# Subhi Dhanasekar

Subhi Dhanasekar is a remote worker on Himalayas, AI/ML Intern at VVDN Technologies, based in India.

Source: https://himalayas.app/@subhidhanasekar

```text
AI/ML intern at VVDN Technologies who compared YOLO object detectors and developed computer vision and image-classification projects.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 1188k+ INR |
| Job categories | Machine Learning Engineer, Computer Vision Engineer, AI Engineer |
| Skills | Machine Learning, Deep Learning, Computer Vision, Image Classification, Object Detection, Transfer Learning, Uncertainty Quantification, Adaptive Conformal Prediction, Model Evaluation, Neural Networks, YOLO V5, YOLOX, ResNet50, VGG16, ViT Base |

## About

```text
At VVDN Technologies, I conducted a theoretical comparison of YOLOv5s and YOLOX-Tiny, deriving their label-assignment mathematics and loss formulations. I assessed accuracy scenarios for dense clustering, small-object detection, and extreme aspect ratios against AP/GFLOPs tradeoffs.

For an Institute Technical Summer Project, I developed an offline face-recognition attendance system using HOG detection and dlib encodings. It included automated enrollment, a Flask REST API, and a dashboard with live streaming.

In my image-classification projects, I reached 90.3% accuracy on Fashion-MNIST with an ANN and improved it to 93.8% by fine-tuning VGG 16. For surface crack detection, I fine-tuned ResNet50 and achieved 99.48% accuracy on unseen data, with results shown in a React dashboard.

My polymer-informatics work applied Adaptive Conformal Prediction to XGBoost, RF, and SVR models, validating 90.4% coverage at 90% confidence. I also fine-tuned ViT-Base for steel microstructure classification, outperforming ResNet50 by 6 points.
```

## Experience

### AI/ML Intern

VVDN Technologies. Jun 2026 - Jul 2026

```text
Conducted theoretical comparison of YOLOv5s and YOLOX-Tiny, deriving label-assignment mathematics and loss formulations. Produced scenario-based accuracy verdicts for dense clustering, small-object detection, and extreme aspect ratios.
```

Skills: YOLO-V5, YOLOX, Object-Detection, Deep-Learning, Computer-Vision, Model-Evaluation

## Education

### Indian Institute of Technology Bombay

B.Tech., Metallurgical Engineering and Materials Science. Grade: 7.42

```text
Pursuing a B.Tech. in Metallurgical Engineering and Materials Science at IIT Bombay, with a current CPI of 7.42 and expected graduation in 2027.
```

## Tech stack

- GitHub
- NumPy
- Pandas
- MySQL
- OpenCV
- React
- Python
- C++
- MATLAB
- TensorFlow
- PyTorch
- scikit-learn
- Keras
- Flask
- Git
- Docker
- Google Colab
- XGBoost
- SciPy
- Optuna
- MediaPipe
- Roboflow
- Seaborn
- Ultralytics

To contact Subhi, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Shyam Sunder](https://himalayas.app/@shyamsunder1): Computer Vision Intern, 10xConstruction.ai
- [Shruti k](https://himalayas.app/@shrutik1): Research Intern Computer Vision, Visvesvaraya National Institute of Technology
- [Harsha Kota](https://himalayas.app/@harshakota): Intern, Infosys Springboard
- [TEJA ADITYA](https://himalayas.app/@tejaaditya1): Python Full Stack Developer Intern, EduSkills
- [PRATHAM YADAV](https://himalayas.app/@prathamyadav2): AI Engineer Intern, Devkraft
- [Shreyas Kocheri](https://himalayas.app/@shreyaskocheri): Machine Learning Intern, Rooman Technologies
- [SAI ROHITH](https://himalayas.app/@sairohith): Trainee Software Engineer, ImageVision.ai
- [Mohit Aditya](https://himalayas.app/@mohitaditya): AI Intern, IRDE, DRDO Ministry of Defence, Govt. of India
- [Ranjith Kumar](https://himalayas.app/@ranjithkumar15): Computer Vision Engineer, Zeus Artificial Intelligence
- [Akshay Agile](https://himalayas.app/@akshayagile): Research Intern, Computer Vision, Centre for Artificial Intelligence and Robotics (CAIR), DRDO
