehicle Technology and Safety
- Advanced Image Processing Techniques
- EEG and Brain-Computer Interfaces
- Advanced Memory and Neural Computing
- Photoreceptor and optogenetics research
- Hand Gesture Recognition Systems
- CCD and CMOS Imaging Sensors
- Robotics and Automated Systems
- Seismology and Earthquake Studies
- Industrial Vision Systems and Defect Detection
University of Aizu
2020-2022
Hand gestures are a kind of nonverbal communication in which visible bodily actions used to communicate important messages. Recently, hand gesture recognition has received significant attention from the research community for various applications, including advanced driver assistance systems, prosthetic, and robotic control. Therefore, accurate fast classification is required. In this research, we created deep neural network as first step develop real-time camera-only system without...
In this work we propose scaling down the image resolution of an autonomous vehicle and measuring performance difference using pre-determined metrics. We formulated a testing strategy provided suitable metrics for RC driven vehicles. Our goal is to measure prove that will result in faster response time higher speeds. model shows increase rate neural models, improving safety results car having
Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due safety concerns, Applying traffic light recognition one of the factors prevent accidents that occur as result violation. To realize safe system, we propose in this work design optimization detection based on deep neural network. We designed lightweight convolution network with parameters less than 10000 implemented software. achieved 98.3% inference accuracy 2.5 fps...
COVID-19 is still disrupting many parts of the world. A rapid and accurate diagnosis solution needed to combat pandemic. As a part AIRBiS(AI-Enabled Real-time Pneumonia Detection Bio-medical System), this work conduct hardware acceleration speed up diagnosis. We found that more than 90% current time spent on convolution function have conducted three methods operations. Firstly, by applying Winograd algorithm layers, multiplication operations matrices can be decreased, which speeds...
Neuromorphic computing tries to model in hardware the biological brain which is adept at operating a rapid, real-time, parallel, low power, adaptive and fault-tolerant manner within volume of 2 liters. Leveraging event driven nature Spiking Neural Network (SNN), neuromorphic systems have been able demonstrate power consumption by gating sections network not an any point time. However, further exploration this field towards building edge application friendly agents efficient scalable with...