SearcharxivSearch

arXiv subjects

Hiroki Kumazaki

Publications and source records attributed to Hiroki Kumazaki.

4 recordsLinked to original sources

Security Camera Movie and ERP Data Matching System to Prevent Theft

"(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works." In this paper, we propose a SaaS service which prevents shoplifting using image analysis and ERP. In Japan, total damage of shoplifting reaches 450 billion yen. Based on cloud and data analysis technology, we propose a shoplifting prevention service with image analysis of security camera and ERP data check for small shops. We evaluated movie analysis. Y. Yamato, Y. Fukumoto and H. Kumazaki, "Security Camera Movie and ERP Data Matching System to Prevent Theft," IEEE Consumer Communications and Networking Conference (CCNC 2017), pp.1021-1022, DOI: 10.1109/CCNC.2017.7983275, Jan. 2017.

cs.CY

Proposal of Real Time Predictive Maintenance Platform with 3D Printer for Business Vehicles

This paper proposes a maintenance platform for business vehicles which detects failure sign using IoT data on the move, orders to create repair parts by 3D printers and to deliver them to the destination. Recently, IoT and 3D printer technologies have been progressed and application cases to manufacturing and maintenance have been increased. Especially in air flight industry, various sensing data are collected during flight by IoT technologies and parts are created by 3D printers. And IoT platforms which improve development/operation of IoT applications also have been appeared. However, existing IoT platforms mainly targets to visualize "things" statuses by batch processing of collected sensing data, and 3 factors of real-time, automatic orders of repair parts and parts stock cost are insufficient to accelerate businesses. This paper targets maintenance of business vehicles such as airplane or high-speed bus. We propose a maintenance platform with real-time analysis, automatic orders of repair parts and minimum stock cost of parts. The proposed platform collects data via closed VPN, analyzes stream data and predicts failures in real-time by online machine learning framework Jubatus, coordinates ERP or SCM via in memory DB to order repair parts and also distributes repair parts data to 3D printers to create repair parts near the destination.

cs.DC

Realtime Predictive Maintenance with Lambda Architecture

Recently, IoT technologies have been progressed and applications of maintenance area are expected. However, IoT maintenance applications are not spread in Japan yet because of insufficient analysis of real time situation, high cost to collect sensing data and to configure failure detection rules. In this paper, using lambda architecture concept, we propose a maintenance platform in which edge nodes analyze sensing data, detect anomaly, extract a new detection rule in real time and a cloud orders maintenance automatically, also analyzes whole data collected by batch process in detail, updates learning model of edge nodes to improve analysis accuracy.

cs.DC

Study of shoplifting prevention using image analysis and ERP check

In this paper, we propose a SaaS service which prevents shoplifting using image analysis and ERP. In Japan, total damage of shoplifting reaches 450 billion yen and more than 1000 small shops gave up their businesses because of shoplifting. Based on recent cloud technology and data analysis technology, we propose a shoplifting prevention service with image analysis of security camera and ERP data check for small shops. We evaluated stream analysis of security camera movie using online machine learining framework Jubatus.

cs.DC