Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System With Combination of Wearable Sensors for Identifying Behavioral Abnormalities

To build cleverly assisted life systems for elderly people, the identification of behavioral abnormalities in human life is essential. Fall detection is a significant public health concern, particularly for the elderly fitness is unavoidable, and consistent monitoring of negative effects is required on time. This paper introduces Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System (HCAFDLBS) to effectively identify behavioral abnormalities in human life based on data obtained from wearable sensors and related location contexts. The machine tracks human body activity, identifies an efficient quaternion algorithm as a decrease in normal daily activities, and sends automatic requests for assistance to caregivers in the region of the patient. The probabilistic theoretical paradigm is used to identify three types of irregularities, including spatial deviations, timing anomalies, and anomalies of sequence. This technique relies on a hierarchical analytical network for the detection of complex behavior; the maximum approximate algorithm and the smoothing Laplace method are used to learn anomaly detection model parameters. The classification is spread on various sensor nodes, and a computer for a specific station, the distribution of multiple action classes is demonstrated to follow a mixture of subspace model for each action class and one subspace. The findings have confirmed the feasibility of the proposed background so that the behavior study can be incorporated in future intelligent elderly homes, this behavioral abnormality detection system is predicted, and their results have been verified.