MyAttorney is a web based application for finding, browsing and rating lawyers andlaw firms in Nepal. The application also provides a list of nearby available lawyersusing Google Maps API. MyAttorney will also try to help users on different legalprocedures like Company Registration, creating Passports, etc

With an end goal to imitate human speculators who read openly accessible materials keeping in mind the end goal to make decisions about their investments. In this Project, I show a programmed stock exchanging process, which depends on a chain of command of a component selecting technique, various machine-learning algorithms and statisticalcalculations

Tweets Sentiment Analysis Using Naïve Bayes is sentiment analysis system which used supervised machine learning classifier i.e. Naïve Bayes classifier.The accuracy of 70% is obtained for the unigram words as feature vector using Naïve Bayes Algorithm

The application’s purpose is to produce a cluster of negative and positive reviews for aparticular movie. The reviews are pulled from imdb.com and sentiment analysis of thesereviews is based on Random Forest Algorithm. The accuracy of 79% has been achieved.

Preparing time table using manual method in colleges and schools is very time consuming and tedious task. This ends up with various classes clashing either at same room or with same teachers having more than one class at a time. Due to manual approach, proper use of resources is neither effective nor efficient. To overcome all these problems, I propose to make an automated system as automatic routine generator. The system will take various inputs like number of subjects, classes and their capacity, teachers, maximal lectures a teacher can conduct, topics to be covered in a week or a lecture. Depending upon these inputs it will generate possible time tables satisfying hard constraints for working days of the week. The generated routine may or may not be useful according to the requirement of the administrations

Recipe Matcher System is concerned on providing the food recipe to the users on given ingredients. In this project, users are allowed to provide ingredients and they are offered with the variety of recipes that are stored in our database. The recipe that include all the ingredients in the search box are displayed to the users. A registered users can also rate the recipes. The search result initially acknowledges the highest rated recipe while displaying and is ordered accordingly.

The business to consumer aspect of electronic commerce (e-commerce) is the most visible business use of the World Wide Web. The primary goal of an e-commerce site is to sell goods and services online.This project deals with developing an e-commerce website for Electronic gadgets. It provides the user with categories of different gadgets available for purchase. In order to facilitate online purchase a shopping cart is provided to the user. The system is implemented using a 2-tier approach, with backend database and PHP, HTML/CSS and a web browser as the front end client.In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client side scripting techniques, programming language (such as HTML/CSS, PHP), relational database (such as MySQL).This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart application and also to know the technologies used to develop such an application.This document will discuss each of the underlying technologies to create and implement an e-commerce website

Breakfast recommendation system is the system of recommending food on the basis of occurrence of the food items with each other. The recommendation is carried out on the basis of pattern of food order in past. It is one of the application of associative rule mining that is carried out by using support and confidence. Apriori algorithm is used for the rule generations and the recommendation is done on the basis of higher support and confidence value

Text-To-Image Steganography is a steganography technique to hide information such as text messages inside a given image file by manipulating bits of the original image file. The technique has been implemented using LSB Algorithm where the least significant bit of the original image is replaced with the given message bits. LSB algorithm in this project has been implemented for red color channel data for given RGB image files. The original image bits are extracted and replaced with the message bits and the image is saved and retrieved to pull back the information from the stego-image. In order to maintain the integrity of the secret message the lossless compression is used to save the carrier image to stego-image. In order to make the stego-image undetectable to the naked eye LSB algorithm has been used. The performance of the algorithm is tested in RGB and grayscale images.

The business-to-consumer aspect of electronic commerce (e-commerce) is the most visible business use of the World Wide Web. The primary goal of an e-commerce site is to sell goods and services online. This project deals with developing an e-commerce website for Mobile systems .It provides the user with a catalog of different cellphones available for purchase in the store. In order to facilitate online purchase a shopping cart is provided to the user. The system is implemented using a 3-tier approach, with a backend database and a web browser as the front end client.

Alien Shooter is a 2D platformer game made in Unity 3D engine using C# scripting. It is a single player game where waves of enemies spawn to kill the player. The player defends himself with a weapon. A* Pathfinding algorithm was used to make the enemy AI. It was based on mechanics of games such as Super Mario Bros. and Contra. Making a game of platform genre that has engaging premise was the objective of the project. The game has been described thoroughly in this document including the major classes. The functional and non-functional requirements are given. The system design is explained. Class diagram and state diagram give a general picture of the working mechanics of the game. Corrective maintenance of the game will be carried out.

