||Log keeper is a web application which is developed for the proper log management of the work done in a project. The primary objective is to supervise the work of the project members and help in the pricing of the project on hourly basis. The application also intend to help supervise the assigned work and the status of the project. The payment for the project members will be automatically calculated by the application itself. This application fits in to any organization which has to supervise the project members closely and pay them on hourly basis. This application can prove to be very helpful to ay project manager who has multiple projects to manage and many project members to supervise.
||TECH JOBS RECOMMENDATION SYSTEM BASED ON ITEM BASED COLLABORATIVE FILTERING
||With the vast amount of data that the word has nowadays, institutions are looking for more and more accurate ways of using data. Companies like Amazon use their huge amount of data to give recommendations to the users. The purpose of this project is likewise to give tech jobs recommendations to the users. Item Based Collaborative Filtering algorithm has been implemented in this project to calculate the similarities among the jobs, which is used to make a recommender system that uses user’s ratings information of the jobs to recommend the jobs that other users might be interested in.
||“Disease Prediction” system based on predictive modeling predicts the disease of the user on the basis of the symptoms that user provides as an input to the system. The system analyzes the symptoms provided by the user as input and gives the probability of the disease as an output Disease Prediction is done by implementing the Naïve Bayes Classifier. Naïve Bayes Classifier calculates the probability of the disease. Therefore, average prediction accuracy probability 60% is obtained.
||PREMIER LEAGUE GAME RESULT PREDICTION
||Prediction is a statement of an uncertain event which uses past data, analyzes it and predicts the future. This application focuses on predicting game result of the premier league on the basis of Back Propagation Algorithm. The input parameters chosen were Home Teams, Away Teams, Home Team Goals, Away Team Goals and Goal Differences. The accuracy of the system was found to be 47 percent.
||MOBILE APPLICATION TO AUTO CALCULATE TAXI AND MICROBUS FARE
||This is an android application built to provide the exact fare to the travellers (inside the Kathmandu valley) and (across Nepal). All the implementation part of this application is included in this report. The main objective behind this application is to help facilitate the traveller through the use of technology and give travellers more control over their travel fare.
This report also includes different analysis that is done prior to the implementation of the application. The application was built on android SDK and Android Studio was used as IDE. The user can choose the type of vehicle in which they are travelling on. The fare is calculated based on the type of vehicle and the standard fare provided by the department of transportation. The Fare is calculated on real time just like the meter of taxi. This application will track the location of user using GPS, Wi-Fi Signals and signals from the cell phone tower. This application will use the best current location based on the location from these three mediums.
The location of user is tracked every 6 seconds and the distance of the user is calculated based on these consecutive locations. This application uses Google maps so that the user can view the exact path in which they are travelling on.
|Arun Tamang and Sanjeev Budha
||BAKHRA GYAN – A MANAGEMENT INFORMATION SYSTEM FOR GOAT FARMING
||Goat rearing is a local business section being practiced by the large volume of people in rural Nepal. Goat has become one of the best profitable business to the farmers with low initial investment. The multifunctional and increased demand of goat meat in national and international market has drawn the attraction of local farmers and business persons on it. However due to the lack of veterinary information on goat farming, farmers are not in position to identify minor diseases and nutrients required without consulting any veterinary expert. At this position, the primary objective of the project is to help farmer by providing basic information regarding the goat farming. This is a web application where admin can collect the information about goat farming by consulting with the expert. The added information is then retrieved by the external users as per their request. In addition to this, the application provides intuitive interface for user to post queries on commercial goat farming in Nepal which than will be answered by the expert. The application uses decision tree algorithm to identify the dieses based on the symptoms added by the farmers.
|Sameer Koirala and Sushant Gurung
||ACCENT TUTOR: A SPEECH RECOGNITION SYSTEM
||Accent Tutor is Automatic Speech Recognition System for Nepali words based on template matching using Mel-frequency Cepstral Coefficients for feature extraction and Dynamic Time Warping for feature matching. Two testing approaches; speaker dependent and speaker independent were used by taking the recording of two Nepali words ‘नमस्ते’ and ‘धन्यवाद’ from 9 volunteers.
