SiGMA - Signal Processing, Machine Learning and Artificial Intelligence Research Lab

SiGMA Lab - The research Lab was established in 2014. The research team aims at data-driven solutions for healthcare, infrastructure and customized user services using Intelligent frameworks boosted by machine learning and artificial intelligence tools. Enhancing user experience and preferences through critical insights, automated decisions and innovative products, the team works towards improving lives in remote areas, villages and smart cities.

People

Ph.D Scholars:

• Mrs. Parvathy Dharmarajan - Decision Support Systems for Remote Healthcare
• Mrs. Sneha Kandacharam - Automatic Incident Detection in Traffic on Indian Roads
• Mrs. S. Vidhya - Evolution of Hidden Communities using Dynamic Graphs
• Mrs. K. R. Bindu - Machine Translation
• Ms. Archana

Research

SiGMA Lab research team focuses on Feature Engineering, Machine Learning, Artificial Intelligence and Quantum Machine Learning. AI can be used for transforming rural India using digital technologies and intelligent systems. The team is involved in exploring problems identified with farmers, tribals and women in building cost-effective solution frameworks.

Projects

Funded Projects

RESPOND-ISRO - “Automation of Transport and Building Feature Extraction using Deep Learning with Super-Resolution Enhancement of Satellite Imagery “ - Rs. 28.5/- lakhs

Research Projects

• Artificial Intelligence for Education - Teaching-Learning and Assessment
• Water Budget Recommendations using Localized Water Resources and Demand Mapping
• G-lets Signal Processing for Functional Approximation in Neural Networks
• Artificial Intelligence Systems for Intelligent Transportation Infrastructure on Indian Roads
• Graph Signal Processing Filters
• Geo-spatial 3D Modelling and Augmented Reality for Smart City Planning and Design
• Real-Time Traffic Incident Detection and Prediction with Machine Learning Tools on Indian Road Networks
• Multi-attribute Utility Model to Scrutinize Patient Data using Machine Learning and Deep Learning for Medical Decision Support System in Remote Healthcare
• Intracranial Hemorrhage Detection and Localization
  Intracranial hemorrhage contributes to strokes requiring urgent intensive treatment. The symptoms include acute neurological such as severe headache or loss of consciousness, highly trained specialists review medical images of the patient’s cranium. Detect acute intracranial hemorrhage and its subtypes, looking for the presence, location and type of hemorrhage.
• Blindness Detection
  To build a machine learning model and detect diabetic retinopathy from thousands of fundus images collected in rural areas by Aravind Eye Hospital in India.
• Liver Disease Diagnosis
  To segment liver in CT data, and liver, spleen, and kidneys in MRI data
• Fetal Head Circumference Detection
  Automated measurement of fetal head circumference using 2D ultrasound images.
• Pneumonia Detection
  Predicting fluid intelligence from T1-weighed MRI (11K subjects in total, age 9-10 years). The data of about 4k individuals will be provided for training.
• X-ray Diagnosis
  MURA (musculoskeletal radiographs) is a large dataset of bone X-rays. Algorithms are tasked with determining whether an X-ray study is normal or abnormal.
• Breast Cancer Diagnosis
  Detect breast cancer metastasis in lymph nodes using image classification of 327,680 color images (96 x 96px) extracted from histopathology images.
• Vessel Extraction in Retinal Images
  Develop a system to automatically segment vessels in human retina fundus images
• Speed-up of MRI Scans
  To explore the use of AI to make MRI scans up to 10 times faster with different dataset images.
• Automatic Structure Segmentation for Radiotherapy Planning
  To set up tasks for evaluating automatic algorithms on segmentation of organs-at-risk (OAR) and gross target volume (GTV) of tumors of two types of cancers, nasopharynx cancer and lung cancer, for radiation therapy planning
• Detect Brain Shift with Intra-Operative Ultrasound Images
  To characterize image registration methods on newly released standardized datasets of iUS-guided brain tumor resection. Image registration algorithms are needed to relate pre-surgical MRI to iUS images.
• Chest Radiograph Diagnosis
  Identify the presence of 14 different abnormalities from chest radiograph images
• Fracture Detection in Spine Images
  To segment and classify vertebrae from the given spine images that include fractured and non-fractured cases.
• Chest CT Scan Nodule Identification
  Lung cancer screening and Fleischner follow-up determination in chest CT through nodule detection, segmentation and characterization

