Hello,

My Name is

Mayukha

my work
img

About me

Hi! I am an incoming master's student in Computer Science at the University of Utah, driven by a passion for leveraging technology to solve real-world problems. My primary areas of interest include sports analytics in computer vision, explainable AI, and deep learning. I am particularly focused on developing AI solutions for healthcare in remote areas with limited resources, aiming to make a meaningful impact in these underserved communities. Beyond academics and research, I am deeply fascinated by the intersection of data science and practical applications, constantly exploring new ways to push the boundaries of what's possible. When I'm not working on my projects, I enjoy listening to the podcast "Linear Digressions," which provides insightful discussions on the latest advancements and trends in data science and machine learning. Explore my portfolio to learn more about my work.

Portfolio

Optimal Sequential AlexNet (OSAN) for Tuberculosis Classification

Developed a customized deep learning algorithm built on the traditional AlexNet. The neural network achieved an accuracy of 99.6% and a Cohen's Kappa score of 0.98 in classifying Tuberculosis-infected chest X-rays.

OSAN Image

Bone Fracture Classification on Musculoskeletal (MURA) Dataset

Developed a bone fracture classification system on the MURA dataset - Stanford ML group. Customized the architecture of InceptionResNetV2 neural network by adding sequential layers.

Bone Fracture Classification Image

Early Cerebral Disease Detection

A Python implementation of a pose estimation model using BlazePose MediaPipe. The model takes input from the webcam or a video file, calculates angles of the body joints, and displays the stage as either "normal" or "affected" depending on the threshold angle. The model also displays the frames per second (FPS) of the video.

Cerebral Disease Detection Image

Gender Classification with YOLOv7

The project on custom object detection using YOLOv7 and gender classification aimed to develop a deep learning model that can detect and classify objects in images or videos. The model was trained using the YOLOv7 architecture and a dataset of images that were manually labeled for object detection.

Gender Classification Image

Object Detection on CCTV Footage

Object detection with Darknet and YOLOv4. Pretrained weights were used to train the model and track objects. The model detects person, bag, tie, backpacks, and handbags. The model can also be enhanced and customized by training it with various weights.

CCTV Footage Detection Image

My Education

Present

Masters in Computer Science

University of Utah

2020 - 2024

Bachelor's in Computer Science

BVRIT Hyderabad College of Engineering for Women

2018 - 2020

High School

Narayana Junior College

My Publications

Journal

A Deep Learning Approach for Enhancing Tuberculosis Classification Leveraging Optimized Sequential AlexNet (OSAN)

Index: Scopus

International Journal of Computing and Digital Systems

Conference paper

Chestnet-TB: A Novel Approach to Tuberculosis Classification from Chest Radiology Using Modified AlexNet

Index: Scopus

Springer

Conference paper

Dynamic gender recognition using YOLOv7 with minimal Frames Per Second

Index: Scopus

International Journal of Modern Physics-B

Conference paper

Improved COVID-19 classification with XceptionNet in radiological data

Index: Scopus

International Journal of Modern Physics-B

Book Chapter

Process and Applications of Structure Based Drug Design

Index: Scopus

Book title: Artificial Intelligence and Machine Learning in Drug Design and Development.

Book Chapter

Process and Applications of Structure Based Drug Design

Index: Scopus

Book title: Artificial Intelligence and Machine Learning in Drug Design and Development.

My Achievements

Best Paper Award

BVRITHCON 23-International Conference on Big Data and Virtual Reality, Information and Communication Technologies

December 23, 2023

img

Microsoft Learn Student Ambassador.

Microsoft.

October 1, 2022

img

Chaitanya Bharathi Institute of Technology Model United Nations 2022.

Chaitanya Bharathi Institute of Technology.

May 7, 2022

img

My Resume

Download my resume to learn more about my education, skills, and experience.

Download Resume

Contact info

Phone

+91 8309953804

Email

mandya.mayukha@gmail.com