In recent years, many models for human skeletal structure estimation (pose estimation) from video using deep learning techniques have been proposed and applied to various domains. On the other hand, pose estimation models only provide information on the coordinates of human joints estimated from video images, and from the standpoint of analysts in the fields of physical therapy and sports management, there are problems that make it difficult to process data for visualization and exploratory data analysis unless there are experts in data processing. In this study, we focus on this point and develop a simple visualization tool for human skeletal structure from video images using deep learning technology in R, aiming to break down the barriers between the two fields.

View full abstract

  Weather data is essential for various fields, including meteorology, epidemiology, ecology, and engineering. International organizations such as the World Meteorological Organization, together with national agencies, collect and preserve this data. In Japan, the Japan Meteorological Agency (JMA) is a primary source. The JMA website allows users to view and download historical weather data; however, the absence of a dedicated API complicates data access.
  To address this issue, the `jmastats' package for R was developed. This package provides an interface to easily access historical weather data and features local caching to reduce website traffic. The jmastats package is the only R package specifically designed for the Japanese context.

View full abstract

  Coronavirus disease 2019 (COVID-19) continues to spread globally, necessitating rapid and accurate information on new infections. To address this, we developed a choropleth map to monitor newly infected individuals in Kanagawa, Tokyo, Kumamoto, Hokkaido, and Shizuoka prefectures. Our visualization system, accessible through the ``Real-time Local Information Provider" website (http : //covid-map.bmi-tokai.jp/), updates in real-time and enables users to intuitively track changes in infection rates. In addition to the choropleth map, the website includes visualizations of trending words and topics derived from tweets containing ”コロナ" (corona) and an analysis of excess deaths in each municipality within Kanagawa Prefecture. This paper introduces the website's visualization system and discusses the changes made during its two years of operation. The system was created using the statistical software R, and the web services are also implemented using R.

View full abstract