Krishnapriya P S

@cce.edu.in

Assistant professor Dept. of Computer Science and Engineering
Christ College of Engineering

Krishnapriya P S


                  Download Compact PDF  
https://researchid.co/krishnapriya3110

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science, Computer Engineering
6

Scopus Publications

5

Scholar Citations

2

Scholar h-index

Scopus Publications

  • Indian Sign Language Translation using Bidirectional Encoder Representations from Transformers (BERT)
    Krishnapriya P S, G. Purushoath, Harichand Manoj, Divya Bisht, Noel Siby
    Proceedings of 8th International Conference on Computing Methodologies and Communication Iccmc 2025, 2025
    This paper aims to tackle the critical issue of effective communication for the deaf community, specifically addressing the divergence between American Sign Language (ASL) and Indian Sign Language (ISL). The challenge is pertinent due to the growing need for inclusive environments in diverse settings, such as multinational firms where staff may use different sign languages. The motivation lies in fostering inclusion and accessibility. However, persistent challenges include crosssign language collaboration in meetings, uniform communication during training, and limited accessibility to information. Existing sign language recognition systems fall short, translating only individual words with low accuracy. The objective is to create an ISL translation system using BERT, with feature extraction using MediaPipe Holistic pipeline, focusing on inclusive sentence translation without word-byword limitations. The impact is to enhance communication between the hearing impaired and society, offering high-accuracy functionality and an implementable API for widespread use
  • Cutting-Edge Deep Learning for Fashion: Image Classification and Outfit Recommendation
    Kisor G, Maanav Thalapilly, Ketone Agasti, Jagruthi Gontu, Krishnapriya P S
    Proceedings of 3rd International Conference on Sustainable Computing and Data Communication Systems Icscds 2025, 2025
    With so many possibilities, online shopping for stylish clothing might be intimidating. The goal of this project is to create a deep learning-powered intelligent recommendation system that will enhance the user-friendliness and enjoyment of that experience. The recommended technique takes under consideration the individual color, pattern, and design preferences of each user when categorizing fashion goods into groups such as dresses, pants, and shoes. But the system doesn’t stop there. To make sure its suggestions are fashionable and pertinent, it also monitors the prevailing trends on the streets and in runway shows. It proposes complementing pieces that work well together based on color, shape, and stylistic theme using sophisticated AI algorithms. The researchers used a sizable dataset of more than 600,000 fashion photos are divided into eight categories to test it. The categorization component showed an amazing 94 % accuracy rate in correctly classifying things. Experts in fashion provided input to the recommendation engine, evaluating the relevance and coherence of the suggested ensembles. This AI technology has the potential to transform online clothing shopping by bridging the gap between personal preferences and prevailing trends, thereby simplifying the process of creating stylish wardrobes that precisely complement our distinctive styles.
  • Scalable Document Query Assistant Using Ai and Cloud-Based Infrastructure
    Manne Leela Naresh, Sri Kaushik Kesanapalli, Nallagattu Rahul, Ambati Koti Reddy, Krishnapriya P S
    Proceedings of the 9th International Conference on Inventive Systems and Control Icisc 2025, 2025
    The proliferation of digital documents today is challenging in finding contextually relevant information. This study introduces a Document Query Assistant that exploits AI and cloud-based services to deliver rapid, exact, and contextually aware answers to user questions. The approach combines the Google Gemini NLP engine, Google Generative AI Embeddings, and the Facebook AI Similarity Search (FAISS) vector database along with Google cloud resources like Firebase and Google Drive allowing the knowledge base to be refreshed automatically and user interaction to be maintained in real-time. This achieves scale and efficiency. This approach outperforms the latest keyworddriven systems by achieving up to 92 % precision in test cases while managing multiple file formats (PDF, DOCX, CSV) via semantic search and cloud integration innovations.
  • Premature Discovery of Long-Term Prolonged Renal Disorder Using Machine Learning Algorithm
    Loga Priya R, Surya R, Krishnapriya P, Narkeesh Raja S
    2nd International Conference on Emerging Trends in Information Technology and Engineering Ic Etite 2024, 2024