Completed Projects

2019

• Topic modelling and summarization from text using NLP - Jariwala Romin Chetankumar, Jassem Mohammed, Krutarth Katharotiya
• Uncertainty estimation in Time Series Prediction by Ensemble Models for Uber Taxi Demand Conditions - T.M. Vijay Meenakshi
• Visual speech recognition using facial mouth features - Vennela, Archana Nair
• Performance Metrics of Cricket Players for Team Selection - Sri Hari, Aakash, Dinesh
• Hospital Recommendation using Machine Learning - Nithil, Gokul, Raakesh
• Analysis of LEOD based Outlier Detection - Ankit, Jishnu, Vivek Nair
• Sentimental Analysis of Movie Reviews using Psychometric Method in Linguistic Study - K C Harikrishnan, Suresh, Nidhin S Dharan
• Trash Object Detection Using SLIC Segmentation - Abhishek Rajesh Pawaskar, Lanka Naga Sai Deep, Ramyapriyanandhini
• Natural Language Querying, Jaivik, Himesh
• Parallelising Convolution Neural Networks - K C Harikrishnan
• Ride Demand Prediction of Taxis - Balaji, B
• Quantum Machine Learning - Balaji, B
• Automatic Drone Navigation - Balaji, B, Jassem, Dinesh, Pooja Sri, Nithil Jose
• Unathorized Personnel Detection and Gesture Recognition using Humanoid Biped Robot - Abhishek, Naga Sai Deep, Krutarth, Romin, Vijay Meenakshi
• Automatic Lane Detection using Smart Robo Car - Aakash, Sri Hari, Archana, Jaivik Dave, Himesh, Darshan
• Simulation of Traffic Situations for Smart Video Robo Car - Vivek Nair, Suresh, Nithin Dharan, Raakesh, Ramyapriyadarshini
• Optimization of Robotic Arm Movements - Ankit, Harikrishnan, Aishwarya, Gokul, Vennela

2018

• Automatic Feature Extraction in Satellite Images

2017

1. Parallelizing Low Vision Feature Extraction through GPUs

2016

1. Super resolution of Images for Breast Cancer from Mammography Images
2. Medical Signal Processing using IoT Devices
3. 3D Map Generation for Visual Wayfinding

2015

1. 3D Modelling from MRI Images
2. Feature based Transfer function design for Volume Rendering
3. 3D Modelling of Nano Surfaces            
4. Context Aware User Profiles for Mobile Phones

Artificial Intelligence Devices

• NVIDIA ano Jetson
• Google Home
• Amazon Echo Dot 
• Smart Robo Car Kit
• Raspberry PI Boards
• Humanoid Biped Robot
• DJI Tello Drone
• Arduino Board

Facilities

The lab contains the following equipment:

• Workstation with 2 NVIDIA V100 GPUs
• Dell Desktop i7 - NVIDIA K40 GPU
• Visualization - 4K monitors, 3D TV

Academic Programs

• Associated with M.Tech(Artificial Intelligence and Data Science) Master’s program at the Department of Computer Science and Engineering, Coimbatore.
• Workshops Series - “Machine Learning and Applications”

