Active Final Year Projects Showcase
Explore verified, ongoing final year projects advancing across all academic batches. Filter by emerging tech stacks, discover architectures, and explore student innovation.
CodeQuest: A Gamified Mobile Platform for Coding Practice
1 - Lack of Beginner-Friendly Practice Platforms: Existing platforms like LeetCode and HackerRank are designed for experienced programmers, making them intimidating and inaccessible for first-year and second-year CS students who are still learning foundational concepts. 2 - No Mobile-First Coding Environment: Most coding practice platforms are desktop/web-based, creating a barrier for Pakistani university students who primarily rely on mobile devices for learning. 3 - Low Motivation and Dropout Rate: Beginners lack structured progression and engagement mechanics, leading to inconsistent practice habits and early dropout from self-directed coding learning. 4 - Generic and Unhelpful Feedback: When beginners make mistakes, existing platforms either reveal the full solution or provide no explanation, preventing students from developing independent problem-solving skills.
AI-Based Community Hub
The AI-Based Community Hub for Local Services and Micro Jobs is a web-based platform designed to connect residents, service providers, and local shop owners within a specific community such as a town or neighborhood. The system allows users...
Agri Vision 360
Project Description: Farmers often face challenges such as crop diseases, improper use of fertilizers, lack of timely information, and limited access to expert agricultural advice. These issues lead to reduced crop yield and financial loss. In rural areas, farmers may not have easy access to agricultural experts or modern tools for diagnosing crop problems. Functional Requirements: * The system shall allow users to register and log in * The system shall allow farmers to upload crop images * The system shall detect crop diseases using AI techniques * The system shall provide fertilizer and pesticide recommendations * The system shall display weather updates * The system shall allow users to enter crop-related problems via text * The system shall support multiple languages (e.g., English, Urdu) * The system shall display solutions and preventive measures Non-Functional Requirements 🔹 Performance * The system should provide results within a few seconds * It should handle multiple users efficiently 🔹 Security * User data (login, inputs) should be securely stored * Authentication system should prevent unauthorized access 🔹 Usability * The interface should be simple and easy to use for farmers * The system should support local languages * The app should work on low-end smartphones 🔹 Reliability * The system should provide consistent and accurate results * It should work properly even with moderate internet connectivity Target Users * Farmers (primary users) * Agricultural students * Agricultural experts
Cafe Point Of Sale
Cafe Point Of Sale It involves Customer management And Dealing With The Payment Methods And Ordering Catalog
Face recognition based attendance management system
Core Problem: Traditional attendance systems in educational institutions rely on manual roll calls, sign-in sheets, or card-based methods that are time-consuming, prone to proxy attendance (students marking attendance for absent peers), and difficult to maintain accurately over time. Faculty spend valuable lecture time on attendance, and administrative staff struggle with compiling and analyzing attendance records. Core Position: The Smart Attendance System leverages face recognition technology to automate the attendance marking process in educational institutions. By capturing and identifying student faces through a webcam or uploaded image, the system eliminates proxy attendance, reduces manual effort, saves classroom time, and provides real-time, accurate attendance records accessible to both students and administrators through a web-based dashboard.
Secure cs portal
Description 1. Problem Statement: University academic portals often experience performance and accessibility issues, particularly during peak usage times such as result announcements, marks submission deadlines, and periods of high concur...
Intrusion Guard: A Hybrid Machine Learning System for Network Intrusion Detection
Modern computer networks face continuous threats from malware, unauthorized access, and zero-day attacks that traditional signature-based security tools often fail to detect. These systems depend heavily on known attack patterns, which makes them less effective against new or evolving intrusions. The growing scale and complexity of network traffic also create a need for intelligent security solutions that can analyze traffic in real time and detect suspicious activity with high accuracy. This project proposes Intrusion Guard, a real-time intrusion detection system that uses machine learning to classify network traffic as normal or malicious. The system is designed for cybersecurity monitoring in environments where fast and accurate threat detection is critical, such as enterprise networks, laboratories, and institutional systems. It combines supervised and unsupervised learning to improve both known-attack detection and anomaly detection, making it more adaptable than conventional rule-based systems. The technical approach uses a hybrid model built around Random Forest for supervised classification and Isolation Forest for anomaly detection. The system processes network traffic data, extracts relevant flow-based features, and applies trained models to generate predictions in real time. To improve transparency and trust, the system also includes explainable AI output so users can understand why traffic is flagged as suspicious. The expected outcome is a practical and scalable intrusion detection solution that improves threat visibility, supports early warning, and strengthens network defense against both known and unknown attacks.
