Proposing a Method for Anomaly Detection in Trajectory of Patients With Alzheimer’s Disease Using Mobile GPS Data and Combination of Deep Neural Network and Adaptive Neuro-fuzzy Inference System

Today, with the industrialization of societies and the reduction of the size of households and tendency to live alone, caring for the elderly and monitoring their performance in daily life has become doubly important. Carrying devices such a GPS is one of the proposed solutions, which may not be a suitable solution due to the unpleasant feeling of carrying such equipment and due to disorders such as Alzheimer’s disease. A proper solution for taking care of old people especially for their outdoor activities is to observe their behavior by using their mobile GPS sensor by which it is possible to detect possible abnormal events. An important challenge in this method is the high number of abnormal events. In this paper, this problem is solved by applying an adaptive neuro-fuzzy inference system (ANFIS). Other important challenge is how to carefully analyze the training data to achieve a powerful model. For tackling this problem, we used a deep neural network.

In this paper, by combination of ANFIS and convolutional neural networks (CNN), a method was proposed for anomaly detection in trajectory of patients with Alzheimer’s disease. The CNN was optimized by the Whale algorithm. The proposed method was applied on a set of movement path data with a specific origin and destination based on the mobile GPS sensor of subjects. 

The proposed method had an accuracy of 95.5% for classification of test data, which indicated the effectiveness of the proposed method.

It seems that the combination of ANFIS and a CNN is a good method for anomaly detection in trajectory of older people with Alzheimer’s disease.