Projects

Publications

1. Aravind A. V, Raadhikaa S, and Rajathilagam B., Electrolaryngeal Speech Improvement through Phoneme Enhancement, Workshop on Speech Processing for Voice, Speech and Hearing Disorders (WSPD) 2018, INTERSPEECH 2018, Mysore, India. (Accepted).
2. Bhalaji N., and Rajathilagam B.,Object Shapes from Regular Curves through Sparse Representations”, Procedia Computer Science, Elsevier, RoSMA 2018.
3. Parvathy Dharmarajan and Rajathilagam B., “Cloud-Based e-Healthcare Service System Design for On-Demand Affordable Remote Patient Care”, IC3T, 2016.
4. Bharani A., Raadhika S., Akshay Kolli., and Vidhya S., Smartphone Based Interactive Indoor Navigation System, Journal of Advanced Research in Dynamic and Control Systems, pp 953-956, 2018.
5. Sobika S and Rajathilagam B., “Intelligent System for Wayfinding Through Unknown Complex Indoor Environment”, ISTA, 2016.
6. Suman S., and Rajathilagam B., Outlier Detection in Time-Series Data: Specific to Nearly Uniform Signals from the Sensors. In: Hemanth D., Smys S. (eds) Computational Vision and Bio Inspired Computing. Lecture Notes in Computational Vision and Biomechanics, vol 28. Springer, Cham, 2018.
7. Swetha R Nair and Rajathilagam, B., “Super Resolution of Mammograms for Breast Cancer Detection”, International Journal of Applied Engineering Research, June 2015.
8. Rajathilagam B and Murali Rangarajan, “Spectral Representation of Principal Components in Signals and Images using G-lets Decomposition of Subbands”, IEEE TENCON 2016, Singapore.
9. Rajathilagam B., Dr. Murali Rangarajan, and Soman, K. P., “G-Lets: Signal Processing Using Transformation Groups”, vol. arXiv:1201.2995v1, 2012
10. Rajathilagam B., Rangarajan, M., and Soman, K. P., “Frequency Analysis of Signals and Images using G-Lets”, International Journal of Imaging and Robotics, vol. 8, pp. 30-48, 2012.[Abstract]
11. Rajathilagam B., Murali, R., and Balaji, B., “Dynamic Context-specific User Profiles by Regression Modelling”, Proceedings of GSTF CGAT. 2015.
12. Rajathilagam B., XC, D. P., and Jayaraj, B., “Techniques for Secure Communication in Emerging Wireless Ubiquitous Networks”, The International conference on High Power Computing (HiPC), Bangalore, India, 2004. 2014.
13. Rajathilagam B., Jayaraj, B., and Rangan, D. P. Venkat, “Naming, Location tracking, Synchronizing and Aggregating Wireless Sensor Networks”, In the proceedings of SPIE, Optics East 2005, Boston, USA., vol. 5993. pp. 5993 - 17, 2005.
14. Dharmarajan and Dr. Rajathilagam B., “Cloud-Based e-Healthcare Service System Design for On-Demand Affordable Remote Patient Care”, in Computer Communication, Networking and Internet Security, Singapore, 2017.[Abstract]
15. Rajathilagam B. and Prakash, K. S. S., “An Adaptive Communication Model for Large Wireless Sensor Networks”, in 2007 2nd International Conference on Pervasive Computing and Applications, 2007.[Abstract]
16. Rajathilagam B., Rangan, D. P. Venkat, and , “Techniques for Secure Communication in Emerging Wireless Ubiquitous Networks”, in The International conference on High Power Computing (HiPC), Bangalore, India, 2004.
17. Rajathilagam B., “G-lets: A New Signal Processing Algorithm”, Ph.D Thesis, 2013

Collaborators

• NVIDIA - Certified Deep Learning Institute Ambassador
• Leadingindia.ai - Bennett University, Delhi, India
• ConfirmU - Behaviour modelling of customers in Banks, Bangalore
• CheckanInvoice - Invoice Fraud Detection, Bangalore
• FrontM - Remote Healthcare, Bangalore
• 24(7).ai - Conversational AI
• Green Shores Capital, UK
• ARAM Foundation, Tirupur
• TCS Research Lab, Bangalore

Products

• Feature Engineering Filters - G-lets feature extractors 
• Feature Engineering Algorithms- Edge Detection
• G-lets Based Machine Learning Models