ZAPNEST: AI-Enabled SaaS E-Commerce Platform for SMEs (MERN Stack Based
ZAPNEST is a web-based Software as a Service (SaaS) e-commerce platform developed to help small and medium-sized enterprises (SMEs) transition from traditional physical businesses to modern digital marketplaces. In today’s rapidly evolving ...
MediTrust : AI Driven doctor recommendation and Fake Review Detection Platform
In recent years, the demand for efficient and intelligent systems in the field of healthcare has significantly increased. However, the existing systems currently in use suffer from several limitations and inefficiencies. These systems are often limited to providing basic search functionality and fail to support disease-based doctor recommendations. Moreover, the presence of fake or unverified reviews reduces the reliability of these platforms. According to the literature review, many systems lack advanced filtering options, real-time doctor availability, and proper integration of appointment scheduling, which makes the overall process inefficient and time-consuming.As a result, users face difficulties in making informed decisions when selecting appropriate doctors, especially due to limited medical knowledge and unreliable feedback systems. This not only reduces the effectiveness of the system but also negatively impacts user satisfaction and decision-making.Although some solutions attempt to address these challenges, they fail to provide intelligent recommendation systems, fake review detection mechanisms, real-time scheduling, and comprehensive doctor information with advanced filtering features.Therefore, there is a strong need for a robust and intelligent system that can overcome these limitations and provide efficient, accurate, and user-friendly solutions.
| Project Information | Status | Batch | Technologies | Action |
|---|---|---|---|---|
|
CodeQuest: A Gamified Mobile Platform for Coding Practice
1 - Lack of Beginner-Friendly Practice Platforms: Existing platforms like LeetCode and Hac...
|
Active | FA23 (2026) |
Flutter
Dart
Firebase
+1
|
Details |
|
AI-Based Community Hub
The AI-Based Community Hub for Local Services and Micro Jobs is a web-based platform desig...
|
Active | FA23 (2026) |
MongoDB
Express.js
React
+1
|
Details |
|
Agri Vision 360
Project Description:
Farmers often face challenges such as crop diseases, improper use of...
|
Active | FA23 (2026) |
|
Details |
|
Cafe Point Of Sale
Cafe Point Of Sale
It involves Customer management And Dealing With The Payment Methods A...
|
Active | FA23 (2026) |
MongoDB
Express.js
React
+1
|
Details |
|
Face recognition based attendance management system
Core Problem:
Traditional attendance systems in educational institutions rely on manual ...
|
Active | FA23 (2026) |
MongoDB
Express.js
React
+3
|
Details |
|
Secure cs portal
Description
1. Problem Statement:
University academic portals often experience performan...
|
Active | FA23 (2026) |
MongoDB
Express.js
React
+1
|
Details |
|
Intrusion Guard: A Hybrid Machine Learning System for Network Intrusion Detection
Modern computer networks face continuous threats from malware, unauthorized access, and ze...
|
Active | FA23 (2026) |
Python
Flask
|
Details |
|
ZAPNEST: AI-Enabled SaaS E-Commerce Platform for SMEs (MERN Stack Based
ZAPNEST is a web-based Software as a Service (SaaS) e-commerce platform developed to help ...
|
Active | FA23 (2026) |
JavaScript
React
Express.js
+3
|
Details |
|
MediTrust : AI Driven doctor recommendation and Fake Review Detection Platform
In recent years, the demand for efficient and intelligent systems in the field of healthca...
|
Active | FA23 (2026) |
JavaScript
Python
Next.js
+6
|
Details |
No Matching Projects Found
No senior projects matched your filter query. Try searching with different keywords, removing specific technologies, or selecting another academic batch.
Face recognition based attendance management system
Traditional attendance systems in educational institutions rely on manual roll calls, sign-in sheets, or card-based methods that are time-consuming, prone to proxy attendance (students marking attendance for absent peers), and difficult to maintain accurately over time. Faculty spend valuable lecture time on attendance, and administrative staff struggle with compiling and analyzing attendance records.
