2025

Permanent URI for this collection

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

Browse

Now showing 1 - 20 of 93

SMART DATA FUSION OF HANDWRITTE
(UMT, Lahore, 2025) Muhammad Bilal, Bisma Amir, Mehmood Hassan and Yalmaz Khan
This project, Smart Data Fusion of Handwritten Text, aims to convert handwritten text into digital format using OCR, CNN, and LSTM networks. It automates data extraction, reduces manual errors, and enhances efficiency in industries like logistics and healthcare. The system recognizes handwritten text, detects key fields, and applies NLP-based error correction, ensuring structured and accurate data output. Designed for easy integration with existing databases, this solution helps businesses transition from manual to automated document processing
Post gen AI
(UMT.Lahore, 2025) Syeda Nimra Zamir; Baseerat Ghazanfar; Hassan Riaz; Rabail Waqar
Post Gen AI is an AI-based content creation and scheduling platform that assists social media managers, content creators, and businesses in automating their social media campaigns. The AI uses artificial intelligence to generate high-quality, engaging, and personalized content based on user interests. The platform integrates well with most social media platforms so that users can schedule posts. The platform also has analytical capability, which allows one to track engagement and refine content strategies. With the integration of AI-powered content creation and automated scheduling and performance analysis, Post Gen AI simplifies productivity complexity and cuts to the chase in the digital marketing process. The project will focus n filling the gap that currently exists between AI-powered creativity and best-in-class content delivery
Jadeed Gadgets
(UMT, Lahore, 2025) Muhammad Hasnain, Ayesha Mustafa and Bushra Bibi
Jadeed Gadgets is a state-of-the-art, AI-powered e-commerce platform designed to offer a seamless, secure, and personalized shopping experience for three distinct user roles: Admin, Seller, and Buyer. With its scalable and user-friendly architecture, the platform stands out through its innovative features, including visual search that allows users to find products using images, a competitive pricing system that monitors market prices and alerts sellers, and a recommendation engine that tailors product suggestions based on user behavior. Aimed at solving challenges in product discovery, inventory management, and pricing, Jadeed Gadgets enhances both customer satisfaction and seller competitiveness through real-time tracking and analytics. Its robust, future-ready design ensures strong security, high performance, and adaptability to evolving market trends, making it a sustainable solution poised to lead the e-commerce industry.
Future Metropolis
(UMT, Lahore, 2025) Hammad Ahmad Niaz, Hamza, Hamza Ali and Tanzeela Akbar
This project focuses on developing a smart city system to improve irrigation, waste management, and traffic control using modern technology. Efficient irrigation will help save water, while smart waste management will reduce pollution. An advanced traffic system will ease congestion and prioritize emergency vehicles. IoT and AI-based solutions will be used to make these systems more effective. The project aims to create a sustainable and eco-friendly urban environment. Overall, this smart city model will improve living standards and resource management.
CourseBot
(UMT, Lahore, 2025) M. Afzal Hashmi, M. Yousaf, M. Hamid Nadeem and M. Shoaib
Real-time ai lie detection.
(UMT.Lahore, 2025) Abdul Wasay; Noraiz Asad; Javeria Noor; Uzair Shahid; Sarmad Imtiaz
Deception detection plays a critical role in criminal investigations, legal proceedings, and security operations. Traditional lie detection methods such as polygraph tests often suffer from limitations, including subjectivity, invasiveness, and dependence on physiological signals that can be consciously controlled. This project proposes a Real-Time AI Lie Detection system that utilizes facial micro-expression analysis to identify potential deception during interrogations. The system captures a suspect’s facial expressions via webcam, processes them using a deep learning pipeline integrating YOLO and XGBoost models, and predicts deception based on temporal emotion patterns and rule-based heuristics. Developed using a combination of Python (Media pipe, OpenCV, Flask API) and C# (ASP.NET MVC), the application features a secure investigator login, suspect management, real-time video analysis, and database logging for future etrieval. Testing demonstrated an accuracy of approximately 90% on validation datasets, enabling reliable classification of truth and lies within wo seconds. While the system enhances investigator decision making by providing fast and interpretable insights, it does not replace human judgment. Future improvements include multimodal integration of audio and physiological data, real-time video stream smoothing, explainable AI features, and compliance with legal and ethical standards to ensure responsible deployment in forensic and security domains.
