SciTePress - Affiliation Profile

Research.Publish.Connect.

*Please fill out at least one Field. *Value must be an number!

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

*Please fill out at least one Field.

Name:
Country:
Subject:

Advanced Search Affiliations Search

If you're looking for an exact phrase use quotation marks on text fields.

Proceedings

Proceedings Search *Please fill out at least one Field. *Value must be an number!

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Papers

Papers Search *Please fill out at least one Field.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Authors

Authors Search *Please fill out at least one Field.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Advanced Search

Affiliation

Select a Subject
Refine Ontology Subject

The University of Electro-Communications, Japan

Context (please use complete words only)

Field

Sort by

22 Papers

ASPERA: Exploring Multimodal Action Recognition in Football Through Video, Audio, and Commentary

Topics: Machine Learning; Deep Learning

Authors: Takane Kumakura , Ryohei Orihara , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Graduate School of Informatics and Engineering Departments, Department of Informatics 1-5-1 Chofugaoka, Chofu, Japan

Digital Object Identifier: 10.5220/0013300700003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

This study proposes ASPERA (Action SPotting thrEe-modal Recognition Architecture), a multimodal football action recognition method based on the ASTRA architecture that incorporates video, audio, and commentary text information. ASPERA showed higher accuracy than models using video and audio only, excluding invisible actions in the video. This result demonstrates the advantage of this multimodal approach. Additionally, we propose three advanced models: ASPERAsrnd incorporating surrounding commentary text within a ±20-second range, ASPERAcln removing irrelevant background information, and ASPERAMC applying a Markov head to provide prior knowledge of football action flow. ASPERAsrnd and ASPERAcln, which refine the text embedding, enhanced the ability to accurately identify the timing of actions. Notably, ASPERAMC with the Markov head demonstrated the highest accuracy for invisible actions in the football video. ASPERAsrnd and ASPERAcln not only demonstrate the utility of text information in football action spotting but also highlight key factors that enhance this effect, such as incorporating surrounding commentary text and removing background information. Finally, ASPERAMC shows the effectiveness of combining Transformer models and Markov chains for recognizing actions in invisible scenes.

Efficient Models Deep Reinforcement Learning for NetHack Strategies

Topics: Agent Models and Architectures; Autonomous Systems; Deep Learning

Authors: Yasuhiro Onuki , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Tokyo, Japan

Digital Object Identifier: 10.5220/0013253100003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

Deep reinforcement learning (DRL) has been widely used in agent research across various video games, demonstrating its effectiveness. Recently, there has been increasing interest in DRL research in complex environments such as Roguelike games. These games, while complex, offer fast execution speeds, making them useful as a testbeds for DRL agents. Among them, the game NetHack has gained of research attention. In this study, we aim to train a DRL agent for efficient learning with reduced training costs using the NetHack Learning Environment (NLE). We propose a method that incorporates a variational autoencoder (VAE). Additionally, since the rewards provided by the NLE are sparse, which complicates training, we also trained a DRL agent with additional rewards. As a result, although we expected that using the VAE would allow for more advantageous progress in the game, contrary to our expectations, it proves ineffective. Conversely, we find that the additional rewards are effective.

Fish Catch Prediction by Combining Fishing, Weather and Tidal Data

Topics: Machine Learning; Data Science

Authors: Tomohiro Tanaka , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Chofu, Tokyo, Japan

Digital Object Identifier: 10.5220/0013263200003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

This study presents a model designed to predict days with increased probabilities of fish catches for inexperienced anglers by utilizing weather and tidal data. Specifically, the study pre-processed catch data, together with meteorological and tidal data from the Japan Meteorological Agency, to consider different fish species. The study applied feature engineering techniques, incorporating lag features and moving average features. Comparative evaluations were conducted against a baseline model that neither accounts for fish species nor includes lag and moving average features. The proposed method exhibited superior performance across all evaluation metrics compared to the baseline model. Specifically, the proposed method achieved a Root Mean Squared Error (RMSE) of 4.36 compared to the baseline's 5.47, a Mean Absolute Error (MAE) of 3.02 versus 4.16, an R² score of 0.20 compared to -0.27, a Mean Absolute Percentage Error (MAPE) of 74.6% versus 133.0%, and a Median Absolute Error (Median AE) of 2.04 compared to 3.33. These improvements highlight the effectiveness of the proposed model in enhancing predictive accuracy and reliability.

