2025

Permanent URI for this collection

https://escholar.umt.edu.pk/handle/123456789/5171

Browse

Browsing 2025 by Title

Now showing 1 - 20 of 93
  • Thumbnail Image
    Item
    Agnes: advance guardian nexus enhanced system –
    (UMT.Lahore, 2025) ALI HAMZA; ABDULLAH AMIN; JAWAD SHAH; ABDULLAH SAFDAR
    The Human Interactive System Software (HISS) is an intelligent, AI-powered security solution designed to enhance safety in both residential and commercial environments. Motivated by the rising concerns of thefts, unauthorised access, and ineffective traditional surveillance systems, HISS aims to provide a proactive approach to security management .Leveraging computer vision, facial recognition, and IoT integration, HISS is capable of identifying visitors, detecting suspicious objects (e.g., weapons), and interacting with individuals through an automated response mechanism. The system employs a Raspberry Pi and Arduino-based architecture, collecting data from a wide range of sensors (motion, door, boundary breach, smoke/gas, etc.) and cameras. An embedded AI module processes visual input in real time, while a decision engine triggers actions such as notifying the owner, sounding alarms, activating deterrent mechanisms, or logging activities for further analysis. HISS also incorporates a role-based access control system, categorising individuals as owners, admins, members, or guests to provide tailored levels of interaction and security response.Importantly, the system supports offline functionality, performing local processing andoffering secure connectivity through a minimal web interface.Through the integration of hardware, artificial intelligence, and real-time communication, HISSbridges the gap between traditional surveillance and modern intelligent threat response systems.Testing and evaluation confirmed reliable performance with strong accuracy in facial recognition and threat detection, validating its potential as a scalable, utonomous, and cost-effective security solution
  • No Thumbnail Available
    Item
    AI Based Fashion Advisor App (OUTFYT)
    (UMT, Lahore, 2025) Muhammad Faisal , Attique Hassan , Ayesha , Anoushe Adnan and Zainab Rizwan
    Fashion is a fundamental form of self-expression, yet many individuals struggle with selecting appropriate outfits due to overwhelming choices, lack of styling knowledge, and limited access to personalized recommendations. The AI-Based Fashion Advisor App, OUTFYT, addresses these challenges by integrating Artificial Intelligence (AI), Machine Learning (ML), and Facial Recognition to provide personalized outfit and grooming recommendations. The system utilizes deep learning models such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and AI-driven recommendation algorithms to analyze users' wardrobe collections, facial features, and contextual factors like weather and occasions. The app enhances styling decisions by offering tailored outfit suggestions, hairstyle and beard recommendations, and real-time fashion insights. The mobile application is developed using Flutter for cross-platform compatibility and connects to a Django-based backend that serves AI-generated recommendations via REST APIs. Firebase and PostgreSQL are used for secure data storage, while cloud services such as AWS EC2 and Google Cloud host the AI models to ensure scalability and real-time processing
  • Thumbnail Image
    Item
    Ai enhanced collaborative research hub
    (UMT.Lahore, 2025) Kainat Munir; Fatima Ghaffar; Minahil Fatima; Hajira Nadeem; Sana Bibi
    The AI Enhanced Collaborative Research Hub is a platform intended to facilitate easier and more effective research collaboration. It offers tools for document sharing, discussion, and project management in a single location. Utilizing AI and machine learning, it provides smart recommendations overview and chatbot. The system further incorporates version control, atavisualization, and security features to ensure research data safety. With an easy anduser friendly interface, researchers can collaborate comfortably from any device. This projectis designed to bridge research teamwork hallenges and enhance the research process as awhole.
  • Thumbnail Image
    Item
    AI Expense Manager
    (UMT, Lahore, 2025) Arooba Imtiaz, Hassan Sohail, Taimoor Ahmad, Muhammad Hashim Shahid and Muhammad Amaan
    Efficient financial management is an essential part of personal and business operations. Conventional ways of expense tracking are plagued by inefficiencies, inaccuracies, and time waste. This thesis introduces an AI-based Expense Management Software based on Flask and Python that automatically and efficiently tracks finances with increased accuracy and speed. The system under development utilizes machine learning algorithms to categorize expenses intelligently, detect anomalies, and forecast. Utilizing AI-powered automation, the software reduces human error, minimizes intervention, and offers real-time financial information. Django, being an efficient and scalable web framework, forms the core of the system, allowing efficient processing of data and smooth user interaction. The application also integrates stringent security features to safeguard confidential financial information.
