Sensor-based human activity recognition using fuzzified deep CNN architecture with λ max method
ISSN: 0260-2288
Article publication date: 18 January 2022
Issue publication date: 8 March 2022
Abstract
Purpose
This work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λmax method for weight initialization, as a data normalization technique, to achieve high accuracy of classification.
Design/methodology/approach
The major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λmax method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λmax method.
Findings
The effectiveness of the proposed FDCNN model with λmax method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795.
Practical implications
The proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λmax method.
Social implications
Contributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition.
Originality/value
A novel FDCNN architecture is implemented with appropriate FAL kernel structures.
Keywords
Acknowledgements
This work is partially supported by NVIDIA GPU Grant – Academic Seed Program (Ref. No. KA1/DUP/0429/17) by sponsoring NVIDIA-GPU processor and further the authors acknowledge National Engineering College, Kovilpatti for extending research ambience and learning opportunities.
Grant information - The author(s) declared that no grants were involved in supporting this work.
Citation
V., G., S., K. and D, T.S. (2022), "Sensor-based human activity recognition using fuzzified deep CNN architecture with
Publisher
:Emerald Publishing Limited
Copyright © 2021, Emerald Publishing Limited