Vignesh S. Profile

0.0

(0 reviews)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$15 USD / hour

eindhoven,

netherlands

$15 USD / hour

It's currently 7:18 PM here

Joined July 30, 2020

0 Recommendations

Vignesh S.

@vigneshs95

0.0

(0 reviews)

0.0

$15 USD / hour

eindhoven,

netherlands

$15 USD / hour

N/A

Jobs Completed

N/A

On Budget

N/A

On Time

N/A

Repeat Hire Rate

Machine Learning Engineer

Master’s graduate of Computer Science & Engineering and specialized in Machine Learning. Worked with multi-cultural teams in the industry and developed deep learning solutions for real-time video processing. Excited to work as a freelance ML engineer and develop cutting edge AI solutions for challenging projects from around the world!

See all Python Developers in Netherlands

Contact Vignesh S. about your job

Portfolio

6920473

• Built a real-time activity recognition system using deep learning models for patient monitoring.
• 86% accuracy even with limited training dataset.
• Implemented factorized 3D-CNN deep learning model in custom Linux environment.
• Analyzed, cleaned and processed 550 videos into 8050 video clips and optimized the model.

Tools: PyTorch, Python, FFMPEG, OpenCV, Git, Jupyter

Real-time activity recognition using deep learning

• Achieved 76% macro-mean AUROC value for classifying 14 diseases in X-ray images.
• Processed 1000 X-ray images using OpenCV, implemented DenseNet CNN model and cross-entropy loss function from scratch for training.
• Visualized the output through GradCam and displayed learned features in the images.
• Tools: Tensorflow, OpenCV, Python, Jupyter

Chest X-Ray Medical Diagnosis with Deep Learning

• Achieved 87% mean sensitivity and 98% mean specificity score for segmenting 3 types of brain tumors in MRI images.
• Processed 484 MRI images in Python and augmented them through patch extraction.
• Implemented 3D U-Net deep learning model and multi-class soft dice loss function from scratch in Tensorflow for object segmentation.
• Tools: Tensorflow, Python, Jupyter

Brain Tumor Segmentation on 3D MRI Images

6920473

Real-time activity recognition using deep learning

Chest X-Ray Medical Diagnosis with Deep Learning

Brain Tumor Segmentation on 3D MRI Images

Reviews

Changes saved

No reviews to see here!

Experience

Philips Research

May 2019 - Jan 2020 (8 months, 1 day)

Thesis title: "Activity recognition in videos for patient monitoring using deep learning" • 86% accuracy even with limited training dataset. • Implemented factorized 3D-CNN deep learning model in custom Linux environment. • Analyzed, cleaned and processed 550 videos into 8050 video clips and optimized the model. • Tools: PyTorch, Python, Linux, Git

Netscalers

Aug 2018 - Oct 2018 (2 months, 1 day)

• Developed custom automated data processing pipelines for 2 clients in Linux environment. • Processed dataset of 2.000.032 transaction data & 19.275 product data entries for 2 clients. • Designed, implemented and tested the software modules in an agile development team. • Tools: Python, Keras, Pandas, Linux, Jira, Git