  • Thumbnail Image
    Item
    Ai powered - the color insights
    (UMT.Lahore, 2025) Raham Kamal; Laiba Afzal; Shifa Orazi
    The Color Insights project leverages cutting-edge AI and image processing technologies to offer personalized fashion recommendations tailored to an individual's unique features, including skin tone, facial attributes, and personal preferences. In today’s fashion-driven society, selecting the right colors for clothing and accessories is crucial, yet often challenging without expert guidance. This is especially true in regions like Pakistan, where access to professional fashion consultants is limited. Our platform bridges this gap by providing users with a seamless, AI-powered web solution that analyzes uploaded photos and input data to generate customized fashion advice. By offering precise color recommendations for outfits and accessories, The Color Insights enhances users' self-confidence and helps retailers reduce return rates, thus improving customer satisfaction and driving sales. The system is designed for scalability and security, making it accessible to a broad user base while maintaining privacy and data integrity. Through its integration with e-commerce platforms and continuous refinement based on user feedback, The Color Insights aims to revolutionize the way consumers approach fashion, making personalized style accessible to everyone.
  • Thumbnail Image
    Item
    Ai powered 3d body wear marketplace
    (UMT.Lahore, 2025) Shahmeer Khan; Umar Raza Mukhtar; Haider Abbas; Ziaullah
    Online shopping has grown significantly, but choosing the right clothing size and style remains a major challenge. Many customers struggle to find outfits that fit well and match their personal preferences. Existing virtual try-on solutions mostly use 2D images, which fail to provide an accurate representation of how clothes will look on a person. This often leads to ustomer dissatisfaction, high return rates, and wasted time and money for both shoppers and retailers. Additionally, traditional shopping methods require customers to visit physical stores, making the process time-consuming and inconvenient. To solve this problem, we have developed an AI-Powered 3D Bodywear Marketplace that enhances the online shopping experience. Our system uses artificial intelligence (AI), computer vision, and 3D modeling to create a realistic virtual try-on experience. Users can upload their images, and the system analyzes their gender, age, and skin tone to recommend the most suitable clothing options. Additionally, it generates a 3D Avatar object with the user’s face and body shape, allowing them to iew a 360-degree preview of how different outfits will look on them. This helps customers make better purchasing decisions, reducing the chances of returning products. The development of this system involves deep learning techniques such as Convolutional Neural Networks (CNNs) for image processing and 3D reconstruction algorithms to create accurate clothing visualizations. Our platform is designed to be accessible across multiple devices, including (Android and iOS) and web browsers. To ensure a smooth user experience, we have integrated Google Firebase for database management, TensorFlow for AI-based image processing, and Three.js for 3D rendering.This AI-powered marketplace provides benefits to both customers and retailers. Customers receive personalized recommendations and a virtual fitting experience ,making online shopping more convenient and reliable. Retailers can effectively show casetheir products in 3D, attracting more buyers and reducing return rates. The system also saves time and effort for shoppers by eliminating the need to visit physical stores.In conclusion, our project aims to revolutionize the online clothing industry byin tegrating AI and 3D technology. By providing a realistic, personalized, and efficient shopping experience, we bridge the gap between hysical and online shopping. This solution enhances customer satisfaction, improves business operations for retailers, and contributes to the future of e-ommerce.
