scispace - formally typeset
Search or ask a question
Author

N. A. Mardhiah

Bio: N. A. Mardhiah is an academic researcher from Universiti Tenaga Nasional. The author has contributed to research in topics: Tropospheric ozone & Solar energy. The author has an hindex of 1, co-authored 2 publications receiving 5 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, a Support vector Machine-SVM was used to predict ozone levels in the tropospheric ozone layer, and the results show that the SVM is capable of predicting ozone levels with acceptable level of accuracy.
Abstract: The prediction of tropospheric ozone concentrations is very important due to negative effects of ozone on human health, atmosphere and vegetation. Ozone Prediction is an intricate procedure and most of the conventional models cannot provide accurate prediction. Machine Learning techniques have been widely used as an effective tool for prediction. This study is investigating the implementation of Support vector Machine-SVM to predict Ozone concentrations. The results show that the SVM is capable in predicting ozone concentrations with acceptable level of accuracy. Sensitivity analysis has been conducted to show what is the most effective parameters on the proposed model .

6 citations

Journal ArticleDOI
TL;DR: In this article, the authors investigated the solar radiation prediction in Kuala Terengganu, Malaysia and developed and tested Genetic Programming Techniques (GP) models to predict solar radiation.
Abstract: The solar radiation prediction in Kuala Terengganu located in Terengganu, Malaysia was investigated in this study to improve the solar system design. Solar radiation data and number of parameters such as solar radiation, temperature, humidity, wind speed and sunshine hours were obtained from Malaysian Meteorological Malaysia MMD. In order to predict the solar radiation, Genetic Programming Techniques (GP) models were develop and tested. Two scenarios were considered in this study in order to validate the efficiency of the proposed model. Coefficients of determination (R2) for the solar radiation during training and testing phases were ranged between 0.99402 to 0.98934 for all months of the year. This study confirms the ability of GP to predict solar radiation values precisely and accurately. The predictions from the GP models could enable scientists to locate and design solar energy systems in Malaysia.

1 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: It can be concluded that hybrid algorithms have significantly improved the prediction accuracy while the majority of the proposed hybrid models have limitations; thus, there is a need to develop better hybrid algorithm that is able to tackle all the drawbacks of the improved algorithms and capable to capture the ozone concentration changes with a high level of accuracy.
Abstract: The prediction of tropospheric ozone concentrations is vital due to ozone’s passive impacts on atmosphere, people’s health, flora and fauna. However, ozone prediction is a complex process and the wide range of traditional models is incapable to obtain an accurate prediction. “Artificial intelligence”, “machine learning” and “ozone prediction model” search terms in the title, abstract or keywords are involved. Inclusion criteria include subject area (engineering, computer science), English language and being published from 2015. This criterion obtained 156 articles, which were categorized into 4 areas of interest based on the machine learning technique applied. Recently as a result of the rapid development in the technology and the increase in the number of measured data, artificial intelligence techniques have been intensively used in predicting ozone concentration as an alternative to the traditional models. Therefore, the main objective of this study is to investigate the most developed techniques that have been used in predicting ozone concentrations as well as theoretic approaches such as information set approaches, fuzzy set approach and probabilistic set approaches. It is clearly stated that the standalone algorithms such as decision tree (DT) and support vector machine (SVM) outperformed multilayer perceptron (MLP); however, the latter is massively implemented by many researchers in the prediction of ozone concentrations. This review paper investigated artificial intelligence techniques integrated with optimization approaches. It can be concluded that hybrid algorithms have significantly improved the prediction accuracy. However, the majority of the proposed hybrid models have limitations; thus, there is a need to develop better hybrid algorithm that is able to tackle all the drawbacks of the improved algorithms and capable to capture the ozone concentration changes with a high level of accuracy.

22 citations

Journal ArticleDOI
TL;DR: Three standard ML models: LR, NB, and SVM are developed for the classification problem and the results showed the significant impact of AI/ML approach in steel plates fault diagnosis problem.
Abstract: Fault detection is the task of discovering patterns of a certain fault in industrial manufacturing. Early detection of fault is an essential task in industrial manufacturing. Traditionally, faults are detected by human experts. However, this method suffers from cost and time. In this era of Industrial revolution IR 4.0, machine learning (ML) methods and techniques are developed to solve fault detection problem. In this study, three standard ML models: LR, NB, and SVM are developed for the classification problem. The experimental dataset used in this study consists of steel plates faults. The dataset is retrieved from UCI machine learning repository. Three standard evaluation methods: accuracy, precision, and recall are validated on the classification models. Logistic regression (LR) model achieved the highest accuracy and precision scores of 94.5% and 0.756 respectively. In addition, the SVM model had the highest recall score of 0.317. The results showed the significant impact of AI/ML approach in steel plates fault diagnosis problem.

4 citations

Journal ArticleDOI
TL;DR: In this paper, the global, diffuse and direct solar radiation empirically on a horizontal surface for the divisional district "Khulna" in Bangladesh (latitude 22o47΄N and longitude 89o34΄E) as well as predict correlations for it by using several meteorological data for 32 years between 1980 and 2012.
Abstract: This study is accomplished to calculate global, diffuse and direct solar radiation empirically on a horizontal surface for the divisional district “Khulna” in Bangladesh (latitude 22o47΄N and longitude 89o34΄E) as well as to predict correlations for it by using several meteorological data for 32 years between 1980 and 2012. The global radiation is found to be maximum in the month of April and minimum in the month of December here. The estimated values of the Angstrom’s regression constants a and b are 0.2388 and 0.5228 respectively. The other regression constants were also computed and the correlations proposed for Khulna can be used in future for the estimation of global, diffuse and direct solar radiation if the meteorological parameters remain available.

2 citations

TL;DR: Hemtanon and Aekwarangkoon as mentioned in this paper proposed a system for community health promotion in Thailand, which is based on the Thailand Excellence Center of Community Health Promotion (ECCHP).
Abstract: Siranuch Hemtanon, Saifon Aekwarangkoon, Nichnan Kittiphattanabawon Management Program, Faculty of Business Administration, Rajamangala University of Technology Srivijaya, Songkla, Thailand School of Nursing, Walailak University, Nakhon Si Thammarat, Thailand Excellence Center of Community Health Promotion, Walailak University, Nakhon Si Thammarat, Thailand School of Informatics, Walailak University, Nakhon Si Thammarat, Thailand