Browse
Recent Submissions
Item On-line shopping mall(UMT Lahore, 2025-01-15) Muhammad Zubair Afzal; Qaisar AbbasIt is a fact that life is an ever-changing phenomenon, and since the inception of life on this planet, each and everything has been changing. Today, the world has become a global village, and this is all possible through the internet, which is gaining great importance in the business world. We have developed a website for online customers, where every user will have their own login name from which the customer can do shopping. In short, the user can simply shop on this website. There are two areas on the website. One is the administrator area, where the administrator can add, modify, and delete items. The database is dynamic, and all the changes that the administrator makes are directly recorded in the database; the administrator does not need to change the database manually. The other is the customer area, where users can do shopping as well as register. When someone clicks on the administrator area and wants to enter as an administrator, they must provide the correct password. If the password is found to be correct, they will be permitted to enter the administrator area. There is no password required for the customer at the start of shopping; the customer can browse the entire site and shop freely. Once the customer has completed their shopping, they will be asked for a username and password. If the user is a registered customer, they must provide the correct username, which is the email address, and password. If the username and password are found to be correct, the order will be placed. If the user is not a member and wants to register, they can click on the new user button and provide details such as email address, name, password, address, telephone, fax, etc. After this, the order will be placed. It can be clearly seen from the above information that this project is a good attempt to build a website through which customers can obtain complete information about the products they need from the online shop and can shop easily. Hence, this project provides benefits to both customers and the administrator.Item Data base system of a book shop(UMT Lahore, 2025-01-14) Mujahid Hussain; Abdul Sattar Baloch; Shahid NawazComputer software is one of the few key technologies that will have a significant impact on nearly every aspect of modern society during the 1990s. It is a mechanism for automating business, industry, and government; a medium for differentiating one company’s products from its competitors; and a window into a corporation’s collective knowledge. Software is pivotal to nearly every aspect of business. But in many ways, software is also a hidden technology. We encounter software when we travel to work, make a retail purchase, stop at the bank, make a phone call, visit the doctor, or perform any of the hundreds of day-to-day activities that reflect modern life. Software is pervasive, and yet many people in positions of responsibility have little or no real understanding of what it really is, how it is built, or what it means to the institutions that they control. More importantly, they have little appreciation of the dangers and opportunities that software offers. The pervasiveness of software leads us to a simple conclusion. Whenever a technology has a broad impact—impact that can save lives or endanger them, build businesses or destroy them, inform government leaders or mislead them—it must be handled with care. By the will of Allah and through our efforts, this project has been developed in a better way.Item Communication through VOIP using an open-source PBX(UMT Lahore, 2025-02-12) Irfan Asif; Usman AsifThis report aims to describe the complete process that was followed while developing a telephone service using VoIP through Asterisk (an open-source PBX). Our project aims to create a telephony system that allows subscribers to make calls using softphones (or computers) for communication via our service. Furthermore, our system also allows users to make and receive GSM and landline calls on their softphones. Hence, our solution is not only cost-effective but also very user-friendly. We have used Asterisk to act as the exchange for our main servers. Asterisk is an open-source private branch exchange (PBX) implemented in Linux. It has the facility to connect to the local telephone exchange or PSTN and other Asterisk exchanges. We have implemented a dial plan on our main server that allows our subscribers to dial the number they desire to connect with. The voice traffic generated after the establishment of a connection is transmitted using voice over IP (VoIP). This document explains the requirements, analysis and design, implementation issues, and testing process of the project, and concludes with future work that can be done in the direction of this project.Item Business accounting system(UMT Lahore, 2025-01-22) Umar SajjadItem Quickfix(UMT.Lahore, 2025) Zeeshan Ali; Khawaja Muhammad Mushood; Muhammad Bilal Yousaf; Muhammad Sanwal Javed; Abu Hurairah bin AmerQuickFix 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.Item Food Frenzy(UMT.Lahore, 2025) Muhammad Talha Abid; Muhammad Noman Arif; Muhammad Mujahid TufailFood Frenzy is an exciting mobile game that puts players in charge of a character responsible for managing and upgrading various "Product Factories" that create items like food. The game draws inspiration from popular titles such as Eatventure and Idle Civilization, blending idle gameplay mechanics with strategic production management to deliver a captivating experience for mobile gamers. Players oversee factories with unique production times, costs, and item types. Upgrading these factories boosts production points, enhancing both the economy and overall efficiency of the game. The