  • Thumbnail Image
    Item
    AI Powered E-Learning Platform
    (UMT, Lahore, 2025) Muhammad Shmaiam, Anas Imran, Anish Saleem, Muhammad Ashhal Awais and Hassan Mahmood
    Education in the modern, fast-evolving world must adapt, and that includes the measurement of learning. This study proposes a novel AI-based e-learning system with the potential to revolutionize the age-old testing mechanism. A platform that will scan your lecture notes and generate differentiated quizzes, midterms, and finals from them, all of which are differentiated based on what is being covered and how a student best absorbs it. The questions we provide are a result of sophisticated natural language processing and machine learning, so we’re able to make new, varied questions each time a test is administered, ensuring that we don’t have questions that remain the same from test to test, reducing the risk of repetition and cheating. There are two main interfaces here: a teacher interface where teachers have some guidance in uploading material, reviewing and refining AI created questions and tracking progress of students; and a student interface where students can take interactive tests, get instant feedback and watch their improvements over time. This system is based on sound cloud technology, safe data storage, and saves teachers hours, even hours, of work and allows a more vastly immersive and individualized learning experience. As well as technical progress, the study is concerned with the great challenges of fairness, prevention of bias, and data privacy, in order to open up an education which is more human oriented
  • Thumbnail Image
    Item
    Ai recruitter
    (UMT.Lahore, 2025) Muhammad Tayyab; Tahir Muhammad; Abdullah Sikandar; Azeem Amna; Amin Abginay Imtiaz
    In our project, AI Recruiter, we are paying attention to the development of an intelligent platform that would automate early-stage recruitment processes. It is meant to serve HR departments, helping them with screening of candidates as well as holding interviews. This lessens work pressure on the recruiters and aids in faster hiring. The system incorporates AI algorithms in the screening of resumes and the profile of the candidate being applied. It makes sure that only the most targeted candidates are forwarded to the next level. This makes everything systematic and requires less time on the part of companies. The platform is adjustable to different industries as well as job positions. Not only does it have a user-friendly interface, but also the HR teams can implement it in their regular work habits with or without troubles. Artificial Intelligence has introduced significant changes in the recruitment process of people nowadays. The manual ways are being changed into automated and speedy and exact manners of tools. Sourcing, filtering and ranking of candidates are now feasible through the provision of AI. These instruments are based on objective data to discriminate the most fit individuals to occupy a job. They liminate human biasness and they make the selection fair. Not only doesthis make hiring less time consuming, it also becomes objective and uniform. Due to this, a company will be able to create stronger, more diversified teams. Another area that AI assists in the revelation of hitherto obscure talent that could otherwise not be noticed by a manual check. It is also more accurate and efficient since a company can use AI-driven solutions such as the AI Recruiter. The automation also gives the recruiters time to oncentrate on strategic duties rather than those that are repetitive. It also makes sure that the decisions on hiring are based on actual data and performance indicators. This also results in an improved process on the part of the recruiters and the applicants. In general, AI-based recruitments support scalability and decision-making. It changes recruitment into a more intelligence and streamlined process. Through ongoing training, the system ets more refined as time goes by to achieve good outcomes. The result is educed long-term costs and more effective planning of workforce.
  • No Thumbnail Available
    Item
    AI Teaching Assistant
    (UMT.Lahore, 2025) M.Faseeh Ur Rehman; Abdul Moeed Piracha; Muhammad Usama; M. Haris Imran
    The AI Teaching Assistant system is designed with the core objective of enhancing the educational experience through real-time assistance for both students and educators. By leveraging advanced Natural Language Processing (NLP) and machine learning techniques, the system delivers intelligent, personalized support, such as answering queries, generating educational content, and automating repetitive academic tasks. This enables a more efficient and engaging learning environment where students receive immediate feedback and teachers are relieved of routine workloads. This project represents a significant step in integrating artificial intelligence into the traditional classroom model. By bridging conventional teaching practices with AI-driven solutions, it aims to create a hybrid educational environment that is more inclusive, interactive, and accessible to diverse learners. The AI Teaching Assistant is equipped with a user-friendly interface and scalable functionalities, making it suitable for widespread adoption across various educational institutions. Its features are developed to foster deeper student participation and to offer customized learning experiences tailored to individual needs.
  • Thumbnail Image
    Item
    AI-Based Talent Identification and Scouting Web App for Cricket
    (UMT, Lahore, 2025) Muhammad Asad Ur Rehman, Muhammad Abdullah and Abdullah Akram Gondal
    The "CrickScout" is designed to revolutionize the search process by using machine learning and data analysis to evaluate and evaluate cricket players based on their performance statistics. This system automates players’ categorization optimizes the role of the player, and allows a player-player to compare with the AI-controlled metrics. The platform is developed using the Next.js for the frontend, Next Js(API Routes)for the backend, Csv for data management and machine learning models based on Python for predictive analysis. The aim of the project is to provide scouts, coaches and analysts in decision -making on informed decisions and to ensure an impartial and effective process of talents. This solution of the driven AI increases the accuracy of the evaluation of players, streamlines searching and helps to identify the emerging talent based on the performance metrics rather than the subjective judgment. The integration of advanced algorithms ensures that players are fairly evaluated and contribute to the growth and development of cricket at all levels.
  • No Thumbnail Available
    Item
    Ai-driven medical chatbot
    (UMT.Lahore, 2025) Ali Ahmed; Ajmal Riaz; Aleena Karamat
    Access to healthcare is a major challenge, especially in areas with few medical facilities or professionals. The HealthBot project is designed to help by creating an AI-powered chatbot that offers real-time medical guidance. It provides symptom-based advice, first-aid tips, and emergency awareness, making healthcare information more accessible. Using advanced language processing and AI technology, HealthBot delivers accurate, evidence-based responses in a simple, conversational way. It understands user queries and retrieves relevant information from a trusted medical database, ensuring reliable answers. For added functionality, it can also analyze skin conditions through image recognition, helping users identify potential issues. By offering a secure and scalable digital solution, HealthBot reduces dependence on unverified online sources and eases the pressure on overwhelmed healthcare systems. This project shows how AI can transform public health, especially in underserved communities, by making medical support more available and improving health outcomes for everyone.
