Fahad | Experience

ARScaner

SwiftUI Object Capture Photogrammetry LiDAR USDZ

ARScaner is a SwiftUI-based iOS application that harnesses Apple's Object Capture and Photogrammetry APIs to perform real-time 3D reconstruction. By integrating LiDAR sensor data with multi-view stereo algorithms, it generates detailed USDZ models from captured image sequences, offering superior accuracy and resolution compared to traditional camera-only scanning methods.

AIOT-Based-Smart-Fridge

Raspberry Pi 4B x3 Temperature and Humidity sensors YOLO Python

Smart Fridge monitors your fridge about temperature and humidity, alerts you when food is about to expire, or when someone steals your food. In addition, it can generate a recipe based on items in the fridge with the help of OpenAI API.

Voice Command Fingerprinting - Attack and Defense

Wireshark BuFLO scikit-learn

Implemented the VCFP (Voice Command Fingerprint) attack and BuFLO defense to analyze voice assistant network traffic, showing how encrypted packets can reveal voice commands and how BuFLO mitigates this traffic analysis.

MedConvFormer : Hybrid CNN-Transformer to Distinguish COVID-19, Normal, and Pneumonia from chest X-ray images

Python EfficientNet-B0 Vision Transformer (ViT)

Implemented a novel hybrid deep learning architecture that uniquely combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) for medical image classification.

Walton-AI: Local conversational AI and Cosine Similarity based Knowledge Management System

Python Langchain LangGraph llama.cpp

Optimized a high-performance RAG pipeline (Corrective RAG) utilizing the Llama-3.2-3B LLM, achieving a 70% reduction in memory requirements (from 12GB to 3.5GB) using 8-bit quantization (llama.cpp backed) while maintaining 99.5% of the original model's performance.

AI Long-Term Memory (ALTM)

Python MongoDB Atlas PageIndex

ALTM has Agentic Routing (PageIndex), Dynamic Importance Decay, and Automated Memory Merging to ensure your agents remember what matters and forget what doesn't.

Automated Chest X-Ray Report Generation Using Vision-Language Models

Python MongoDB Atlas PageIndex

A research project exploring automated generation of chest X-ray diagnostic reports using various Vision-Language Models (VLMs) and CNN backbones with distillation and finetuning.

Real Time Image Pattern Detection and Recognition using OpenCV and CLIP Embeddings

OpenCV CLIP Embeddings YOLOv8 QdrantDB

Developed an end-to-end computer vision system combining YOLOv8 for real-time refrigerator detection, CLIP embeddings for feature extraction, and Qdrant vector database for similarity search.

Early and Late Fusion For Multimedia Hateful Meme Classification

Python ResNet VGG19 DenseNet Transformers

Early and Late Fusion techniques for multimodal hateful meme classification by integrating visual features from pretrained CNNs with textual features from pretrained BERT models.

Multi-class Bangla News Classification using Early Fusion and Late Fusion

Python Bi-LSTM CNN

Implemented Early Fusion with BiLSTM, CNN, and LSTM+CNN and Late Fusion by concatenating the output of BiLSTM, CNN, and BiLSTM+CNN.

Control Sequencer for SAP-1 Architecture

Logisim

Designed a control sequencer incorporating a 6-bit ring counter to facilitate efficient loading of two data values into registers. Integrated user-friendly buttons for voting and ensured accurate tallying and display of results in real time.

Microcontroller and IoT Projects

Mosquitto MQTT ESP32 Arduino whisper.cpp AC Relay Wifi Module

Developed an AI-based-voice controlled over-the-internet Automatic Warehouse Switching and Monitoring system. Real-time Weather Monitoring and Forecasting system.