Core Position: The Smart Attendance System leverages face recognition technology to automate the attendance marking process in educational institutions. By capturing and identifying student faces through a webcam or uploaded image, the system eliminates proxy attendance, reduces manual effort, saves classroom time, and provides real-time, accurate attendance records accessible to both students and administrators through a web-based dashboard.
Primary users who register their faces, view their attendance records, and receive low-attendance alerts
Faculty/Teachers:
Initiate attendance sessions, monitor class-wise attendance, generate reports, and manually override records
Admin/HOD:
Manage the entire system — user management, course configuration, system monitoring, and overall attendance analytics
Primary Focus: The system is built for students in educational institutions (colleges/universities) to streamline their attendance experience and provide transparency in their attendance records.
1- User Authentication & Authorization:
Secure login/signup for students, faculty, and admin with role-based access control (JWT-based authentication)
2- Student Registration with Face Enrollment:
Students register by uploading multiple face images; the system extracts and stores facial encodings in the database
3- Face Detection & Recognition:
Python-based face recognition engine (using libraries like face_recognition/dlib/OpenCV) detects and identifies students from live webcam feed or uploaded images
4- Automated Attendance Marking:
Once a face is recognized, attendance is automatically marked with timestamp, course, and session details
5- Course & Section Management:
Admin/faculty can create courses, assign students to sections, and schedule classes
6- Attendance Dashboard:
Visual dashboard showing attendance statistics, percentages, trends (daily/weekly/monthly) for students and faculty
7- Attendance Reports & Export:
Generate and download attendance reports in PDF/CSV format filtered by date, course, or student
8- Manual Override:
Faculty can manually mark/edit attendance in case of system failure or exceptions
9- Notification System:
Email/in-app alerts for low attendance warnings (e.g., below 75% threshold)
10-Student Profile Management:
Students can view their attendance records, update profile info, and re-enroll face data
11-Admin Panel:
Full system control — manage users, view logs, configure recognition thresholds, and monitor system health
12-Anti-Spoofing Detection:
Basic liveness detection to prevent photo/video spoofing attempts
- 🎯 Real-Time Face Recognition via Webcam:
- No hardware dependency (no biometric devices needed) — works with any standard webcam
- 🛡️ Anti-Spoofing / Liveness Detection:
- Prevents cheating through photos or videos, ensuring only live presence is counted
- 📊 Interactive Analytics Dashboard:
- Visual charts and graphs showing attendance trends, making data actionable for both students and faculty
- 🚫 Proxy-Proof Attendance:
- Biometric face verification completely eliminates the possibility of proxy attendance
- ⚡ Multi-Face Recognition:
- Can identify multiple students simultaneously in a single frame — ideal for batch attendance
- 🔗 Hybrid Architecture (MERN + Python):
- Combines the power of Python's ML ecosystem with the speed of a modern MERN web stack via REST API integration
- 📱 Responsive Web App:
- Accessible from any device — students can check records on mobile; faculty can take attendance from a laptop
- 📧 Smart Notifications:
- Automated alerts when attendance drops below institutional threshold (e.g., 75%), giving students time to recover
- 📄 One-Click Report Generation:
- Faculty and admin can export formatted attendance reports instantly for institutional records
- 🔄 Self-Service Face Re-Enrollment:
- Students can update their face data if recognition accuracy drops (e.g., due to changed appearance)
JWT-based token authentication with refresh tokens
Password hashing using bcrypt
Role-based access control (RBAC) — Student, Faculty, Admin
HTTPS encryption for data in transit
Face encoding data stored securely (not raw images) with encryption at rest
Protection against SQL injection, XSS, and CSRF attacks
Rate limiting on API endpoints to prevent brute force attacks
⚡ Performance
Face recognition processing should complete within 2-3 seconds per student
System should handle concurrent recognition of up to 30-50 faces in a single frame
API response time should be under 500ms for dashboard queries
Database queries optimized with proper indexing in MongoDB
📈 Scalability
Modular microservice architecture (Node.js backend + Python recognition service)
Ability to scale the recognition service independently
Support for 500+ registered students without performance degradation
Cloud-deployable architecture (AWS/GCP/Heroku compatible)
🎨 UI/UX
Clean, responsive design (mobile + desktop compatible)
Intuitive navigation with minimal clicks to perform core actions
Real-time feedback during face capture (bounding boxes, recognition status)
Accessibility standards (WCAG 2.1 basic compliance)
Loading indicators and error messages for all async operations