Data Scientist

Aditya Mhaske,


1. EEG Based Depression Detection Using Ensemble Approach

International Conference on Applied Intelligence and Sustainable Computing

The research focused on developing a system that can detect depression by analyzing brain activity captured through electroencephalogram (EEG) signals. The project utilizes an ensemble approach, combining multiple algorithms and techniques to improve the accuracy and reliability of depression detection.

Skills - Feature Reduction, Neural Network, Signal Processing, Tensorflow

2. Road Conditions Indication and Autonomous Braking System

IEEE 3rd International Conference on Intelligent Sustainable Systems

Developed a Road Conditions and Obstacles Indication System that added an automatic option to vehicles. It consisted of camera sensors, a processing unit, and an indicating device. The system provided real-time indications of road conditions and obstacles.

Skills - Computer Vision, Neural Networks, Tensorflow, PyTorch

3. Cardiovascular Disease Prediction Using Machine Learning Models

IEEE Pune Section International Conference

In this research, we explored the prediction of cardiovascular disease using machine learning techniques. We focused on the impact of BMI as a key feature in the prediction process. The results showed that BMI plays a significant role in predicting cardiovascular disease.

Skills - Machine Learning, Feature Engineering, Exploratory Data Analysis 

4. Smart Glasses to Assist Monocular Vision to Estimate Depth

IEEE International Conference for Innovation in Technology 2020, Bangalore, India

With my team, I designed smart glasses to assist individuals with monocular vision. The glasses utilized Convolution Neural Network and YOLOv3 for depth perception and object recognition. 

Skills - Computer Vision, Neural Networks, Tensorflow, PyTorch

5. A Survey: Feature Extraction Techniques And Machine Learning Models For Depression Analysis

12th International Conference on Computing, Communication, and Networking Technologies

Conducted a study on depression detection, focusing on the early identification of the disorder. By analyzing behavior, emotions, speech qualities, facial expressions, and other factors, I explored the effectiveness of various techniques and machine learning models.

Skills - Signal Processing, Neural Networks, Data Manipulation, PyTorch

6. Multimodal System for Depression Analysis Using Machine Learning Techniques

In review with IEEE

Demonstrated a real-time system that can successfully recognize depression by extracting features from Facial expressions, EEG signals, and Speech modules by analyzing human behavior with the help of the deep learning model trained on various datasets. Integrated a Multimodal system for depression analysis

Skills - Image Processing, NN, NLP, Signal Processing, Tensorflow

Contact Information

Indiana University, Bloomington
Master of Science in Data Science