Abstract
A challenging key aspect of modelling and recognising human activity is to design a model that can deal with the uncertainty in human behaviour. Several machine learning and deep learning techniques are employed to model the Activity of Daily Living (ADL) representing the human activity. This paper proposes an enhanced Fuzzy Finite State Machine (FFSM) model by combining the classical FFSM with Long Short-Term Memory (LSTM) neural network and Convolutional Neural Network (CNN). The learning capability in the LSTM and CNN allows the system to learn the relationship in the temporal human activity data and to identify the parameters of the rule-based system as building blocks of the FFSM through time steps in the learning mode. The learned parameters are then used for generating the fuzzy rules that govern the transitions between the system’s states representing activities. The proposed enhanced FFSMs were tested and evaluated using two different datasets; a real dataset collected by our research group and a public dataset collected from CASAS smart home project. Using LSTM-FFSM, the experimental results achieved 95.7% and 97.6% for the first dataset and the second dataset, respectively. Once CNN-FFSM was applied to both datasets, the obtained results were 94.2% and 99.3%, respectively.
Highlights
Monitoring and recognising human activities within a home environment are investigated in order to support the independent living of older adults in Ambient Intelligence (AmI) environments (Chen et al 2012; Medina-Quero et al 2018)
The results obtained by applying Long Short-Term Memory (LSTM)-Fuzzy Finite State Machine (FFSM) and Convolutional Neural Network (CNN)-FFSM based on dataset A are illustrated in Fig. 7a, b respectively
The work presented in this paper has proposed two new methods for improving modelling and recognising human activities using data gathered from low-level sensory devices
Summary
Monitoring and recognising human activities within a home environment are investigated in order to support the independent living of older adults in Ambient Intelligence (AmI) environments (Chen et al 2012; Medina-Quero et al 2018). Several techniques are used to gather the information that represents the Activity of Daily Living (ADL) from a real environment for the monitored user (Cook et al 2013; Langensiepen et al 2014). This information is commonly gathered from the signals that are collected from ambient sensors such as door entry sensors, movement and occupancy sensors etc., (Hassan et al 2018). Since humans behaviour is not restricted to a single state at any time and there are uncertainties associated with each state, it is reasonable to consider some degree of fuzziness within the FSM,
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Ambient Intelligence and Humanized Computing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
