http://hdl.handle.net/123456789/17505 Sat, 04 Apr 2026 12:13:13 GMT 2026-04-04T12:13:13Z http://hdl.handle.net/123456789/20010 RecoVoyage 03-135212-029, RAMEEN SAJID The continuous evolution of mobile and artificial intelligence technologies has opened new possibilities for enhancing user experiences in the tourism sector. Despite the abundance of travel-related applications, many fall short in delivering a seamless, intelligent, and localized travel planning experience—especially in regions like Pakistan. RecoVoyage addresses this gap by offering a smart, AI-driven mobile application designed to assist users in planning, managing, and enhancing their travel experiences through a centralized platform. Developed using Flutter for cross-platform compatibility and Firebase as the backend, RecoVoyage integrates essential modules such as trip planning, real-time alerts, booking simulations, and offline access. The app employs an AI-powered recommendation engine to suggest destinations and experiences tailored to user preferences. It uses dummy APIs to simulate hotel, flight, and cab booking workflows and incorporates a conversational assistant powered by Mistral API to guide users interactively through travel-related queries. To ensure reliability and scalability, the app features cloud-based data management through Firestore, supports multi-language accessibility, and enables offline functionality using cached data. Additional features include review and rating systems, loyalty rewards, and local deals to increase engagement and promote community-based tourism. Real-time notifications keep users updated with alerts like weather changes, flight status, and itinerary reminders. Security and usability were key priorities in development, with encryption protocols and OWASP-guided testing ensuring robust protection. Future enhancements include integrating real-time payment gateways, extending local partnerships, and deploying the app for live user testing. RecoVoyage demonstrates a practical and innovative solution to modern travel challenges, offering an intelligent, inclusive, and user-friendly platform tailored for the evolving needs of Pakistani travellers. Mr.ZUNNURAIN HUSSAIN Sun, 01 Jun 2025 00:00:00 GMT http://hdl.handle.net/123456789/20010 2025-06-01T00:00:00Z http://hdl.handle.net/123456789/20019 GilgitGhoomo 03-135211-033, SALMAN DINAR The GilgitGhoomo mobile application that answers the need for easy access to credible hotel bookings services in Gilgit Baltistan was developed in response to the rising demands for tourism, especially with focus on the Hunza region that is particularly popular among tourists. However, the no internet connection and also absence of information regarding the currently developing systems for bookings may raise severe issues although the area seems very promising from the environmental perspective. Finding reasonably good places to stay is usually not an easy task when traveling; the local companies are not visible to potential consumers. The idea presented here is an attempt to provide a local solution, using the Airbnb idea. It provides an environment that easily enables a local owner of a guesthouse to showcase their homes and for a traveller to search and book a place to stay. Besides, booking lodging, the app will contain such conveniences as the secure payment form; the data about the current weather; and info’s about the available options for entertainment. The present application is made using Visual Studio, and the above project will also support Android devices. For the back-end part, the data will be stored in MongoDB and location-based services will be provided with the help of Google Map API. The app will have the feature of user registration and account management for security and user customization. The app will at first only be operational in Hunza but can be expanded into other valleys in Gilgit Baltistan including Skardu, Astore, and Ghizer in future. Other functionalities like Localization, Advanced Recommendations, Voice Interface, will be incorporated as a part of the future. The purpose of this project is to increase local businesses’ influence, improve the tourist experience and overall socioeconomic development of the area with the help of an effective and easily usable tourism website. Ms. Summaira Nosheen Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/20019 2025-01-01T00:00:00Z http://hdl.handle.net/123456789/20869 Used Mobile Phones Price Prediction for E-Commerce Application 03-135211-014, Muhammad Nasr The second-hand mobile phone market is riddled with challenges such as inconsistent pricing and inaccurate condition evaluations, which impact buyer trust and seller profitability. This project aims to address these challenges by developing a comprehensive system for predicting the condition and price of used mobile phones, tailored to the Pakistani e-commerce market. We used a dual approach with the deep learning and the machine learning methodologies. During the condition prediction, the VGG16 model was selected as the best model with high accuracy across front on, front off and back view image classifications into Good, Average and Bad categories. An ensemble of machine learning models including XGBoost was used for price prediction; namely, XGBoost outperformed others by the R² score and error metrics, showing its strength in dealing with complex pricing features. Next, these models were integrated into a user friendly Flutter based mobile application, through which users could upload images and provide specifications for the real time predictions. It is an application that bridges usability and technology, and gives a scalable solution to market inefficiencies. Future work includes expanding the dataset to include additional phone models and market data, increasing the number of image views for condition assessment, and adapting the system for international markets. This project lays a strong foundation for creating transparency and consistency in the used mobile phone marketplace. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/20869 2025-01-01T00:00:00Z http://hdl.handle.net/123456789/20868 WizLogics: A Learning Platform 03-135211-023, Zain Ahmad In this era of Information Technology, tools for effective learning are crucial and play an important role in building one’s skill set. While these tools are great for learning, most of them demand hefty prices to use all the features and this leads to a decline in adoption rate by students from humble backgrounds. Another problem is that many students find it difficult to retain information as they don’t have the right tools to practice their knowledge upon and they ultimately forget it. To cater to the above-mentioned problems, this document proposes a Web Application named WizLogics: A Learning Platform. WizLogics will help students to learn in-demand programming languages by providing text-based bite sized tutorials. Students will also be able to test their knowledge on Flashcards which are scientifically proven to enhance knowledge retention among individuals. Other features include Social Networking so that peers can connect with one another, Write code in the built-in code editor, Ask AI any question related to computer science. Gamification elements will also be included like Leaderboard to keep students motivated and foster an environment of healthy competitions. The platform will be made using MERN Stack (MongoDB, Express, React, Node.js) and additionally OpenAI’s API and JDoodle API will be used for Ask AI and built-in code editor features respectively. Wed, 01 Jan 2025 00:00:00 GMT http://hdl.handle.net/123456789/20868 2025-01-01T00:00:00Z