kavali kranthi kumar

Agents_Skills_List

February 19, 2026 – Present

Listing out all the skills markdown files from different sources.

Face-Emotion-Analysis

March 14, 2025 – March 14, 2025

Face-Emotion-Analysis — GitHub repository

Explore-Chunking-Techniques

February 11, 2025 – February 17, 2025

Different chunking techniques used to split the larger documents to smaller sub documents.

LLM_and_Agents_Projects

January 29, 2025 – August 7, 2025

LLM_and_Agents_Projects — GitHub repository

Browser-Agents

January 22, 2025 – February 4, 2025

Browser-Agents — GitHub repository

DSA-Practice

December 21, 2024 – January 2, 2025

DSA-Practice — GitHub repository

Explore-RAG

November 16, 2024 – February 28, 2025

This repository showcases various advanced retrieval techniques for Retrieval-Augmented Generation (RAG) systems.

Effective-Deep-Learning-approach-based-on-VGG-Mini-Architecture-for-Iris-Recognition

August 1, 2021 – August 2, 2021

Biometric system is a pattern recognition system that works by collecting biometric data from a user, extracting a feature set from that data, and comparing that feature set to a database template set. Through this paper, we propose a biometric recognition system based on iris recognition. Iris is the most secured and unique biometric trait among other biometric traits. In our work, we have proposed a modified Hough Transform and considered the Mini-VGG Net model without its weights, and trained the network to obtain the best features. Using the Neural Networks, we have performed the classification and obtained Accuracy, Precision, and Recall of 98%, 0.99, and 0.99 respectively. Our experiments were performed on the CASIA Version-1, which includes 756 samples of iris in 108 folders with 7 samples having dimensions 280X320 each.

Iris-recognition-based-on-Gabor-and-Deep-Convolutional-Networks

July 27, 2021 – July 30, 2021

Nowadays, authorizing a person has become a significant need. Authorizing a person based on their behavioral or characteristic traits such as fingerprint, iris, face, etc. has brought in a lot of secure feelings in society. In our work, we present Iris-based Biometric systems that have been considered the most secure and accurate form of identifying an individual because of their unique features and textual richness present in them. In our work, we proposed two modified feature extraction techniques namely Convolutional Neural Networks (CNN) and Gabor filter, and then performed different classification algorithms namely SVM (Support Vector Machine) and Neural Networks (NN), and analyzed the change in accuracies affected by the features extracted from the two different techniques and finally landed with the best combination of CNN-NN with the accuracy of 98%. The CASIA Version 1 benchmark database has been used to perform our experiments for both testing and comparison.

Turkiye-Student-Evaluation-Data-Set

August 11, 2020 – July 30, 2021

Our goal in this project is to group the students based on the similarity of their answers on the survey. Notice that we don’t know how many cluster (group) of students will be. In fact, we will use different methods of clustering to decide the best “natural” number of group of this dataset. We will attempt to perform k-means clustering technique to monitor and assess the student performance and behavior as well as give improvement toward e-learning system in the future. The challenge in this project is that we do not have the labelled data and our algorithm must be able to cluster such that intra cluster similarity must be high and intra cluster similarity must be low.This dataset is based on an evaluation form filled out by students for different courses. It has different attributes including attendance, difficulty, score for each evaluation question, among others. The dataset has 5820 rows and 33 columns.