論文 - 高橋 伸弥
-
Extension of ASLA Which Is a Segmentation and Labeling Tool for Application to New Document Formats and Improvement of Label Generation Accuracy
Chihaya Takuma, Nobuya Takahashi, Tetsuro Katayama, Yoshihiro Kita
The 2026 International Conference on Artificial Life and Robotics (ICAROB2026) 303 - 307 2026年2月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Extension to Support Multi-Class Specification in BWDM that Generates Test Cases from VDM++ Specification
Tomohiro Takahashi, Nobuya Takahashi, Tetsuro Katayama, Yoshihiro Kita
The 2026 International Conference on Artificial Life and Robotics (ICAROB2026) 298 - 302 2026年2月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Malware Classification Using Transformer-Based Modeling of API Call Sequences
Ryoga Sakai, Shotaro Usuzaki, Kentaro Aburada, Hisaaki Yamaba, Nobuya Takahashi, Mirang Park, Naonobu Okazaki
Proceedings of the Joint Symposium of Thirty-First International Symposium on Artificial Life and Robotics (AROB 31st 2026) and Eleventh International Symposium on BioComplexity (ISBC 11th 2026) 1254 - 1259 2026年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Investigation of an Authentication Method Using Vibration-Based Secret Cues and a Virtual Dial Interface
Takumi Kido, Shotaro Usuzaki, Kentaro Aburada, Hisaaki Yamaba, Nobuya Takahashi, Mirang Park, Naonobu Okazaki
Proceedings of the Joint Symposium of Thirty-First International Symposium on Artificial Life and Robotics (AROB 31st 2026) and Eleventh International Symposium on BioComplexity (ISBC 11th 2026) 1248 - 1253 2026年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Modified Linear Attentions for Image Classification with Mobile ViT
Masahiro Yokomichi, Nobuya Takahashi
Proceedings of the Joint Symposium of Thirty-First International Symposium on Artificial Life and Robotics (AROB 31st 2026) and Eleventh International Symposium on BioComplexity (ISBC 11th 2026) 1211 - 1215 2026年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
A Closed-Loop Neurofeedback System Based on Four-Channel EEG and an Abstract Avatar for Affective State Regulation
Renta Kokubo, Nobuya Takahashi, Masahiro Yokomichi
Proceedings of the Joint Symposium of Thirty-First International Symposium on Artificial Life and Robotics (AROB 31st 2026) and Eleventh International Symposium on BioComplexity (ISBC 11th 2026) 1207 - 1210 2026年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Multi-Label Classification of Spectrogram Features for Rhythm Game Chart Generation Using Recurrent Neural Networks
Taichi Inoue, Nobuya Takahashi, Masahiro Yokomichi, Shotaro Usuzaki, Kentaro Aburada
Proceedings of the Joint Symposium of Thirty-First International Symposium on Artificial Life and Robotics (AROB 31st 2026) and Eleventh International Symposium on BioComplexity (ISBC 11th 2026) 1220 - 1224 2026年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
MIXVRT: MIX Visual Regression Testing Tool Which Mixes Image Comparison and HTML Code Comparison 査読あり
Aridome Naoki, Takahashi Nobuya, Katayama Tetsuro, Kita Yoshihiro, Yamaba Hisaaki, Aburada Kentaro, Okazaki Naonobu
Journal of Robotics, Networking and Artificial Life 11 ( 3 ) 214 - 219 2026年
記述言語：英語 掲載種別：研究論文（学術雑誌） 出版者・発行元：一般社団法人 ロボット人工生命学会
Image-based visual regression testing has the problem that it takes time required to find layout defects. Therefore, this paper develops MIXVRT (MIX Visual Regression Testing tool), which mixes image comparison and HTML code comparison. It highlights the layout defects. From evaluation experiments, we have confirmed that the time required to find layout defects can be reduced compared to the conventional methods of image-based visual regression testing, while detecting them accurately without omissions or false detections.
-
Implementation of a Tool for Automatic Entry Fields Detection and for Labels Allocation to Generate Electronic Forms 査読あり
Kimura Yuya, Takahashi Nobuya, Katayama Tetsuro, Kita Yoshihiro, Yamaba Hisaaki, Aburada Kentaro, Okazaki Naonobu
Journal of Robotics, Networking and Artificial Life 11 ( 3 ) 220 - 225 2026年
記述言語：英語 掲載種別：研究論文（学術雑誌） 出版者・発行元：一般社団法人 ロボット人工生命学会
An effective approach to manage the content entered in forms is the use of electronic forms. However, if you use a paper form, it takes time to generate electronic forms. This paper has implemented a tool for automatic entry fields detection and for labels allocation to reduce the time required to place entry fields. As a result, we have verified that the implemented tool is useful to reduce the time to place entry fields.