Nowadays, people send or receive goods like gadgets, electronic items, furniture etc. From one place to another. People usually use transport systems for receiving or sending goods which is a manual way. There is no guarantee that it is received or delivered and also there is no way to let the customer know what happened in transit, once he sends the goods. So, in these kinds of condition we need a computerized system for the cargo activities which is solved by Courier Management System which helps in management of cargo by tracking whether they are received or delivered

Typically in a restaurant/hotels, food order process involves several steps for ordering the food. Firstly, customer start by browsing the paper based menu and then inform to the waiter for ordering items. Usually, the process require that the customer has to be seated before starting and wait for the ordered food. An alternative method for the customers is “Food Pre-Order System using Web Based Application”.OrderByMe is online food ordering system. It is a web-based application that will be hosted by the hotel owners/restaurants to provide service of ordering food to customers. These orders will be made earlier through the application so as for customer to reach the hotel on time for service and avoid waiting time. Other features that the system will be providing is articles of featured dish of that respective hotels and also there is a provision for admin to implement coupon/ scheme as per owner’s requirements. Functional and non-functional requirements were brainstormed. Feasibility analysis was done which includes technical and operational feasibility.For the system development, waterfall methodology has been implemented as on every stage, deliverable will be obtained. For testing, unit testing has been performed and test cases has been prepared. Keywords: Online Food Ordering, web-based application, food pre-order system

Futsal Booking Application is a web application which allows users to view information about the futsal arenas inside Kathmandu Valley and book those arenas through the same application. This web application was built using web application development framework Laravel and blade php as its core language.

This project is about a software that recognizes digits of Nepali language i.e. Devanagi digits. When given a set of Nepali digits from 0-9 it easily recognizes them. It can be further developed to recognize characters or words of Nepali languages. It implements theconcept of neural network that includes Back-propagation and Gradient descent Algorithm.In general perspective, one of the primary means by which computers are endowed with human like abilities is through the use of a neural network. Neural networks are particularly useful for solving problems that cannot be expressed as a series of steps, such as recognizing patterns, classifying them into groups, series prediction and data mining.Therefore, with an aim to make computer recognize the digits, this project have been developed.A neural network trained for classification has been designed to take input samples and classify them into groups of digits. The accuracy obtained for classifying handwritten Devanagari digits is 96.7%.At first, data (images) that are needed for the training and testing are collected andpreprocessing is done. Then after, those training data set are supplied as a means of input and these are computed through different nodes of the neural network to produce certain outputs. Obtained output is compared with the target value, and error is calculated. The implementation of back propagation comes at the time of back-propagating error produced and gradient descent is used to minimize the error to update the link weight accordingly. The training process continues until the system produce the output that is same as the target value. Testing process is simply done by providing pixels values of image as an input to the input nodes that need to be predicated, and the output is compared with the target value and result about predication is displayed. Testing process does not involve the back-propagation and gradient descent.

Computer are known for their wide range of uses especially in scientific and mathematical fields. However little or no thought has been given to designing a complete and thorough intelligence entrance examination on a computer system in our immediate environment.The design of the system is quite simple and easily understood. The question of the online entrance examination system are programmed and visually displayed on the system’s screen in an interactive form. The student answers the question on the computer system, immediately the question is marked and notified. The result of the examination is also displayed at the end of the examination which goes a long way to lessen the fears of students that they were marked down in the examination. Since the entrance examination is examined by the computer, time cost of manual examination is saved.DWIT Aptitude Test Online is a web based application that takes an entrance examination. It will help DWIT to replace traditional method of exams that involves the paperwork. Exam results are calculated automatically at the end of the exam.

Leave Management System is a web based application which provides a platform for Students and Administration to apply, respond and record leave applications received on a daily basis. This System will help eliminate the manual method of sending leave emails by attaching a word document and manual record keeping of past leave records. Further, it will provide an easy access to the past records as per the category as and when required.

Gadgets Price Comparison Using Web Scraping is the web based application that the customers use to filter and compare products from different online stores based on price and features. This application aggregates product listings from many different retailers but does not directly sell products. Web Scraping technology is used in order to collect the data from various online stores about the product in real time and compare them. In order to scrape the data in real time, URLs were used to find the scraping location in the website and regular expressions to match the pattern with the string to get the required results. The scraped data was processed and categorized according to the online dealers so that proper comparison between the products could be done.

Smile detection camera is a desktop camera application that detects if the user is smiling or not and captures image automatically if the user is found smiling. The smile detection algorithm is implemented using OpenCV Haar Cascade Classifier algorithm.In this algorithm, 3000 negative images and 1500 positive images are used. Negative images are those image that does not contain anything related to users smile. Similarly, positive images are those image that contains smile of the user or human. Negative images are downloaded from the internet and positive images are generated from my friend’s smiling video. All the images are converted into grayscale format and converted into lower pixel values for training purpose because if the images were normal, it would take forever for a simple machine to train. The accuracy of 65% was obtained during testing phase.