interaction between customers and workers is powered by A* pathfinding, creating a smooth and dynamic environment. Customers place orders while workers manage production and delivery. The game also features NPCs (non-playable characters) who perform essential tasks, such as processing orders, operating the factories, and ensuring timely delivery to customers. Players are encouraged to optimize production chains and make strategic decisions, with a variety of upgrades available to improve resource management and streamline gameplay. The game can be played from a first-person perspective, offering flexibility in how players experience the game. The ultimate aim of Food Frenzy is to immerse players in a world that combines idle progression with strategic resource management, all within the engaging context of food factories and customer satisfaction. Future updates may include sound design enhancements and monetization features to further enrich the player's experience.Item Medprep(UMT.Lahore, 2025) Muhammad Aqib; Abdullah Amjad; Ammar Shahid; Abdul RaheemMDCAT preparation is essential for aspiring doctors in Pakistan, but traditional study methods often lack personalization and engagement. To address this, we developed MedPrep: AI-Powered MDCAT Preparation Assistant, a smart, web-based platform designed to meet individual student needs. MedPrep uses AI to deliver adaptive quizzes, offer real-time feedback, provide explanations for incorrect answers, and track progress dynamically. By training the Llama 3.2 3b model to analyze student performance, the system helps streamline and organize the study process. With few MDCAT tools offering such intelligent support, MedPrep aims to modernize preparation by blending conventional learning with AI-driven features, making the experience more effective, interactive, and student-focused.Item Criminal detection system(UMT.Lahore, 2025) Abdullah Saleem; Tanveer Ahmed; Haroon Javaid; Abdul Hannan; Danish KaleemPeace and security are priority for people, private sector and public sector. Existing security systems, for example, CCTV camera systems, suffer from the disadvantage of being manned, and thus, are not capable to perform any operations without a man and are also very susceptible for the human errors. The development of IoT and artificial intelligence there is a raising demand of automatic real time crime dete ction system. Criminal Detection w/ IoT device This Project“Criminal Detection via IoT Devices” is about a Smart Security system which is Connected on Internet of Things (IoT) that incorporates a machine learning model to detect any Suspicious activity. The system consists of smart cameras, connected to a centralized processing unit. The core functionalities include object detection, facial recognition, real-time monitoring, and instant alerts via SMS and mobile notifications. The system will utilize Raspberry Pi and camera modules for data acquisition, Firebase for cloud storage, and machine learning algorithms (Face Recognition Library, OpenCv) for image and activity analysis. The user interface will include a web-based admin panel (built with HTML, CSS, and JavaScript) and a mobile application (developed using Flutter) to provide seamless access to real-time security alerts and analytics. This project aims to provide an automated security solution for residential, commercial, and government sectors, reducing manual effort and improving crime response time. By integrating IoT technology with AI-driven analysis, the system will help law enforcement agencies enhance surveillance, identify criminals, and take immediate actionItem Ai-driven medical chatbot(UMT.Lahore, 2025) Ali Ahmed; Ajmal Riaz; Aleena KaramatAccess 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.Item N. bone fracture frame(UMT.Lahore, 2025) Nisar Ahmed; Nayyab ZahraBone fractures are a significant medical challenge, requiring accurate and timely diagnosis to ensure effective treatment. Traditional methods of fracture detection, which rely heavily on manual analysis, are often prone to human error and can lead to delayed treatments, adversely affecting patient recovery. To address these challenges, this project introduces "Bone racture Frame," an AI-powered desktop application designed to detect bone fractures in X-ray images with high accuracy and efficiency. The system utilizes advanced deep learning models to analyze medical images, identify anomalies, and generate actionable insights for healthcare professionals. Key features of the application include user registration, image upload functionality, real-time fracture detection, result visualization, and downloadable reports. Designed with a focus on user- friendliness, the application ensures accessibility for medical practitioners of varying technical expertise. By automating the fracture detection process, the application significantly reduces diagnostic errors, alleviates the workload on medical professionals, and enables faster treatment planning. This project highlights the transformative potential of integrating artificial intelligence into medical imaging, offering a scalable and adaptable solution to enhance healthcare delivery and improve patient outcomes. "Bone Fracture Frame" serves as a foundation for future innovations in AI-driven diagnostics, paving the way for broader applications in the medical field.Item DreamBoard AI(UMT.Lahore, 2025) Muhammad Awais; Asad Abbas; Muhammad HamzaDreamBoard AI is a web based tool that helps filmmakers, animators and other creatives turn written ideas into full storyboards in minutes instead of hours. Using large language model (LLM) “scene planners” and Flux based image engines, the system writes a structured plan for each scene and then generates four matching frames while keeping characters, lighting and