Volume 5, Issue 3

Posted on by Arshdeep Kaur

Volume 5, Issue 3

March, 2020

Research Paper

1. 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 KyinResearch Area: Recommender System with Item Based Collaborative Filtering

Organisation: University of Computer Studies, Pyay, MyanmarKeywords: Recommender Systems, Collaborative Filtering (CF), Item-Based, Rating Values

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

2. 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 OoResearch Area: Data Mining

Organisation: University of Computer Studies, Taungoo, MyanmarKeywords: Decision Tree, Decision Rules, J48 Algorithm, Job Seekers, Job Advertisement

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

3. 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 KyinResearch Area: Data Mining

Organisation: University of Computer Studies, Taungoo, MyanmarKeywords: Data Mining, Discovery, Comparative, Spatial

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

4. 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 KhaingResearch Area: Digital Signal Processing

Organisation: University of Computer Studies, Magway, MyanmarKeywords: Deep Belief Network, Deep Neural Network, Support Vector Machines, Convolutional Neural Network, Artificial Intelligence

Full Details View PDF Search on Google
Full Details View PDF  Google
Research Paper

5. 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 GandhiResearch Area: Astrophysics

Organisation: United World College of South East Asia, Dover, SingaporeKeywords: Schwarzschild Black Hole, Hawking Radiation, AGN Supermassive Black Hole Database, Mass, Frequency of radiation

Full Details View PDF Search on Google
Full Details View PDF  Google