Phyu Thwe

Followers

Following

Public Views

Judith L Green

University of California, Santa Barbara

E. Wayne Ross

University of British Columbia

Alejandra B Osorio

Wellesley College

Remo Caponi

University of Cologne

Florin Curta

University of Florida

Roshan Chitrakar

Nepal College of Information Technology

Lev Manovich

Graduate Center of the City University of New York

Isad Saric

University of Sarajevo

José Manuel Santos

University of Salamanca

Guilherme Moerbeck

UERJ - Universidade do Estado do Rio de Janeiro / Rio de Janeiro State University

Interests

Uploads

Papers by Phyu Thwe

Object-oriented Composition Tool

A Markov Chain Approach on Daily Rainfall Occurrence

Markov modeling is one of the tools that can be used to help planners for assess precipitation. T... more Markov modeling is one of the tools that can be used to help planners for assess precipitation. The first order Markov chain model was used to predict daily precipitation intervals using transition probability matrices. The demand for precipitation is increasing, not only for data invention, but also to provide useful information in numerous applications, including water properties organization and the hydrological and agricultural subdivisions. In this study, the objective is to predict the probability of future precipitation of the city of Pyin Oo Lwin using the Markov chain model. The system was developed on the basis of the Markov method to forecast the occurrence of precipitation. The results show that models can forecast the state of a given day by 74 on average. Phyu Thwe | Ei Khaing Win | Hnin Pwint Myu Wai "A Markov Chain Approach on Daily Rainfall Occurrence" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6...

Download

Web Page Access Prediction Based on Integrated Approach

International Journal of Computer Science and Business Informatics, 2014

Predicting the user's web page access is a challenging task that is continuing to gain import... more Predicting the user's web page access is a challenging task that is continuing to gain importance as the web. Understanding users' next page access helps in formulating guidelines for web site personalization. Server side log files provide information that enables to reconstruct the user navigation sessions within the web site, where a session consists of a sequence of web pages viewed by a user within a given time. A web navigation behavior is helpful in understanding what information of online users demand. In this paper, we present the system that focuses on the improvements of predicting web page access. We proposed to use clustering techniques to cluster the web log data sets. As a result, a more accurate Markov model is built based on each group rather than the whole data sets. Markov models are commonly used in the identification of the next page to be accessed by the user based on the previously accessed pages. Then, we use popularity and similarity based-page rank a...

Download

Analyzing Sentiment Level of Social Media Data Based on SVM and Naïve Bayes Algorithms

Advances in Intelligent Systems and Computing, 2018

Social media is a popular network through which users can share their reviews about various topic... more Social media is a popular network through which users can share their reviews about various topics, news, products etc. People use internet to access or update reviews so it is necessary to express opinion. Twitter is a hugely valuable resource from which insights can be extracted by using text mining tools like sentiment analysis. Sentiment analysis is the task of identifying opinion from reviews. The system performs classification by combining Naive Bayes (NB) and Support Vector Machine (SVM). The system is intended to measure the impact of ASEAN citizens’ social media based on their usage behavior. The system is developed for analyzing National Educational Rate, Business Rate and Crime Rate occurred in Malaysia, Singapore, Vietnam and our country, Myanmar. The system compares the performance of these two classifiers in accuracy, precision and recall.

Proposed Approach For Web Page AccessPrediction Using Popularity And Similarity Based Page Rank Algorithm

Nowadays, the Web is an important source of information retrieval, and the users accessing the We... more Nowadays, the Web is an important source of information retrieval, and the users accessing the Web are from different backgrounds. The usage information about users are recorded in web logs. Analyzing web log files to extract useful patterns is called Web Usage Mining. Web usage mining approaches include clustering, association rule mining, sequential pattern mining etc. The web usage mining appr oaches can be applied to predict next page access. In this paper, we proposed a Page Rank-like algorithm is proposed for conducting web page access prediction. We extend the use of page rank algorithm for next page prediction with several navigational attributes, which are the similar ity of the page, size of the page, access-time of the page, duration of the page and transition(two pages visits sequentially) and frequency of page and transition.

