https://elibrary.khec.edu.np/handle/123456789/433 2026-07-17T04:33:59Z 2026-07-17T04:33:59Z Prajapati, Nirajan KCE074BCT024 Prajapati, Nirjal KCE074BCT026 Prajapati, Rohit KCE074BCT033 Prajapati, Sahas KCE074BCT037 https://elibrary.khec.edu.np/handle/123456789/444 2024-08-10T10:30:25Z 2021-01-01T00:00:00Z

Title: Video Conferencing with Gesture Based AR Control Authors: Prajapati, Nirajan KCE074BCT024; Prajapati, Nirjal KCE074BCT026; Prajapati, Rohit KCE074BCT033; Prajapati, Sahas KCE074BCT037 Abstract: Video conferencing in this day and age has been a norm due to an unforeseen pandemic that halted many daily activities. It can be seen that many video conferencing applications which were previously not so familiar to the general public came into popularity viz. Zoom and Microsoft Teams. The present video conferencing applications are doing fine for the current scenario as it has helped millions of people to connect. However, video conferencing will be more attractive with the addition of augmented reality and gesture-based control system. Adding of augmented reality to video conferencing make presentations more interactive. It is suggested that augmented reality is an intuitive and user-friendly paradigm to communicate information about the physical environment. With the addition of augmented reality, users get an alternative and interactive way of presenting themselves during a conference. In addition to gesture control, this project includes the controlling of the augmented reality items and other features of the video conference via hand gestures.For the implementation of the hand gesture control of the augmented reality, library provided by google, mediapipe hands(consisting of palm detection model and hand landmark model) is used and to control the basic functions of the application such as toggling the microphone, opening and closing chat bar etc., model made from video vision transformer is used.The introduction of the hand gesture removes the bottleneck in the effective utilization of the available information flow as human already uses lots of hand gestures to communicate non verbally.

2021-01-01T00:00:00Z Neupane, Abhishek KCE074BCT006 Shahi, Rojash KCE074BCT034 Shrestha, Sachit Kumar KCE074BCT036 Gosai, Suraj KCE074BCT046 https://elibrary.khec.edu.np/handle/123456789/443 2024-08-10T10:44:46Z 2021-01-01T00:00:00Z

Title: STORY BASED 3D ADVENTURE GAME USING UNIVERSAL RENDERING PIPELINE IN UNITY Authors: Neupane, Abhishek KCE074BCT006; Shahi, Rojash KCE074BCT034; Shrestha, Sachit Kumar KCE074BCT036; Gosai, Suraj KCE074BCT046 Abstract: Unlike most other video game genres, which are classified by their game-play, Adventure games are nearly always based on narrative or visual presentation centered on fiction and typically designed to entertain the player. To create a 3D Story based Adventure game in which players dive deep into the ocean of the knowledge the game offers through various narration of the story. This project started with script development. Dijkstra and A* algorithms are implemented for the path finding. Reinforcement learning for the model training using the bellman equation using Q-table. Sweep based CCD and Speculative CCD were used for the collision detection of the object. Terrain builder was also introduced for the generation of the environment. Cinemachine was implemented to develop player perspective and provide the aerial view, along side with the user interface system to make the navigation system successful. To ensure realistic view, post processing stack were used. It is aimed to release our project first on Android and will expand to other platforms.

2021-01-01T00:00:00Z Rajthala, Bibash KCE074BCT014 Rokaya, Sangat KCE074BCT039 Timilsina, Subin KCE074BCT042 Acharya, Sujan KCE074BCT043 https://elibrary.khec.edu.np/handle/123456789/442 2024-08-10T10:42:03Z 2021-01-01T00:00:00Z

Title: STOCK MARKET PREDICTION USING SENTIMENT AND TECHNICAL ANALYSIS Authors: Rajthala, Bibash KCE074BCT014; Rokaya, Sangat KCE074BCT039; Timilsina, Subin KCE074BCT042; Acharya, Sujan KCE074BCT043 Abstract: Stock market prediction is a thriving topic across the globe, millions of new dematerialised accounts were opened in past few years. In the context of Nepal, Demat account holder has reached to the count of 48,95,021 as of 16th Feb 2022. Craze in investment over company’s stocks has seen an exponential growth. Stock market prediction has been a challenging problem for both economists and data scientists. For the sake of building effective prediction model, various researchers are coming with new techniques and approaches achieving good yet capricious results as market depends upon various stochastic factors. Hence, stock prediction methods incorporating the technical and sentiment analysis has been best for assisting investors in general. With the dataset available sentiment analysis was performed with 71.75% accuracy and with GRU accuracy of 70.11% to predict the future price of stock. Adversarial training accuracy was 53.25% for the trend prediction.

2021-01-01T00:00:00Z Shrestha, Aakash Sunar, Amar Pradhan, Ankit Adhikari, Prasanna https://elibrary.khec.edu.np/handle/123456789/441 2024-08-10T10:36:55Z 2021-01-01T00:00:00Z

Title: Spam Detection in Chat Application Authors: Shrestha, Aakash; Sunar, Amar; Pradhan, Ankit; Adhikari, Prasanna Abstract: Emails, Chats, SMS are widely used in this day and age for communication. But this rise in technology has invited spammers. Text spams are used in SMS, chats, emails, etc. Spam detection in messages has been since a long time. However nowadays these spams are increasing in the form of images. This project displays an application of Naive Bayes for text-based Spam classification and Deep CNN for image-based Spam classification in our own chat application. In addition to these, another method of Image spam classification is used, using Tesseract for Object Character Recognition technique and feeding the text extracted to our text based classifier. This proposed approach in text based spam classification has achieved 97% using Naive Bayes classifier. The CNN model achieved 96.87% accuracy for image spam classification. The app takes less than a second to send text with spam classification feature and took around five seconds to send image with spam classification in web. However in mobile, it takes slightly more time for image spam classification (1 minute and 10 seconds).

2021-01-01T00:00:00Z