Leave Form Classification Using Naïve Bayes is a Classification system which uses supervised machine learning classifier i.e. Naïve Bayes classifier.Naïve Bayes Algorithm is a basic classification algorithm that uses keywords as features. It assumes every keyword on the document as independent entity, computes the conditional probability of each words and multiplies to get overall probability given a class. Leave Form is a document in which student write the reason they are on leave. The reason contains some fixed keywords like headache, out of valley which is our main target. This algorithm takes these words in account to classify the document. They calculate the individual probability of each word and finally put them in the class with the highest probability of occurrence.

In this paper, we discuss the implementation of a rule based expert system for diagnosing diseases in paddy, wheat and maize. The proposed system is implemented as a rule based expert system in a MVC framework of PHP Laravel for the diagnosis of diseases in crops. In the system, the user is presented with a list of questionnaires about the symptoms seen in the crops and system identifies which is the most likely disease.In the system the users can access the application through the browser. They can choose to view the table that contains information about the disease and symptoms seen in leaf, steam and roots. User can also choose the view where they get to select one crop from paddy, wheat and maize that they want to diagnose. Then the users will be redirected to a view where they can select the symptoms that they have seen in their crops. When the users press submit button the result will be shown to them. Symptoms of disease that were known in priori was given to the system. The system correctly identified what disease the plant was suffering from in most of the cases. The system gave unable to identify for new disease that was not in the knowledge base.

I would like to thank Ms. Shweta Shrestha, Lecturer, DWIT and Mr. Abhishek Gupta for supervising this project and giving assistance when faced with problems. Without their guidance and persistent help, this project would not have been possible.I would like to thank Dr. Basanta Joshi, Assistant Professor, IOE, TU for providing technical help and providing deeper knowledge about the technology needed for this project. Without his help, I would be struggling to understand the theory needed and might have reached an incorrect conclusion.I would like to thank Mr. Hitesh Karki, Chief Academic Officer and Mr. Ritu Raj Lamsal, Lecturer of DWIT College for guiding us on various aspect of this project.At last but not the least my sincere thanks goes to my parents and member of my family, who has always supported me and to all of my friends who directly or indirectly helped me to complete this project report

Medictionary is a mobile application based on android that will be used to find the description and use of medicine that is generally used in home for treatment of common and simple health problems. Hardware device (Smart Phones with Android OS) and emulator (BlueStacks) were used for instrumented testing of the application.

Online Document Formatter is a web application which provides a platform for users for writing documents with pre-defined formatting rules. Formatting will be hardcoded. This application will help to reduce time consumption rate while preparing documentation. Further it will provide simple User Interface with limited content so that even person with basic knowledge will be able to use this application.

Restaurant Recommender is an item-based recommendation website that recommends restaurant to the users according to their preferences. The similar items are found by using Pearson’s correlation score and it is compared to the user’s items then the recommendation is made on the basis of highest score

Baby Friendly Places Recommendation System is targeted for the working parents who are not able to spend much of their time with their small children. This application helps all such parents to not waste their time searching for “The Perfect Place” to find where they can go out and have quality time with their small ones. The System uses Nearest Neighbor Algorithm for classification based on similarity with the location of the place. The similarity function that is used is Haversine Distance function which is used to give a circle-based distance on the basis of the source and the destination’s latitude and the longitude. The application has a rich database where all the information regarding the place is kept which is then viewed to the user from the system.The application is beneficial to the working parents allowing them to save their time in searching for the best place and providing them more time so that they can go out and have fun with their small ones.

This is web application named as Online Printed t-shirt ordering system. This a platform for ordering printed t-shirt according to the users selected design available in the system. This system will allow users to print T-shirt according to selected design which is available in the system. Online Printed T-shirt ordering will have registration for new Users and login for Members. The system allows users to select t-shirt design. After that user may choose desired color. The next step allows users to choose designs and text to be printed on the tshirt. After user confirms the order, a notification will be send to them in their mail or number

Friends group is web application that helps us to invite friends on the application to different kind of events. Anyone can create the event and the friends on the friend list can only be invited to that event. Therefore, this paper includes the implementation of friends group project. On implementing this project including its introduction, scope, feasibility analysis and its limitation for the use are described. Later the System Design methodology is described including its state flow diagram, ER diagram, and Data flow diagram is represented. Listing of tools used and Major classes of the project is described.

