I’m a passionate UI/UX designer, frontend developer, and AI enthusiast with a strong foundation in human-computer interaction (HCI), machine learning, and web development. With a keen eye for design and functionality, I specialize in crafting seamless digital experiences that blend aesthetics with user-centric principles.
What I Offer
- UI/UX Design – Wireframing, prototyping, user research, and designing intuitive interfaces for web and mobile applications.
- Frontend Development – Building responsive and engaging web applications using modern frameworks.
- AI & Machine Learning Solutions – Developing and integrating intelligent features, such as computer vision, NLP, and deep learning models, into applications.
- WhatsApp Automation & B2B Solutions – Automating business workflows to optimize operations and enhance engagement.
Experience & Achievements:
- Runner-up in an International UI/UX Competition – Redesigned the Carlo Rino website, with the prize awarded by Universiti Putra Malaysia.
- Co-founder & Chief Design Officer at Zestral – Leading branding, UI/UX design, and AI-driven solutions for automation.
Developed AI Projects – Sign language classification (YOLO), fetal health classification (ML), and DDoS attack detection (CNN).
Current Focus
Enhancing fairness and inclusivity in LLM-driven interactions.
Let’s Collaborate!
If you’re looking for a freelance designer, developer, or AI consultant, I’d love to work with you! Let’s create something impactful together.
Skills
Experience Level
Language
Work Experience
Education
Qualifications
Industry Experience
This project implements a robust ensemble-based machine learning framework for fetal health classification, integrating automated feature engineering, hyperparameter tuning, drift detection, and explainability techniques. The system preprocesses the dataset by handling missing values, scaling features, and performing feature selection while also introducing polynomial transformations and statistical enhancements. It employs an ensemble of Random Forest, XGBoost, Support Vector Machine (SVM), and LightGBM models, optimizing them using Bayesian hyperparameter tuning to enhance predictive performance. The framework effectively addresses class imbalance using SMOTE and ADASYN resampling techniques, ensuring a fair representation of different fetal health categories. To maintain model reliability over time, a concept drift detection mechanism is implemented, continuously monitoring model performance and triggering retraining when necessary. The system also includes explainability through the Feature Perturbation Explanation (FPEX) method, which helps analyze the impact of individual features on predictions, making the model more interpretable for medical practitioners. Additionally, the framework evaluates the model using accuracy, precision, recall, F1-score, and confusion matrices, offering a thorough analysis of classification performance. This project demonstrates advanced AI techniques, combining automated model selection, real-time performance monitoring, and explainability to create a powerful and interpretable fetal health classification system, showcasing expertise in real-world AI applications.
Hire a Graphic Designer
We have the best graphic designer experts on Twine. Hire a graphic designer in Chennai today.