Research Topic: Depression Detection Using EEG signals and Machine Learning methods
Brief Description: Depression detection using EEG data involves analyzing electrical activity in the brain to identify patterns associated with depression. Machine learning and Deep learning algorithms can then be used to accurately classify individuals as either depressed or not based on these patterns.
Lead: Dr. Karnati Mohan
Area: Brain Computer Interface & Machine Learning
Research Topic: Parkinson's Disease Detection using EEG Signals and Deep leaerning methods
Brief Description: Parkinson's disease detection using EEG data and deep learning involves analyzing brain wave patterns to identify signs of the disease. Deep learning algorithms can be trained on EEG data to accurately classify individuals as either healthy or with Parkinson's disease based on these patterns.
Lead: Dr. Karnati Mohan, Dr. Geet Sahu
Area: Deep Learning & Brain Computer Interface
Research Topic: Visibility restoration of hazy images using Deep Learning methods
Brief Description: Image dehazing involves removing unwanted haze or fog from images to improve their clarity and visual quality. This can be achieved using various traditional and deep learning techniques, which can help to restore the original details and colors of the image.
Lead: Dr. Geet Sahu
Area: Computer Vision & Deep Learning
Research Topic: Alzheimer's disease detection using brain computer interface and Deep learning
Brief Description: Alzheimer's disease detection using MRI images involves analyzing patterns in brain to identify Alzheimer's disease. Further, a deep learning model can be trained to classify Alzheimer patients.
Lead: Dr. Geet Sahu
Area: Deep Learning & Brain Computer Interface
Research Topic: Schizophrenia disease detection using EEG Signals and Deep Learning
Brief Description: Schizophrenia disease detection using EEG involves analyzing electrical activity in the brain to identify patterns associated with schizophrenia, such as abnormalities in gamma waves, connectivity patterns, and event-related potentials. Later, a deep learning algorithm can be developed and trained for Schizophrenia detection.
Lead: Dr. Geet Sahu, Dr. Karnati Mohan
Area: Deep Learning & Brain Computer Interface
Research Topic: Multi-modal hand gesture recognition for robotic control application
Brief Description: Video and time-series data has been recorded for a large set of hand motion activities. Novel machine learning and deep learning models are being developed for integrated processing of this multi-modal data in order to improve classification performance.
Lead: Dr Rinki Gupta
Area: Human Computer Interaction & Time Series
Research Topic: Handling Data Scarcity in Deep Learning
Brief Description: Deep learning models require large amount of data for parameter optimization. Other techniques for training the deep learning model with limited labelled data are being implemented and evaluated for classification task. These include data augmentation using generative adversarial networks and use of Siamese network for time series data.
Lead: Dr Rinki Gupta
Area: Deep Learning
Research Topic: IoT-enabled Hand Gesture recognition and it's application
Brief Description: Hand gestures is one of the prominent way to express and convey any information. This involves multiple applications such as prosthetic control, virtual gamming, rehabilitation, sign language and much more. In this we intend to develop such a IoT enabled wearable sensor based system for personal interaction in either of the application as given above
Lead: Ms. Sneha Sharma
Area: Human computer interaction
Research Topic: Automated depression detection using deep learning with EEG signals
Brief Description: Depression detection using EEG data involves analyzing electrical activity in the brain to identify patterns associated with depression. Machine learning and Deep learning algorithms can then be used to accurately classify individuals as either depressed or not based on these patterns.
Lead: Ms. Sneha Sharma, Dr Rinki Gupta
Area: Brain Computer Interface & Deep Learning
Research Topic: Ensemble based transfer learning methods for wearable hand gesture recognition system.
Brief Description: Development of a novel ensemble-based transfer learning algorithm for wearable hand gesture recognition system, which uses small amount of labelled data from a new user along with labelled data from other users to train an ensemble of learners for predicting unlabeled data from the new user.
Lead: Ms. Sneha Sharma, Dr Rinki Gupta
Area: Human Computer Interaction & Machine Learning
Research Topic: Deep transfer learning is proposed for recognition of continuous hand gestures from isolated hand gestures.
Brief Description: The proposed deep learning model consists of convolutional neural network (CNN), two bidirectional long short-term memory (Bi-LSTM) layers and connectionist temporal classification (CTC) to enable end-to-end recognition without requiring the knowledge of sign boundaries.
Lead: Ms. Sneha Sharma, Dr Rinki Gupta
Area: Deep Learning
Research Topic: Breast Cancer Classification Using Lightweight Transformer Models
Brief Description: Breast Cancer Classification Using Lightweight Transformer Models involves utilizing efficient transformer architectures to accurately identify and classify breast cancer. These models provide a computationally lightweight solution, enabling faster inference and efficient deployment while maintaining high classification performance for early detection and diagnosis of breast cancer.
