| 津﨑 圭祐 | M, 2回目発表 | 環境知能学 | 萩田 紀博, 加藤 博一, 神原 誠之 |
|
title:
Effect Investigation of dialogue motivation by contagious laughter of interaction robot during TV watching
abstract:This research investigates effect of dialogue motivation by contagious laughter of interactive robot during TV watching. Conventional research in psychonomic field has shown that contagious laughter has sufficient stimulus for laughs and smile for others. This study carries out experiments which evaluate psychologic influence of user when the interactive robots give user contagious laughs. This presentation shows experimental environments which the interactive robots give contagious laughs to user during TV watching.
language of the presentation: Japanese | |||
| 池田 裕哉 | M, 1回目発表 | コンピューティング・アーキテクチャ | 中島 康彦 |
|
title: Research and development of neuromorphic system using oxide semiconductor synapse
abstract: A letter reproduction system has been developed by a cellar neunal network and oxide semiconductor synapses and evaluated by logic simulation. A cellular neural network is utilized because it is suitable for large-scale integration of electronic devices, and oxide semiconductor devices are utilized as synapse elements because the characteristic deterioration can be employed as strength plasticity of synaptic connection with modified Hebbian learning. In this article, first, the structure and operation of the letter reproduction system are explained. Next, it is evaluated by logic simulation, where the dependence of the correction accuracy of the letter reproduction on the variation of deterioration rate of the oxide semiconductor synapses is analyzed language of the presentation: Japanese | |||
| STIRAPONGSASUTI SOPICHA | M, 1回目発表 | ユビキタスコンピューティングシステム | 安本 慶一 |
|
title: A Study of BLE-based Mesh Network for Distributed Sensor Processing
abstract: In the next few years Machine Learning (ML) will become an important role of in-network processing in Wireless Sensor Network (WSN). As a system is designed to distribute sensor nodes working stand-alone, energy consumption should be considered. To satisfy our purpose of exploring deep learning over WSN, we developed a first prototype of sensor node. However, the previous node development, which is a low power sensor node composing of Intel a processing part using Intel Edison and Senstick as a sensor node, has been limited to save energy consumption for processing and networking. In order to find a solution for this issue, we proposed a method to accomplish lower energy consumption leveraging BLE based on mesh network. Also, we set up an experiment with a simple mesh network to evaluate performance at different BLE central role duration to support an application on the top of BLE mesh network. language of the presentation: English | |||