Depression is one of the most common mental disorders that at its worst can lead to suicide. Diagnosing depression in the early curable stage is very important. It may also lead to various disorders like sleep disorders and alcoholism. Here in this project the Electroencephalogram Gram (EEG) signals are obtained from publicly available database are processed in MATLAB. This can be useful in classifying subjects with the disorders using classifier tools present in it. For this aim, the features are extracted from frequency bands (alpha, delta and theta). Primarily the EEG signals were read using EDF browser software and the signals were loaded into Matlab to get log Power Spectral Density from EEG bands. The results obtained from Matlab are fed into neural network pattern recognition tool and ANFIS tool box which is integrated in MATLAB. These are powerful tool for data classification. Relevant extracted features parameters are used as inputs to the ANFIS and nprtool. The evaluated outputs are helpful to distinguish alcoholics from controls and various sleep disorders like insomnia, narcolepsy, bruxism and nocturnal frontal lobe epilepsy. 20 samples are trained and evaluated for Alcoholism and 40 samples are trained and evaluated for 4 different sleep disorders in ANFIS tool. The evaluated ANFIS output is read as 0 for Insomnia, 1 is for No sleep disorder, 2 for Narcolepsy, 3 for NFLE, 4 for Bruxism. 240 samples for 4 different sleep disorders and 60 samples for Alcoholism/ Control are trained and classified in nprtool.
:
Depression is the most underestimated and widespread health condition among people in developing countries. Depression levels among Indian population are rapidly increasing. It can be attributed to work pressure, social challenges, addiction to social media, adoption of the western culture and several other reasons. Indians’ depression levels are as high as 36 per cent and shockingly this number is the highest in the world. What makes this even more alarming is the fact that WHO projects depression to be the second leading cause of disability worldwide by 2020. In this work, the focus is on Machine learning based Depression prediction by utilizing different brain wave frequency bands. It is carried out by asking universal standard Patient Health Questionnaire (PHQ.9) to subjects which are related to respective emotions. Neurosky’s Mind Wave Head kit is connected to the forehead (of subject) and 86 sample values are recorded. Total 85 Samples are trained, whereas 1 data is tested.
The MANOGLANISTARA- android App is designed which sends the Emotional Wellness output (depressed/normal) to the subject via email. This provides the basis of analysis as to whether the subject is suffering from depression or not. Customization of the medication and treatment to such subjects can be initiated by the doctors.
In this work, the MATLAB SVM based Depression prediction model is developed by evaluating the data built from Mindwave kit and standard PHQ.9 questionnaire.
Work is also extended by using Orange Toolbox for classification of depressed/ normal subjects. In Orange toolbox, Prediction, ROC Analysis and Confusion Matrix are evaluated for different classifiers such as SVM, Naïve Bayes, Classification tree, Random forest and CN2 Rule Inducer. Accuracy, Precision, Sensitivity and Specificity is computed for all the above mentioned classifiers. CN2 Rule Inducer classifier gave higher accuracy of 0.9418, sensitivity 0.9778, Specificity 0.9736 and Precision 0.9778.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.