Lead: Dr. Ritesh Maurya
Area: Computer Vision & Deep Learning
Research Topic: Tomato plant diseased Image Generation using Conditional GAN and Classification
Brief Description: Tomato plant disease generation using conditional GAN and classification is a technique that combines generative adversarial networks (GANs) with classification models to create synthetic images of diseased tomato plants. By conditioning the GAN on different disease labels, it can generate realistic images representative of specific tomato plant diseases. This approach aids in training robust disease classification models by augmenting the dataset with synthetic samples, facilitating improved disease detection and diagnosis in tomato plants.
Lead: Dr. Ritesh Maurya
Area: GAN & Computer Vision
Research Topic: A novel Retinal Blood Vessels Segmentation Architecture and Multi-Class Classification of Fundus Images using Deep Learning
Brief Description: A new artificial intelligence framework is developed for segmenting retinal blood vessels and categorizing fundus images. It uses a modified U-Net backbone architecture, a six-depth-level encoder-decoder network, and a hybrid architecture to enhance fundus image classification into multiple categories. This approach combines features from segmented vessel images and raw fundus images, enabling a broader range of information integration.
Lead: Prof. M.K. Dutta
Area: Computer Vision & Deep Learning
Research Topic: Customized Deep Neural Networks for Fine-grained Feature Extraction from Agricultural Images on large database
Brief Description: This study presents a multi-model deep learning-based feature fusion framework for fine-grained classification in agricultural images with low inter-class visual discrimination and demonstrating its generalizability for similar classification problems. The framework extracts discriminatory and meaningful features from deep learning models, capturing discriminative semantic information associated with multi-class agricultural images.
Lead: Prof. M.K. Dutta
Area: Computer Vision & Deep Learning
Research Topic: AI-based automatic classification of lumbar spine intervertebral disc-slices
Brief Description: An AI architecture is developed for the automatic classification of MRI images of mid-height intervertebral disc-slices of the lumbar spine. A diverse dataset is used for training, and various image pre-processing, model optimization and overfitting-handling strategies are incorporated for better decision-making. The multi-layer deep learning architecture extracts relevant features from multi-class MRI data, fine-tuning iterations for proper weight adjustments.
Lead: Prof. M.K. Dutta
Area: Computer Vision & Deep Learning
Research Topic: A machine learning technique utilizing artificial intelligence for detecting and predicting various grades of breast cancer
Brief Description: A novel machine-learning-based approach is proposed for identifying breast cancer and its multi-grade classification using biomarker data. The ensemble-based model can recognize control subjects and subjects susceptible to breast cancer, categorizing them into four levels of grades. The model is fine-tuned using minority oversampling techniques to avoid overfitting. The robust model is based on performance statistics, demonstrating its ability to accurately predict breast cancer risk.
Lead: Prof. M.K. Dutta
Area: Machine Learning
Research Topic: Ensemble Machine Learning and Evolutionary Algorithms for Computer-Assisted Diagnosis and Multi-Grade Classification of Liver Cancer
Brief Description: This retrospective cohort study develops a machine-learning-based system for liver cancer prediction and precise diagnosis. The system uses ensemble learning to analyze data from diverse subjects and biomarkers. The system uses an evolutionary algorithm for hyper-parameter selection and minority oversampling to address class imbalance.
Lead: Prof. M.K. Dutta
Area: Machine Learning
Research Topic: An affordable and efficient AI-powered support system for individuals with visual impairments
Brief Description: This work presents an AI-based wearable assistive device that analyzes visual and sensory information about objects and obstacles. It combines sensor and computer vision technologies, generating auditory information and audio warnings for identified objects. The low-cost, easy-to-integrate, and small volume make it helpful for visually impaired individuals.
Lead: Prof. M.K. Dutta
Area: Computer Vision & Deep Learning
Research Topic: Improved Ensemble based Transfer learning approach for Indian Sign Language (ISL) Recognition
Brief Description: This work aims at an ensemble of transfer learning methods for ISL recognition. The proposed approach uses three pre-trained models, namely VGG16, ResNet50, and InceptionV3. The pre-trained models will be fine-tuned on a dataset of ISL images. The predictions of the three models will be combined using an ensemble learning technique to find a solution.
Lead: Dr. Sneha Sharma
Area: Human Computer Interaction & Deep Learning
Research Topic: Autistic behavior analysis using Machine learning methods.
Brief Description: Taking fish as a specimen and with control and intoxicated fishes – the movements tracking of the fishes will be done and based on the various parameters a machine learning method will be developed to determine autistic behavior of the sample specimen under observations.