Quick mart
(UMT.Lahore, 2025) Waqas Ali; Mamoon Ayoub; Amna Shah; Muhammad Ali
QuickMart is a smart, Al-powered e-commerce platform developed to enhance the onlinegrocery shopping experience in Pakistan. The primary objective behind building QuickMart wasto address common inefficiencies in traditional e-commerce systems such as delayed customersupport, stock mismanagement, and poor user engagement-by leveraging modern webtechnologies and artificial intelligence. At its core, QuickMart is designed to provide a seamless,real-time shopping experience that benefits customers, vendors, administrators, and deliverypersonnel alike.One of the standout features of QuickMart is its integration of an Al-powered chatbot thatprovides instant customer support on the platform. Unlike conventional systems where usershave to wait for a representative, QuickMart's chatbot is available 24/7 to answer queries, guideusers, and help resolve common issues in real-time. Another key innovation is the demandforecasting module. Using Al models and historical sales data, the system can predict productdemand in advance, allowing vendors and admins to manage inventory more accurately andreduce losses from overstocking or stckouts.The system is built using a modern MERN (MongoDB, Express.js, React.js, Node.js) stack, withadditional technologies like Firebase for real-time otifications and Socket.IO for real-timecommunication. A role-based ashboard ensures that every user-whether a customer, vendor,admin, or ider-has access to a personalized interface tailored to their needs. stomers anregister, browse products place orders, and track their deliveries in real ime. Vendors manageinventory, receive stock predictions, and monitor salesanalytics, while riders update deliverystatuses and communicate with ustomers and admins
Islam Orbit: Your Personalized Islamic Learning Hub
(UMT, Lahore, 2025) Aymen Zahra Hashmi, Tayyab Hashmi, Usman Ghani and Hammad Saleem
Islam Orbit is an AI-driven platform for Islamic education for families and children utilizing multimedia elements, gamification and adaptive learning to boost engagement. Traditional methods of Islamic education often lack of communicating and interactive features, which makes them less attractive and learning technique to younger audiences. Islam Orbit remedies this by providing customized learning paths, Quran recitations, and animated guides for prayer, and gamified evaluations. Developed this project by using Flutter, Firebase Fire store, and AI technologies such as PyTorch and TensorFlow, the platform certifies real-time data management, cross platform compatibility, and adaptive learning experiences. Important stakeholders include Islamic educational institutions, children, parents, and community leaders, who can take benefit from vibrant educational content and community-centric features, including forums and competitions.
POSifyAi.
(UMT, Lahore, 2025) Arham Ahmad, Nawwal Aftab Waseer and Misbah Tahir
The POSifyAi. system implements artificial intelligence to enhance points of sale management in retail and hospitality operations by integrating MERN stack with MongoDB, Express.js, React.js and Node.js. A cloud-based framework underlies the system which distributes data efficiently moreover the interface is user-friendly and the AI system functions through automated chat support for both sales and customer service sections. POSifyAi employs predictive analytics to conduct automatic order management and business insights provide real-time data for inventory management security optimization and transaction efficiency. POSifyAi uses its abilities to correct traditional POS system flaws by supporting inventory management and AI features while providing modern interfaces that build an intelligent scalable user-friendly system for operation efficiency and business growth opportunities.
Reality Wear
(UMT, Lahore, 2025) Fatika Azam, Rubab Ali and Subhan Abdullah
The project "Reality Wear" focuses on integrating Artificial Intelligence (AI) within e-commerce to enhance user experiences through personalized recommendations, visual search capabilities, AR, and interactive chatbots. This integration aims to revolutionize consumer interactions with services and products, making processes more efficient, tailored, and engaging.
Fit Fusion
(UMT.Lahore, 2025) Uswah Sajjil; Amna Tariq; Noor Fatima
