STUDENT PROJECTS

Following projects have been made as a part of my academic journey in groups of 2-5 members.

COMPARATIVE ANALYSIS OF DATA AUGMENTATION TECHNIQUES

Course Work: Numerical Analysis
(M.S. in Applied Mathematics)

Evaluated data augmentation techniques and interpolation methods in computer vision, determining the best-performing method based on metrics.
Dataset preparation, augmentation, metric calculation, and statistical analysis were conducted to highlight the impact of interpolation methods on image quality.

Course Work: Applied Statistics
(M.S. in Applied Mathematics)

Performed statistical analysis of RNA sequencing data to identify potential biomarkers, pathways, and gene signatures associated with aging, dementia, and traumatic brain injury (TBI).
Utilized various statistical techniques including differential expression analysis, functional enrichment analysis, correlation analysis, clustering analysis, and diagnostic performance analysis using R.
Gained insights into the underlying biological mechanisms, relationships between genes, biomarkers, and pathways associated with aging, dementia, and TBI, contributing to the development of new diagnostic and therapeutic strategies.

Course Work: Numerical Analysis
(M.S. in Applied Mathematics)

Utilized Hankel Singular Value Decomposition (SVD) and Fast Fourier Transform (FFT) denoising techniques to effectively remove noise from ECG signals.
Improved the accuracy of ECG signal analysis by reducing noise interference, enabling more reliable detection and diagnosis of apnea.
Facilitated early diagnosis and treatment of apnea, leading to better patient outcomes and potentially saving lives.

Course Work: Applied Linear Algebra and Matrix Analysis
(M.S. in Applied Mathematics)

Performed Principal Component Analysis, Principal Component Regression, and Kernel Principal Component Analysis on the Life Insurance Data to reduce the number of features using Pandas, Matplotlib, NumPy, and Math libraries.
Trained the data on various Machine Learning Models such as Logistic Regression, Linear Regression, K-Neighbours Classifier, XG Boost Classifier, Stochastic Gradient Decent Regressor, Artificial Neural Network, Random Forest etc. in order to compare and study the results from on PCA and Kernel PCA.

Course Work: Probability
(M.S. in Applied Mathematics)

Performed data cleaning on the raw data and kept only opening prices of the bitcoin for this project.
Calculated the transition matrix and predicted bitcoin prices using Markov Chains.

Course Work: Programming for Data Science
(M.S. in Applied Mathematics)

Created a python module to develop and analyze mathematical models using Pandas, Matplotlib, NumPy, and Math libraries.
Implemented the Lotka-Volterra and Chemostat model, with the scope of adding more models in the future.

Course Work: Machine Learning and Statistical Theory
(M.S. in Applied Mathematics)

Trained a CNN in order to classify the location of hemorrhage in CT Scans with an accuracy of 68% on the testing set.
Utilized U-Net, a pre-trained model to train a segmentation network with an accuracy of 92% on the testing set.

Course Work: Mathematical Methods and Modeling
(M.S. in Applied Mathematics)

Developed a dynamic system to predict the population growth of whales.
The logistic Model was also deployed on the same database to optimize the model.
The model was studied and compared by changing parameter values.

Course Work: Final Thesis
(B.Tech Biomedical Engineer)

Decision Tree Learning, SVM Kernel Method, and Artificial Neural Network were used to quantify the relationship between arterial pulse signal features and the presence of disease in a subject.
Processed raw signals, developed filters to reduce noise in the collected signals.
Due to the nature of the data, a nonlinear decision function was chosen over a linear decision function.
On the validation set, accuracy was 73% for ANN, 55% for SVM, and 45% for decision tree.

Course Work: Enigma (Project Competition Event) in Technoczar (Technical Festival)
(B.Tech. in Biomedical Engineering)

Deployed a CNN classifier on an image database from Kaggle to determine the presence of Diabetic Retinopathy.
Implemented a data augmentation method and created a generator pipeline in the Keras module, in order to overcome the small magnitude of training data.
On the validation set, accuracy was 70%