Lead: Prof. M. K. Dutta
Area: Neural Science & Machine Learning
Research Topic: Training Pace Optimization Algorithm for Low Frequency Time Series Signals.
Brief Description: This research work is aimed at developing training pace optimization algorithm and a customized convolutional neural network architecture for the analysis of low-frequency time series data where the bias-correction and smoothing adaptive learning rate has opted to tune different hyperparameters and improve the convergence rate of customized neural network architecture.
Lead: Prof. M. K. Dutta
Area: Time Series & Deep Learning
Research Topic: Development of Deep Neural Network for Detection of Pulmonary Sounds.
Brief Description: This study aims at a deep learning-based diagnostic framework to create an objective, non-invasive method of identifying pulmonary sounds. The work is proposed to develop a AI architecture is a highly optimised deep learning network that considers different optimisers and is adaptive to train the model.
Lead: Prof. M. K. Dutta
Area: Time Series & Deep Learning
Research Topic: Transformer-based network utilizing CNN and multilayer perceptron for classification of environmental microorganisms using microscopic images
Brief Description: Extracting the discriminatory features from a limited-size dataset is very challenging for a deep learning model and a pure transformer-based network cannot achieve good classification results on a limited-size dataset due to the lack of muti-scale features. In this research a novel vision transformer-based deep neural network is attempted by integrating the transformer with CNN for the classification of EM using microscopic images.
Lead: Prof. M. K. Dutta
Area: Vision Transformer
Research Topic: AI based Predictive Model for Drug-Protein binding affinity prediction using 1D-CNN.
Brief Description: Predicting drug target binding affinity has huge relevance in Modern drug discovery and drug repositioning processes which assist doctors to come up with new drugs or even use the existing drugs for new target proteins. In silico models using advanced deep learning techniques could further assist these prediction tasks by providing most prominent drug target pairs. Considering these factors, a deep learning based algorithmic framework will be developed in this study to support drug target interaction prediction.
Lead: Prof. M. K. Dutta
Area: Time Series & Deep Learning
Research Topic: Skin Cancer Classification using Multi-model Deep Learning and Grey Wolf Optimization Method.
Brief Description: In this study, a novel skin lesion classification framework has been targeted based on deep learning and swarm intelligence. However, the activations obtained from single deep convolution neural architecture may not be discriminatory enough; therefore, the activations obtained from multiple models, having different architectural designs, have been taken into consideration. Thus, considering the high-dimensionality of resultant feature space, the non-distinguishing and redundant features needs to be eliminated; the information gain and the swarm intelligence based-grey wolf optimisation method have been used for that purpose.
Lead: Dr. Ritesh Maurya
Area: Computer Vision & Deep Learning
Research Topic: Application of Machine Learning in Risk Prediction of Type 2 Diabetes Mellitus (T2DM) using Anthropometric, Biochemical, and Genetic Parameters.
Brief Description: The study will include multiple variables from anthropometric, biochemical, and genetic parameters of T2DM patients and healthy individuals as a dataset. Different features from all the parameters will be analyzed to establish their relevancy for generating machine learning classification models. Top features will be extracted using recursive feature elimination technique to find the best risk factor for T2DM diagnosing.
Lead: Prof. M. K. Dutta
Area: Machine Learning
Research Topic: Design of Fast Converging Optimization Framework with Enhanced Learning Stability Classification of Large Scale Datasets.
Brief Description: The work focuses on advanced optimization techniques which provides the better learning stability with minimal hyper-parameter tuning. The targeted framework will involve advanced optimization scheme along with some significant architectural specifications which are structured in such a way to obtain the fast convergence rate. The usage of less no. of parameters will not only provide the high speed but also makes the framework less complex.
Lead: Prof. M. K. Dutta
Area: Deep Learning
Research Topic: A Deep Neural Network-Based Generic Framework for Analysis of WBCs using Microscopic Blood Cell Images.
Brief Description: This study is targeted to develop a deep learning-based framework for categorizing various microscopic blood cell images that is generic in nature. The targeted model will be trained on different microscopic blood cell images to address the challenges posed by each dataset like different resolutions, staining effects and variations in the illumination process.
Lead: Prof. M. K. Dutta
Area: Computer Vision & Deep Learning
Research Topic: Deep Learning-based Diagnosis of Brain Tumor
Brief Description: Design of Deep Learning based AI architectures for multiple categories of Brain Tumors.
Lead: Dr. Ritesh Maurya.
Area: Computer Vision & Deep Learning
Research Topic: Deep Convolution Neural Network for Epilepsy Detection Using EEG Signals.
