Ratnik is an Assistant Professor with School of Engineering and Applied Science, Ahmedabad University.
Before joining AU he was a postdoctoral fellow with Tel Aviv University, Israel and Tata Institute of Fundamental Research
(TIFR), Mumbai. He obtained his PhD and MTech in Information and Communication Technology from
Dhirubhai Ambani Institute (DA-IICT), Gandhinagar, in 2011 and 2005 respectively, and his BE in Computer Engineering
from Dharamsinh Desai University, Nadiad, in 2002. Ratnik mentors start-ups at VentureStudio.
Recommendation System for HR
Human Resource (HR) Management is one of the most essential part of a myriad of institutions across the globe. From an institution’s viewpoint, Recruiting talent has been one of the crucial problem faced by HR Department and which fits the job description. From a professional’s perspective, job hunting is also a challenging problem where one has to spend hours to find the right match of job with skills they have meeting their expectations.
Most of this job hiring & hunting process is manual, where human intervention is needed to make decisions and we have attempted to automate that process. This project aims to provide a solution for both users - Institutions & Professionals - that recommends prospective employees and jobs respectively.
Fast Implementation of Face Recognition on GPU
In this information era, we have most of our data secured by computers by incurring different security mechanisms such as passwords, encryption keys, fingerprints, faces as well iris data. Over Last three decades, face recognition have been a pervasive research problem in computer vision due to its wide applicability. Computation of high dimensional data in real-time can increase time complexity. To overcome time complexity, we can use hardware with more processing powers. Though high-end CPUs can reduce the computation time, GPUs can reduce computation time significantly, because they have been designed for specialized optimization for faster arithmetic operations than traditional processors exploiting the power of streaming multiprocessors.
Besides, these high-end hardware (CPUs & GPUs) can cost a fortune. We are designing faster algorithms for Face Recognition that runs on commodity hardware. We use Principal Component Analysis, and Linear Discriminant Analysis as a training model. Training time on GPU linearly increases whereas on CPU it remains quadratic. We also use Incremental algorithms for PCA and LDA to learn from videos in online fashion. By sacrifice of some frames, we had been able to preserve frame rates and retain recognition accuracy of around 90%.
We have created a benchmark database, SEAS-FR-Database, with HD videos and has multiple subjects.
Online Outlier Detection Algorithm on FPGA
The project involves comparative study, implementation and analyse of various anomaly detection algorithms. The desired goal is to build a hardware (FPGA module) that runs an algorithm designed to detect anomalies on data streams. A typical use case of this project is to generate real time alerts. We have already designed a constant space and linear time online algorithm. Next we will implement it on FPGA.
- Applications of algebra for some Game theoretic problems. International Journal of Foundations of Computer Science. Vol 26, No. 01, 51-78, 2015 (with Samaresh Chatterji).
- Computing Equilibria with Group Actions. ACM Communications in Computer Algebra. vol 45, no. 1, issue 176. June 2011 (Poster presentations in ACM-Symposium on Theory of Computing (STOC) and International Symposium on Symbolic and Algebraic Computation (ISSAC), 2011.). (with Samaresh Chatterji)
- Construction of Games: Some Approaches. Poster presentation at Workshop on Innovations in Algorithmic Game Theory. Hebrew University, Israel. May 2011.
- An Algebraic Approach to Nash Equilibria for Finite Normal Form Games. PhD Thesis. April 2011.
- Some Algebraic Properties of a Subclass of Finite Normal Form Games. CoRR. January 2010. (with Samaresh Chatterji)
- An Algebraic Approach for Computing Equilibria of a Subclass of Finite Normal Form Games. CoRR. May 2010. (with Samaresh Chatterji)
- Selfish Routing and Network Creation Games. MTech Thesis. May 2005.
- Genetic Algorithm solutions for some Complex Problems. National Seminar on Algorithms and Artificial Systems. University of Madras. February 2003. (with C K Bhensdadia)
- Cooling Parameter Optimizer: Genetic Algorithm Approach. Instrumentation and Control Engineering National Conference. NIT Trichy. December 2003.