style consistent. A Python “Consistency Engine” checks every new frame with YOLO v8, CLIP and DeepFace to be sure the main characters still look the same from shot to shot. Users can edit, in paint, regenerate single frames or export the final board as PDF, PNG or ZIP. Real time WebSocket updates, JWT secured accounts and a PostgreSQL + AWS S3 backend make the app fast, safe and scalable. Internal tests show the first image appears in under 25 seconds and overall character matching accuracy reaches about 89 percent. By automating repetitive drawing tasks, DreamBoard AI lowers pre production costs and lets storytellers focus on creativity.Item Disease detection using X-Rays(UMT.Lahore, 2025) Muhammad Anas; Abdul Rafay; Tayyab; Maryam JahangirMedical imaging is essential to contemporary healthcare since it makes it possible to diagnose a number of illnesses via X-ray analysis. But finding qualified radiologists is still difficult, especially in underprivileged areas, which causes delays, incorrect diagnoses, and financial strain on patients. By combining medical imaging and artificial intelligence (AI), MedX-GPT seeks to close this gap and offer a quick, affordable, and precise diagnostic solution. Convolutional Neural Networks (CNNs) are used in this study to classify and diagnose diseases in X-ray pictures. Additionally, a Large Language Model (LLM) is integrated to help medical practitioners by offering interactive diagnostic insights. The system is intended to provide accessibility to medical imaging solutions, decrease radiologists' burden, and improve diagnosis accuracy. MedX-GPT hopes to improve healthcare accessibility and dependability by creating a real-time, AI-powered X-ray analysis tool, especially for individuals who face financial and geographic obstacles. The experiment shows how artificial intelligence (AI) may transform medical diagnosis, lower human error, and speed up patient treatmentItem Unmasking gan variants(UMT.Lahore, 2025) Muhammad Awais Dar; Manahil Suriya; Muhammad Ali Malik; Muhammad SajjadThe authenticity of medical images created using a computer is now a problem due to the quick application of generative adversarial networks (GANs) in image creation. In this research study, we were trying to solve the problem of determining whether the type of GAN used in the generation of fake breast cancer ultrasound images was DCGAN, Style GAN, or Stack GAN. We were looking to create a system that would accurately recognize real and fake pictures and then classify fake pictures based on the source: DCGAN, Style GAN, or Stack GAN. We created 1000 images for every GAN odel from a real data set of 300 cancer ultrasound images. 300 images were randomly chosen as fake images from every GAN to balance the dataset. Real, DCGAN, Style GAN, and Stack GAN were the four balanced classes of the final dataset. Six deep learning classifiers, i.e., VGG16, esNet50, EfficientNetB0, and MobileNetV2 (custom-trained and pretrained), were trained. Class-wise report of performance, confusion matrices, and accuracy were used to benchmark all models. It was found in our experiments that the pretrained MobileNetV2 classifier outperformed all the others with a test accuracy of ~100% (99±1%). It illustrates how well transfer learning can find extremely fine distinctions between artificially created and actual medical images. Our system also performed favorably in labeling fake images correctly to their generative GAN model. The work proposed is the foundation for ensuring computer- assisted diagnosis systems and a sound method of identifying fake images within the healthcare fieldItem AI Teaching Assistant(UMT.Lahore, 2025) M.Faseeh Ur Rehman; Abdul Moeed Piracha; Muhammad Usama; M. Haris ImranThe 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.Item Virtual Wear (V-Wear)(UMT.Lahore, 2025) Hannan Muzammil; Muhammad Awais; Muhammad SohaibVirtual Try-On technology is revolutionizing garment retail by enabling consumers to visualize garments themselves. In 2024, the revenue in Pakistan's garment industry was estimated to be 16 billion rupees, with a projected market volume growth of 0.2% in 2025. This growing demand calls for innovation, especially in addressing the challenges of nual/physical in-store and traditional online shopping methods. Traditionally, in- store shopping is limited to physical travel constraints, discomfort in manual try-ons, and even health concerns like disease spread. While convenient, online shopping suffers from issues like inaccurate size, and appearance, which causes a higher return, leading to customer issatisfaction and negative environmental impact. Virtual Try On ddresses these challenges by allowing users to see how a garment fits and looks virtually, boosting customer confidence and reducing returns. Efforts have been made to computerize this process using classical methods and newer, advanced techniques. Classical techniques (Splines, Thin Plate Splines) for virtual garment fitting faced limitations due to handcrafted feature extraction. However, the advent of deep learning models, particularly automated feature extraction through technologies like Convolutional Neural Networks, etc., and more advanced technologies, Generative adversarial Networks (GAN), diffusion models, and reinforcement learning, has significantly improved Virtual Try On accuracy and Quality. These recent models offer high-quality virtual try-on experiences but still have gaps that require further research. Despite advancements, still challenges remain. So, there is a need for a system that can seamlessly integrate with the current garment market while solving these issues. The proposed V-Wear system will provide an automated platform that allows customers to try on garments virtually, ensuring confidence in their purchases. V-Wear