Sonvi Assis Noronha

student

BengaluruArtificial Intelligence and Machine Learning
1roles
35skills
1education
5credentials

About

Machine Learning Engineer specializing in Computer Vision and Deep Learning, with experience in hybrid CNN–Transformer architectures, feature fusion systems, biometric recognition models, and deployment-ready AI systems.

Experience

Android App Development using Generative AI

Mind Matrix.io

Feb 2, 2026 – May 16, 2026 · Bengaluru

Developed AI-powered Android applications using Android Studio, Firebase, and Generative AI tools. Worked on mobile UI integration, backend connectivity, and scalable application workflows.

Education

HKBK College of Engineering

Bachelor of Engineering, Artificial Intelligence and Machine Learning

2022 – 2026

Skills

PythonKotlinSQLJavaCJuliaPyTorchTensorFlowCNNsTransformersArcFaceFeature FusionModel OptimizationOpenCVMediaPipeImage ProcessingFace RecognitionAndroid StudioFirebaseREST APIsMobile UI DevelopmentPandasNumPyScikit-learnPower BIGitGitHubGoogle ColabJupyter NotebookVS CodeJetson NanoCross-ValidationOpen-Set RecognitionHyperparameter TuningRecommendation Systems

Projects

SI-FF-ArcNet: Identical Twin Face Recognition (IEEE Published)

Designed a hybrid deep learning architecture integrating Swin Transformer and InceptionV4 using multi-scale feature fusion. Built a 512-D ArcFace embedding pipeline with 5-fold cross-validation and advanced augmentation. Achieved 99.96% validation accuracy and 98.20% F1-score across 50 epochs. Implemented cosine similarity-based open-set recognition for biometric authentication. Technologies: Python, PyTorch, Swin Transformer, InceptionV4, ArcFace Loss, OpenCV.

RakthaVahini—Blood Donation Platform

Developed an AI-assisted blood donation and emergency response application with donor registration, emergency requests, Firebase backend integration, and UI/UX for donor search, notifications, and request management. Technologies: Android Studio, Firebase, Kotlin, Generative AI.

Movie Recommendation System

Built a content-based recommendation engine using TF-IDF vectorization and cosine similarity. Achieved 85% recommendation accuracy through similarity scoring. Technologies: Python, Pandas, Scikit-learn.

Real-Time Semaphore Detection System

Developed a real-time pose-based signal recognition system and deployed it on NVIDIA Jetson Nano for efficient edge inference. Technologies: Python, OpenCV, MediaPipe, Flask, Jetson Nano.