Sudoku Solver is a Java Based application that solves the Sudoku Problem of Size 9*9. Here I have implemented a simple computational model of human solving activity. In addition different algorithms for image processing, OCR are implemented for the preprocessing of Sudoku images. The Sudoku Solving algorithm actually is able to solve Sudoku of any size but the application is bounded to only of size 9*9 due to complexity of image processing and OCR.

Music genres are categories that can be used to identify and arrange growing amount of music emerging at present. Conventionally, music genre labeling was done manually. However, due to the advent of new techniques and growing number of researches in Music Information Retrieval, some form of automation has been seen in the field of music genre categorization. In this project, a stepping stone for automatic music genre categorization of vast number of music files available in digital form online or offline has been developed. Out of the various techniques of music genre recognition, content based technique has been used to automatically label the particular user uploaded song into one of five distinct genres: Classical, Pop, Metal, Jazz, and Blues. Digital signal processing techniques of Fast Fourier Transform and Mel-Frequency Cepstral Coefficients have been used to generate feature values of feature vector, which is then fed into the classifier developed using Support Vector Machine, in order to classify user input song. The training and testing of the system has been performed successfully obtaining an accuracy of 74.0%, which is significant in the field of music analysis. Training has been carried outusing 80 music clips of each of the five genres, and testing, using 20 music clips of each of the five genres. GTZAN Music Dataset, a popular Western music dataset prepared for music analysis, has been used during training and testing; hence, this system works well only with Western music files. The system has been implemented with two graphical user interfaces: one for admin (training and testing) and another for user (uploading music file and finding genre) using Python programming language and Flask framework.

Sentiment analysis is the task in Natural Language Processing to determine whether the writer’s attitude about a topic is positive, negative or neutral. Nowadays, a lot of companies use sentiment analysis of the opinion on the social media sites to extract the valuable information. In this project I have performed the sentiment analysis of Android app reviews by using Naïve Bayes classification algorithm. I have taken the dataset of positive and negative reviews for training purpose. The system takes reviews and displays the result in webpage classifying positive reviews and negative reviews in two groups. The accuracy of 78.22% was obtained while testing the classification algorithm using test dataset.

Image Encryption and Decryption uses Advanced Encryption Standard (AES) algorithm fo encrypting and decrypting the grayscale images. The system uses AES-128 block. The block size and key length is both 128 bit. It follow 10 rounds where 9 rounds are same and last round is different. The rounds perform four steps: Sub bytes, Shift Row, Mix Column, Add round Key. First the image pixels are converted into bytes and they are processed by four steps. AES algorithm was successfully implemented to encrypt and decrypt the grey scale image

Emails are the most common mode of communication for events, assignments, and other notices among DWIT members. The bunch of emails are send to inboxes each day concerning various events, assignments or informational notices. Unfortunately, with so many emails going around, not all of the emails sent out to the inbox can be read or even organized into useful categories that could help disseminate information better. The goal of DWIT Email Classifier is to address this problem, and the approach used is to build a training model using Logistic Regression Classification Model which automatically syncs with the user Gmail inbox and classifies the new, unseen emails into one of the four categories; Club emails, Class emails, Administration emails and Miscellaneous. The 4,000 existing emails were used as the training set in this system.

Ask-Me is a question-and-answer site where questions are asked, answered, edited and organized by its community of users. It is a dedicated platform to grab and share knowledge between different users. Questions from any categories can be asked in this platform and user will respond accordingly. In our day to day life different kind of problem arises, the problem may be related to our personal life and study life. The problem we have been facing today might have been faced already from other people around the world and also they might have discovered some way to tackle those problems. So this platform will provide to share the solution that have been discovered. Every problem posted by the user can have many response so user can select the efficient way to solve that particular problem. The problem posted by the user can be subjective and even open ended questions. This platform doesn’t have any restriction for the type of questions to be asked.

The volume of data has grown on a huge scale in recent days. As a result, there is always a plethora of choices in any product or service. It is very natural to get lost in the sheer amount of such choices and finding hard to make decisions. This project aims at addressing this problem by using recommendation system. This project makes use of Apache Spark, a distributed big data processing framework. Compared to the traditional map-reduce paradigm, Spark offers a huge advantage in the way it handles iterative and interactive algorithms. The dataset for the project were obtained from Stanford Network Analysis Platform and we observed that the Alternating Least Squares algorithm built into the MLlib library performs well by making use of the Spark RDDs for fast execution of iterative algorithms. We also observed that the results of the recommendation engine are accurate.