article · IEEE Internet of Things Journal
Human activity recognition focuses on automatically identifying and classifying physical movement through tracking devices and sensors, including standard smartphones fitted with accelerometers and gyroscopes. This technology supports applications across the Internet of Things and smart home sectors. A new deep learning architecture, designated MLCNNwav, has been developed to process wearable sensor data effectively. The system couples residual convolutional neural networks with a one-dimensional trainable discrete wavelet transform. Within this architecture, the multilevel network structure captures overarching global features, whilst the wavelet transformation learns activity-related features to improve representation and model generalisation. When evaluated against other deep learning approaches across four public benchmark datasets, the model consistently demonstrated high accuracy rates in classifying human activities.
Automatic tracking of human movement through everyday devices such as smartphones is essential for connected technologies. Improving the accuracy of activity recognition algorithms helps smart homes and Internet of Things platforms respond intelligently to human behaviour, providing useful data from existing motion sensors without requiring separate or intrusive tracking infrastructure.
The model offers potential utility for smart home and Internet of Things developers seeking more accurate sensor-based activity classification from standard mobile devices. As the system has been evaluated exclusively on four public benchmark datasets, it currently sits at the stage of applied and tested algorithmic research, requiring practical software integration and real-world trials before potential commercial deployment.
AI-generated from the published abstract. Always read the original work before citing.
Human activity recognition (HAR) is a rapidly growing field of research that aims to automatically identify and classify human motions and activities from different tracking devices, such as cameras and sensors. One of the most widely used sensor modalities for HAR is the smartphone, which has various sensors, such as gyroscopes, accelerometers, and GPS, that can provide rich information about a person’s movements and actions. HAR applications are essential for the Internet of Things (IoT) and smart home industries. We used the recent advances in deep learning techniques to develop a new HAR model for wearable sensors. The proposed model, MLCNNwav, relies on residual convolutional neural networks and 1-D trainable discrete wavelet transform. The multilevel CNN is designed to capture global features, whereas the wavelet transformation enhances the representation and generalization by learning activity-related features. Several deep learning approaches are compared to assess the superiority of the developed model. Four public benchmarks HAR data sets were used for the evaluation. The outcomes confirmed that the developed MLCNNwav recorded high-accuracy rates on all data sets.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/jiot.2023.3286378
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
