Multi-Headed Deep Learning Models to Detect Abnormality of Alzheimer’s Patients

Abstract

Worldwide, many elders are suffering from Alzheimer’s disease (AD). The elders with AD exhibit various abnormalities in their activities, such as sleep disturbances, wandering aimlessly, forgetting activities, etc., which are the strong signs and symptoms of AD progression. Recognizing these symptoms in advance could assist to a quicker diagnosis and treatment and to prevent the progression of Disease to the next stage. The proposed method aims to detect the behavioral abnormalities found in Daily activities of AD patients (ADP) using wearables. In the proposed work, a publicly available dataset collected using wearables is applied. Currently, no real-world data is available to illustrate the daily activities of ADP. Hence, the proposed method has synthesized the wearables data according to the abnormal activities of ADP. In the proposed work, multi-headed (MH) architectures such as MH Convolutional Neural Network-Long Short-Term Memory Network (CNN-LSTM), MH one-dimensional Convolutional Neural Network (1D-CNN) and MH two dimensional Convolutional Neural Network (2D-CNN) as well as conventional methods, namely CNN-LSTM, 1D-CNN, 2D-CNN have been implemented to model activity pattern. A multi-label prediction technique is applied to detect abnormal activities. The results obtained show that the proposed MH architectures achieve improved performance than the conventional methods. Moreover, the MH models for activity recognition perform better than the abnormality detection.