    Prolonged Renal Disorder is a serious worldwide sickness that has an elevated illness Level and fatalities and is linked to several other ailments. Initial identification of Prolonged Renal Disorder is crucial for appropriate intervention and management because the asymptomatic character of the disease in its early stages frequently results in underdiagnosis. Healthcare practitioners may find it useful to use machine learning models' accuracy and effectiveness as a useful tool in doing this. In this work, we suggest using logistic regression to accurately diagnose renal illness that is prolonged. We investigate and contrast a number of methods, such as NB, DT, KSTAR, LOGISTIC, and SVM, in order to maximize precision. To improve the diagnostic performance, provide a novel integrated model based on perceptron. This model effectively dissects errors generated by individual models by combining the strengths of analytical techniques like logistic regression with ensemble methods like Random Forests. This framework's incorporation of increasingly intricate clinical data points to a possible direction for better disease identification. We suggest that the utilization of advanced machine learning models, when combined with a comprehensive analysis of clinical data may considerably improve the precision and dependability of the diagnosis of prolonged renal disorder. This research demonstrates how artificial intelligence may both assist ongoing attempts to improve medical technology and revolutionize healthcare practices.
  • Multi-Disease Prediction and Classifier: A Comprehensive Approach for Healthcare Decision Support
    Sudha S V, Kamali Priya S, Krishnapriya P, Prathiksha P N
    2024 5th International Conference for Emerging Technology Incet 2024, 2024
    The speedy identification and early detection of diseases that are deadly are greatly important when it comes to human life saving. On the other hand, the existence of poor medical system alongside the lack of equal distribution of healthcare presents a barrier towards early disease detection leaving death as the only option. One of the ways to tackle these problems is the utilization of machine learning in detection and analysis of diseases risk is machine learning promising. Utilizing predictive analytics in medicine, practitioners can make accurate and relevant medical insights promptly, relying on the information they have. The work focused on generating prediction models to identify seven most severe illnesses: diabetes, pneumonia, malaria, heart disease, kidney disease, breast cancer, and liver disease, using an algorithm of Random Forest Classifier. Alongside this, the Convolutional Neural Networks were utilized for the detection of malaria and pneumonia. Users can get better knowledge about their health problems and at the same time reduce the access constraints to healthcare by using machine learning. This research is also about designing a web app with the Flask framework and will give its consumers an easy-to-use tool for the simultaneous prediction of all seven diseases. Such a user interface grants better healthcare access and results in the use of proactive measures, as people can take a more active role in their wellness.
  • A Deep Learning-based Smart System for Ornaments and Devices Detection during Check-In of Entrance Exams
    P S Krishnapriya, Gundam Nikitha, Kalla Vishwas Uday Kiran, Kuruba Aparna, Singamsetty Chandu Priya
    Procedia Computer Science, 2024
    Nowadays, individuals are experiencing an era characterized by a pandemic situation. Given the challenging circumstances face these days, it is imperative to develop a real-time model that automatically detects whether candidates are wearing ornaments or carrying any devices before appearing for an entrance examination, as it serves as a vital precautionary measure for our health and safety. The proposed system will function in two stages: firstly, it will employ the YOLOv7 algorithm, which operates on Convolutional Neural Networks (CNN), to detect any gadgets or ornaments worn by the candidate. Additionally, we incorporated Mobile Net and HairNet into the code, utilizing TensorFlow's Keras API. Notably, all the datasets used in this system have been created from scratch. Upon successfully detecting gadgets such as wristwatches, Bluetooth devices, earrings, and other materials, the system will promptly display a warning message, denying entry to the respective individuals. Moreover, the proposed system includes real-time monitoring of the examination hall through CCTV cameras. As a cost-effective, time-saving, and accurate solution, it can be implemented across various examinations to ensure candidates' and invigilators' safety and adhere to examination norms.