The accuracy of 81.25 % and 62.5 % was obtained for speaker dependent and speaker independent speech recognition system respectively.
|Sujan Chauhan and Pankaj KC
||Bigram Analyzer Model for Devanagari Word Prediction
||This paper includes the implementation of the Devanagari Keyboard for next word recommendation technique while typing in Devanagari. The prediction for the next word is made using Bigram Analyzer (sequences of words of length 2) for word categorization. For implementation of this project, two techniques have been used. To gather the list of all possible words, Web Crawling has been used and to predict the 'next' word and enable prediction multiple techniques like Content Scrapping, Content Filtering, Split Word have been used. The project successfully implements the predictive algorithm and recommending words that are widely used in very day communication by referring to frequency count of the pair of words and their conditional probability using Bigram Model.
||The project entitled “Doctor’s Time” is based on doctor, hospital and user entity. It provide platform for user to view list of hospital and doctor. User can search hospital and their associated doctor with respect to location of hospital. Besides detail description on hospital and doctor, user can request for appointment to doctor.
First come first service (FCFS) scheduling algorithm is implemented for scheduling the user appointment.
||ROUTINE MANAGEMENT SYSTEM
||Routine Management System is a web based application as well as a mobile device application. The system is used to create and manipulate the class routine of an educational institution. Routines of different educational institutions are created and maintained using the web application. Also the routine can be viewed from the web application. The primary purpose of developing a mobile application is to have an instant access of the routine from anywhere. The mobile application is primarily able to view the routine while the maintenance and creation is done through web application. Sample routine of Deerwalk Institute of Technology was created and used and was uploaded to the server and the users were easily able to view the routine from both the systems.
||SAHYOGI: LOCATE HOTELS
||There are many difficulties in finding places to spend some spare time and vacation. Hotels and home stay are generally cheap and finding the right one is a troublesome activity. This project provides a platform to search hotels based on locations and price. User is provided with the interface with the options to search either by location through Google places API or budget, based on the input given by the user appropriate result would be shown. If the search is through location required hotels available in the destination would be shown else if the search is by budget then the list of hotels matching the user budget would be shown.
Hence, this project aims to build a web application which would be a centralized information sharing platform which is focused to help students and teenagers know abou hotels’ cost and locations of various beautiful places to explore
||RESTAURAURANT RECOMMENDATION SYSTEM BASED ON COLLBORATIVE FILTERING
||Technology has created an exceptional platform for growth of every kind of businesses. The emerging use of technology urges the need of use of IT is all possible aspects of business. Today hotel and restaurant business is one of the most growing business and has been helping a lot in the economy of the country. Through this project, I have collected the necessary details of some of the most popular restaurants in Kathmandu Valley. The project analyzes the data of rating provided by the end users and use the data to recommend foods and restaurants to the users. The recommendation is based on the feedback of different people on the food items. The recommendation is done on the basis of collaborative filtering algorithm.
||SERVER MONITORING SYSTEM
||Network Monitoring Systems are essential in running the complex computer networks at present. They ensure all faults on the network are known and assist the network operator in fixing these faults. This project aims to plan and implement a system designed to monitor a modern network and includes all tools in a single extendable system. By using today’s technologies and making good design decisions, this project aims to build a unified and fresh network monitoring system that is easy to configure, maintain and use, streamlining the work flow of a network operator. The network administrator needs to know the various resource usages of the server computer. The administrator can see the resource usages such as RAM, CPU and Disk as well as the IP address of the server. This application can notify if any problems occur in the system (server failure). Network administrator can receive the alerts if the resource usages exceed the threshold value. The administrator can get the time-series graph of the resource usage of the server computer.
||AUTOMATIC FRUIT CLASSIFICATION USING ADABOOST ALGORITHM
||Object Recognition is an important study in Computer Science. Object recognition is emerging technology to detect and classify objects based on their characteristics. Fruit recognition and automatic classification of fruits is also a domain of object recognition and it is still a complicated task due to the various properties of numerous types of fruits. Different fruits have different shapes, sizes, color, textures and other properties. Similarly, some of the fruits like Tangerines and Mandarin Oranges share the same characteristics like color, texture, size, etc. This project aims to find a better way of a fruit classification method using supervised machine learning algorithms and image processing mechanisms based on multi-feature extraction methods. Firstly, we pre-process the training sample of fruits’ images. Preprocessing includes separating foreground and background, scaling and cropping the image to reduce the dimension so that the processing is fast. Then, we extract features from the fruit’s image, which includes color, texture and shape of the fruit image. Extracted features are then fitted into the AdaBoost classifier machine learning algorithm. Finally, the results obtained from the machine learning network are cross validated with the test sample. The output obtained will give us the prediction accuracy and class of the fruit that it has acknowledged. Experimental results have been collected using a fruit image database consisting of 5 different classes of fruits and 120 fruits images overall. Therefore, average prediction accuracy of more than 55% is obtained with a learning rate of 0.7.
