FL-PMI: Federated Learning-Based Person Movement Identification through Wearable Devices in Smart Healthcare Systems

Abstract

Recent technological developments, such as the Internet of Things (IoT), artificial intelligence, edge, and cloud computing, have paved the way in transforming traditional healthcare systems into smart healthcare (SHC) systems. SHC escalates healthcare management with increased efficiency, convenience, and personalization, via use of wearable devices and connectivity, to access information with rapid responses. Wearable devices are equipped with multiple sensors to identify a person’s movements. The unlabeled data acquired from these sensors are directly trained in the cloud servers, which require vast memory and high computational costs. To overcome this limitation in SHC, we propose a federated learning-based person movement identification (FL-PMI). The deep reinforcement learning (DRL) framework is leveraged in FL-PMI for auto-labeling the unlabeled data. The data are then trained using federated learning (FL), in which the edge servers allow the parameters alone to pass on the cloud, rather than passing vast amounts of sensor data. Finally, the bidirectional long short-term memory (BiLSTM) in FL-PMI classifies the data for various processes associated with the SHC. The simulation results proved the efficiency of FL-PMI, with 99.67% accuracy scores, minimized memory usage and computational costs, and reduced transmission data by 36.73%.

Using Identity-Based Cryptography as a Foundation for an Effective and Secure Cloud Model for E-Health

“…The workflow of our proposed algorithm for role-based proxy decryption at level II is depicted in Figure 1 . In the workflow, first of all, the third-party user will give a request to access the data that is the record of patients [ 39 ]. Request from the physical group or third party to access the user is given as the input for the decryption algorithm.…”

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

“…The attention mechanism is a model for medical image examination that naturally figures out how to focus on the targeted image of changing shapes and sizes ( 35 – 40 ). An attention mechanism helps the decoder focus on the area of interest.…”

Deep Conviction Systems for Biomedical Applications Using Intuiting Procedures With Cross Point Approach

“…However, it is much easier to separate different signals at unique frequency periods but a wearable device must be created for separating the individual monitored values rather than signals. Further biomedical signals are tested for the prediction of cardiovascular disease using conventional neural networks where a short-term memory coder is implemented in the system ( 16 , 17 ). The major disadvantage is that if signals are processed, then high memory is required for storing the information that can be accessed at later stages.…”