Manuscripts

Recent Papers

Research Paper

Myanmar Word Sense Disambiguation based on HMM

In natural language processing, word sense disambiguation (WSD) is the problem of determining which "sense" (meaning) of a word is activated by the use of the word in a particular context, a process that appears to be largely unconscious in people. Nowadays, Word Sense Disambiguation (WSD) is an important technique for many natural language processing applications such as information retrieval and machine translation. Among them, the WSD technique is used for machine translation to find the correct sense of a word in a specific context. In machine translation, the input sentences in the source language are disambiguated in order to translate correctly in the target language which is Myanmar language that has many ambiguous words. Therefore, Hidden Markov Model-based WSD method is used to resolve the ambiguity of words in Myanmar language. A Myanmar-English bilingual corpus is used as the training data. This system can solve the semantic ambiguous problems that usually happen in Myanmar-to-English translation.

Published by: Phyo Phyo Wai, Htwe Htwe Lin, Kyi Kyi Lwin

Author: Phyo Phyo Wai

Paper ID: V5I4-1137

Paper Status: published

Published: April 11, 2020

Full Details
Research Paper

Relationship between the mass of a Schwarzschild Black Hole and the frequency of Hawking Radiation emitted

This research paper aims to understand how an increase in the mass of a Schwarzschild Black Hole affects the amount of Hawking Radiation emitted. To create a hypothesis, a theoretical and mathematical relationship between the two variables was derived. Several physics concepts including Schwarzschild radius, Blackbody Radiation and the Uncertainty principle along with certain reasonable assumptions were used to create this model. The paper used data collected from the AGN Database of Supermassive Black Holes, which was then extrapolated to form graphs to conclude that there is an inversely proportional relationship between the two variables in question with an increase in the mass of a Schwarzschild Black Hole the frequency of Hawking radiation decreases. The paper finds that Hawking Radiation emitted by AGN Supermassive Black Holes correspond to ‘long radio waves’ in the EM spectrum. The paper further examines the assumptions made while constructing the models used for investigating the hypothesis and addresses their impact on the conclusions drawn and data analysis conducted.

Published by: Pranad Gandhi

Author: Pranad Gandhi

Paper ID: V5I3-1137

Paper Status: published

Published: April 6, 2020

Full Details
Research Paper

Review on continuous speech recognition system

Automatic Speech Recognition System is based on the voice as the research area as a cross-disciplinary. Speech Recognition is the high-tech that allows the machine to turn the speech signal into the text through the process of identification and understanding and also make the function of natural voice communication. It has a very close relationship with acoustics, phonetics, linguistics, information theory, pattern recognition theory and neurobiology disciplinary. Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech application area, especially speech recognition step. However, in the past few years, many research has developed on the deep learning approach for speech related application areas such as speech emotional recognition system, speaker recognition and motor sound classification system. Nowadays, this development of deep learning approach has yielded the better results when compared to the others various applications including speech. Deep learning algorithm have been mostly used to further enhance the capabilities of computers so that it understands what humans can do, which includes speech recognition. . Deep Learning classifier is used in many research areas of speech recognition system and speaker recognition system to improve the accuracy of the system. The extracted features and converted feature images are used as the input of the various Deep learning classifiers to get the higher accuracy for speech recognition system. This paper provides the various result based on the different analysis of different speech recognition process when deep learning become a new popular area of machine learning for speech applications. As the experimental results of the system, the various recognition results of different deep learning classifiers in the recognition step of the speech recognition system.

Published by: Zaw Win Myint, Yin Win Chit, Phyoe Theingi Khaing

Author: Zaw Win Myint

Paper ID: V5I3-1143

Paper Status: published

Published: April 5, 2020

Full Details
Research Paper

Discovery and comparative study on spatial co-location and association rule mining of spatial data mining

Spatial data mining is the process of discovering interesting implicit knowledge in spatial databases that is an important task for understanding and use if spatial data-and knowledge-base and previously unknown, but potentially useful patterns from large spatial datasets; it is an important task for understanding and use the spatial data. Extracting interesting and useful patterns from spatial datasets is more difficult than extracting the corresponding patterns from conventional transaction based database due to the complexity of spatial data types, spatial relationships, and spatial autocorrelation The purpose of in this paper is to do comparative study on spatial co-location rule mining and association rule mining of spatial data mining application based on classical papers, and refine some previous algorithms.

