Advanced Hybrid Mask Convolutional Neural Network with Backpropagation Optimization for Precise Sensor Node Classification in Wireless Body Area Networks

Abstract

Wireless Body Area Networks (WBANs) are crucial in continuous health monitoring, fitness tracking, and other applications where a real-time collection of physiological data is needed by sensors worn on the body. This is important in WBAN to achieve reliable data transmission, energy efficiency, and overall system performance. Still WBANs present several challenges: for example, the data that is being collected is heterogeneous since it originates from diverse IMDs measuring different bio-physiological signals; these can be also quite noisy because of motion artifacts when moving; as well high limitations when it comes to energy, bandwidth or storage push for low-complexity methods rather than standard deep learning techniques. Common Convolutional Neural Networks) CNNs( are successfully utilized for spatial information extraction but they cannot catch temporal dependencies well and also, WBAN sensor data has a noisy and multi-modal structure which acts as an additional challenge for traditional CNNs. These limitations emphasize the need of a flexible, fast and precise classification model based on the specific needs of WBAN applications. To overcome these challenges, this paper presents a novel hybrid neural network architecture consisting of combined 2D and 3D convolutions for spatial-temporal feature extraction along with masked convolution layers to provide an ability to adaptively ignore uninterested parts of the data. The model aims at achieving a high classification performance while also balancing with the system computational efficiency, perfect for its ipsi deployment on resource constrained WBAN devices. Then, we apply further backpropagation optimization measures such as adaptive learning rate scheduling and gradient clipping, to improve the stability of training speed and reduce latency which in return finds its way into supporting real-time processing capabilities of the model. By using each of these components, the model is able to deal with the multi-dimension aspects and high noise level nature of WBANs without excessive computation resources [18]. The Hybrid Masked CNN model is shown to out-perform existing approaches without such masking, yielding substantially higher performance in terms of accuracy, precision, recall and F1-score across all metrics defined for the application as compared to traditional 2DCNNs, 3DCNNs and other hybrid models. Consequently, the latency of the model is significantly decreased as well which confirms its applicability to real-time WBAN applications. The obtained results confirm the efficacy of features from hybrid architectures with masked convolutions along with optimization in training techniques for WBAN sensor node classification. The results of this paper improve WBAN technology by providing a solid and scalable solution which can be implemented when more reliability and flexibility are required from such systems in applications like healthcare, fitness or any other field.