https://onlineresource.ucsy.edu.mm/handle/123456789/17 2026-07-18T15:46:02Z https://onlineresource.ucsy.edu.mm/handle/123456789/2335 A Study of Myanmar Word Segmentation Schemes for Statistical Machine Translation Thu, Ye Kyaw; Finch, Andrew; Sagisaka, Yoshinori; Sumita, Eiichiro Myanmar sentences are written as contiguous sequences of syllables with no characters delimiting the words. In statistical machine translation (SMT), word segmentation is a necessary step for languages that do not naturally delimit words. Myanmar is a low-resource language and therefore it is difficult to develop a good word segmentation tool based on machine learning techniques. In this paper, we examine various word segmentation schemes and their effect on the translation from Myanmar to seven other languages. We performed experiments based on character segmentation, syllable segmentation, human lexical/phrasal segmentation, and unsupervised/supervised word segmentation. The results show that the highest quality machine translation was attained with syllable segmentation, and we found this effect to be greatest for translation into subject-objectverb (SOV) structured languages such as Japanese and Korean. Approaches based on machine learning were unable to match this performance for most language pairs, and we believe this was due to the lack of linguistic resources. However, a machine learning approach that extended syllable segmentation produced promising results and we expect this can be developed into a viable method as more data becomes available in the future. 2013-02-26T00:00:00Z https://onlineresource.ucsy.edu.mm/handle/123456789/2334 Practical and Potential Applications of an Unmanned Airship based on Automatic Control - Embedded Computer System Design Nguyen, Tuan Anh; Lee, Seulki; Wi, Miseon; Eom, Taehoon; Park, Jong Sou; Comina, Germán; Bedon, Hector Unmanned Airship is useful and applicable for a variety of fields especially in resource exploration and environmental monitoring. This measure enhances the flexibility, on-demand supply and reasonable cost. This is a fruitful approach to meet actual needs. In this paper, we propose an embedded automatic computer system architecture design for an Unmanned Airship in terms of hardware system, software system and automatic control algorithm perspectives. At last, we discuss the practical results in resource exploration and environmental monitoring that we have achieved as well as other potential applications of the Unmanned Airship. 2013-02-26T00:00:00Z https://onlineresource.ucsy.edu.mm/handle/123456789/2333 Server Workload Classification and Analysis with Machine Learning Algorithms Myint, San Hlaing The main factor in measuring server performance is the accuracy of detection mechanisms. Sever is needed to detect server overload condition accurately. Therefore, it can be satisfied customers by reducing request drop rate. Server overload detection would be an initial step of overload control system. In order to provide such a detection mechanism, it is important to choose the best classifier which is the most suitable for our dataset. Selecting correct classifier maximize the performance of detection mechanism. In this paper, we present how server workload classification task is performed by using different machine learning classification methods and how the best classifier improve overload detection mechanism. We make a synthetic dataset by using window performance monitor tool. Many classifiers are evaluated over synthetic dataset. 2013-02-26T00:00:00Z https://onlineresource.ucsy.edu.mm/handle/123456789/2332 Analysis of Physical Health by Estimating Physical Working Capacity Nway, Zon Nyein; Kham, Nang Saing Moon It is clear that physically active people have a lower disease risk than the others who don’t have. Nowadays, the components of activity which determine particular health gains are poorly understood. Thus the analysis for physical health is the subject of current research interest. In this paper, a model is proposed to analyze the physical health by estimating physical working capacity. This study shows associations between physical parameters and physical performance by using multiple linear regressions. The aim of the use of multiple linear regression is to minimize the error in our prediction of the dependent variable, and minimize the residuals we made. And regression is a statistical method and is the most suitable method for this statistical information system. This paper is concerned with future contributions to a physical performance for exercise recommendations both to the public and to individuals. 2013-02-26T00:00:00Z