Key points are not available for this paper at this time.
Recent technological advances in sensor networks show rapid growth in healthcare monitoring systems based on Wireless Body Area Networks (WBANs). A small sensor attached to the body can record various psychological parameters. WBAN sensors frequently fail due to noise, misalignment of the hardware, and patient perspiration. It is difficult for healthcare professionals to determine whether the data collected by these sensing devices is defected or influenced by a malicious attacker. Even inaccurate information can result in a wrong diagnosis, and the physiological parameters are categorized as normal or abnormal. This research focuses on reading anomaly detection for wireless body sensors and proposes a novel method based on hybrid machine-learning algorithms. A hybrid Artificial Neural Network – Grasshopper Optimization Algorithm (ANN-GOA) is proposed to find anomalous records in the dataset. Each anomalous record's predicted value determines whether the recognized form is anomalous. The suggested hybrid ANN-GOA method results are compared with the parameters like recall, accuracy, F1 score, loss, and precision. The simulation results of the proposed hybrid ANN-GOA algorithm provide better accuracy of 98.8%, recall of 99.9%, F-score of 97.9% and precision of 99.8% when compared with other conventional algorithms.
Thamaraimanalan et al. (Wed,) studied this question.