Scribd
Upload
16 views2 pages

Phase 2 - Week-4 ANKI

The document is a weekly project report for Ankitha K S, a student at the Bangalore Institute of Technology, detailing her work on a vitamin deficiency detection model. The report outlines the data splitting strategy and the selection of a Convolutional Neural Network (CNN) architecture, specifically using pretrained models for effective image classification. The project's aim is to facilitate early detection of vitamin deficiencies through digital health screening applications.

Uploaded by

a66824966
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views2 pages

Phase 2 - Week-4 ANKI

The document is a weekly project report for Ankitha K S, a student at the Bangalore Institute of Technology, detailing her work on a vitamin deficiency detection model. The report outlines the data splitting strategy and the selection of a Convolutional Neural Network (CNN) architecture, specifically using pretrained models for effective image classification. The project's aim is to facilitate early detection of vitamin deficiencies through digital health screening applications.

Uploaded by

a66824966
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

BANGALORE INSTITUTE OF TECHNOLOGY

(Affiliated to Visvesvaraya Technological University – VTU)


K.R. Road, V.V. Puram, Bangalore – 560 004, India. Phone: 26613237 Fax: 22426796

DEPARTMENT OF MASTER OF COMPUTER APPLICATIONS

Project Phase 2
Project Weekly Report for the Academic Year 2024-25
(2023 Batch)

Name : ANKITHA K S

USN : 1BI23MC011

Project Title : VITAMIN DEFICIENCY DETECTION

From : 20-06-2025 To: 28-06-2025

Details of work done

1. Data Splitting: To prepare a reliable vitamin deficiency detection model, the


dataset was divided into three subsets: 70% for training, 20% for validation, and
10% for testing. This approach ensures that the model has sufficient data to
learn meaningful patterns while also providing separate datasets to fine-tune
and evaluate performance. The validation set helps in adjusting
hyperparameters and monitoring for overfitting during training, while the test
set, which remains completely unseen during the development process, serves
as a final benchmark to assess how well the model generalizes to new, real-
world data.

Vision : To transform young graduates into skilled computer professionals to meet industrial and societal needs.
Mission: To enhance the Teaching learning process to meet quality education in the field of computer applications.
To impart the knowledge in current technologies to meet the industrial needs.
To inculcate ethical values and leadership qualities for the betterment of society.
2. Model Selection: For this project, a Convolutional Neural Network (CNN)-
based architecture was chosen due to its proven effectiveness in image-based
classification tasks, especially within the medical domain. Specifically, pretrained
models such as ResNet50 or EfficientNet were selected for their balance of high
accuracy and computational efficiency. By using transfer learning, these models
were fine-tuned on a dataset containing labeled images that exhibit visual
symptoms of various vitamin deficiencies, such as discoloration of the skin,
abnormalities on the tongue, or changes around the eyes and nails. This approach
enables early and non-invasive detection of deficiencies like Vitamin B12,
Vitamin D, and iron, making the model a valuable tool for digital health screening
applications.

Prof. SUMA N R Dr. H.K Madhu


Assistant Professor Associate Professor
BIT, Bengaluru Head, Dept. of MCA
BIT, Bengaluru

……………………….. ………………………..
(Internal Guide) (HOD, Dept. of MCA)

Vision : To transform young graduates into skilled computer professionals to meet industrial and societal needs.
Mission: To enhance the Teaching learning process to meet quality education in the field of computer applications.
To impart the knowledge in current technologies to meet the industrial needs.
To inculcate ethical values and leadership qualities for the betterment of society.

You might also like