RECENT SCHOLAR PUBLICATIONS

  • Scalable Document Query Assistant Using Ai and Cloud-Based Infrastructure
    ML Naresh, SK Kesanapalli, N Rahul, AK Reddy, K PS
    2025 9th International Conference on Inventive Systems and Control (ICISC … , 2025
    2025
    Citations: 1
  • Real-Time News Aggregation and Sentiment Analysis Using Web Scraping and Firebase Integration
    BM Gopal, YN Reddy, CB Siddhartha, R Shaik, K PS
    2025 9th International Conference on Inventive Systems and Control (ICISC … , 2025
    2025
    Citations: 2
  • Cutting-Edge Deep Learning for Fashion: Image Classification and Outfit Recommendation
    G Kisor, M Thalapilly, K Agasti, J Gontu, PS Krishnapriya
    2025 3rd International Conference on Sustainable Computing and Data … , 2025
    2025
  • Indian Sign Language Translation using Bidirectional Encoder Representations from Transformers (BERT)
    PS Krishnapriya, G Purushoath, H Manoj, D Bisht, N Siby
    2025 8th International Conference on Computing Methodologies and … , 2025
    2025
  • A Deep Learning-based Smart System for Ornaments and Devices Detection during Check-In of Entrance Exams
    PS Krishnapriya, G Nikitha, KVU Kiran, K Aparna, SC Priya
    Procedia Computer Science 233, 464-473 , 2024
    2024
    Citations: 2
  • AutoCAP: An Automatic Caption Generation System based on the Text Knowledge Power Series Representation Model
    PS Krishnapriya, K Usha
    International Journal of Computer Applications 975, 8887 , 2015
    2015
  • on Advanced Computing and Communication Techniques for High Performance Applications© 2015 by IJCA Journal ICACCTHPA 2014-Number 4 Year of Publication: 2015
    PS Krishnapriya, K Usha
    2015

MOST CITED SCHOLAR PUBLICATIONS

  • Real-Time News Aggregation and Sentiment Analysis Using Web Scraping and Firebase Integration
    BM Gopal, YN Reddy, CB Siddhartha, R Shaik, K PS
    2025 9th International Conference on Inventive Systems and Control (ICISC … , 2025
    2025
    Citations: 2
  • A Deep Learning-based Smart System for Ornaments and Devices Detection during Check-In of Entrance Exams
    PS Krishnapriya, G Nikitha, KVU Kiran, K Aparna, SC Priya
    Procedia Computer Science 233, 464-473 , 2024
    2024
    Citations: 2
  • Scalable Document Query Assistant Using Ai and Cloud-Based Infrastructure
    ML Naresh, SK Kesanapalli, N Rahul, AK Reddy, K PS
    2025 9th International Conference on Inventive Systems and Control (ICISC … , 2025
    2025
    Citations: 1
  • Cutting-Edge Deep Learning for Fashion: Image Classification and Outfit Recommendation
    G Kisor, M Thalapilly, K Agasti, J Gontu, PS Krishnapriya
    2025 3rd International Conference on Sustainable Computing and Data … , 2025
    2025
  • Indian Sign Language Translation using Bidirectional Encoder Representations from Transformers (BERT)
    PS Krishnapriya, G Purushoath, H Manoj, D Bisht, N Siby
    2025 8th International Conference on Computing Methodologies and … , 2025
    2025
  • AutoCAP: An Automatic Caption Generation System based on the Text Knowledge Power Series Representation Model
    PS Krishnapriya, K Usha
    International Journal of Computer Applications 975, 8887 , 2015
    2015
  • on Advanced Computing and Communication Techniques for High Performance Applications© 2015 by IJCA Journal ICACCTHPA 2014-Number 4 Year of Publication: 2015
    PS Krishnapriya, K Usha
    2015