LSTM and HMM Comparison for Home Activity Anomaly Detection

Citation

Tan, Wooi Haw and Ooi, Chee Pun and Cheong, Soon Nyean and Guo, Xiaoning and Tan, Yi Fei and Poh, Soon Chang (2019) LSTM and HMM Comparison for Home Activity Anomaly Detection. In: 3rd IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2019, 15-17 March 2019, Chengdu, China.

[img] Text
234.pdf - Published Version
Restricted to Repository staff only

Download (280kB)

Abstract

Behavioral changes in daily home activities may be linked with health problems. Therefore, anomaly detection on sequence pattern of home activities is important for healthcare monitoring. In this paper, an anomaly detection method based on Long Short-Term Memory (LSTM) neural network is proposed to detect anomalies on sequence pattern of home activities. A comparison study of LSTM and Hidden Markov Model (HMM) was conducted to evaluate their performance under different training set size and model's hyperparameters. The experimental results demonstrated that LSTM is comparable to HMM in detecting anomalies on sequence pattern of home activities. The test accuracies of the best LSTM and HMM models are both 87.50%.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Sequence pattern
Subjects: Q Science > QA Mathematics > QA299.6-433 Analysis
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 14 Jan 2022 02:03
Last Modified: 14 Jan 2022 02:03
URII: http://shdl.mmu.edu.my/id/eprint/8997

Downloads

Downloads per month over past year

View ItemEdit (login required)