Browse by author
Lookup NU author(s): Dr Jie ZhangORCiD
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Human activity recognition (HAR) is gaining interest with many important applications including ubiquitous computing, health-care services and detection of diseases. Smartphone sensors have high acceptance and adherence in daily life and they provide an alternative and economic way for HAR. To improve the recognition performance, this paper proposes a novel smartphone sensor-based HAR method, hybrid diversity enhancement with selective ensemble learning (HDESEN), by utilizing selective ensemble learning with differentiated extreme learning machines (ELMs). A hybrid diversity enhancement is proposed to boost the diversity of base models and an improved binary glowworm swarm optimization (IBGSO) is employed to effectively enhance the learning process by choosing a superior subset for ensemble instead of all. Firstly, statistical features in the time domain and frequency domain from smartphone sensors are extracted and integrated and then three filter-based feature selection methods are utilized for desirable base models. Secondly, to enhance the diversity of the base models, three types of diversities are introduced to construct different base models. Among them, Bootstrap is introduced to design distinctive training data subsets for differential base models, random subspace and optimized subspace are proposed to obtain different feature spaces for constructing base models. Thirdly, a pruning method based on glowworm swarm optimization (GSO) is proposed to find the optimal sub-ensemble from the pool of models from all diverse types to implement selective ensemble learning. The experimental results on a publicly available data set demonstrate the proposed HDESEN can reliably improve the performance of HAR and outperforms the relevant state-of-the-art approaches.
Author(s): Tian Y, Zhang J, Chen Q, Liu Z
Publication type: Article
Publication status: Published
Journal: IEEE Access
Online publication date: 30/11/2022
Acceptance date: 30/10/2022
ISSN (electronic): 2169-3536
Altmetrics provided by Altmetric