KARIMNAGAR, JUNE 13, 2025: A Research Project report designed by the students of Jyothishmathi Institute of Technology and Sciences (JITS) Karimnagar (autonomous) has been selected as a regular paper for presentation at the IEEE-2025 Smart World Congress which will be held from August 18-22, 2025, in Canada.
The project titled “Python Programming for Efficient Breathomics Image Processing and Analysis” was designed by students Sharanya Gajjela, Srilekha Kuchana, Namratha Bellam and Shreeja Chintakindi under the guidance of Ravikiran Babu, associate professor, ECE department and T Anil Kumar, professor and principal of the college.
The paper abstract says— Breathomics has emerged as a promising frontier in non-invasive medical diagnostics, focusing on the analysis of biomarkers in exhaled breath. This project presents an approach utilising both traditional machine learning (ML) and deep learning (DL) models to classify human breathing patterns—normal, shallow, and deep— through image-based analysis of breath condensation on cold surfaces. The dataset comprised grayscale images labelled based on visual density and spread characteristics of condensation. Traditional ML models, including Support Vector Machines, Random Forest, and Logistic Regression, were trained using statistical features such as mean intensity, texture variation, and condensation area.
In parallel, a series of deep learning models—including a custom Convolutional Neural Network (CNN) and state-of-the-art transfer learning architectures like MobileNetV2, InceptionV3, ResNet50, EfficientNetB0, DenseNet121, AlexNet AND VGG16 —were trained on raw image data. Evaluation was performed in multiple testing rounds using held-out and out-of-distribution data subsets to measure model robustness and generalizability. Experimental results indicate that DL models significantly outperform traditional classifiers, with custom CNN achieving the highest classification accuracy. This work highlights the potential of image-based breathomics for scalable, contactless respiratory monitoring applications in clinical and home settings.The above paper has been funded by Anusandhan National Research Foundation (ANRF), DST, India.
On this achievement, JITS chairman J Sagar Rao, Secretary J Sumith Sai and other faculty members congratulated the students for their achievement in the international level.
