Faculty Profiles - KITA, Eisuke

Papers - KITA, Eisuke

Division display 61 - 80 of about 500 ／ All the affair displays >>

The Application of Sequential Generative Adversarial Networks for Stock Price Prediction Reviewed

Bate He, Eisuke Kita

The Review of Socionetwork Strategies Vol. 15 ( 2 ) page： 455 - 470 2021.12

Successive Future Image Generation of a Walking Pedestrian Using Generative Adversarial Networks Reviewed

He Bate, Kita Eisuke

Vol. 15 ( 2 ) page： 309 - 325 2021.12

Application of Machine Learning for Growth Environment Prediction in Agriculture Invited Reviewed

Momoko Fujita, Akari Yamada, Mao Susuki, Hiroya Makino, Eisuke Kita

2021 IEEE International Conference on Data Minig Workshop (IEEE ICDMW2021) 2021.11

Stochastic Schemata Exploiter-Based Hyper-Parameter Optimization of XGBoost Invited Reviewed

Hiroya Makino, Eisuke Kita

2021 IEEE International Conference on Data Minig Workshop (IEEE ICDMW2021) 2021.11

隊列走行の開発動向 Invited Reviewed

北　栄輔

高速道路と自動車 Vol. 64 ( 11 ) page： 5 - 8 2021.11

Application of Machine Learning for Growth Environment Prediction in Agriculture Invited Reviewed

Momoko Fujita, Akari Yamada, Mao Susuki, Hiroya Makino, Eisuke Kita

2021 IEEE International Conference on Data Minig Workshop (IEEE ICDMW2021) 2021.11

Control Program Design of Autonomous Vehicle Robot using Grammatical Evolution Invited Reviewed

Shuya Yamada, Ryoma Sato, Tatsuhiro Tamaki, Eisuke Kita

6th International Conference on Robotics and Automation Engineering (ICRAE-2021) 2021.11

トマト栽培における飽差推定とその応用 Invited Reviewed

藤田桃子，山田明里，鈴木麻央，北栄輔

日本機械学会第31回設計工学システム部門講演会論文集 2021.9

ベイジアンネットワークによる景気動向予測について

中村典雅, 北田宙士, 北栄輔

日本機械学会第31回設計工学システム部門講演会 2021.9

Genetic Algorithm-based Optimization of Deep Neural Network Ensemble Invited Reviewed

Feng, XN; Zhao, JN; Kita, E

REVIEW OF SOCIONETWORK STRATEGIES Vol. 15 ( 1 ) page： 27 - 47 2021.6

隊列走行車両群と単独車両の合流挙動シミュレーション Reviewed

大野颯汰,山田修也,玉城龍洋,北栄輔

計算工学講演会論文集 2021.5

Genetic Algorithm based Optimization of Deep Neural Network Ensemble for Personal Identification in Pedestrians Behaviors Invited Reviewed

Xuanang Feng, Jianing Zhao, Eisuke Kita

The Review of Socionetwork Strategies Vol. 14 ( 2 ) page： -- 2021.2

Yield and Quality Prediction of Rice Cultivation Using Machine Learning Invited Reviewed

Akari Yamada, Yuichiro Maeda, Eisuke Kita

Proceedings of World Congress on Computational Mechanics 2021.1

Stochastic Schemata Exploiter-Based AutoML Reviewed

Makino, H; Kita, E

21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS ICDMW 2021 Vol. 2021-December page： 238 - 245 2021

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings) Publisher：IEEE International Conference on Data Mining Workshops, ICDMW

Machine Learning (ML) models are often determined by relying on knowledge and experience. In recent years, many automatic building methods are proposed, but there are some problems related to accuracy, computation cost, and explainability. We propose the Stochastic Schemata Exploiter-Based AutoML. The Stochastic Schemata Exploiter (SSE) is one of the Evolutionary Algorithms. In each generation, SSE calculates fitness of the individuals, defines the best subsets according to their average fitness, generates individuals based on the subsets, and applies a mutation operator. Since the original SSE uses a binary string representation, we have to modify the SSE algorithm in the following points for parameter optimization: the initialization method, the schema extraction method, the new individual generation method, the mutation method, and the generation update method. In this paper, we propose a genetic representation of the stacking model and optimize the stacking model using SSE. Compared with the Genetic Algorithm, the Tree-structured Parzen Estimator, the Covariance Matrix Adaptation-Evolution Strategy, and Random Search, SSE shows an interesting feature: a better accuracy for combinatorial optimization problems with categorical, discrete, and continuous variables, such as hyper-parameter optimization. In addition, we propose the visualization of the process of SSE. The visualization helps us to understand the process, which is another advantage of the SSE-based optimization (SSEopt).

DOI： 10.1109/ICDMW53433.2021.00037

Web of Science

Scopus

Control Program Design of Autonomous Vehicle Robot Using Grammatical Evolution Reviewed

Yamada S., Sato R., Tamaki T., Kita E.

2021 6th International Conference on Robotics and Automation Engineering, ICRAE 2021 page： 308 - 312 2021

Authorship：Last author,　Corresponding author Language：English Publishing type：Research paper (international conference proceedings) Publisher：2021 6th International Conference on Robotics and Automation Engineering, ICRAE 2021

The automatic design of the control program of the vehicle robot is presented in this study. LEGO MINDSTORM EV3 and RVW Level Builder are used for this study. The control program of EV3 is designed automatically by using Grammatical Evolution (GE), which is one of the evolutionary algorithms. The generated program is applied for controlling EV3. The results show that the robot behavior in the experiment of EV3 was roughly equivalent to it in simulator. Therefore, the proposed algorithm based on GE can generate the control program of robot automatically.

DOI： 10.1109/ICRAE53653.2021.9657773

Scopus

Application of Machine Learning for Growth Environment Prediction in Agriculture Reviewed

Fujita, M; Yamada, A; Susuki, M; Makino, H; Kita, E

21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS ICDMW 2021 Vol. 2021-December page： 208 - 213 2021

It is very important to control the value of saturation in the adequate range in tomato cultivation in greenhouse. The prediction of the saturation value in greenhouse are discussed in this study. The mathematical model for prediction of saturation is defined by regression analysis of Ridge regression, Lasso regression, Random Forest and XGBoost. The results show that Random Forest and XGBoost has better accuracy than the others and that Random Forest is the best among them. The variable importance analysis shows that the indoor temperature, temperature inside greenhouse, is the most effective for the saturation. The prediction model is applied for controlling the saturation in the adequate range by changing the temperature.

DOI： 10.1109/ICDMW53433.2021.00033

Web of Science

Scopus

隊列走行車両群の分流走行挙動シミュレーション Reviewed

北　栄輔，高上寛斗，玉城龍洋，村井希

日本計算数理工学論文集 Vol. 20 page： 95 - 100 2020.12

Simulation of Vehicles Platoons Passing Through Intersection Reviewed

Eisuke Kita, Shuji Hayashi, Tatsuhiro Tamaki

International Structural Engineering and Construction Emerging Technologies and Sustainability Principles 2020.11

Stock Price Prediction by Using Hybrid Sequential Generative Adversarial Networks Reviewed

Bate He, Eisuke Kita

2020 IEEE International Conference on Data Mining 2020.11

確率推定モデルを用いた株価予測手法について

北栄輔, 中村典雅, 城之内奈

計力スクエア 2020.11

　 PREV - NEXT 　

<KITA, Eisuke>

Papers - KITA, Eisuke