20201020
FTR: 瀬川
Classification of running shoes from 2D images
There is a demand for investigating which brand’s running shoes is widely accepted. For now it is performed manually.
The aim of this research is to automate the investigation using machine learning
Firstly, I did an examination to find out what makes this classification difficult. In this seminar, I’ll show the result of the examination
Named Entity Recognition with Fine-tuning BERT in Japanese Medical Text
In recent years, the spread of electronic health records has increased the demand for the utilization of large-scale medical data.In my research, I propose a method to perform named entity recognition from medical documents using BERT.
In this seminar, I will explain the progress of my research.
Time Difference Penalized Traffic Signal Timing by LSTM Q-Network to Balance Safety and Capacity at Intersections
The conflict between limited road resources and rapid car ownership makes the traffic signal timing become a pivotal challenge. Emerging studies have been carried out on adaptive signal timing, but most of them still focus on the throughput of intersections, leaving safety and travel experience unconsidered. This paper proposes a time difference penalized traffic signal timing method by reinforcement learning technique to balance safety and throughput capacity in traffic control system