  • Thumbnail Image
    Item
    Ai-powered attendance & smart assistance
    (2025) Muhammad Shahan Butt; Muhammad Haroon; Rida Ibrar; Asma Amir
    Our AI-Powered Attendance and Smart Assistant project leverages advanced artificial intelligence technologies to revolutionize attendance management in educational institutions. The system combines real-time facial recognition for accurate attendance tracking with an application-based interface for seamless operation. For backend development, we tilized Flask and Fast APIs, while frontend development employs HTML, SS, and React Native for a responsive and user-friendly experience. By ntegrating YOLO for real-time detection and Face Net/DeepFace for facial recognition, the application ensures high accuracy and efficiency. The aim of his project is to provide an automated solution for educational institutions hat saves time, reduces errors, and enhances classroom managem ent. With a focus on scalability and performance, this systemrepresents a modern fusion of AI technologies and applic ation development, offering an innovative approach to attendance tracking.
  • Thumbnail Image
    Item
    Ai-powered real estate platform with renovation services
    (UMT.Lahore, 2025) Bilawal Hassan Dogar; Abdullah Khan; Ali Husnain; Husnain Ali; Muhammad Haris
    Gharbaar Estate is an Artificial Intelligence-based real estate portal that helps to solve one of the main problems in the Pakistani property market -the absence of a single platform to buy/sell a house and secure a renovation service. Maximizing util ization of existing systems: Existing systems are scattered and causes inefficiency in the processes, poor communications and support and no consolidated support. Our project filled this gap through the unification of these services into a single digital platform. Its undamental aspirations are the consolidation of property listings and renovation services, thefacilitation of natural language-based property finding, the provision of AI-basedrenovation recommendations on uploaded property photographs, the association of a userwith verified renovators, and lastly the provision of safe, transparent, and legaltransactions. It is eveloped on MERN stack (MongoDB, Express.js, React.js, de.js),RESNET50 will be used in renovation analysis, NLP will be used to make searchingproperties intuitive, communicate in real-time by using Socket.io, and utilize Google Maps API as the location mapping tool, and it will deploy Render and MongoDB Atlas.The system is self-contained with customized dashboards by buyers, sellers, andrenovators, AI-connective modules of renovation tips, and chat responsiveness. Theresults of the testing demonstrated 86 ercent accuracy in the predictions of therenovation and a 70 percent saving of time in search result using natural language input. These can be seen as results of enhanced user interaction and decision-making whencompared with the old platforms. Conclusively, Gharbaar Estate automates the process fbuying/selling property and carrying out home improvement into an easily navigable AI-supported journey that makes individuals invest wiser and develop trust among all parties. The areas of future improvement are augmented reality-based previewing of renovations and the regional anguage support to make it more approachable.
  • Thumbnail Image
    Item
    Al-ibat-ul-urf
    (UMT.Lahore, 2025) Hamna Shahid; Areej Jawad; Ahad Danish
    AL-IBA-TUL-URF is an advanced e-commerce platform specifically designed for the abaya sector, aiming to provide a seamless and interactive shopping experience. The web platform integrates key technologies such as PHP (Laravel) for backend development, HTML, CSS, and JavaScript for frontend design, and MySQL for efficient data management and mobile app integrates Kotlin. It offers a range of features, including interactive product customization, AI-powered chatbots, voice-to-text integration, 360-degree product views, and role-based access for customers, shop owners, and administrators. The primary objective of AL-IBA-TUL-URF is to bridge the gap between traditional Islamic fashion and modern e-commerce by providing an intuitive and engaging interface. Shop owners can efficiently manage their products, while customers can explore and personalize their purchases with ease. The inclusion of AI-driven assistance enhances user interaction, making the shopping process more dynamic and efficient. This project demonstrates the potential of technology in redefining the modest fashion industry, offering a well-structured and scalable solution for online retailers. By ensuring a user-friendly experience, secure transactions, and comprehensive product management, AL-IBA-TUL-URF sets a new standard for digital commerce in the Islamic fashion market.
