🚀 The Lab

#

Welcome to my engineering workspace. Here, I turn complex data challenges into functional code. Each project represents a specific hurdle overcome, whether it’s optimizing C++ memory management or deploying intelligent AI agents.

💡 My Approach

#

• Data-Centric: Every project is grounded in reliable data structures.
• Performance-First: I build with C++ and TypeScript to ensure speed and reliability.
• Scalable: Architected to handle growth and integration.

🛠 Featured Works

#

(Your project cards will automatically appear here based on the files in this folder. Ensure each project file has a unique title and summary in its own front matter.)

“Engineering is the art of turning possibilities into solutions.”

🚀 AI-Powered Library Management System:

#

Overview

#

A robust, menu-driven C++17 console application engineered for efficient library operations. This project bridges the gap between academic exercises and production-ready architecture.

Core Capabilities

#

• Persistent Data Architecture: Implements local file I/O to ensure library records survive across sessions.
• Role-Based Access Control (RBAC): Distinct workflows for Librarians and Students.
• AI-Style Recommendation Engine: Features popularity insights and borrowing analytics.
• Modular OOP Design: Built using modern C++17 paradigms.

Technical Stack

#

• Language: C++17
• Paradigm: Modular OOP
• Storage: Local File I/O

Access the Source

#

👉 View Repository on GitHub

🚀 Student Digital Twin System:

#

Overview

#

The Student Digital Twin System is a sophisticated console-based C++ application designed as an academic analytics engine. It effectively simulates and manages diverse student records (Undergraduate, Postgraduate, and Scholarship students) while providing risk prediction and performance analytics.

Core Capabilities

#

• Polymorphic Scoring Behavior: Uses advanced OOP techniques to handle distinct grading and scoring logic across different student types through a unified interface.
• Smart Analytics Engine: Processes student data to predict academic risk and generate comprehensive report cards.
• Persistent Data Management: Utilizes robust file I/O to store and retrieve complex student records, ensuring data integrity between sessions.
• Modular Separation of Concerns: Architected with a clean multi-file structure:
  • Student: Core model definition.
  • UGStudent, PGStudent, ScholarshipStudent: Specialized classes implementing polymorphic behavior.
  • FileManager: Dedicated I/O handling.

Technical Stack

#

• Language: C++
• Paradigm: Advanced Object-Oriented Programming (OOP)
• Design Pattern: Polymorphism, Inheritance
• Persistence: Persistent Text-Based Storage

Engineering Significance

#

This project demonstrates an ability to move beyond basic coding to architectural design. By leveraging polymorphism, you show how to write clean, reusable, and extensible code that can easily scale as new student categories or analytics requirements are added.

Access the Source

#

👉 View Repository on GitHub

🚀 Amna AI Assistant:

#

Overview

#

The Amna AI Assistant is a cutting-edge, fully functional AI agent designed for high-performance interaction. By leveraging a modern tech stack, this project showcases the ability to integrate complex AI logic with robust web architecture, focusing on clean, scalable code.

Core Capabilities

#

• Modern Web Integration: Built using TypeScript and Vite, ensuring optimal development speed and high-performance production builds.
• Backend-as-a-Service (BaaS): Utilizes Firebase for secure, real-time data management and scalable cloud functionality.
• Modular Codebase: Features a highly decoupled structure, allowing for seamless expansion of features such as voice processing, AI model integration, and UI enhancements.
• Asynchronous Logic: Implements advanced state management and event-driven patterns to provide a responsive, lag-free user experience.

Technical Stack

#

• Language: TypeScript
• Build Tool: Vite
• Infrastructure: Firebase (Firestore, Config)
• Architecture: Modular, Component-Based Design

Engineering Significance

#

This project serves as a demonstration of full-stack engineering proficiency. It shows a deep understanding of combining frontend tooling with backend cloud infrastructure, essential for building modern, intelligent web applications. The choice of TypeScript highlights a commitment to robust, maintainable code quality.

Access the Source

#

👉 View Repository on GitHub

🚀 Pakistan’s Data Science Landscape:

#

Overview

#

This project provides a comprehensive analytical deep-dive into the data science ecosystem within Pakistan. By processing and analyzing a dataset of over 6,000 Pakistani Kagglers, the project uncovers hidden growth trends, maps regional skill distribution, and explores the factors correlating with Kaggle Grandmaster success.