Brief Description: Design of Deep Learning based AI architectures for Epilepsy identification using EEG signals.
Lead: Dr. Karnati Mohan & Dr. Geet Sahu.
Area: Time Series & Deep Learning
Research Topic: Facial Expression Recognition using Fractal Dimension and Deep Convolutional Neural Networks
Brief Description: Design of Deep Learning based AI architectures for classification of FER.
Lead: Dr. Karnati Mohan
Area: Computer Vision & Deep Learning
Research Topic: Wearable sensor-based Elderly fall detection and monitoring system.
Brief Description: Development of a novel framework to detect and monitor the fall activities in Old age people.
Lead: Dr. Sneha Sharma
Area: Human Computer Interaction & Deep Learning
Research Topic: Joint Angle Prediction in Robotics using Machine Learning methods.
Brief Description: Machine Learning-Driven Inverse Kinematics and Joint Angle Prediction for Six-DoF Anthropomorphic Robots with Explainable AI
Lead: Dr. J.K.Rai & Dr. M.K.Dutta
Area: Machine Learning & Robotics
Research Topic: WBC classification using Deep Neural Network from microscopic images.
Brief Description: Design of deep learning-based generic framework for segmentation and classification of microscopic white blood cell images.
Lead: Prof. M. K. Dutta.
Area: Computer Vision & Deep Learning
Research Topic: Training pace optimization under noisy conditions for Time Series signals.
Brief Description: Design of Robust Gradient Estimation using a Optimizer for Deep Neural Networks to Efficiently Handle Noisy Time Series Signals.
Lead: Prof. M. K. Dutta.
Area: Deep Learning
Research Topic: Early Detection of Schizophrenia using Deep Neural Network
Brief Description: Design and Development of Deep Learning based Architectures for Classification of EEG Signals for Detection of Schizophrenia in Real Time.
Lead: Dr. Geet Sahu
Area: Time Series & Deep Learning
Research Topic: A Multimodality based depression Detection System
Brief Description: To design a robust neural network using the multimodal data to detect the stage of depression
Lead: Dr. Sneha Sharma
Area: Deep Learning
Research Topic: Deep Learning Model for Early Diagnosis of Alzheimer’s Disease
Brief Description: Design of Deep Learning Framework for Automatic Detection of Alzheimer’s Disease from EEG Signal.
Lead: Dr. Geet Sahu
Area: Deep Learning
Research Topic: Enhancing Safety and Durability: Deep Learning-Powered Detection of Cracks in Decks, Walls, and Pavements
Brief Description: In this groundbreaking research, deep learning technology is leveraged to revolutionize the detection of cracks in essential infrastructure components such as decks, walls, and pavements. By utilizing advanced neural networks and computer vision, this approach ensures earlier and more accurate identification of structural damage, contributing to increased safety and longevity. The system provides real-time monitoring, enabling prompt maintenance and preventing accidents. This innovative solution has the potential to save significant repair costs and enhance the resilience of critical urban infrastructure, ensuring a safer and more sustainable future.
Lead: Ayush Singh Rajput, Prof. M.K. Dutta, Dr. Priyanka Singh
Area: Deep Learning
Research Topic: Comprehensive Comparative Analysis of Machine Learning Algorithms for Predicting the Bond Strength of Concrete
Brief Description: Predicting the bond strength of concrete is a crucial task in the field of civil engineering and construction, as it directly impacts the structural integrity and safety of built environments. Machine learning algorithms offer a data-driven approach to predict bond strength based on various input parameters. Several machine learning algorithms can be applied to this predictive modeling task, each with its own strengths and weaknesses. This method ensures a thorough evaluation of the bond strength for best outcomes.
Lead: Mr. Mayank Chaudhary, Dr. Priyanka Singh, Dr. Malay Kishor Dutta
Area: Machine Learning
Research Topic: Deep learaning framework to predict the trend in stock market
Brief Description: Development of deep learning methods that predict the financial market by automating the existing statical data and forecasting the trends in stock price
Lead: Sneha Sharma
Area: Time series forecasting
Research Topic: Deep Learning-based Diagnosis of Brain Stroke
Brief Description: To develop deep learning based method for automatic detection of brain stroke using CT scans. It will help in faster diagnosis of brain stroke cases.
Lead: Dr. Ritesh Maurya
Area: Deep Learning, Computer Vision
Research Topic: Pnuemonia Detection using Deep Learning with Novel loss function
Brief Description: To develop a deep learning-based methodology for faster diagnosis of pneumonia using X-ray images with the help of customised loss function designed for that purpose.
Lead: Dr. Ritesh Maurya
Area: Deep Learning, Computer Vision