Understanding Domain Knowledge in Initialization Method for K-Mean Clustering Algorithm in Medical Images

Tan, Xiao Jian; Mustafa, Nazahah; Mashor, Mohd Yusoff; Rahman, Khairul Shakir Ab; Muhamad, Wan Zuki Azman Wan; Leow, W.Z.; Cheor, Wai Loon; Oung, Q.W.

doi:10.1007/978-981-16-8690-0_71

Cited by 3 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each set of data is evaluated by computing the median. Initial centroids are computed using the speci ed medium, and clusters are built using the design of the initial cluster [6].…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Simple K-Mean and Parallel K-Mean Clustering Algorithms: Big Data Business Process Management Concept

Zada

Ali

Khan³

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

Data is the most valuable asset in any firm. As time passes, the data expands at a breakneck speed. A major research issue is the extraction of meaningful information from a complex and huge data source. Clustering is one of the data extraction methods. The basic K-Mean and Parallel K-Mean partition clustering algorithms work by picking random starting centroids. The basic and K-Mean parallel clustering methods are investigated in this work using two different datasets with sizes of 10000 and 5000, respectively. The findings of the Simple K-Mean clustering algorithms alter throughout numerous runs or iterations, according to the study, and so iterations differ for each run or execution. In some circumstances, the clustering algorithms’ outcomes are always different, and the algorithms separate and identify unique properties of the K-Mean Simple clustering algorithm from the K-Mean Parallel clustering algorithm. Differentiating these features will improve cluster quality, lapsed time, and iterations. Experiments are designed to show that parallel algorithms considerably improve the Simple K-Mean techniques. The findings of the parallel techniques are also consistent; however, the Simple K-Mean algorithm’s results vary from run to run. Both the 10,000 and 5000 data item datasets are divided into ten subdatasets for ten different client systems. Clusters are generated in two iterations, i.e., the time it takes for all client systems to complete one iteration (mentioned in chapter number 4). In the first execution, Client No. 5 has the longest elapsed time (8 ms), whereas the longest elapsed time in the following iterations is 6 ms, for a total elapsed time of 12 ms for the K-Mean clustering technique. In addition, the Parallel algorithms reduce the number of executions and the time it takes to complete a task.

show abstract

“…Each set of data is evaluated by computing the median. Initial centroids are computed using the speci ed medium, and clusters are built using the design of the initial cluster [6].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Technology, Earth sciences, engineering, social and economic sciences, medical sciences, and life are just a few of the elds that employ clustering. A parallel K-Mean clustering technique is proposed in [6,11]. Each data point's distance from the next is calculated.…”

Section: Simple Parallel K-mean Clustering Algorithmmentioning

confidence: 99%

Performance Evaluation of Simple K-Mean and Parallel K-Mean Clustering Algorithms: Big Data Business Process Management Concept

Zada

Ali

Khan³

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

AI in Context: Harnessing Domain Knowledge for Smarter Machine Learning

Miller,

Durlik,

Łobodzińska

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This article delves into the critical integration of domain knowledge into AI/ML systems across various industries, highlighting its importance in developing ethically responsible, effective, and contextually relevant solutions. Through detailed case studies from the healthcare and manufacturing sectors, we explore the challenges, strategies, and successes of this integration. We discuss the evolving role of domain experts and the emerging tools and technologies that facilitate the incorporation of human expertise into AI/ML models. The article forecasts future trends, predicting a more seamless and strategic collaboration between AI/ML and domain expertise. It emphasizes the necessity of this synergy for fostering innovation, ensuring ethical practices, and aligning technological advancements with human values and real-world complexities.

show abstract

Exploration of Therapeutic Strategies of Herbal Prescriptions for Carbuncle Treatment to Suggest Modern Approaches to Inflammatory Bowel Disease: Cluster and Network Analyses of the Book «Liu Juan Zi Gui Yi Fang»

Park,

Jeong,

Leem

2024

Healthcare

View full text Add to dashboard Cite

Inflammatory bowel disease (IBD) treatments in East Asian traditional medicine (EATM) originate from principles for treating abscesses and carbuncles. Understanding the therapeutic principles of Liu Juan Zi Gui Yi Fang (GYF) is essential for optimizing EATM treatment strategies for IBD, but quantitative analysis is lacking. This study aims to extract quantitative information on therapeutic strategies from GYF and present the EATM conceptual framework for IBD treatment. Oral prescriptions for carbuncles were selected, and their constituent herbs and indications were standardized and tokenized for analysis. An EATM expert group classified prescriptions based on the similarity of herbs and indications. Hierarchical and k-means cluster analyses were performed based on herb similarity. The herb–indication (H-I) network for all prescriptions was constructed. Additionally, H-I subnetworks based on the expert group’s classifications and the k-means clustering results were constructed and compared to identify treatment goals and the herbs used for each goal. The results showed that the treatment focused on abscess status, wound healing, and patient’s recovery capacity, with ‘fever’ and ‘deficiency’ as the main indications addressed by tonifying and anti-inflammatory herbs. The therapeutic principles identified in this study can serve as a foundation for developing future herbal intervention units. Further preclinical and clinical research is needed to validate these findings.

show abstract

Understanding Domain Knowledge in Initialization Method for K-Mean Clustering Algorithm in Medical Images

Cited by 3 publications

References 24 publications

Performance Evaluation of Simple K-Mean and Parallel K-Mean Clustering Algorithms: Big Data Business Process Management Concept

Performance Evaluation of Simple K-Mean and Parallel K-Mean Clustering Algorithms: Big Data Business Process Management Concept

AI in Context: Harnessing Domain Knowledge for Smarter Machine Learning

Exploration of Therapeutic Strategies of Herbal Prescriptions for Carbuncle Treatment to Suggest Modern Approaches to Inflammatory Bowel Disease: Cluster and Network Analyses of the Book «Liu Juan Zi Gui Yi Fang»

Contact Info

Product

Resources

About