-
Usuzaki Shotaro, Takahashi Nobuya, Kamada Taiki, Aburada Kentaro, Yamaba Hisaaki, Park Mirang, Okazaki Naonobu
IEICE Communications Express 14 ( 12 ) 441 - 444 2025年12月
記述言語：英語 掲載種別：研究論文（学術雑誌） 出版者・発行元：一般社団法人 電子情報通信学会
In this study, we propose a text-based CAPTCHA that utilizes human visual completion to prevent automated programs from getting through, without affecting human cognition. This CAPTCHA requires users to enter the reading of the kanji strings, whose centers are hidden behind a black bar. This method makes it challenging for machines to recognize the characters, while still allowing humans to identify the original text through their visual completion ability. We evaluate both the usability and security of the proposed CAPTCHA. To assess usability, we observed how humans respond to the CAPTCHA challenge. For the security evaluation, we tested the machine’s ability to read the kanji using a Convolutional Neural Network (CNN). The results showed that the proposed CAPTCHA achieves a success rate comparable to traditional CAPTCHAs, with a slightly shorter response time than a similar type of CAPTCHA. Furthermore, security experiments have shown that it exhibits a certain degree of resistance against simple convolutional neural networks.
-
Shotaro Usuzaki, Kosei Iwasa,Nobuya Takahashi, Kentaro Aburada, Hisaaki Yamaba, Mirang Park, Naonobu Okazaki
2025 9th International Conference on Information Technology (InCIT) 543 - 550 2025年12月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス） 出版者・発行元：Proceedings 9th International Conference on Information Technology Incit 2025
In this paper, we discuss a sketch-reconstructionbased In-band Network Telemetry (INT) method that can achieve practical flow count estimation accuracy during sketch collection. Measuring and aggregating per-flow information of network traffic helps to monitor the current network-wide status. Sketch-reconstruction-based INT methods were proposed to efficiently collect flow information measured by each device, which combine sketch techniques and INT. Sketch is a probabilistic algorithm that can estimate the count of entire flows with limited memory, and INT can carry measured data on the network device piggybacked in the business packet header. The combination of sketch and INT can reduce bandwidth consumption for collecting per-flow information, as the sketch can be regarded as a compact aggregation of the per-flow data. To minimize overhead, these methods split a sketch into smaller units called sketchlets and transmit them. The sent sketchlets are reconstructed into a sketch at the collection destination. However, existing methods have the disadvantage that they require a long time to collect sketchlets because they randomly select them, and the accuracy is low during the collection. In this study, we propose a new sketchlet algorithm, called HitFlow Sketchlet, that prioritizes sending buckets necessary for the sketch's query algorithm to function, which each method does not fully consider. We also propose the Flag data structure, aiming at the comprehensive sketchlet transmission. Evaluation experiments showed that HitFlow Sketchlet can output accurate estimates, especially in the earliest epochs, and that by combining it with Flag, comprehensiveness can be improved.
-
Conjugate Gradient Based Multiplicative Update Rules for Nonnegative Matrix Factorization 査読あり
Nobuya Takahashi, Shotaro Usuzaki, Tetsuro Katayama, Masahiro Yokomichi, Kentaro Aburada, Naonobu Okazaki
2025 9th International Conference on Information Technology (InCIT) 637 - 642 2025年12月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス） 出版者・発行元：Proceedings 9th International Conference on Information Technology Incit 2025
In this paper, we propose a general solution for nonnegative matrix factorization (NMF), a technique widely used in the field of machine learning. NMF is a type of matrix factorization used for dimensionality reduction. By approximating a nonnegative matrix as the product of two nonnegative matrices, it is possible to extract frequent patterns in the data matrix into the basis matrix together with their corresponding weights. Since many types of information, such as images, spectrograms of acoustic signals, and text data, are represented by nonnegative values, NMF is a useful algorithm applicable across a wide range of fields. Standard approaches to solving NMF include algorithms based on multiplicative update rules. However, because the applicable algorithm depends on the problem structure, extending NMF to new problem settings can be challenging. Another approach is the gradient method, which is an additive iterative procedure for solving a nonlinear optimization problem. The update direction of the state is given by the gradient of the objective function. The gradient method is versatile. It can be applied to any optimization problem with an available gradient, regardless of the problem structure. However, when applying it to the NMF problem, it is necessary to maintain the nonnegativity of the matrices throughout the iterative computation. As a result, several issues must be addressed, including vanishing gradients, proper tuning of the learning rate, and the need for gradient clipping. In this paper, we propose a new algorithm based on a multiplicative update rule incorporating the gradient. A multiplier function consisting of the hyperbolic tangent function and the linear functions is used. This function ensures that the pair of factor matrices remain nonnegative throughout the entire computation process. As with general gradient methods, the proposed algorithm has the advantage of being widely applicable to NMF problems formulated in a differentiable form. Furthermore, the convergence speed is improved by utilizing the nonlinear conjugate gradient method. Numerical experiments show that the decomposed matrices have a property specified by the penalty terms and confirming the effectiveness of the proposed method.