Fit Fusion is a technology designed to transform the fitness industry by boosting member engagement and optimizing gym and fitness facility operating efficiency. This provides ongoing management of memberships , fees, and trainer assignments in addition to a personalized and engaging experience by centralizing member data. Fit Fusion's AI-powered training programs and real-time progress tracking help members accomplish their goals more quickly. Its safe and adaptable architecture allows it to meet the evolving needs of fitness businesses, fostering long- term growth and data-driven decision-making. Fit Fusion combines state-of-the-art technology with physical training management to give members and staff a more ntelligent, connected, and effective gym experience.
SKINSCAN - AI POWERED SKIN DISEASE DETECTION AND CONSULTATION SYSTEM
(UMT, Lahore, 2025) Ali Khalid, Zara Abrar, Hurria Khaliq, Muhammad Saad and Aqsa Ghafoor
A large number of people worldwide suffer from skin conditions that need correct identification to minimize serious medical issues. Health risks become more paramount because rural areas lack dermatologists together with delayed medical interventions. Several people suffer from restricted access to affordable and timely dermatological care which results in misdiagnoses and self-treatment with adverse effects on their health conditions. The AI-powered SkinScan was developed as a web and mobile application which offers users immediate skin disease detection capabilities together AI-based consultation through Machine Learning (ML) and Deep Learning (DL). Users can upload skin images through the system that uses Convolutional Neural Networks (CNNs) to diagnose skin conditions. Traditional healthcare methods diverge from SkinScan because this solution depends solely on Artificial Intelligence which eliminates the requirement for dermatologist assistance and provides inexpensive accessible disease detection. Generative AI symptom assessment through the system lets users describe their symptoms so the system can make further evaluations despite image-based detection. The Gen-AI chatbot system powered by LLM technology responds instantly to provide users with information about their needs and skincare recommendations along with treatment options. Users access image upload and chatbot interaction through the Frontend Layer while the Backend Layer maintains authentication and AI type processing alongside chatbot implementation and the AI & Database Layer handles image classification through CNNs and stores data and chatbot information. Through automated dermatological screening, SkinScan delivers user-powered skin health management which facilitates scalability and enables continual advancement. The introduction of AI technology through SkinScan enables worldwide users to obtain accessible and precise skin health management services at enhanced efficiency level.
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.
Iot based smart electricity monitoring and control system
(UMT.Lahore, 2025) Hasham Ahmad; IMRAN QURISHI; AZEEMULLAH STANIKZAI
The increasing global demand for electricity, coupled with the inherent inefficiencies in current energy infrastructure, presents a critical challenge. Manual energy management methods are prone to inaccuracies, resulting in suboptimal resource utilization and potential economic andenvironmental consequences. This project addresses the challenges posed by manual nergy management methods by proposing an Internet of Things (IoT)- ased mart electricity monitoring and control system. Utilizing modules like zem-04t interfaced with Lolin D32 v1.0.0 (ESP32), the system provides real-time data transmitted to Firebase Realtime Database RTDB. A custom Flutter pplication offers users insights into voltage, current, power, and total energyy consumption. The project's objectives include deploying IoT ensors, developing real-time analysis algorithms,and creating a user-riendly interface for remote control. Key features encompass real-timemonitoring, energy efficiency, cost savings, sustainability, smart automation, and ffordability.The system's architecture leverages Pzem 004t module, Esp32, and Firebase Realtime Database.IoT-based smart electricity monitoring and control system emerges as a transformative solutionfor efficient energy management, aligning with global trends towards sustainable living and smarthome technologies.
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.
NexGen HR
(UMT, Lahore, 2025) M. Arhum Qayyum Khan, Rana M Shahzaib, Ahmed Bin Aleem and Bisma Sharif