Published by: Zaw Lin Oo, Mya Sandar Kyin

Author: Zaw Lin Oo

Paper ID: V5I3-1142

Paper Status: published

Published: March 31, 2020

Full Details
Research Paper

Online job advertisement search system using J48 Algorithm

The number of jobless graduates has become one of the serious problems existing both in the developing and developed countries, today. The Internet has changed the way of looking for jobs, through the development of an online job search system. A job search system is a kind of web application that provides an efficient way of searching the Internet or the web for job types available. Finding jobs that best suits the interests and skill set is quite a challenging task for job seekers. This paper proposes an online job advertisement search system that is the solution where the employers, as well as the job seekers, meet aiming at fulfilling their individual requirements. The main purpose of proposed system is to offer and provide different job types for the job seekers based on their preferred criteria. The system administrator will collect the suitable facts (qualifications, salary, age, etc.) of job positions. Then, this system will build decision tree for the job types to generate decision rules by using J48 algorithm. Finally, this system will display suitable job types for job seekers provided by employers.

Published by: Mya Sandar Kyin, Khin Mar Cho, Zaw Lin Oo

Author: Mya Sandar Kyin

Paper ID: V5I3-1141

Paper Status: published

Published: March 31, 2020

Full Details
Research Paper

Mobile game applications Recommendation System with item-based Collaborative Filtering

Recommender Systems are software techniques that are being widely used in many applications to suggest products, services, and items to potential users. The main purpose of Recommender Systems is to provide meaningful recommendations about the items or products to a collection of users for their interested items. There are two popular approaches in recommendation: user-based and item-based collaborative filtering. The difference between them is that user-based takes users’ behaviors and item-based takes items’ rating values. The purpose of this paper is to present a recommender system that provides meaningful recommended mobile phone applications to mobile phone users which are relative to their needs or targets. This system emphasizes mainly on item-based collaborative filtering method that bases on rating values of the items because the computational complexity of user-based recommendation grows linearly with the number of users. By using this system, mobile phone applications users can obtain optimized suggestions without their waste of time and effort.

Published by: Khin Mar Cho, Mya Sandar Kyin

Author: Khin Mar Cho

Paper ID: V5I3-1139

Paper Status: published

Published: March 31, 2020

Full Details
Thesis

A study to assess the effect of parent-child-programme on knowledge regarding balanced diet among school children in selected schools, at Kulasekharam, Kanyakumari District

School going period is considered a nutritionally critical period of life. The importance of nutrition in school-age children has been emphasizing because malnutrition during these can decrease not only in physical and mental development but also the learning ability of the children. In a school environment playing a board game has many benefits for children of all age groups, helping to develop their visual alertness increase their attention span, assisting with memory strategies and reasoning. The study was a quasi-experimental study with a quantitative approach. The study was conducted in 2 government schools ( Koodathooki & Kalladimamoodu ) at Kulasekharam. Data collection period was one month. the population was school-age children between the ages group of 9-11 years. Purposive sampling technique was used, sample size was 40. The tools used for data collection were demographic variables and structured questionnaire. The questionnaire consists of 20 items regarding a balanced diet. The findings revealed that the pretest means a score of the school-age children was 6.20. The post-test means the score of school-age children was 16.32. It showed that before implementing the snake and ladder game, the school-age children had a poor level of knowledge regarding a balanced diet. The ‘t’ value was 18.08, df =79,table value = 3.90 and P < 0.0001, so it is highly significant. The pretest means score of parents of school-age children was 5.46. The post-test mean score of parents of school-age children was 16.46. It showed that before implementing the intervention, the parents of school-age children had a poor level of knowledge regarding a balanced diet. The t value was 9.04, df = 29 and table value = 4.25 and P<0.0001, so it is highly significant. There is no statistically significant association between pretest level of knowledge with the selected demographic variables.

Published by: Pradheba K., Daly Christabel, Suja Renjani, Shanthi, Agin Navis Mary

Author: Pradheba K.

