Depression has become a serious problem in this current generation and the number of people affected by depression is increasing day by day. However, some of them manage to acknowledge that they are facing depression while some of them do not know it. The existing system is acoustic features are used to train a classification model to categorize a human as Depressed or not- Depressed. DIAC-WOZ database available with AVEC2016 (Audio/Visual Emotion Challenge) challenge is considered for training the classifiers. Prosodic, Spectral and Voice control features are extracted using the COVAREP toolbox and are feature fused. SMOTE analysis is used for the class imbalance and accuracy is obtained with the SVM algorithm resulting in Depression Classification Model (DCM) is Oversimplifies the human behavior. In this work, a new weighted activation function is being proposed to get high accuracy for deep learning. The weighted activation function is going to be applied and tested on a depression dataset to evaluate the intensity of depression. Naïve bayes and ANN (Artificial Neural Network) techniques are used in this proposed system. The application is tested on real time data of 50 subjects under the supervision of a qualified psychiatrist and an accuracy of 93% is obtained. The results will be compared based on the highest accuracy value to determine the best algorithm to detect depression.