Browsing by Author "Sarkar, Utpaul"

Now showing 1 - 3 of 3

Machine Learning Based Depression Detection
(Daffodil International University, 2022-01-04) Islam, Md. Mozahidul; Biswas, Saikat; Sarkar, Utpaul
Depression is a common disorder that causes constant mood swings and feelings of sadness. Nowadays It is considered to be a deadly disorder in the world. At present, everyone from young to old is suffering from depression but most of them do not have the right idea about their mental state. It is very important for everyone to have the right idea about their mental state. We will detect depression through machine learning. First, we study some related papers, journals, and online articles then we talk to psychologists and depressed people and then we find some common factors that are related to becoming depressed. Then we collect data based on those factors, such as age, gender, profession, marital status, life satisfaction, feelings, interests, etc. We collect data from both depressed and non-depressed people. We have two outcomes. One is ‘Yes’ which means depressed and another is ‘No’ means not depressed. After data collection, we processed all the data and created a processed dataset. Then we applied machine-learning algorithms to our processed dataset. Machine learning, deep learning, and artificial intelligence are used in various predictions, detection, and recognition systems. We use k-nearest neighbor (kNN), logistic regression, Support Vector Classifier (SVC) Linear, naïve Bayes, random forest, adaptive boosting (ADA boosting), decision tree, and Linear Discriminant Analysis (LDA) Classifier. In our work, logistics regression gave the best performance based on accuracy and the accuracy of logistic regression was 93.50%.
Machine Learning Based Depression Detection
(Daffodil International University, 2022-01-04) Islam, Md. Mozahidul; Biswas, Saikat; Sarkar, Utpaul
Depression is a common disorder that causes constant mood swings and feelings of sadness. Nowadays It is considered to be a deadly disorder in the world. At present, everyone from young to old is suffering from depression but most of them do not have the right idea about their mental state. It is very important for everyone to have the right idea about their mental state. We will detect depression through machine learning. First, we study some related papers, journals, and online articles then we talk to psychologists and depressed people and then we find some common factors that are related to becoming depressed. Then we collect data based on those factors, such as age, gender, profession, marital status, life satisfaction, feelings, interests, etc. We collect data from both depressed and non-depressed people. We have two outcomes. One is ‘Yes’ which means depressed and another is ‘No’ means not depressed. After data collection, we processed all the data and created a processed dataset. Then we applied machine-learning algorithms to our processed dataset. Machine learning, deep learning, and artificial intelligence are used in various predictions, detection, and recognition systems. We use k-nearest neighbor (kNN), logistic regression, Support Vector Classifier (SVC) Linear, naïve Bayes, random forest, adaptive boosting (ADA boosting), decision tree, and Linear Discriminant Analysis (LDA) Classifier. In our work, logistics regression gave the best performance based on accuracy and the accuracy of logistic regression was 93.50%.
Machine Learning Based Depression Detection
(Daffodil International University, 2022-01-04) Islam, Md. Mozahidul; Biswas, Saikat; Sarkar, Utpaul
Depression is a common disorder that causes constant mood swings and feelings of sadness. Nowadays It is considered to be a deadly disorder in the world. At present, everyone from young to old is suffering from depression but most of them do not have the right idea about their mental state. It is very important for everyone to have the right idea about their mental state. We will detect depression through machine learning. First, we study some related papers, journals, and online articles then we talk to psychologists and depressed people and then we find some common factors that are related to becoming depressed. Then we collect data based on those factors, such as age, gender, profession, marital status, life satisfaction, feelings, interests, etc. We collect data from both depressed and non-depressed people. We have two outcomes. One is ‘Yes’ which means depressed and another is ‘No’ means not depressed. After data collection, we processed all the data and created a processed dataset. Then we applied machine-learning algorithms to our processed dataset. Machine learning, deep learning, and artificial intelligence are used in various predictions, detection, and recognition systems. We use k-nearest neighbor (kNN), logistic regression, Support Vector Classifier (SVC) Linear, naïve Bayes, random forest, adaptive boosting (ADA boosting), decision tree, and Linear Discriminant Analysis (LDA) Classifier. In our work, logistics regression gave the best performance based on accuracy and the accuracy of logistic regression was 93.50%.