Download

Ontology Based Web Page Classification System by Using Enhanced C4.5 and Naïve Bayesian Classifiers

Today, web is a huge repository of information which needs for accurate automated classifiers for... more Today, web is a huge repository of information which needs for accurate automated classifiers for Web pages. Classification of Web page is essential to many tasks in Web information retrieval such as maintaining, web directories and focused crawling. So, this system proposes as the web page classification system based on semantic logic. For semantic, this system uses the ontology that stores each concept of each word. For classification, this system proposes the enhanced C4.5 decision tree and Naive Bayesian (NB) classifiers. In the original C4.5 classification algorithm, the traditional entropy measure is unable to measure the appropriateness of nodes when the class labels are the same. By using semantic technology, this system can effectively support to classify web pages into each category. To show the effectiveness, this system is tested by using HTML documents in the computer science domain.

Naïve Bayes Classifier for Sentiment Analysis

Sentiment analysis is an approach to explore whether collected content is in a positive, negative... more Sentiment analysis is an approach to explore whether collected content is in a positive, negative, or neutral state. When thinking varied prospects, for instance, celebrities, politicians, food, places, or another topic, sentiment analysis is employed to examine people's opinions, likes, and interests. Social media are additionally used to communicate our feelings on items and administrations. The remarks and evaluations of millions of clients of the social site can be gathered to extricate their perspectives and emotions towards any item or administration and utilize this data for future business and business enhancements or for domain investigation. This paper presents an open source approach where we gather tweets from the Twitter API, at that point preprocessing, investigate, and visualize those tweets. This sentiment analysis depends on retrieving text information from the communicated web, at that point characterizing individuals' perspectives into three remarkable not...

Download

Performance Comparison between Keyword-based and Semantic-based Web Page Classification Systems

International Journal of Scientific and Research Publications (IJSRP), 2019

With the increase of information, web page classification as one of the methods of text mining pl... more With the increase of information, web page classification as one of the methods of text mining plays vital role in many management and organizing information. Web page classification is the process of assigning a web page to one or more predefined category labels. With the high availability of information from diverse sources, web page classification tasks have attained paramount importance. The traditional web page classification usually ignores the semantic relations among the keywords or web pages. To effectively solve the semantic problem, the ontology is used to capture the semantic information among web pages. So, this system proposes the semantic-based web page classification system by using NB-based C4.5 algorithm. This algorithm can solve the barrier from both the C4.5 algorithm and keyword-based web page classification. To know which classifier is more than other, this system compares the performance between keyword-based and semantic-based web page classification.

Download

Using Markov Model and Popularity and Similarity-based Page Rank Algorithm for Web Page Access Prediction

International Conference on Advances in Engineering and Technology (ICAET'2014) March 29-30, 2014 Singapore, 2014

With the rapid growth of the World Wide Web, the Internet has become a huge repository of data an... more With the rapid growth of the World Wide Web, the Internet has become a huge repository of data and serves as an important platform for the dissemination of information. The users' accesses to Web sites are stored in Web server log file. These series can be considered as a web access pattern which is helpful to find out the user behaviour. Through this behaviour information, we can find out the accurate user next request prediction that can reduce the browsing time of web pages. In this paper, we proposed to use clustering techniques to cluster the data sets from the results of the preprocessing phase. As a result, a more accurate Markov model is built based on each group rather than the whole data sets. The accuracy of low order Markov model is normally not satisfactory. Therefore, we use popularity and similarity-based page rank algorithm to make prediction when the ambiguous results are found.

Download

Object-oriented Composition Tool

A Markov Chain Approach on Daily Rainfall Occurrence

Download

Web Page Access Prediction Based on Integrated Approach

International Journal of Computer Science and Business Informatics, 2014

Download

Analyzing Sentiment Level of Social Media Data Based on SVM and Naïve Bayes Algorithms

Advances in Intelligent Systems and Computing, 2018