1. ep2as project
Company: Nicosys Co. Ltd. http://www.nicosys.co.jp/
I worked on this project in 2021.5~2022.5.
This project includes the backend and frontend as the following.
ep2as-api ( Nodejs Nestjs, Postgresql),
ep2as-batch-for-script( Python Fastapi, Postgresql),
ep2as-console (Vue.js),
ep2as-public-api (Express.js),
ep2as-public-front-end( React.js).
and AWS, Docker
My role:
ep2as-api(backend): development, test cases
ep2as-batch-for-script(backend): development, test cases
ep2as-console(frontend): development
ep2as-public-api(backend): development
ep2as-public-front-end(frontend): design and development
Bitbucket pipline development for all packages
https://www.ep2as.com/
https://ep2as.io/
2. Commuting management project
Applink Co. Ltd (Japan)-I worked on this project in 2019.11~2021.4.
(Web, Android, IOS)
This app is a company employee attendance management app.
・ Get location information on whether or not you left home before going to work
・ Get the location information of your place of employment when you go to work
・ Push notifications that tell you the time you go to work
・ Operation in the background after launching the app
・ Request for correction such as stamping
My role:
backend development,
web site development,
Android app development
Web site url: https://e-kant.j-tm.jp/
App: https://play.google.com/store/apps/details?id=com.business.ekant&hl=en
3. Ainst Project
AiNST Co. Ltd. (China), Telephone:-
I worked on this project in 2017.5~2020.4.
About this project
The purpose of this project is to output a comprehensive nutritional diagnosis through the
manufacture of medical devices, analysis of the current characteristics of the human body, and
analysis of the patient's input data.
It integrates the functions of "nutrition screening-assessment-diagnosis-treatment" to provide
comprehensive nutritional diagnosis results and nutritional treatment recommendations for
cancer patients, which can realize standardized nutritional management of patients from
admission to discharge.
Skills: Machine learning , Mathematics, Statistics, Algorithm, Linux, Debian, Raspberry pi, C, C++,
Qt, PCB
My Role:
Database development (HL7),
Algorithm Development
Backend and frontend Development
Linux development
Web site: http://www.ainst.com/
4. Bucket Detection using Deep learning in industrial environment
I developed Bucket’s 4 apex detection project in industrial application.
I can detect many kinds of Buckets in many environments using one application.
I can also classify the bucket kind. Processing time is 100ms on cpu, not gpu.
This task is developed for real-time processing in industrial environment.
5. Electric Accessories Detection and Classify using Deep learning
There are more then 20 kinds of Electric Accessories.
I can detect , count and classify them.
Directional Object detection
Original Object Detection
Especially, I can detect object and predict its’ direction.
Many Original Object detection algorithms only detect object position, cannot detect direction.
But with predict detection, also can predict object’s size.
This task is developed for real-time processing in industry environment.
6. Face Detection with KeyPoint using Deep Learning
Processing time for Face Detection with KeyPoint is 10ms on cpu.
With Face KeyPoint, we can develop many Face-related projects, such as face recognition,
emotion recognition, age prediction and so on.
In such projects, KeyPoint position’s accuracy is very important.
And such projects are running on edge device, so fast running time is very important.
This task is developed for biometric recognition.
Input Image
Detect Face Region
Detect Result
Crop Face Region
Detect Face KeyPoint
7. Car Plate Recognition using Deep Learning
I developed car plate recognition using Deep Learning.
Running time is 100ms/frame on cpu.
In this task, most important is high accuracy and fast real time processing.
I developed light deep learning model and implement fast car plate recognition using deep
learning.
This task is developed for fast car plate recognition in edge device.
8. Fingernail Segmention
Using the segmentation method of deep learning, implement segmentation of fingernail.
After getting segmentation model, transform the model and implement using c++.
9. Soccer Result Prediction Application
Skill: Python, Qt, PySide2, Selenium, Web scraping, Tensorflow, Mathematics,
Stochastics, etc …
This program analyzes the data of all 38 major soccer federations around the world and obtains
information on all current soccer federation matches from the betting site www.pinnacle.com
to predict the results of each match and suggest a betting plan.
Established a data base with rich data including detailed game process analysis data of all 38
major soccer league matches in the world from 2000 to 2022, odds of 10 betting sites, and 34
technical index data of every player who participated in the game I did.
The program is mainly composed of three parts. Soccer match data update, soccer match
analysis, soccer match prediction - Update soccer game data.
The current match season match schedule for every soccer league match and the match data
that have already been played are automatically updated using web crawling. - Soccer match
analysis Match analysis is performed for each soccer league match to obtain the characteristic
values of the corresponding soccer federation match and the characteristic values of the
participating teams in the current match season. ELO rating model, regression analysis model
using Poisson and Weibull distribution, and deep learning models are used as learning models. Soccer match prediction.
We obtain real-time odds data from www.pinnacle.com for every predicted soccer league
match, and combine these values with a learning model to predict the match result of the
match. The match result is obtained as the probability that the home team wins, the probability
of a tie, and the probability that the away team wins, and the betting plan for the match is
presented.
10.Poker Solution Application
Skill: Python, Qt, PySide2, Selenium, Tensorflow, Mathematics, Stochastics, Poker
GTO, Flask, Javascript, etc…
11.Pedometer Project
(Web, Android, IOS)
Skill: Python Django, HTML5, CSS3, PHP, Google Map, Android, IOS, etc…
url: http://dependa.co.jp/
APK: https://play.google.com/store/apps/details?id=com.dependa.pedometer
IOS: https://appagg.com/ios/healthcare/pedo-visor-.html
12.Uber-Style Application Using React-Native
13.Reactjs Front-end Web