Advances in Data Mining and Applications in Power Plants

Ang, Bao; Pan, Wei; Wang, Wen Huan

doi:10.4028/www.scientific.net/amr.347-353.487

Cited by 3 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, data mining methods are in the form of regression, classification, clustering, and association rules. Due to the characteristic of the Thailand COVID-19 dataset, a clustering approach is considered to be applied to solve the problem [29]- [31].…”

Section: The Framework Of Data Miningmentioning

confidence: 99%

Thai COVID-19 patient clustering for monitoring and prevention: data mining techniques

Pansayta,

Chansanam

2024

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">This research aims to optimize emerging infectious disease monitoring techniques in Thailand, which will be extremely valuable to the government, doctors, police, and others involved in understanding the seriousness of the spread of novel coronavirus to improve government policies, decisions, medical facilities, treatment. The data mining techniques included cluster analysis using K-means clustering. The infection data were obtained from the open data of the digital government development agency, Thailand. The dataset consisted of 1,893,941 cumulative cases from January 2020 to October 2021 of the outbreak. The results from clustering consisted of 8 groups. Clustering results determined the three largest, three medium-sized, and the two most minor numbers of infected people, respectively. These clusters represent their activities, namely touching an infected person and checking themselves. The components of emerging diseases in Thailand are closely related to waves, gender, age, nationality, career, behavioral risk, and region. The province of onset was mainly in Bangkok and its vicinity or central Thailand, as well as industrial areas. Adult workers aged 19 to 27 years and 43 to 54 years or over were seeds of new infection sources.</span>

show abstract

Section: The Framework Of Data Miningmentioning

confidence: 99%

Thai COVID-19 patient clustering for monitoring and prevention: data mining techniques

Pansayta,

Chansanam

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Usually, data mining methods are in the form of regression, classification, clustering, and association rules [16], [17]. The four basic steps that constitute the data mining process are shown in Figure 1: problem definition, data pre-processing, data mining and discovery, result interpretation, and confirmation [18]. As aforementioned, the data mining and machine learning are classified into 3 approaches of association, classification, and clustering.…”

Section: B the Framework Of Data Miningmentioning

confidence: 99%

The Implementation of K-Means Clustering in Coal-fired Power Plant Performance

Wahyuningtyas¹,

Asrol²

2022

IJETAE

View full text Add to dashboard Cite

Performance monitoring for power plant industry is important to know current condition and determined the prior way for improvement strategy. This study aims to classified performance index which are Equivalent Availability Factor (EAF) and Equivalent Forced Outage Rate (EFOR) in various coal-fired power plant in Java Bali, Indonesia. The results of this plants grouping possible to be applied as one of the supports systems in real-time operational decisions to determine plant maintenance priorities. The proposed clustering model is possible to be applied for power plant’s control centre unit in Indonesia in grouping power plants based on performance indexes. The result show that there were 4 clusters of the power plant performance. The clustering drives to identify which plant that must be prioritized for improvement. The clustering method has a model accuracy rate of 87% which indicates that model was valid and applicable. For further research, a decision support system design was required for operational validation. Keywords—Decision-making, Decision support system, Kmeans clustering, Performance, Power plant.

show abstract