Saikiruthika G

• Myself Saikiruthika .G, I Completed my B.Tech Electronics and Communication Engineering in SRM with aggregate of 70%. I furthered my education by pursuing a Master's degree in Embedded System Technology achieving an aggregate score

of 76 %.

• Technical Skill

1.Programming languages : Python

2.Machine learning

• My hobbies are playing games, listening to music.

Python Programming, Coursera, NPTEL Cloud Computing

• Teamwork
• Communication

• PPT
• Excel
• Word

• Advanced Techniques for smart phone service and Trouble shooting, 04/21 - 04/22
• Insight of Analog and Digital IC design, 11/14 - 11/19

• Father's Name: Dr.A. Govindarajan
• Mother's Name: Dr.M. Vidhya
• Date of Birth: 12/20/99

• Collaborated with team of [Number] in the development of [Project name].
• Denoising Algorithm for Medical and Ultrasound image
• OBJECTIVE
• Remove noise from original medical and ultrasound images.
• Effectively suppress noise in uniform regions.
• Compare the performance of different denoising techniques.
• METHODOLOGY
• Image Selection : Use the Lena image as the original image and add noise to create a noisy image. Also, create a blurred image for comparison.
• Speckle Reducing Anisotropic Diffusion (Filter) : Implement the SRAD filter to reduce noise in the noisy image.
• Performance Evaluation : Calculate the Peak Signal -to - Noise Ratio (PSNR) , Mean Squared Error (MSE), and Signal- to- Noise Ratio (SNR) to evaluate the performance of SRAD filter.
• Noise Reduction : To reduce noise by 90%.
• Expected Outcomes :
• Improved image quality with reduced noise
• Comparative analysis of different denoising techniques.

Anna University

Smart Agriculture : Agrobot Concept for Smart Farming Practices.

Overview

Smart Agriculture is an innovative approach to farming that leverages technology to optimize crop yields, reduce waste, and promote sustainable practices. Our Agrobot concept utilizes a web- based platform to integrate sensor data, actuator responses, and automation techniques to create a smart farming ecosystem.

Sensor Data

Sensor 1 Sensor 2

.Status : ON Status : OFF

Actuator Control

Actuator 1 Actuator 2

Status : ON Status : OFF

IOT - Based Healthcare Using Machine Learning for food image classification

Overview :

This project leverages the power of machine learning and IOT to develop a food image classification system. The system uses a Convolutional Neural Network (CNN) model, specifically MobileNet V2 to classify food images with high accuracy.

Dataset

The dataset consist of 10,000 food images , divided into:

Training set : 80% (8000 images)

Testing set : 20% (2,000 images)

Results

• Accuracy : The model achieves an impressive accuracy of 90 % on the testing set.
• Performance Metrics : Precision, Recall, F1-Score, and Confusion Matrix are calculated to evaluate the model's performance.