T
Tomohiro Hayashida
Researcher at Hiroshima University
Publications - 103
Citations - 371
Tomohiro Hayashida is an academic researcher from Hiroshima University. The author has contributed to research in topics: Artificial neural network & Network formation. The author has an hindex of 8, co-authored 102 publications receiving 306 citations.
Papers
More filters
Journal ArticleDOI
Electricity retail market model with flexible price settings and elastic price-based demand responses by consumers in distribution network
TL;DR: In this article, a novel electricity retail market model is presented in which elastic demands of consumers in a distribution network are traded at flexible selling prices offered by a retailer, and the main works are in three points: (1) Flexible and divided selling price settings over one day by the retailer, (2) flexible and elastic responses corresponding to the selling prices by different types of consumers, and (3) distribution network physical constraints to obtain the realistic cost of tariff for usage of the distribution network imposed to the retailer are formulated.
Journal ArticleDOI
A hybrid algorithm based on tabu search and ant colony optimization for k-minimum spanning tree problems
TL;DR: An efficient approximate algorithm for solving k-minimum spanning tree problems which is one of the combinatorial optimization in networks and a new hybrid algorithm based on tabu search and ant colony optimization is provided.
Journal ArticleDOI
Decision making of electricity retailer with multiple channels of purchase based on fractile criterion with rational responses of consumers
TL;DR: Computational experiments are demonstrated to demonstrate validity of the proposed decision making framework and some findings revealed by introducing the rational response of the consumer.
Journal ArticleDOI
Multiattribute utility analysis for policy selection and financing for the preservation of the forest
TL;DR: Examining effective policies for financing and activities for the preservation of the forest on Mount Ryuoh in the city of Higashi-Hiroshima by multiattribute utility analysis finds the most effective solution among several alternatives by deriving preference of the decision maker.
Journal ArticleDOI
Multiobjective Evolutionary Optimization of Training and Topology of Recurrent Neural Networks for Time-Series Prediction
TL;DR: A new evolutionary multiobjective optimization method for automatically optimizing the network topology of recurrent neural networks that involves a procedure of intensively exploring a region including solutions with small training errors in the Pareto frontier.