Hierarchical Self Organizing Map for Novelty Detection using Mobile Robot with Robust Sensor

Autor:	Mnah Sha’abani, Muhammad Fahmi Miskon, H Sakidin
Rok vydání:	2013
Předmět:	Self-organizing map Hierarchical neural network Engineering Orientation (computer vision) business.industry Position (vector) Computer vision Mobile robot Sensitivity (control systems) Artificial intelligence Self organizing map neural network business Novelty detection
Zdroj:	IOP Conference Series: Materials Science and Engineering. 53:012018
ISSN:	1757-899X 1757-8981
DOI:	10.1088/1757-899x/53/1/012018
Popis:	This paper presents a novelty detection method based on Self Organizing Map neural network using a mobile robot. Based on hierarchical neural network, the network is divided into three networks; position, orientation and sensor measurement network. A simulation was done to demonstrate and validate the proposed method using MobileSim. Three cases of abnormal events; new, missing and shifted objects are employed for performance evaluation. The result of detection was then filtered for false positive detection. The result shows that the inspection produced less than 2% false positive detection at high sensitivity settings.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::c0c3f9c21a92282c3f9966dc6563ddfd https://doi.org/10.1088/1757-899x/53/1/012018 Zobrazit plný text záznamu