Yangon Technological University

About: Yangon Technological University is a education organization based out in Yangon, Myanmar. It is known for research contribution in the topics: Drainage basin & Fault (power engineering). The organization has 205 authors who have published 185 publications receiving 1071 citations.

Performance Comparison of Feature Selection Methods

Abstract: Feature Subset Selection is an essential pre-processing task in Data Mining. Feature selection process refers to choosing subset of attributes from the set of original attributes. This technique attempts to identify and remove as much irrelevant and redundant information as possible. In this paper, a new feature subset selection algorithm based on conditional mutual information approach is proposed to select the effective feature subset. The effectiveness of the proposed algorithm is evaluated by comparing with the other well-known existing feature selection algorithms using standard datasets from UC Iravine and WEKA (Waikato Environment for Knowledge Analysis). The performance of the proposed algorithm is evaluated by multi-criteria that take into account not only the classification accuracy but also number of selected features.

Parameter optimization of a diesel engine to reduce noise, fuel consumption, and exhaust emissions using response surface methodology:

Abstract: The conflicting effects of the operating parameters and the injection parameter (injection timing) on engine performance and environmental pollution factors is studied in this paper. As an optimization objective, a 3.5 kW small direct injection diesel engine was used as the test engine, and its speed, load, and static injection timing were varied as per 4 × 4 × 3 full factorial design array. Radiated engine noise, smoke level, brake specific fuel consumption, and emissions of unburned hydrocarbons and nitrogen oxides were captured for all test runs. Objective functions relating input and output parameters were obtained using response surface methodology (RSM). Parameter optimization was carried out to control output responses under their mean limit using multi-objective goal programming and minimax programming optimization techniques.

A local level relationship between floods and poverty: A case in Myanmar

Abstract: The frequency of floods is predicted to increase in south-east Asia, and this may exacerbate the living conditions of poor people in flood-prone areas. Though much work has been conducted on the effects of poverty, there is a pressing need for more analysis on the local effects of floods. The work that does exist usually is based on qualitative analysis. This paper investigates the relationship between floods and poverty at a household level. It is based on a questionnaire survey conducted in Bago city, Myanmar. Using multi-regression analysis and spatial analysis, we found that poor people tend to live in flood-prone areas, and that floods can cause and exacerbate poverty. Spatial distribution results show that the people who suffer most from floods are those who live in the worst conditions. We discuss the resettlement of communities as an option for countering the effects of floods and alleviating poverty.

Smart Air Quality Monitoring System with LoRaWAN

Abstract: Nowadays, cities all over the globe are transforming into smart cities. Smart cities initiatives need to address environmental concerns such as air pollution to provide clean air. A scalable and cost-effective air monitoring system is imperative to monitor and control air pollution for smart city development. Air pollution has notable effects on the well-being of the population a whole, global atmosphere, and worldwide economy. This paper presents a scalable smart air quality monitoring system with low-cost sensors and long-range communication protocol. The sensors collect four parameters, temperature, humidity, dust and carbon dioxide in the air. The proposed end-to-end system has been implemented and deployed in Yangon, the business capital of Myanmar, as a case study since Jun 2018. The system allows the users to log in to an online dashboard to monitor the real-time status. In addition, based the collected air quality parameters for the past two months, a machine learning model has been trained to make predictions of parameters such that proactive actions can be taken to alleviate the impacts from air pollution.

Coverage Path Planning for Decomposition Reconfigurable Grid-Maps Using Deep Reinforcement Learning Based Travelling Salesman Problem

Abstract: Optimizing the coverage path planning (CPP) in robotics has become essential to accomplish efficient coverage applications. This work presents a novel approach to solve the CPP problem in large complex environments based on the Travelling Salesman Problem (TSP) and Deep Reinforcement Learning (DRL) leveraging the grid-based maps. The proposed algorithm applies the cellular decomposition methods to decompose the environment and generate the coverage path by recursively solving each decomposed cell formulated as TSP. A solution to TSP is determined by training Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) layers using Reinforcement Learning (RL). We validated the proposed method by systematically benchmarked with other conventional methods in terms of path length, execution time, and overlapping rate under four different map layouts with various obstacle density. The results depict that the proposed method outperforms all considered parameters than the conventional schemes. Moreover, simulation experiments demonstrate that the proposed approach is scalable to the larger grid-maps and guarantees complete coverage with efficiently generated coverage paths.