Proposal of an Automated Testing Method for GraphQL APIs Using Reinforcement Learning

Topics: Machine Learning; Task Planning and Execution

Authors: Kenzaburo Saito , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Japan

Digital Object Identifier: 10.5220/0013263100003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

GraphQL is a new query language for APIs that has a different structure from the commonly used REST API, making it difficult to apply conventional automated testing methods. This necessitates new approaches. This study proposes GQL-QL, an automated testing method for GraphQL APIs using reinforcement learning. The proposed method uses Q-learning to explore the test space. It generates requests by selecting API fields and arguments based on the schema and updates Q-values according to the response. By repeating this process and learning from it, efficient black-box testing is achieved. Experiments were conducted on publicly available APIs to evaluate the effectiveness of the proposed method using schema coverage and error response rate as metrics. The results showed that the proposed method outperformed existing methods on both metrics.

Punish the Pun-ish: Enhancing Text-to-Pun Generation with Synthetic Data from Supervised Fine-tuned Models

Topics: AI and Creativity; Deep Learning

Authors: Tomohito Minami , Ryohei Orihara , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Chofu, Japan

Digital Object Identifier: 10.5220/0013262900003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

Puns are clever wordplays that exploit sound similarities while contrasting different meanings. Such complex puns remain challenging to create, even with today’s advanced large language models. This study focuses on generating Japanese juxtaposed puns while preserving the original meaning of input sentences. We propose a novel approach, applying Direct Preference Optimization (DPO) after supervised fine-tuning (SFT) of a pre-trained language model, utilizing synthetic data generated from the SFT model to refine pun generation. Experimental results indicate that our approach yields a marked improvement, evaluated using neural network-based and rule-based metrics designed to measure pun-ness, with a 2.3-point increase and a 7.9-point increase, respectively, over the baseline SFT model. These findings suggest that integrating SFT with DPO enhances the model’s ability to capture phonetic nuances essential for generating juxtaposed puns.

Using LLM-Based Deep Reinforcement Learning Agents to Detect Bugs in Web Applications

Topics: Neural Networks; Machine Learning; State Space Search; Industrial Applications of AI; Deep Learning

Authors: Yuki Sakai , Yasuyuki Tahara , Akihiko Ohsuga and Yuichi Sei

Affiliation: The University of Electro-Communications, Japan

Digital Object Identifier: 10.5220/0013248800003890

Proceedings of ICAART 2025, ISBN: 978-989-758-737-5

Quick Abstract

This paper presents an approach to automate black-box GUI testing for web applications by integrating deep reinforcement learning (DRL) with large language models (LLMs). Traditional GUI testing is often inefficient and costly due to the difficulty in generating comprehensive test scenarios. While DRL has shown potential in automating exploratory testing by leveraging GUI interaction data, such data is browser-dependent and not always accessible in web applications. To address this challenge, we propose using LLMs to infer interaction information directly from HTML code, incorporating these inferences into the DRL’s state representation. We hypothesize that combining the inferential capabilities of LLMs with the robustness of DRL can match the accuracy of methods relying on direct data collection. Through experiments, we demonstrate that LLM-inferred interaction information effectively substitutes for direct data, enhancing both the efficiency and accuracy of automated GUI testing. Our results indicate that this approach not only streamlines GUI testing for web applications but also has broader implications for domains where direct state information is hard to obtain. The study suggests that integrating LLMs with DRL offers a promising path toward more efficient and scalable automation in GUI testing.

An Analysis of Knowledge Representation for Anime Recommendation Using Graph Neural Networks

Topics: Neural Networks; Machine Learning; Knowledge Representation and Reasoning; Data Mining; Data Science

Authors: Yuki Saito ¹ , Shusaku Egami ^{1

;

2} , Yuichi Sei ¹ , Yasuyuki Tahara ¹ and Akihiko Ohsuga ¹

Affiliations: ¹ Department of Informatics, University of Electro-Communications 1–5–1 Chofugaoka, Chofu, Tokyo, 182–8585, Japan , ² National Institute of Advanced Industrial Science and Technology (AIST), 2–4–7 Aomi, Koto-ku, Tokyo, 135–0064, Japan

