Hardware simulation of pattern matching and reinforcement learning to predict the user next action of smart home device usage

Mohd Marufuzzaman, Md. Mamun Ibne Reaz

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Future Smart-Home device usage prediction is a very important module in artificial intelligence. The technique involves analyzing the user performed actions history and apply mathematical methods to predict the most feasible next user action. Unfortunately most of the techniques tend to ignore the adaptation to the user preferred actions and the relation between the actions and the state of the environment which is not practical for Smart-Home systems. This paper present a new algorithm of user action prediction based on pattern matching and techniques of reinforcement learning. The algorithm is modeled using hardware description language VHDL. Synthetic data had been used to test the algorithm and the result shows that the accuracy of the proposed algorithm is 87%, which is better than ONSI, SHIP and IPAM algorithms from other researchers. Thus the algorithm performs realistically better than the current available techniques.

Original languageEnglish
Pages (from-to)1302-1309
Number of pages8
JournalWorld Applied Sciences Journal
Volume22
Issue number9
DOIs
Publication statusPublished - 2013

Fingerprint

Pattern matching
Reinforcement learning
Hardware
Computer hardware description languages
Artificial intelligence

Keywords

  • Action prediction
  • Multi-agent system
  • Reinforcement learning
  • Smart home

ASJC Scopus subject areas

  • General

Cite this

@article{5e77e5829861460c8c61be6f6c285f5a,
title = "Hardware simulation of pattern matching and reinforcement learning to predict the user next action of smart home device usage",
abstract = "Future Smart-Home device usage prediction is a very important module in artificial intelligence. The technique involves analyzing the user performed actions history and apply mathematical methods to predict the most feasible next user action. Unfortunately most of the techniques tend to ignore the adaptation to the user preferred actions and the relation between the actions and the state of the environment which is not practical for Smart-Home systems. This paper present a new algorithm of user action prediction based on pattern matching and techniques of reinforcement learning. The algorithm is modeled using hardware description language VHDL. Synthetic data had been used to test the algorithm and the result shows that the accuracy of the proposed algorithm is 87{\%}, which is better than ONSI, SHIP and IPAM algorithms from other researchers. Thus the algorithm performs realistically better than the current available techniques.",
keywords = "Action prediction, Multi-agent system, Reinforcement learning, Smart home",
author = "Mohd Marufuzzaman and {Ibne Reaz}, {Md. Mamun}",
year = "2013",
doi = "10.5829/idosi.wasj.2013.22.09.188",
language = "English",
volume = "22",
pages = "1302--1309",
journal = "World Applied Sciences Journal",
issn = "1818-4952",
publisher = "International Digital Organization for Scientific Information",
number = "9",

}

TY - JOUR

T1 - Hardware simulation of pattern matching and reinforcement learning to predict the user next action of smart home device usage

AU - Marufuzzaman, Mohd

AU - Ibne Reaz, Md. Mamun

PY - 2013

Y1 - 2013

N2 - Future Smart-Home device usage prediction is a very important module in artificial intelligence. The technique involves analyzing the user performed actions history and apply mathematical methods to predict the most feasible next user action. Unfortunately most of the techniques tend to ignore the adaptation to the user preferred actions and the relation between the actions and the state of the environment which is not practical for Smart-Home systems. This paper present a new algorithm of user action prediction based on pattern matching and techniques of reinforcement learning. The algorithm is modeled using hardware description language VHDL. Synthetic data had been used to test the algorithm and the result shows that the accuracy of the proposed algorithm is 87%, which is better than ONSI, SHIP and IPAM algorithms from other researchers. Thus the algorithm performs realistically better than the current available techniques.

AB - Future Smart-Home device usage prediction is a very important module in artificial intelligence. The technique involves analyzing the user performed actions history and apply mathematical methods to predict the most feasible next user action. Unfortunately most of the techniques tend to ignore the adaptation to the user preferred actions and the relation between the actions and the state of the environment which is not practical for Smart-Home systems. This paper present a new algorithm of user action prediction based on pattern matching and techniques of reinforcement learning. The algorithm is modeled using hardware description language VHDL. Synthetic data had been used to test the algorithm and the result shows that the accuracy of the proposed algorithm is 87%, which is better than ONSI, SHIP and IPAM algorithms from other researchers. Thus the algorithm performs realistically better than the current available techniques.

KW - Action prediction

KW - Multi-agent system

KW - Reinforcement learning

KW - Smart home

UR - http://www.scopus.com/inward/record.url?scp=84877726207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877726207&partnerID=8YFLogxK

U2 - 10.5829/idosi.wasj.2013.22.09.188

DO - 10.5829/idosi.wasj.2013.22.09.188

M3 - Article

AN - SCOPUS:84877726207

VL - 22

SP - 1302

EP - 1309

JO - World Applied Sciences Journal

JF - World Applied Sciences Journal

SN - 1818-4952

IS - 9

ER -