A Hybrid Deep Learning Framework and Dwarf Mangoose Optimized Layers for an Effective Depression Classification

Depression is considered to be one of the dangerous diseases that affects physical state of human and even causes the fatal end to the patients. The depression leads to the anxiety disorders, bipolar disorders and at the same time may hit the person’s mind set to the suicide thoughts. Hence it is considerably demanding task to recognise the individuals with mental conditions. Traditionally, depression detection was done through patient’s interview and PHQ scores, but these traditional methods produce the accuracy which has very little effect on the diagnosis and treatment process. With the advent of machine (ML) and deep learning (DL) models, depression detection has reached its new dimensional path but still diagnosis performance and computational overhead remains to be real bottleneck for achieving its own strength of classification and early diagnosis. To solve this aforementioned problem, this research paper proposed hybrid ensemble of deep learning models and optimized training networks. Proposed framework consists of three components: first, adaptive dilated convolutional networks in which the model is trained with text and audio features, third is Bi-GRU Networks a finally the learning layers are optimized by DwarfMangoose Model to attain the better classification of depressions. The recommended model is examined and evaluated by utilizingDAIC-WOZ database and performance metrics such as accuracy, precision, recall, specificity and F1-score are measured and examined with the varied state-of-art learning procedures. The results demonstrate the recommended model has provided the optimal solution in detecting the depressions and produced the accuracy of 0.98, precision of 0.972, recall of 0.98, specificity of 0.98 and F1-score of 0.987 respectively. Experimental findings have proved that the proposed model has produced the promising results that improvises the clinical treatment and overcomes the fatal fears of the patients caused by the depression.