E-Health Monitoring System for Life Style Disorder

Depression and anxiety are mental illnesses that affected more than 3 million people even before the COVID-19 pandemic. This number of patients is expected to increase exponentially in the coming years as the masses have experienced monitory, social, and societal losses. Consequently, the number of

Project Title

E-Health Monitoring System for Life Style Disorder

Project Area of Specialization

NeuroTech

Project Summary

Depression and anxiety are mental illnesses that affected more than 3 million people even before the COVID-19 pandemic. This number of patients is expected to increase exponentially in the coming years as the masses have experienced monitory, social, and societal losses. Consequently, the number of suicides has also risen all across the world. There is an urgent need to provide a solution to this critical problem to mitigate its consequences. Previous studies have shown that patients with depression and anxiety have different frontal brain-wave asymmetry than healthy people. Therefore, we propose a noninvasive method to detect depression and anxiety using wearable devices. The project design includes mobile application development and integration of wearable devices for monitoring of Activities of Daily Living (ADL). The device sends collected data to the cloud through Personal Area Network (PAN) where an appropriate pattern recognition algorithm is applied to detect depression and anxiety. In case of early detection of neurological or lifestyle disorders, we may provide better support and care for the patients. The completed project may include software and hardware components. Hardware would include wearable sensors that can be integrated with a mobile application that is capable of transferring the recorded data to the cloud where decision making would be done. The identified patterns would be notified back to the application from the cloud.Different medical devices can be used to obtain the EEG of the people in their daily lives. Recently a wearable device used to gain the EEG signals is OpenBCI EEG headband kit.

Project Objectives

The objective of this project is to employ wearable devices for the detection and recognition of ADL. A record of this would enable us to identify the trends or patterns that individuals exhibit over a longer period. The observance of this trend can help us identify long-term health as well as neurological disorders that an individual might be exposed to in the coming years. The captured data using the mobile phone will be transmitted to the cloud. The data will be categorized into different classes in database storage.

The following are the objectives that must be achieved in order to complete the project.

• Obtain EEG signals through wearable sensors for the monitoring and detection of ADLs of the user.
• Use of time domain and frequency domain analysis techniques in pattern recognition.
• Implementing machine learning algorithms for ADL classification.
• Creating an interactive mobile application.
• Integration of mobile application with cloud server
• Database handling and maintaining records of each user on the cloud server.
• Detection of patients suffering from neurological disorders i.e. depression or anxiety.

Project Implementation Method

Following are the methods for implementation:

This Project is being implemented by collecting dataset of Depression and Anxiety from patients and healthy people with the help of EEG sensor. Preprocessed the Collected Dataset to remove unwanted values in dataset. Get Alpha, Beta, Theta, Gamma, frequency rhythm bands of EEG in python. Bands Values can also be used for algorithm that extract their own features. Then Machine Learning algorithm will implement to train the model and get best accuracy by implementing various methods.

• KNN
• Decision Tree
• SVM
• XGBoost

Statistical Time series method on the frequency rhythm bands of EEG

• WEASEL+MUSE
• Mr-SEQL in Sktime.

And for the android application, creating an interactive mobile application and its Integration of mobile application with cloud server with Database handling and maintaining records of each user on the cloud server. Detection of patients suffering from neurological disorders i.e. depression or anxiety.

The outcomes of these tests will then be compared to those acquired from accelerometer, to verify higher level of accuracy through the new system implemented. Then according to the result, the individuals will be suggested to perform certain tasks to get off from depression through mobile applications. Besides, recommendations will be provided on how to maintain and improve the new system developed to approach greater accuracy.

Benefits of the Project

The following are the benifits of our project:

• This project would serve as a solution to neurological issues in Pakistan.
• Cut down the healthcare expenses and step ahead in the accuracy of disease prediction.
• With the advent of COVID-19 in Pakistan, people in quarantine can acquire sensory data from their homes.
• An active and reliable mobile phone application will be helpful for the people reluctant to open up about their mental state to other humans
• This mobile phone application may be integrated with existing social media applications such as food panda, uber, Facebook, maps, and calendar applications etc. These social media applications can be used to provide the user with suggestions if needed.
• Scalability and flexibility in the configured network for future expansion.

Technical Details of Final Deliverable

The hardware we have used to obtain the EEG signals is a device known as OpenBCI EEG headband kit. which is connected through NodeMCU wireless with the smartphone or PC in which the application is installed. This sensor takes the EEG signals of the subjects brain that are further processed to identify the activity performed, as different activities give different EEG signals. The signal is recorder for a specific time duration and it is transmitted from the sensor to the cloud database where it is classified into different bands on which Machine Learning Algorithm is applied to train the models.If the activity is classified as a normal class then it is simply stored in the cloud based database but if the activity is classified as an abnormal class then along with storing in the database. In case of abnormal behaviour,the subject is also suggested to perform certain tasks to get off from depression or anxioty through mobile applications. The developed mobile application is userfriendly and can be used by both suject and caretakers. Other hardware used is Raspberry Pi and Arduino mega to record the accelerometer data by using wearable Api which we compared the accuracies with already existing system. The user has to register in the mobile application and once the account is created, the user is assigned a unique ID against which his data is stored in the database and the history of his activities and the mental health of patients suffering from neurological disorders i.e. depression or anxiety.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

IT , Health , Telecommunication

Core Technology

NeuroTech

Other Technologies

Artificial Intelligence(AI), Internet of Things (IoT), Cloud Infrastructure, Wearables and Implantables

Sustainable Development Goals

Good Health and Well-Being for People, Gender Equality, Decent Work and Economic Growth, Reduced Inequality

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com