Core Capabilities

#

• Large-Scale Data Analysis: Utilizes advanced Python-based data processing to derive insights from 6,000+ user data points.
• Predictive Modeling: Implements a Random Forest-based predictive model to identify high-potential skill paths for aspiring data scientists.
• Trend & Hub Visualization: Maps the geographic distribution of data science hubs within the country and analyzes the evolution of skillsets over time.
• Actionable Intelligence: Provides a roadmap for researchers and students to understand the requirements for reaching top-tier global rankings.

Technical Stack

#

• Language: Python (3.10+)
• Libraries: Pandas, NumPy, Matplotlib/Seaborn (for visualization), Scikit-Learn
• Machine Learning: Random Forest Regressor/Classifier
• Platform: Jupyter Notebook

Engineering Significance

#

This project demonstrates Applied Data Science. It shows the ability to go beyond simple code execution to perform meaningful Exploratory Data Analysis (EDA) and predictive modeling. It highlights an understanding of how to translate raw community data into strategic insights—an invaluable skill for any AI professional.

Access the Source

#

👉 View Repository on GitHub

🚀 Fruit Signature AI:

#

Overview

#

The Fruit Signature AI project is an applied machine learning initiative that explores image classification and automated feature extraction. By analyzing visual data patterns, this project demonstrates the capability to train models to distinguish between complex visual signatures, bridging the gap between raw datasets and actionable AI predictions.

Core Capabilities

#

• Image Classification: Implements computer vision techniques to process, analyze, and categorize visual input with high accuracy.
• Pattern Recognition: Leverages machine learning algorithms to detect unique “signatures” or features within dataset images.
• Data Preprocessing: Demonstrates proficiency in handling and cleaning image datasets, a foundational skill for real-world AI pipelines.
• Modular Research Workflow: Architected to support iterative experimentation and model fine-tuning.

Technical Stack

#

• Language: Python
• Domains: Machine Learning (ML), Computer Vision
• Core Logic: Feature extraction, model training, and pattern analysis.

Engineering Significance

#

This project highlights your competence in AI model development. By building a system that extracts meaning from image data, you demonstrate the analytical rigor required to solve real-world computer vision problems—a core competency for modern AI engineers.

Access the Source

#

👉 View Repository on GitHub

🚀 Arcane Tic-Tac-Toe:

#

Overview

#

The Arcane Tic-Tac-Toe is a polished gaming experience that bridges low-level logic with modern web accessibility. By blending a compact C++ engine with a responsive browser-based front end, this project demonstrates technical versatility and an understanding of cross-platform integration.

Core Capabilities

#

• Hybrid Architecture: Combines C++ OOP game logic with a sleek HTML/CSS/JavaScript front end for a balanced tech stack.
• Intelligent Features: Includes a “Smart Hint” button for move suggestions, enhancing the user experience.
• Responsive Design: Features an animated, responsive interface optimized for both desktop and mobile platforms.
• Extensible Core: Designed for easy extension, including optional WebAssembly integration for the C++ core and a JavaScript fallback for immediate browser execution.
• Comprehensive Controls: Implements name entry, round-based scoreboards, and turn tracking for a complete gaming experience.

Technical Stack

#

• Core Logic: C++ (OOP)
• Interface: HTML, CSS, JavaScript
• Integration: Optional WebAssembly support

Engineering Significance

#

This project showcases an advanced approach to application architecture. By successfully integrating a C++ engine within a web-based environment, you demonstrate the ability to optimize performance-heavy logic for browser accessibility—a key requirement for high-level full-stack development.

Access the Source

#

👉 View Repository on GitHub

🚀Artificial Intelligence Labs:

#

Overview

#

This repository serves as a technical collection of laboratory tasks and practical implementations completed during the 4th Semester of the BS Computer Science program. It offers a structured deep-dive into foundational AI concepts, ranging from theoretical search algorithms to practical intelligent agent development.

Core Capabilities

#

• Intelligent Agents: Implementation of agent-based models and environmental interactions.
• Search Algorithms: Practical application of classical AI search techniques (e.g., BFS, DFS, A*).
• Knowledge Representation & Reasoning: Exploration of methods to represent and manipulate knowledge within computational systems.
• AI Problem-Solving: Practical exercises demonstrating core AI problem-solving paradigms using Python.

