Enhanced Deep Hierarchical Classification Model for Smart Home-Based Alzheimer Disease Detection

Abstract

AbstractAdvancement in medical field increases population of ageing society and monitor their health using sensors without disturbing their routine works. At the same time, elderly persons suffer from various age-related cognitive impairments. This work focuses on Alzheimer Disease (AD) which is one of the important causes of dementia. Though there are many existing machine learning models and deep learning approaches are developed for AD detection, handling class imbalance and inconsistencies are the primary issues faced by these standard classification models. The main objective of this paper is to construct an enhanced model which takes both class imbalance and inconsistencies in Alzheimer disease detection at its earlier stages using deep learning classification model. The proposed Enhanced Deep Hierarchical Classification Model (EDHCM) comprised of three different layers functions in a hierarchal manner of parent–child relationship using CASAS dataset which is a smart home resident’s daily activity collected using sensor devices. The first layer is the flat neural network whose functionality is enhanced using analytical hierarchal processing to fine-tune the parameters. The next layer is the hierarchal embedding layer which uses softmax to classify the severity of Alzheimer dataset. Final layer is hierarchical loss network which improves the learning model by punishing it based on layer loss and dependency loss. The simulation results explored the efficiency of the EDHCM by producing highest rate of accurate detection rate with less false alarms in AD detection compared to Support Vector Machine, Artificial Neural Network, Multilayer perceptron and Deep Neural Network.KeywordsInconsistencyAlzheimerSoftmaxMultilayer perceptronEmbedded layerArtificial neural networkDeep hierarchical classification