Paper ID: V4I12-1136

Paper Status: published

Published: December 16, 2019

Full Details
Research Paper

Marathi text summarization using Neural Networks

The internet is comprised of web pages, news articles, status updates, blogs and much more. It is difficult to navigate through this data as it is unstructured and usually discursive. Condensed versions of this data are generated so we can navigate it more effectively as well as check whether the larger documents contain the information that we are looking for. We propose a system for extractive text summarization method using neural networks for Marathi text. Extractive summaries or extracts are produced by identifying important sentences or words which are directly selected from the document. To perform extractive text summarization we propose to use a Recurrent Neural Network (RNN) – a type of neural network that can perform calculations on sequential data (e.g. sequences of words) – as it has become the standard approach for many Natural Language Processing tasks. The translation of the Marathi text to English will be done using the Google translate API for this proposed system.

Published by: Anishka Chaudhari, Akash Dole, Deepali Kadam

Author: Anishka Chaudhari

Paper ID: V4I11-1136

Paper Status: published

Published: November 18, 2019

Full Details
Case Study

Management of a rare case of spontaneous meckel’s diverticular perforation in an old age patient presented in the emergency room

Introduction: Meckel's diverticulum is the commonest congenital abnormality of the gastrointestinal tract. Haemorrhage, obstruction and inflammation are the three main categories of complications resulting from Meckel's diverticulum. Spontaneously perforation of Meckel's diverticulum is very rare and mimics acute appendicitis. Case: 50yr old male patient presented to the emergency room of our institute with abdominal pain for five days associated with fever with chills and complain of vomiting and anorexia. On the subsequent investigation it was found out to be a gastro-intestinal perforation. We operated the patient under general anaesthesia and intra-operative it was found out to be the Meckel’s diverticular perforation. So, we have done resection of contained part and done ileo-ileal anastomosis. Discussion: Meckel’s diverticulum is the result of dysgenesis of the small bowel as it develops in relation to the embryologic yolk sack and arises from the incomplete obliteration of the vitelline duct between the 5th and 8th weeks of gestation. Perforation is an uncommon complication of MD, and the symptom can mimic other acute abdominal conditions such as acute appendicitis as well as gynaecological and urological condition while in the emergency space. We should take diagnosis under consideration as a differential diagnosis when we encounter patients whose impression was firstly acute appendicitis and treatment should be followed accordingly.

Published by: Dr. Archit P. Parikh, Dr. Bhavesh V. Vaishnani, Dr. Setu N. Ladani, Dr. Jatin V. Dhameliya

Author: Dr. Archit P. Parikh

Paper ID: V4I9-1158

Paper Status: published

Published: November 1, 2019

Full Details
Research Paper

Declining crude oil prices and its implications on the indian economy

The following research paper aims to study the implications of oil prices on the Indian economy especially the impact of declining prices. Oil prices are highly important for the economy especially a developing country like India. India is the 3rd largest energy and oil consumer in the world after China and the US. Oil is a factor that helps an economy to move forward and achieve high levels of growth. The research paper studies the oil production and the supply of oil. This paper has tried to estimate using various tools a correlation between oil prices and various economic and market factors. The paper studies the impact on various leading and lagging indicators in the economy that help give an idea about the implications of declining oil price on the economy. This research entails a study of economic factors like inflation, GDP, the impact on foreign reserves, etc. India depends highly on oil imports and thus an intensive study is required to understand the impact of the oil prices. Major imports for India come from Iraq and Saudi Arabia and the demand for oil in India is on the rise with every coming year. This Research has helped us conclude that Oil prices have an inverse relation with stock prices which means declining oil process have a positive impact on the stock prices and thus the economy. It is observed statistically that the role of inflation is significant in declining GDP growth of Indian economy. The two variables of oil prices and GDP of India are negatively correlated. This can explained by the fact that increase in oil prices lead to greater inflation, lower profits of firms, lower tax revenues for the government, higher current account deficit and dampened investor sentiment. All this factors restrict the economy from growing at its full potential.

Published by: Manvi Mehta, Ruchi Mamania, Manasvi Mehta, Mehnaz Ali, Naman Bhatt, Yash Agarwal

Author: Manvi Mehta

Paper ID: V4I9-1157

Paper Status: published

Published: November 1, 2019

Full Details