SPADE: Activity Prediction in Smart Homes Using Prefix Tree Based Context Generation

Research output: Contribution to journalArticle

Abstract

An automated smart home system is a key contributor to user assistance technology in modern civilization. Crucial merit of such a system is its ability to train itself through recorded data and recognize patterns in resident behaviors. Lack of sufficient prediction accuracy, exponential memory consumption, and extensive runtime prevent many of the current activity prediction approaches from being seamlessly integrated into consumer residences. This research introduces a sequence prediction algorithm which uses a prefix tree-based data model in order to learn and predict user actions. The algorithm applies episode discovery to detect correlated sensor events and learns the activities using a lossless data compression technique. This process assigns a probability of occurrence to sensor events and uses these probabilities to detect patterns in resident behavior. A complexity analysis of the algorithm is done to prove its efficiency in terms of memory usage and runtime. Using the presented technique, predictions are performed on popular datasets and contrasted with existing algorithms. The proposed algorithm achieves an 8.22% improvement in prediction accuracy over its predecessors, along with 66.69% better memory efficiency and 37% faster runtime.

Original languageEnglish
Article number8584418
Pages (from-to)5492-5501
Number of pages10
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

Data storage equipment
Trees (mathematics)
Sensors
Data compression
Data structures

Keywords

  • Activity prediction
  • data compression
  • prediction by partial matching
  • prefix tree
  • sequence prediction
  • smart home

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

SPADE : Activity Prediction in Smart Homes Using Prefix Tree Based Context Generation. / Farayez, Araf; Ibne Reaz, Md. Mamun; Arsad, Norhana.

In: IEEE Access, Vol. 7, 8584418, 01.01.2019, p. 5492-5501.

Research output: Contribution to journalArticle

@article{6c8b2901173c41b5b5db7a7eee6d6e2f,
title = "SPADE: Activity Prediction in Smart Homes Using Prefix Tree Based Context Generation",
abstract = "An automated smart home system is a key contributor to user assistance technology in modern civilization. Crucial merit of such a system is its ability to train itself through recorded data and recognize patterns in resident behaviors. Lack of sufficient prediction accuracy, exponential memory consumption, and extensive runtime prevent many of the current activity prediction approaches from being seamlessly integrated into consumer residences. This research introduces a sequence prediction algorithm which uses a prefix tree-based data model in order to learn and predict user actions. The algorithm applies episode discovery to detect correlated sensor events and learns the activities using a lossless data compression technique. This process assigns a probability of occurrence to sensor events and uses these probabilities to detect patterns in resident behavior. A complexity analysis of the algorithm is done to prove its efficiency in terms of memory usage and runtime. Using the presented technique, predictions are performed on popular datasets and contrasted with existing algorithms. The proposed algorithm achieves an 8.22{\%} improvement in prediction accuracy over its predecessors, along with 66.69{\%} better memory efficiency and 37{\%} faster runtime.",
keywords = "Activity prediction, data compression, prediction by partial matching, prefix tree, sequence prediction, smart home",
author = "Araf Farayez and {Ibne Reaz}, {Md. Mamun} and Norhana Arsad",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2018.2888923",
language = "English",
volume = "7",
pages = "5492--5501",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - SPADE

T2 - Activity Prediction in Smart Homes Using Prefix Tree Based Context Generation

AU - Farayez, Araf

AU - Ibne Reaz, Md. Mamun

AU - Arsad, Norhana

PY - 2019/1/1

Y1 - 2019/1/1

N2 - An automated smart home system is a key contributor to user assistance technology in modern civilization. Crucial merit of such a system is its ability to train itself through recorded data and recognize patterns in resident behaviors. Lack of sufficient prediction accuracy, exponential memory consumption, and extensive runtime prevent many of the current activity prediction approaches from being seamlessly integrated into consumer residences. This research introduces a sequence prediction algorithm which uses a prefix tree-based data model in order to learn and predict user actions. The algorithm applies episode discovery to detect correlated sensor events and learns the activities using a lossless data compression technique. This process assigns a probability of occurrence to sensor events and uses these probabilities to detect patterns in resident behavior. A complexity analysis of the algorithm is done to prove its efficiency in terms of memory usage and runtime. Using the presented technique, predictions are performed on popular datasets and contrasted with existing algorithms. The proposed algorithm achieves an 8.22% improvement in prediction accuracy over its predecessors, along with 66.69% better memory efficiency and 37% faster runtime.

AB - An automated smart home system is a key contributor to user assistance technology in modern civilization. Crucial merit of such a system is its ability to train itself through recorded data and recognize patterns in resident behaviors. Lack of sufficient prediction accuracy, exponential memory consumption, and extensive runtime prevent many of the current activity prediction approaches from being seamlessly integrated into consumer residences. This research introduces a sequence prediction algorithm which uses a prefix tree-based data model in order to learn and predict user actions. The algorithm applies episode discovery to detect correlated sensor events and learns the activities using a lossless data compression technique. This process assigns a probability of occurrence to sensor events and uses these probabilities to detect patterns in resident behavior. A complexity analysis of the algorithm is done to prove its efficiency in terms of memory usage and runtime. Using the presented technique, predictions are performed on popular datasets and contrasted with existing algorithms. The proposed algorithm achieves an 8.22% improvement in prediction accuracy over its predecessors, along with 66.69% better memory efficiency and 37% faster runtime.

KW - Activity prediction

KW - data compression

KW - prediction by partial matching

KW - prefix tree

KW - sequence prediction

KW - smart home

UR - http://www.scopus.com/inward/record.url?scp=85059021062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059021062&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2888923

DO - 10.1109/ACCESS.2018.2888923

M3 - Article

AN - SCOPUS:85059021062

VL - 7

SP - 5492

EP - 5501

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8584418

ER -