MENU

Graduate School of Informatics and Engineering,
The University of Electro-Communications
Japanese

Software

A Trial of University Entrance Examinations Using Item-Bank-Based CBT Including “Informatics I”

Software developed in the Ministry of Education, Culture, Sports, Science and Technology Commissioned Project for University Entrance Examination Reform Promotion (Utilization of CBT in Individual Universities’ Entrance Examinations and Related Selection Processes).

Details (English) |
Details (Japanese)

Installation

Set up a TAO 3.6.0 environment, then install the following four PCI modules from the TAO administration panel.

Next, download and extract the ZIP file below, and replace {TAO_ROOT_DIR}/tao/models/classes/export/implementation/CsvExporter.php in your TAO environment with the extracted CsvExporter.php.

Deep Item Response Theory as a Novel Test Theory Based on Deep Learning

Source code of the proposed method in: Emiko Tsutsumi, Ryo Kinoshita, and Maomi Ueno. Deep Item Response Theory as a Novel Test Theory Based on Deep Learning. Electronics, 2021.

Code (GitHub)

DeepIRT with a Hypernetwork to Optimize the Degree of Forgetting of Past Data

Source code of the proposed method in: Emiko Tsutsumi, Yiming Guo, and Maomi Ueno. DeepIRT with a Hypernetwork to Optimize the Degree of Forgetting of Past Data. In International Conference on Educational Data Mining (EDM), 2022.

Code (GitHub)

Deep-IRT with a Temporal Convolutional Network for Reflecting Students’ Long-Term History of Ability Data

Source code of the proposed method in: Emiko Tsutsumi, Tetsurou Nishio, and Maomi Ueno. Deep-IRT with a Temporal Convolutional Network for Reflecting Students’ Long-Term History of Ability Data. In Artificial Intelligence in Education (AIED), 2024.

Code (GitHub)

OptimalTriangulation

Chao Li and Maomi Ueno:
OptimalTriangulation is a JAVA software package that implements several triangulation algorithms for Bayesian networks, as described in [1, 2, 3]. The software can be reused and redistributed except for commercial purposes.
Detail here

Structure Learning

Source code of the proposed method (the depth-first branch-and-bound algorithm) described in the AAAI paper (Sugahara, Kato, and Ueno, 2024) and the JMLR paper (Sugahara, Kato, Cussens, and Ueno, 2026) is available here: Download link.
The datasets used in these two papers are also available here: Download link.

Source code of the methods compared in an Entropy paper (Sugahara and Ueno ,2021) are available: Download link.
We can easily execute the compared methods using jar files in the zip file.
For more details, please see “ReadMe.txt” in the zip file.
The datasets used in experiments of Sugahara and Ueno (2021) are available: Download link.

Uniform Tests Assembly

Source code of the methods compared in IEEE Transactions on Learning Technologies (Fuchimoto, Ishii, and Ueno 2022) are available: Download link (under review).

JAPANESE