Tadaaki Kirishima

dblp:87/6131 · DBLP profile ↗
← Back
6ranked-venue papers
1as first author
3since 2021 · last 2023
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Software engineering, systems software and programming languages · 5 · 1 first-author · 3 since 2021Artificial intelligence and machine learning · 2 · 1 first-authorSystems, architecture and hardware · 1
YearPublicationVenuePosition
2023 Novel Music Genre Classification System Using Transfer Learning on a Small Dataset
abstract
Music is an essential "element" in our lives. With the rapid development of technology, the use of compact disks and tapes for listening various forms of music of different cultures has become obsolete. Because of the generation of considerable music data, the accurate classification of music data has become a critical topic of research, and the development of deep learning technology provides a solution for music classification. Transfer learning techniques are widely used in image recognition but are rarely used for music classification. In this study, a small music dataset is used for music classification using transfer learning.
Takaaki Goto, Tadaaki Kirishima, Kensei Tsuchida
SERA3
2023 Detection of a Novel Object-Detection-Based Cheat Tool for First-Person Shooter Games Using Machine Learning
abstract
Detection of novel game cheating tools is critical for ensuring fair online play. Such cheating tools are visual-based and effectively avoid detection because they do not change the data of game software. With the development and popularity of artificial intelligence technology, it has become easier for individuals to develop cheating tools, such as a new cheating tool for first-person shooter games that searches for characters on the game screen and automatically targets them. Therefore, in this study, a new cheat detection method is proposed using machine learning. The proposed method can be used to detect new cheating tools based on object detection.
Zhang Xiao, Takaaki Goto, Partha Ghosh, Tadaaki Kirishima, Kensei Tsuchida
SERA4
2023 Improve Accuracy of PC Skill Assessment Using PC Operation Log Data
abstract
Information and communication technologies have spread rapidly, and as a result, people's attention to computer skills has reached a level as never before. However, most conventional skill assessment tools are often multiple-choice types and ask only for PC knowledge but not PC skills. Meanwhile, skill assessment using eye tracking has already been realized in the medical field and has been proven to be a reliable tool for skill assessment and may apply to other fields. Therefore, unlike the knowledge-questioning type PC skill assessment, this study is to propose a method to measure an operator's real skill level using PC operation log data. In this study, we use the operator's PC operation logs to generate heatmaps and operation features and compare these data with standard data generated by the KML model in order to assess the operator's pc skills.
Takaaki Goto, Tadaaki Kirishima, Kensei Tsuchida
SERA3
2016 A graph grammar for entity relationship diagrams
abstract
Databases are mainly used in many systems in order to store data. Databases in large scale systems are difficult to grasp their logical structure, therefore, visualizing databases are quite important. To the present entity relationship diagrams (ER diagrams) have been proposed and used in designing and managing databases. However there are not so many tools which are based on formal mechanisms. In this paper, we propose a graph grammar for entity relationship diagrams which are based on formal mechanisms by using graph grammars. We also describe an application of the grammar.
Toshihiro Yoshizumi, Tadaaki Kirishima, Takaaki Goto, Kensei Tsuchida, Takeo Yaku
INDIN2
2013 Optimality and Complexity for Drawing Problems of Tree-Structured Diagrams
abstract
We investigated sets of conditions with respect to narrower drawing of tree-structured diagrams on an integral lattice. We found that under certain sets of conditions there are practical procedural algorithms for narrower drawing of tree-structured diagrams, while under other sets of conditions there are none. Based on our findings, we presented efficient algorithms that provide narrower placement satisfying given amorphous conditions. In this paper we review our these previous results regarding with sets of constraints for tidily drawing TSDs, efficient algorithms which produce minimum width drawings of TSDs while satisfying certain constraints and NP-completeness of drawing problems of TSDs. Then we discuss the relation among constraints and the optimality with respect to the widths of drawing TSDs. Finally we indicate a key constraint which is not only for obtaining the optimality but also for the practical uses.
Kensei Tsuchida, Tadaaki Kirishima, Yasunori Shiono, Futoshi Sugimoto, Chieko Kato, Takeo Yaku
SNPD2
2012 O(n) and O(n2) Time Algorithms for Drawing Problems of Tree-Structured Diagrams
abstract
We investigate sets of conditions with respect to narrower drawing of tree-structured diagrams on an integral lattice. We found that under certain sets of conditions there are practical procedural algorithms for narrower drawing of tree-structured diagrams, while under other sets of conditions there are none. Based on our findings, we present efficient algorithms that provide narrower placement satisfying given amorphous conditions. In intractable conditions, we propose a constraint-based algorithm for drawing tree-structured diagrams with a minimum-width by limiting the number of cells. Our results provide a criterion for deciding under given conditions, whether to use procedural or constraint-based algorithms to draw a tree-structured diagram.
Tadaaki Kirishima, Tomoo Sumida, Yasunori Shiono, Takaaki Goto, Takeo Yaku, Tetsuro Nishino, Kensei Tsuchida
SNPD1