-
Reinforcement learning and LiDAR-SLAM based obstacle avoidance of drone with depth camera
Ren Shigenaga and Masahiro Yokomichi and Nobuya Takahashi
The Thirtieth International Symposium on Artificial Life and Robotics 2025 (AROB 30th 2025) 1464 - 1467 2025年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Gradient-based Multiplicative Update Rules for Non-negative Matrix Factorization
Nobuya Takahashi and Masahiro Yokomichi
The Thirtieth International Symposium on Artificial Life and Robotics 2025 (AROB 30th 2025) 1460 - 1464 2025年1月
担当区分：筆頭著者 記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
SGLDOMP–Stochastic Gradient Langevin Dynamics Optimization-based Motion Planning
Masahiro Yokomichi and Nobuya Takahashi
The Thirtieth International Symposium on Artificial Life and Robotics 2025 (AROB 30th 2025) 1455 - 1459 2025年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
A Genetic Algorithm-based Approach for Design-level Class Decomposition 査読あり
Priyambadha B., Takahashi N., Katayama T.
International Journal of Advanced Computer Science and Applications 15 ( 4 ) 461 - 468 2024年4月
掲載種別：研究論文（学術雑誌） 出版者・発行元：International Journal of Advanced Computer Science and Applications
Software is always changed to accommodate environmental changes to preserve its existence. While changes happen to the software, the internal structure tends to decline in quality. The refactoring process is worth running to preserve the internal structure of the software. The decomposition process is a suitable refactoring process for Blob smell in class. It tried to split up the class based on the context in order to arrange it based on each responsibility. The previous approach has been implemented but still leaves problems. The optimum arrangement of class cannot be achieved using the previous approach. The genetic algorithm provides the search mechanism to find the optimum state based on the criterion stated at the beginning of the process. This paper presents the use of genetic algorithms to solve the design-level class decomposition problem. The paper explained several points, including the conversion from class to the chromosome construct, the fitness function calculation, selection, crossover, and mutation. The results show that the use of a genetic algorithm was able to solve the previous problems. The genetic algorithm can solve the local optimum problem from the previous approach. The increment of the fitness function of the study case proves it.
-
HMC-PSO : Hamiltonian Monte Carlo-embedded Particle Swarm Optimization
Masahiro Yokomichi, Nobuya Takahashi
The Twenty-Ninth International Symposium on Artificial Life and Robotics 2024 1147 - 1151 2024年1月
記述言語：英語 掲載種別：研究論文（国際会議プロシーディングス）
-
Fundamental study focusing on structural similarity of street based on geographic information using graph neural network
Hiroya Hoshihara, Nobuya Takahashi, Masahiro Yokomichi
The Twenty-Ninth International Symposium on Artificial Life and Robotics 2024 1156 - 1159 2024年1月
担当区分：責任著者 記述言語：英語 掲載種別：研究論文（学術雑誌）
-
UAV flight path planning based on deep reinforcement learning
Masami Hisayama, Nobuya Takahashi, Masahiro Yokomichi
The Twenty-Ninth International Symposium on Artificial Life and Robotics 2024 1152 - 1155 2024年1月
担当区分：責任著者 記述言語：英語 掲載種別：研究論文（学術雑誌）
-
The method for reproducing the haptic feedback of fluid in a virtual space using multiple stimuli
Masahiro Yokomichi, Nobuya Takahashi and Yuki Komatsu
Proceedings of the 28th International Symposium on Artificial Life and Robotics 2023 1173 - 1176 2023年1月
掲載種別：研究論文（国際会議プロシーディングス）