PROJECTS

Securing evacuation shelters is essential to mitigate tsunami damage, but developing new facilities requires significant financial and human resources, leading to a serious shortage of shelters in many municipalities. While utilizing existing buildings is an option, there are tens of thousands of potential candidates, making it impossible to evaluate them all through on-site investigations. We are researching a mechanism that combines online task-based information collection with prioritization algorithms to select evacuation shelters that can cover wide areas at low cost.

The purpose of this project is to (1) maintain the memory and records on experiences of people and communities in Futaba town, Fukushima prefecture, Japan, who suffered the earthquakes, tsunamis, and nuclear plant accidents, and (2) foster the utilization of and research on the archives.

For further Information on Futaba town, See:
https://en.wikipedia.org/wiki/Futaba,_Fukushima

Click here for the Special Project Page

Manga is becoming accessible through electronic books, web posting and sharing sites, SNS, and other various approaches on the Web. Manga on the Web is mostly provided using bitmap images, which are expressed as a set of fine dots for each page or several pages of manga. Therefore, the convenience of searching such manga content on the Web has fallen behind when compared to text or video content.

The purpose of this project is to allow for a high usage of manga content in the digital environment. We are working on the creation and technology development for metadata (i.e. data about data) about content of manga images. In detail, searching of manga content, such as text search and scene search, can be realized using our proposed metadata.

Click here for the Special Project Page

L-Crowd is the project started by active LIS researchers in Japan to apply crowdsourcing technologies to library problems. In the first attempt, we designed microtasks to identify different books that have the same ISBN.

The attempt is significant in several ways. First, the result will be open to public and used for cleaning bibliographic data. Second, the result will be the first to clarify the actual situation of inappropriate usage of ISBNs.

Finally, through the experience, we try to find principles to appropriately design microtasks for library problems.

Click here for the Special Project Page

A purpose of this collaborative project is to transcribe Japanese public domain books in the digital repository of the National Diet Library so that Japanese text data can be processed easily in the digital age. It aims to make them searchable from full-text search engines such as Goole, Baidu, Bing, and so on in the first phase.

Click here for the Special Project Page

Crowdsourcing proved to be an effective solution for help in natural disasters and catastrophes. However, how t\o use the power of the crowd is non-trivial. In this project, we use real data on natural hazards and disasters to develop effective crowdsourcing algorithms for help in natural disasters. Currently, we use data of buildings and houses damaged by Typhoon Wipha in 2013. We designed microtasks to understand how buildings are damaged in the scene and analyze the results to continuously improve the algorithms and microtask designs. The developed algorithms and task design will be used when we encounter future natural disasters and catastrophes.

Click here for the Special Project Page