About Centre

Data science research Centre has started in the year 2021, by encompasses with data preparing, cleansing, aggregating, and manipulating the data to perform advanced data analysis. Additionally, Data Science Centre has grown into a significant research facility with high configured systems and a multidisciplinary staff of experts with specializations in Data Science, Social media analytics, Data analytics, Machine Learning, Natural Language Processing, Graph Theory, Neutrosophic set and systems, Stochastic models, Theoretical Computer Science. To incorporate the art of Data Science in the field of research to bring out innovations in all scientific disciplines.

Facilities Available

Intel Server Configuration

• Server Board: S2600WFT
• Processor: Intel Xeon Silver4210 CPU @2.20GHZ 2.19GHZ
• RAM: 64 GB HDD :1863 GB

Details of Completed/Ongoing Projects

1. Detection of Voice changes using Acoustic Analysis (Ongoing) Voice is the most natural way to express one’s thoughts, but thyroid disease degrades the quality of one’s voice. Thyroid nodules are lumps of thyrocytes in the thyroid gland that may press the voice box, which results in voice change. To visualize the growth in the thyroid gland, the modified 3D Level Set Volumetric Segmentation (3D LSVS) techniques were used. Thyroid nodules’ severity can be measured based on the volume of the lump. An inferential statistic occurs with confidence intervals between the substance of very high concern (SVHC), Systemic Viral Infection (SVI), STMW and SVHD using Multivariate analysis (MVA) and testing. Acoustic analysis measured the voice changes. Different prevalent methods are compared concurrently and the results of quantitative analysis are better.

2. Prediction Model for a Good Learning Environment (Ongoing) It consists of a series of modules; data preprocessing, data normalization, data split and finally classification or prediction by the RF classifier. The preprocessed data is normalized using minmax normalization often used before model fitting. As the input data or variables are measured at different scales, it is necessary to normalize them to contribute equally to the model fitting. Then, the RF classifier is employed for course selection which is an ensemble learning method and k-fold cross-validation (k = 10) is used to validate the model. The proposed Prediction Model for Course Selection (PMCS) system is considered a multi-class problem that predicts the course for a particular learner with three complexity levels, namely low, medium and high. It is operated under two modes; locally and globally. The former considers the gender of the learner and the later does not consider the gender of the learner. The database comprises the learner opinions from 75 males and 75 females per category (low, medium and high). Thus the system uses a total of 450 samples to evaluate the performance of the PMCS system. Results show that the system’s performance, while using locally i.e., gender-wise has slightly higher performance than the global system. The RF classifier with 75 decision trees in the global system provides an average accuracy of 97.6%, whereas in the local system it is 97% (male) and 97.6% (female). The overall performance of the RF classifier with 75 trees is better than 25, 50 and 100 decision trees in both local and global systems.

3. Android Application to Increase Faculty Performance Using Gamified Leaderboard (Completed) In today’s world, Android Applications have changed our lives and have become an indispensable part of our lives because of its specialty to simplify our routine work, thereby saving our time and improving us professionally. Currently most of the Ranking system in any organization recruitments, Faculties performance are paper based, which costs time and resources. Criteria’s are developed, printed, and then collected data, entry, editing, cleaning, which is time consuming and costly. Proposed application is the starting to avoid those circumstances which have been currently faced by any organization. This application all about ranking and managing the faculties’ research works to identify top, deserves performers across the College campus. This program keeps the faculties driven by displaying their individual scores with an overall leaderboard, which motivates and helps to achieve their goal. The user has to sign up with their details and once it's done, a verification mail will be sent to their respective email Ids. Unless the user is verified, they won’t be able to proceed. Then it will be directed to the home screen where they can view their overall performance leaderboard, coding leaderboard, Mentorship leaderboard etc. They can avail leave and mark attendance through it. The faculties will add their individual achievements in the respective fields. After that, a request will be sent to the admin app, where the details given and the certification will be verified and approved. If the admin declines the request, the results will not be reflected in the leaderboard. Its use in the teaching-learning process has been carried out in parallel with active methodologies, and in the use of learning management systems that include various elements of the animation to be integrated for ranking and evaluation activities. The gamified programmatic contents idea is presented, and it specifies a level-based programmatic contents structure as well as other elements used, such as points and different types of rewards, the progress bar, and the leaderboard. These contents on the platform will help the organization for evaluation and motivate the faculties to learn and explore. KEYWORDS - Android application, College faculty management system, gamified leaderboard, Online leave management Team Mentor - Ms. N. DEEPIKA, AP/CSE Team Members - KISHORE THEERAJ V J, KOUSHIK EASWAR D and NARAYANI S

4. Meta-Data-Based Recommendation System for Movies(Completed) The amount of data on the World Wide Web is growing exponentially. Users often get lost in this vast ocean of data. Recommendation systems are used to filter out valuable information from a large amount of data. According to the user's choice, the work proposes a movie recommendation system in this document. The proposed system aims to provide personalized movie recommendations selected by users. Generally, the underlying recommendation system uses the following factors to make recommendations: user preferences, called content-based filtering, or similar user preferences, called collaborative filtering. The proposed work uses a hybrid filtering, a combined approach of content and collaborative filtering Technology, to improve and expand user recommendations. KEYWORDS - Recommendation systems, Hybrid recommender, Meta Data-Based Filtering Team Mentor - Ms. N. DEEPIKA, AP/CSE Team Members - MORRIS DARREN, KARTHICK RAJ D and KARTHIKEYAN M

Seminar on Artificial Intelligence and Data Science

The Centre for Artificial Intelligence and Data Science organized the power seminar on “AI & Data Science”. The main objective of the programme is to bring together the Instructor Led Live Learning and Personalized self-paced Learning Experiences to help the student build requisite skill across. Resource Person: Mr.RajKumar Kalaimani, CITIUS Technologies Date: 23rd April 2022 The trainer focused on various concepts which are listed as follows: 1. Basics of Artificial Intelligence 2. Data Science 3. Real Time Application in AI & Data Science

Click here to know more...

Enquire Now