Alzheimer's Disease Diagnosis Based on Cognitive Methods in Virtual Environments and Emotions Analysis
This work addresses early detection of Alzheimer's disease to improve patient quality of life and reduce costs, but it appears incremental as it builds on existing technologies like virtual environments and emotion analysis.
The paper tackles early Alzheimer's disease diagnosis by introducing non-invasive screening tests using virtual environments and emotion recognition, achieving classification of autobiographical memory deficits with novel EEG and facial descriptors.
Dementia is a syndrome characterised by the decline of different cognitive abilities. Alzheimer's Disease (AD) is the most common dementia affecting cognitive domains such as memory and learning, perceptual-motion or executive function. High rate of deaths and high cost for detection, treatments and patient's care count amongst its consequences. Early detection of AD is considered of high importance for improving the quality of life of patients and their families. The aim of this thesis is to introduce novel non-invasive early diagnosis methods in order to speed the diagnosis, reduce the associated costs and make them widely accessible. Novel AD's screening tests based on virtual environments using new immersive technologies combined with advanced Human Computer Interaction (HCI) systems are introduced. Four tests demonstrate the wide range of screening mechanisms based on cognitive domain impairments that can be designed using virtual environments. The use of emotion recognition to analyse AD symptoms has been also proposed. A novel multimodal dataset was specifically created to remark the autobiographical memory deficits of AD patients. Data from this dataset is used to introduce novel descriptors for Electroencephalogram (EEG) and facial images data. EEG features are based on quaternions in order to keep the correlation information between sensors, whereas, for facial expression recognition, a preprocessing method for motion magnification and descriptors based on origami crease pattern algorithm are proposed to enhance facial micro-expressions. These features have been proved on classifiers such as SVM and Adaboost for the classification of reactions to autobiographical stimuli such as long and short term memories.