|Sunil Shrestha and Aashish Bikram Lamichhane
||STUDENT BOARD SCORE PREDICTION : AN IMPLEMENTATION OF NEURAL NETWORK
||Prediction is one of the powerful technique that is used in neural network for accurate prediction using back propagation technique and multilayer perceptron. A study was conducted to predict the board score of the students studying in any particular batch in DWIT college. Midterm score, pre-board score, assignment score, internal score, and attendance score of the students were used for prediction and the result shows that board score can be predicted with 95 percent accuracy.
||IMAGE COMPRESSION USING DEEP AUTOENCODER
||Big enterprises and organizations store a vast amount of images. The current technologies of image compression use similar characteristics within an image to compress the image. Deep Autoencoder neural network trains on a large set of images to figure out similarities between the images in the set. The network then uses those similarities to compress them and represent them using fewer codes than usually possible from current compression techniques. This document builds on to demonstrate how Deep Autoencoder neural network can be used to train on and compress large sets of images. MNIST handwritten digits dataset is used as training and testing set. 28 x 28 image is converted to a vector of size 784 x 1 which is then fed to the network. The 784 x 1 vector is then gradually compressed in each iteration of the training phase of the network. Once the vector is compressed, the middle hidden layer of the network will hold a compressed feature vector which can be stored or transmitted. This compressed feature vector later can be converted back to obtain a near approximation of the original image.
|Kundan Sumsher Rana
||FOOD RECOMMENDATION SYSTEM BASED ON CONTENT FILTERING ALGORITHM
||The project entitled “Food Recommendation System based on Content Based Filtering Algorithm” recommends a food item list and displays the result depending on the nutritional value of the food item. Here, a primary food ingredients is selected. If the food items that are in the database have either ingredient as a main ingredient, then the food items are listed in order of their nutritional value. (WHO, 2010.)
The project analyzes the food items in database and their main ingredients. When the ingredient that the user queried about is found, in the database of the food items present, they are sorted and filtered according to the nutritional value they contain. The amount of calorie that the food contains is taken into consideration here. The suggestion to the user is based on the amount of calories present in the food item. The recommendation is done based on Content Based Filtering Algorithm.
|Anish Thakuri, Bidish Acharya
||1790 & 1797
||SENTIMENT ANALYSIS OF MOVIE REVIEWS
||Sentiment Analysis is a Natural Language Processing task to identify opinions expressed in a source material. There has been a lot of research in the field of Sentiment Analysis. Nowadays, as a lot of people voice their opinion on different social media sites, opinion mining has been very talked about topic, as it helps to analyze those opinion and generate some valuable information from it.
In this project, sentiment analysis of movie reviews has been performed by comparing the polarity of input text with the polarity of the words that are stored in the system, using the baseline model. This project has used movie reviews as the dataset. The system generates the result based on the text provided and displays it on the web-page deciding if the movie review is either positive, negative, or neutral.
||KIRAFATYANGRA - A TOOL TO RECOMMEND INSECTICIDES
||Insecticides are used to control diseases that occur in plants. If insecticides are not used properly then it can cause damage to environment and plant. The project analyzes the data of rating provided by the end users and use the data to recommend insecticides to be used for the plants to the farmer. The recommendation is based on the feedback of different people on the insecticides used. The recommendation is done on the basis of item based collaborative filtering algorithm. The system is useful for users as they get a recommendation as per their preference. In addition to that, the system also acts as an information system with the description and usages of different insecticides for different plants.
||MARKET BASKET ANALYSIS
||Market Basket Analysis is an important part of the analytical system in the retail organization to determine the placement of goods, designing sales promotion for different segments of customers to improve customer satisfaction and hence the profit of the supermarkets.MBA is well known activity of ARM ultimately used for business intelligent decisions. Mining frequent item sets and hence deduce rules to build classifiers with good accuracy is essential for efficient algorithm. The issues for a leading supermarket are addressed here using frequent item set mining.
The project uses file as database. Here, the itemsets and transactions of items are kept in a matrix form representing rows as list of items and column as transactions. The frequent item sets are mined from database using the Apriori algorithm and then the association rules are generated. The project is beneficial for supermarket managers to determine the relationship between the items that are purchased by their customers.
|Surya Raj Timsina
||TROUBLE TICKET MANAGER
||Different software tools have been developed and are in use in order to handle and manage the daily IT related issues in the IT industries like software industries, institutions, ISPs, repairing and support centers. but they are not the scalable according to the organizational need. Trouble Ticket Manager is the web based tool that is able to generate the trouble tickets and provide automated ticket routing to a respective technician or group of IT members. Trouble Ticket Manager provides the platform for the users to communicate with the IT Technician. The trouble ticket manager is able to generate the report based on the employee performance and the type of most re-currying issues in the organization.