- Implementation of PDE solver and Function Optimizer using Genetic Algorithms. IEEE-SPCTS. Ahmedabad. October 2003.
- A note on rank reduction in Suslin matrices. Ratnik Gandhi, Ravi A Rao and Aditya Tatu. Working Paper. 2017.
- Updating Singular Value Decomposition for Rank One Matrix Perturbation. Ratnik Gandhi and Amoli Rajgor. Submitted. 2016.
- Shaking ICL Tree. Mehul Raval and Ratnik Gandhi, Submitted 2016.
- Delegation in Resource Allocation Games. Amos Fiat, Ratnik Gandhi and Eran Nir. 2016.
- Co-organizer, International School on Computational Commutative Algebra, Feb 22-26, 2016, IIT Gandhinagar, India.
- Technical Program Committee, Workshop Session on Big Data Analytics in Agriculture, Seventh Workshop on Big Data Benchmarking, December 14-15, 2015, India Habitat Centre, New Delhi, India.
- Co-organizer, IEEE Workshop on Emerging Research Trends in Engineering (July 19-20, 2014), Ahmedabad.
- Co-organizer, Formal Methods Update (July 15-17, 2010) at DA-IICT, Gandhinagar.
- Member, Indian Association for Research in Computing Science (IARCS).
- Reviewer, ACM Transactions on Computation Theory, WINE 2013, SAGT 2013, Journal of Microeconomics, EC 2013.
- Dimensionality Reduction, Machine learning for big data analytics, GCET, Vallabh Vidhyanagar, Gujarat, November 2016.
- Algorithmic Economics, Research Trends in Engineering and Technology, BVM, Vallabh Vidhyanagar, Gujarat, August 2016.
- Economics and Computation, Seminar, IIM Ahmedabad, December 2015.
- Delegation games: Choosing strategy over Tactics, Invited Talk, IIIT Vadodara, Gandhinagar, Gujarat, 2015.
- Games, Equilibria and Computation, Algorithm Design Practices, DDU, Nadiad, Gujarat, May 2015.
- Detecting disease spread in a Geographic location - A big data approach, Expert Lecture, CSI & GCET, Vallabh Vidhyanagar, Gujarat, March 2015.
- Algorithm design for Big Data- Introduction and a Case Study, Computer Algorithms and Applications, BVM, Gujarat,2015.
- Nash equilibria using Polynomial Algebra, Advanced Algorithm Seminar, Tel Aviv University, 2013.
- Symbolic computation of Equilibria of a Subclass of Finite Normal Form Games, 14th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, Romania. 2012.
- Sparsely supported Correlated Equilibrium, STCS Seminar, TIFR, 2012.
- Nash equilibria computation, Mathematics Seminar, IISER Pune, 2012.
- Introduction to Game Theory, DDU, Nadiad, 2012.
- Lower bound on pure strategy Nash equilibrium, Game Theory Seminar, IIT Gandhinagar, 2012.
- Nash equilibria computation with Group Actions, Algorithms and Complexity Theory Seminar, Aarhus University, Denmark, 2011.
- Noncommutative polynomial factorization, STCS Annual Symposium, TIFR, 2011.
- Construction of Some finite normal form games, STCS Seminar, TIFR, 2011.
- Rationality of Galois and irrationality of Nash, STCS Seminar, TIFR, 2010.
- Some Algebraic Properties of a Subclass of Finite Normal Form Games, STCS Seminar, TIFR, 2010.
- Nash equilibria via Polynomial Algebra, Formal Methods Update Meeting, Gandhinagar, 2010.
138, School of Engineering and Applied Science,
Ahmedabad Education Society FP. 4,
Near Commerce Six Roads,
Navrangpura, Ahmedabad - 380 009, India
+91-79-619 11- (144)