Digital Object Identifier: 10.5220/0012359500003636

Proceedings of ICAART 2024, ISBN: 978-989-758-680-4

Quick Abstract

In recent years, entertainment content, such as movies, music, and anime, has been gaining attention due to the stay-at-home demand caused by the expansion of COVID-19. In the content domain, research in the field of knowledge representation is primarily concerned with accurately describing metadata. Therefore, different knowledge representations are required for applications in downstream tasks. In this study, we aim to clarify effective knowledge representation through a case study of recommending anime works. Thus, we hypothesized how to represent anime works knowledge to improve recommendation performance from both quantitative and qualitative aspects and verified the hypotheses by changing the knowledge representation structure according to the hypothesis. Initially, we collected data about anime works from multiple data sources and integrated them to construct a knowledge graph (KG). We also prepared several KGs by varying the knowledge configuration. Subsequently, we compared the recommendation performance of each KG as an input to the graph neural networks. As a result, it was found that the amount of semantic relationships was proportional to the recommendation performance and that the properties that can characterize the work contributed to the recommendation.

Proposal of a Cosmetic Product Recommendation Method with Review Text that is Predicted to Be Write by Users

Topics: Natural Language Processing; Data Mining; Deep Learning

Authors: Natsumi Baba , Yuichi Sei , Yasuyuki Tahara and Akihiko Ohsuga

Affiliation: The University of Electro-Communications, Tokyo, Japan

Digital Object Identifier: 10.5220/0012377500003636

Proceedings of ICAART 2024, ISBN: 978-989-758-680-4

Quick Abstract

There are a variety of product introduction sites on the Internet, and many of these usually provide a combination of product composition information and user review text. It is difficult to understand the features of a product in detail from the information on these sites. Furthermore, these review sites often include product recommendations such as "recommended for you," but often lack an explanation of why the product is recommended. Therefore, this study proposes an approach that provides both the user’s opinion of the product and the reason for recommending the product in a simplified manner. Using cosmetics as a case study, where the user’s actual experience is important, we scored product features on a 5-point scale based on review submitted by users. This data was used for collaborative filtering to determine product recommendations and generate review sentences that target users are expected to write when using the product. The generated reviews facilitate users to understand the details of a product before purchasing it and are useful for comparison before purchasing a product. To verify the usefulness of the proposed method, we conducted a questionnaire comparing it with existing methods. The proposed method aims to improve user satisfaction in product recommendations.

A k-Anonymization Method for Social Network Data with Link Prediction

Topics: Privacy Enhancing Technologies; Privacy, Security and Trust in Social Media; Security and Privacy Metrics; Privacy and Security Models

Authors: Risa Sugai , Yuichi Sei , Yasuyuki Tahara and Akihiko Ohsuga

Affiliation: Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan

Digital Object Identifier: 10.5220/0011676800003405

Proceedings of ICISSP 2023, ISBN: 978-989-758-624-8

Quick Abstract

Recently, social networking services have come to pervade every aspect of our lives, increasing the demand for the utilization of social network data. However, since the utilization of social network data has the risk of personal identification, k-anonymization methods have been proposed to protect privacy as a solution. In addition, the actual data contains missing values, which may reduce the utility of the data by applying conventional methods. In this paper, we propose a method for k-anonymization of social network data with link prediction, with the aim of improving the utility of anonymized data. Based on evaluation experiments on real data, we examine the utility of anonymized data.

Background Image Editing with HyperStyle and Semantic Segmentation

Topics: Neural Networks; Vision and Perception; AI and Creativity; Deep Learning

Authors: Syuusuke Ishihata , Ryohei Orihara , Yuichi Sei , Yasuyuki Tahara and Akihiko Ohsuga

Affiliation: The University of Electro-Communications, Tokyo, Japan

Digital Object Identifier: 10.5220/0011661500003393

Proceedings of ICAART 2023, ISBN: 978-989-758-623-1

Quick Abstract

Recently, research has been conducted on applying StyleGAN to image editing tasks. Although the technique can be applied to editing background images, because they are more diverse than foreground images such as face images, specifying an object in background images to be edited is difficult. For example, because natural language instructions can be ambiguous, edited images become undesirable for the user. It is challenging to resolve style and content dependencies in image editing. In our study, we propose an editing method that adapts Style Transformer, the latest GAN inversion encoder approach, to HyperStyle by introducing semantic segmentation to maintain the reconstruction quality and separate the style and the content of the background image. The content is edited while keeping the original style by manipulating the coarse part of latent variables and the residual parameters obtained by HyperStyle, and the style is edited without changing the content by manipulating the medium and fine part of latent vectors as in the conventional StyleGAN. As a result, the qualitative evaluation confirms that our model enabled the editing of image content and style separately, and the quantitative evaluation validates that the reconstruction quality is comparable to the conventional method.