Machine learning techniques may be able to help with checking the accuracy of code problems by providing automated code evaluations that go beyond just checking for correctness. By examining code structure, grammar, and patterns, machine learning algorithms can detect potential deficiencies in students’ comprehension and offer specific guidance to enhance their programming proficiency. These approaches can accommodate the diverse learning styles of individual students and offer tailored education, enhancing their comprehension and application of programming principles across many contexts. The provision of real-time feedback during coding activities has a substantial impact on the educational achievements of students, as it enables them to promptly identify and rectify errors, thereby facilitating instant learning and comprehension. The primary objective of this project is to enable educators to analyze, provide feedback, and evaluate students’ skills through the use of natural language processing (NLP) and deep learning (DL) techniques.
Academic Criteria : Master’s degree in Computer Science/Artificial Intelligence/Data Science or other related subjects. Degree-level mathematics, computer science (or equivalent) required. Applicants should be good at programming.
Genome rearrangement problems is a class of combinatorial optimization problems where a genome is modelled using a sequence and a genomic mutation is realized using sequence rearrangement operations. The fundamental problem is to find the minimum number of rearrangement operations required to transform a given sequence to another. These problems have applications in Bioinformatics, Interconnection networks, Music synthesis, Optical character recognition, and Quantum computing.
Academic Criteria : Master’s degree in Computer Science, Mathematics, or other related subjects. Good understanding in Design and Analysis of Algorithms and Discrete maths.
The widespread adoption of smart contracts within blockchain technology has transformed digital transactions, introducing revolutionary changes. However, the intricate nature of these contracts presents security challenges that result in vulnerabilities on a global scale. Despite the availability of both static and dynamic security analysis tools, persistent issues with smart contracts underscore the imperative for thorough pre-deployment analysis. Static tools meticulously examine code before deployment, while dynamic analysis observes the run-time behaviour during execution. It is crucial to address the requirements of multiple languages and environments to ensure comprehensive security measures. This emphasizes the necessity for a robust pre-deployment and post-deployment analysis that accommodates diverse linguistic and environmental considerations.
Academic Criteria : Master’s degree in computer Science with good understanding in Blockchain, Cryptography and distributed system .
This involves deploying advanced authentication protocols and technologies to safeguard against unauthorized access and cyber threats, thereby maintaining the reliability and safety of IIoT systems.
Academic Criteria : Academic Requirements: We are looking for candidates with an M.Tech degree in Computer Science and Engineering (CSE) or Electronics and Communication Engineering (ECE). Those who have demonstrated an interest in learning and advancing in the field of cybersecurity, as evidenced by published research papers or related projects, will be given special consideration in our evaluation process.
Developing an innovative system for Abnormal Human Action Recognition by seamlessly integrating advanced techniques in object tracking and behavioral biometric analysis. Leveraging state-of-the-art computer vision methodologies, the system can employ robust object detection models to identify and track individuals within a closed and dynamic environment. Subsequently, the project delves into behavioral biometric analysis, extracting key features from the tracked objects to discern patterns inherent to normal human actions.
Academic Criteria
Identify the minimum number of events needed to rearrange one genome into the other