The system is called NexGenHR, an artificial intelligence (AI) enabled Human Resource Management System that automates and optimizes core human resource processes such as job postings, screening of curricula vitae (CVs), management of employee data, generation of payroll as well as automatic email messages. It is constructed on MERN stack and has secure role-based authentication, and incorporates the functionality of an AI-powered resume screening tool, it automates the recruitment process by using intelligent shortlisting and enables central storage of employee information that can be accessed quickly and reliably without error. The system increases productivity, administrative integrity, and the decision-making process of HR Managers and employees have self-service dashboards where they could learn history and changes on their salaries. NexGenHR is a smart end-to-end HR solution, with scalable architecture and integrated to the future, NexGenHR can support organizations of any size.
Quickfix
(UMT.Lahore, 2025) Zeeshan Ali; Khawaja Muhammad Mushood; Muhammad Bilal Yousaf; Muhammad Sanwal Javed; Abu Hurairah bin Amer
QuickFix is a young service management solution which will strive to bridge the gap between business and professionals and provide efficient solutions towards the management of demand. This site helps to communicate effectively, monitor progress, create customer request-based lists, and gives the professionals immediate tools to better organize their work. There is the integration of AI-powered chatbots; the experience given to the customers through this process of chatbots is enhanced with regards to personalized service implemented, answering queries, and giving status. It is possible to use predictive analytics and machine learning models by which businesses can predict demand and better allocate resources. QuickFix is founded on the MERN family and comprises technologies that include instant messaging tools, cloud service, and machine learning to streamline the service delivery to enhance business performance within divergent industries. Besides that, the platform connects to the most important services, including DialogFlow as natural language processing and Google Maps as geolocation, which makes it a solution to modern service management.
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.
Lexibot
(UMT.Lahore, 2025) Muhammad Abdullah Shaheen; Fasi Ur Rehman; Abdullah
The exponential growth of legal documentation has made finding the way through complex legal texts a time-consuming challenge. LexiBot, a Legal Document Summarization and Analysis Chatbot, is the solution for the above by using AI and NLP to automate the extraction of important information from legal documents. In the project, the major aspects are summarization of long court decisions, contracts, and legislative texts, the key clauses, precedents, and legal terms identification, and the user's provision with brief, query-specific insights. Along with the creation of a structured dataset from court judgments, the use of NLP techniques, and the fine-tuning of the advanced models like BERT and GPT for the purpose of summarization, analysis are the parts of the development process. Users are interacting with LexiBot through the chatbot interface, as a result, they are able to upload the documents and get the summaries and analyses they need. LexiBot aims to improve the accessibility, reduce manual effort, and streamline legal research, which makes it become the necessary tool for legal professionals and the ones who want to understand the legal material. Created with Python and the latest AI frameworks, this is a project that instigates the beginning of the process of legal document processing revolution.
VIP Power Club: Drop-shipping web application
(UMT, Lahore, 2025) Talha, Muhammad Haris Arshad and Muhammad Hassan Asif
This project focuses on the development of a drop shipping store that integrates Amazon ASIN listings and affiliate marketing to provide customers with a seamless shopping experience and access to discounted products. The platform leverages modern web technologies, including React for the frontend, Node.js and Express.js for the backend, and MongoDB/PostgreSQL for database management. Key features of the store include a recommendation system that suggests personalized products based on user behavior, an AI powered Chabot for customer support, user activity tracking for data-driven insights, and integration with Social Graph APIs (e.g., Facebook, Twitter) to enable social sharing and friend-based recommendations. Additionally, a coupon and discount system is implemented to incentivize purchases and increase customer retention. The project demonstrates the successful integration of these features, resulting in a scalable, secure, and user-friendly e-commerce platform. By combining drop shipping, affiliate marketing, and advanced AI functionalities, this project aims to enhance the online shopping experience for customers while providing sellers with a powerful tool to showcase their products.

Browse

Browsing 2025 by Issue Date

Results Per Page

Sort Options