LAUSR

Wearable technology has shown to be a crucial tool for reliable and long-term monitoring. The aim of this monitoring effort is to identify early biomarkers in physiological, physical, and biochemical profiles, such as heart rate (HR), HR Variability, breathing rate, oxygen saturation, that can be used for encouraging supposedly healthy people to change their lifestyle and improve their wellness and (ii) assisting clinicians by providing objective measures of patient’s state in daily activities. The challenge of this human centered approach includes the design of non-invasive sensors for user-friendly and unobtrusive wearables, handling the noisy sensor data obtained in uncontrolled environment, performing multi-sensor fusion for reliable inferences and AI based analytics on longitudinal sensor data. According to the World Health Organization (WHO), health is a state of physical, mental and social wellbeing and not just the absence of disease. Cardiovascular disease (CVD), neurodegenerative diseases, diabetes, and cancer are among the leading causes of mortality and morbidity, but the causes and origins of these diseases are often controversial. Therefore, it is important to recognize early signs of stress, such as changes in physiological parameters that can be related to depression, to encourage people to lead healthier lifestyles. Electroencephalogram (EEG) signals can serve to detect depression by using multichannel data fusion and clipping augmentation and convolutional neural network as discussed by Wang et al., According to experimental findings, the combination of multichannel fusion (MCF) and multiscale clipping (MSC) enhancement can fully utilize the data present in individual sensor recordings and considerably enhance the classification accuracy and clustering effect of the diagnosis of depression. OPEN ACCESS