Technical Stack

#

• Language: Python
• Focus: AI Theory and Algorithmic Implementation
• Format: Laboratory Assignments and Practical Implementations

Engineering Significance

#

This project represents a solid foundation in the principles of artificial intelligence. It demonstrates the ability to translate complex AI theories into functional Python code, establishing a baseline of competence in algorithmic design and problem-solving.

Access the Source

#

👉 View Repository on GitHub

🚀 Wine Quality EDA:

#

Overview

#

The Wine Quality EDA project is a comprehensive, notebook-driven analysis of the Wine Quality dataset. This project explores the complex relationship between various chemical properties and wine quality ratings, providing a clear visual narrative that prepares the data for advanced machine learning modeling.

Core Capabilities

#

• Data Integrity Checks: Rigorous inspection of the dataset for missing values, duplicates, and general data quality issues.
• Exploratory Visualization: Utilizes visual techniques to map feature distributions and identify significant outliers.
• Feature Engineering: Compares wine chemistry against quality ratings to isolate the most impactful variables.
• Correlation Modeling: Builds a comprehensive correlation view to understand the underlying structure of the dataset.
• Actionable Summaries: Provides data-driven insights essential for guiding next-step predictive modeling efforts.

Technical Stack

#

• Language: Python
• Platform: Jupyter Notebook
• Focus: Exploratory Data Analysis (EDA), Statistical Visualization

Engineering Significance

#

This project demonstrates your proficiency in data preparation and statistical analysis. Showing a systematic approach—from cleaning to correlation—proves you possess the analytical discipline required to turn raw, real-world data into clear, strategic intelligence.

Access the Source

#

👉 View Repository on GitHub

🚀 Used Car Price Prediction:

#

Overview

#

The Used Car Price Prediction project is an end-to-end regression pipeline designed to solve the challenges of real-world, “messy” data. Unlike polished textbook datasets, this project utilizes raw scraped listings to test the robustness of predictive models, specifically highlighting how regularization techniques prevent model collapse in the face of high-cardinality categorical noise.

Core Capabilities

#

• End-to-End Pipeline: Implementation of a complete regression workflow from raw data ingestion to model deployment.
• Real-World Data Handling: Successfully processes scraped data with significant noise, missing values, and high-cardinality categorical attributes (e.g., specific car models).
• Comparative Model Analysis: Demonstrates the contrast between unregularized linear models—which struggle with complex data—and regularized models that offer stable, accurate predictions.
• Feature Processing: Advanced strategies for handling categorical features to extract predictive signals despite the presence of significant noise.

Technical Stack

#

• Language: Python (3.10+)
• Libraries: Scikit-Learn, Pandas, NumPy
• Methodology: Regression, Feature Engineering, Model Regularization

Engineering Significance

#

This project proves you understand Model Robustness. By demonstrating that you can diagnose why a model “collapses” and fix it with regularization, you showcase the critical engineering mindset needed to build production-grade AI systems rather than just running static scripts.

Access the Source

#

👉 View Repository on GitHub

🚀Python Learning Journey:

#

Overview

#

The Python Learning Journey is a curated repository that tracks my evolution from foundational scripting to professional-grade Python development. This project serves as both a library of learning exercises and a showcase of best practices in modern Python architecture.

Core Capabilities

#

• Object-Oriented Programming (OOP): Demonstrates modular design through class structures, inheritance, and encapsulation to create clean, reusable code.
• Professional File Handling: Implements “Pythonic” file I/O operations using context managers (with statements) to ensure resource safety and memory efficiency.
• Data Serialization: Bridges the gap between static scripts and data-driven applications by mastering JSON serialization for persistent data storage.
• Separation of Concerns: Features a clean architectural split between data models (Entities) and logic controllers (Managers), essential for scalable software development.

Technical Stack

#

• Language: Python
• Paradigms: Object-Oriented Programming (OOP), Procedural Programming
• Techniques: JSON Serialization, Context Management, Modular Design

Engineering Significance

#

This project highlights a disciplined approach to learning and implementation. By transitioning from basic syntax to structured OOP and persistent data management, I demonstrate the ability to write maintainable, production-ready code.

Access the Source

#

👉 View Repository on GitHub