will benefit customers and sellers by reducing return rates, enhancing customer satisfaction, and contributing to sustainable shopping practicesItem Collabix(UMT.Lahore, 2025) Mian Muhammad Ans; Faizan Tanveer; Ali Hassan; M. WaleedIn this digital era, inflencer marketing has become an influential tool for businesses to promote their products and services. Because small and medium size businesses (SMBs) find struggles the right influencers due to lack of established platforms and inefficient communication. In Pakistan here is not any platform where there is entrepreneurs, business owners and influencers seeking for business and making connections, there is a huge gap in Pakistan for platform. That’s where Collabix comes in and aimed to fill this gap by proper platform for these connection only where business owners easily find influencers to promote their product or services and influncers easily close the deals with the business owners in order to encourage their businesses. By providing AI recommendations, this platform efficiently recommend influencers who best fit their audience demographics, budgets and brand identity. And with its user friendly platform, real time messaging, paymet gateways and data driven compaigns. Collabix guarantees flawless collaborations. Influencers benefits from increased visiblity, established pricing models and also one to one communication with potential brand partners. We developed this project by MERN Stack (MongoDB, Express, React and NodeJs) for the resposive web app platform ith AI features like content based recommendation and predictive analysis enhances its performances and efficiency and make it more scalable. We also provide security measures like JWT (Json Web Token) for the uthentication purposes and secure payment gateways are implemented to secure the trust of users. As the name Collabix-Where businesses meet influencers, there seems to be collaboration between the users in order to revolutionize mar keting in Pakistan, empowering small and medium size businesses (SMBs) efficiently while helping the influencers community to monetize their reach effictively. We aimed to make this system to be calable and positive for future enhancement like compaign tracking, automated contracts, AI driven fraud detectionItem Foster Learner Autonomy(UMT.Lahore, 2025) Nasir Ali; Muzammal Nazeer; M Ismail; Sadia GhafoorThe rapid growth of digital learning has transformed traditional education, offering learners greater flexibility, accessibility, and personalized learning experiences. However, many online learners still face challenges in maintaining motivation, managing their own learning pace, and accessing relevant resources effectively. This project, Foster Learner Autonomy, aims to address these challenges by developing an interactive web-based platform that empowers learners to take control of their educational journey. The system integrates features such as personalized learning paths, resource recommendations, progress tracking, and self-assessment tools. Leveraging modern web technologies, the platform incorporates an intuitive user interface and adaptive functionalities to support independent learning across diverse domains. It applies user-centric design principles and feedback mechanisms to ensure usability and engagement. The development process follows agile methodologies, ensuring iterative mprovement and alignment with learner needs. This project contributes to the enhancement of learner autonomy by bridging the gap between traditional instruction and self-directed learning in an online environment. The outcome is a scalable, adaptable solution that can be deployed for academic institutions, corporate training, and lifelong learning initiatives, ultimately fostering independent, motivated, and self-regulated learnersItem Sign Bridge(UMT.Lahore, 2025) Ahsaan Munir; Rimsha Tariq; Muneeb AhmadThe Sign Bridge is an AI-powered solution developed to bridge the critical communication gap between individuals with hearing impairments and the general public in Pakistan. This system focuses on recognizing and interpreting gestures from USL and converting them into readable Urdu text. By leveraging advanced techniques in computer vision, deep learning, and gesture recognition, the project contributes meaningfully to inclusive technology and accessible communication. At the core of the system is a combination of Convolutional Neural Networks (CNNs) for image-based feature extraction, and MediaPipe for real-time hand landmark detection The model is trained on a custom-built dataset comprising 54 frequently used Urdu sign language words, each recorded through 20 short-duration videos. This dataset provides the foundational training data for model learning and testing. Despite its relatively modest size, the model achieved 55% accuracy, proving the feasibility of real-time Urdu sign language nterpretation using a lightweight, scalable approach. The application features a user-friendly interface that captures hand movements via webcam and displays the translated text on-screen, offering real-time interaction. The system is suitable for use in educational institutions, accessibility tools, and healthcare settings, promoting digital inclusion and independence for the deaf and hard-of-hearing community. Overall, this project showcases how AI and machine learning can be effectively utilized to develop localized, meaningful assistive technologies that support both accessibility and linguistic diversity in emerging markets like Pakistan.Item Fit Fusion(UMT.Lahore, 2025) Uswah Sajjil; Amna Tariq; Noor FatimaFit 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.Item Al-ibat-ul-urf(UMT.Lahore, 2025) Hamna Shahid; Areej Jawad; Ahad DanishAL-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.