Fall detection system for elderly people using IoT and ensemble machine learning algorithm

Abstract

Falls represent a major public health risk worldwide for the elderly people. A fall not assisted in time can cause functional impairment in an elderly and a significant decrease in his mobility, independence, and life quality. In this sense, we propose IoTE-Fall system, an intelligent system for detecting falls of elderly people in indoor environments that takes advantages of the Internet of Thing and the ensemble machine learning algorithm. IoTE-Fall system employs a 3D-axis accelerometer embedded into a 6LowPAN wearable device capable of capturing in real time the data of the movements of elderly volunteers. To provide high efficiency in fall detection, in this paper, four machine learning algorithms (classifiers): decision trees, ensemble, logistic regression, and Deepnets are evaluated in terms of AUC ROC, training time and testing time. The acceleration readings are processed and analyzed at the edge of the network using an ensemble-based predictor model that is identified as the most suitable predictor for fall detection. The experiment results from collection data, interoperability services, data processing, data analysis, alert emergency service, and cloud services show that our system achieves accuracy, precision, sensitivity, and specificity above 94%.

Machine learning and data analytics for the IoT

“…In its deployment, a gateway can be installed as a hub at the edge of network to exchange ontology information with the cloud using HTTP, while facilitating local communications with the IoT devices under CoAP [108]. The deployment can be an implementation of a study to alert remote emergency services when elderly people are in need, such as when a fall is detected.…”

Smart Tracking and Wearables: Techniques in Gait Analysis and Movement in Pathological Aging

“…Another example is documented by Yacchirema et al, who proposed a system for detection of falls using IoT and machine learning algorithms; this system uses three-axis accelerometers, embedded in a wearable 6LowPan device able to capture in real time the information associated with the movements of the volunteers [65]. However, not only the development of intelligent solutions and low obstruction is enough, it is also necessary to promote the integration of these solutions with the ambient assisted living environment and the work environments of the current aging population [66,67].…”

Authentication and Access control Mechanism using Elliptical Curve Cryptography with Message Authentication Code

“…There were insufficient features presents in the ensemble method, which results that it was unable to build the dynamic profile. D. Yacchirema, et al, [18] integrated the advantages of IoT and ensemble learning algorithms, this work used to identify the fall of elderly people in indoor environments using IoTE-Fall system. The four classifiers such as Deepnets, LR, DT and ensembles were used to achieve high efficiency in detecting the fall using training and testing time.…”

“…In this section, the quantitative analysis of proposed method is carried out with existing techniques namely fuzzy based Secure-MQTT [14], several machine learning algorithms [15], ensemble intrusion detection techniques (i.e. NB, ensemble) [17] and ensemble learning algorithm [18] in terms of metrics such as accuracy, F-measure, recall, FPR and precision. Table 1 shows the comparative values of accuracy and precision over proposed method.…”