  • Thumbnail Image
    Item
    An AI approach for goat breed prediction and price estimation
    (UMT.Lahore, 2025) Hammad Razzaq; Usman Faisal; Adeem Inam
    The project aim is to remove the gap between farmhouses owner and customers by connecting them through an innovative online platform. The proposed system will register different farmhouse owners and customers by connecting them through the development of an innovative online platform. If one wants to sell animals and the other wants to buy, the platform will provide innovative solutions to both. The buyers and vendors ill be connected to bridge the gap between them and sells products and alal animal exchange, especially on Eid-ul-Adha. The buyers will be rovided with a smart Convolutional Neural Network and a machine- learning model. One will be trained to identify breeds of goats. A custom orpus of goat images from different animal markets will be made and a NN ill be trained to achieve desirable results. The second Model will be trained n goat prices with their features like breed, color, and weight. The gression Model will be used to achieve this. For the overall platform, ERN Stack will e used to design interactive designs and functionalities. The project will not nly simplify dairy-related issues but will also be a feasible solution in romoting trading between goat products and Buyers.
  • Thumbnail Image
    Item
    Apply Hub
    (UMT.Lahore, 2025) Muhammad Saqib Hameed; Rana Muhammad Abubakar; Adeel Javed
    The project aims to create an innovative software platform that streamlines the admission process for students applying to medical colleges, universities, private schools, and academies. This solution allows stu dents to input their preferences, academic scores, and interests to receive tailored institution matches. Key features include automated web scraping for real-time admission data, a Retrieval-Augmented Generation (RAG) model for personalized recommendations, and an auto-apply function for seamless application submissions. The platform will also offer user-friendly web application for tracking applications and receiving updates. By enhancing efficiency and simplifying the application process, this software aims to increase students' chances of successful admission to their desired nstitutions.
  • Thumbnail Image
    Item
    Auction.io
    (UMT, Lahore, 2025) Muhammad Raheel, Talha Qaisar, Muhammad Nabeel and Saliha Yasir
    The AI-Powered Online Auction Platform is a web-based system designed to facilitate secure and transparent online auctions while integrating artificial intelligence for automated moderation and bidding. Built using the MERN stack with Next.js, the platform enables users to list items for auction, place bids manually, or utilize an AI-powered bidding bot to bid on their behalf up to a predefined threshold. To ensure compliance with legal and ethical standards, an AI model (Flask based) scans item images and descriptions to detect any inappropriate or illegal content (e.g., drugs, firearms). The auction process follows an incremental bidding mechanism, where the highest bidder wins. If multiple users enable AI auto-bidding, the system ensures a fair competition by prioritizing the first placed bid until outbid. Web Sockets enable real-time updates, ensuring a seamless live bidding experience. Additionally, users can report suspicious items or fraudulent activities, with an admin panel available for moderation. The platform is designed for cloud deployment, ensuring scalability and availability. This project aims to provide a secure, AI-driven, and user-friendly auction experience while preventing misuse and fraudulent activities
  • Thumbnail Image
    Item
    Auto connect
    (UMT.Lahore, 2025) Muhammad Waleed Amir; Hamza Khan; Muhammad Umer —; Muhammad Talha; Muhammad Rafique
    Auto Connect is an innovative web and mobile platform designed to streamline the process ofbuying and selling cars, car accessories and related services in Pakistan. With advanced AI-drivenfeatures, it enhances user experience by providing personalized recommendations, real-time car listings, and secure transactions. Auto Connect simplifies the search for vehicles by offeringverified car inspections, AI-powered price estimations (tentative), and direct communicationbetween buyers and sellers. Imagine effortlessly finding a car, accessing real-time updates onavailability, and making secure payments with confidence all in one place. Auto Connect makescar buying, selling, and trading seamless, bridging the gap between buyer and automotivebusinesses with ease.
  • Thumbnail Image
    Item
    AutoCare+ The Automobile Car Services Platform
    (UMT, Lahore, 2025) Hafiz Saad Tanvir, Misbah Hafeez, Muhammad Waheed and Muhammad Zohaib
    AutoCare+ is a comprehensive, user-centered mobile application designed to address the evolving demands of automobile owners for reliable, efficient, and transparent vehicle service solutions. This platform was developed in response to the frequent challenges car owners encounter, such as identifying reputable service providers, maintaining accurate and accessible maintenance records, and assessing trade-in and resale values with accuracy. The application leverages a combination of advanced technologies—including real-time communication via Api, predictive analytics, and interactive chatbot support—to deliver a high-quality, seamless experience for both vehicle owners and service providers.
  • No Thumbnail Available
    Item
    Business accounting system
    (UMT Lahore, 2025-01-22) Umar Sajjad