Implementation and comparison of K-means and fuzzy C-means algorithms for agricultural data

Shedthi, B Shabari; Shetty, Surendra; Siddappa, M.

doi:10.1109/icicct.2017.7975168

Cited by 22 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although we did our research on the data of a company that sells electronic components, we think that the proposed CRISP-DM model can also be used in the field of agriculture, where it would allow the analysis of consumer behavior, for example in the sale of seeds, agricultural products, or tools usable in the agro-industry. Unlike the other studies mentioned (Gandhi and Armstrong, 2016; Kumar and Balakrishnan, 2019; Shedthi et al, 2017;Zhao et al, 2009), we propose a model that uses a combination of multiple data mining methods and allows real-time research of consumer behavior analysis of sales of agricultural products in the environment of online sales.…”

Section: Resultsmentioning

confidence: 99%

“…Santosh Kumar and Balakrishnan (2019) use the Apriori algorithm directly to recommend products to customers in the agricultural market. Clustering is also often used in the analysis of agricultural data (Shedthi et al 2017;Zhao et al, 2009). However, none of these studies focuses on the use of these methods in real-time in the analysis of consumer behavior.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Online Consumer Behavior - Design of CRISP-DM Process Model

Exenberger

Bucko

2020

AOL

View full text Add to dashboard Cite

The basis of the modern marketing of a business entity is to know the behavior of its customers. Advanced artificial intelligence methods, such as data mining and machine learning methods, penetrate data analysis. The application of these methods is most appropriate in the case of online sales of any goods in large quantities and various industries. They are very often used in the sale of electronics, PCs or clothes. However, it is also possible to apply them to the agricultural industry, not only in B2C, but also in B2B in the sale of seeds, agricultural products, or agricultural machinery. Appropriate combinations of offers and knowledge of customers can bring the selling entity higher profits or competitive advantages. The main goal of our study is to design a CRISP-DM process model that will enable small businesses to analyze online customers' behavior. To reach the main goal we perform a data analysis of the online sales data by using machine learning methods as clustering, decision tree and association rules mining. After evaluating the proposed model, we discuss its use of the proposed model in the field of internet sales in the agricultural sector.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analysis of Online Consumer Behavior - Design of CRISP-DM Process Model

Exenberger

Bucko

2020

AOL

View full text Add to dashboard Cite

show abstract

“…Dalam tiap iterasinya dihitung keanggotaan data terhadap pusat cluster baru. Proses akan berhenti apabila pusat cluster serta keanggotaan data tidak berubah [14].…”

Section: Clusteringunclassified

Perbandingan Metode Clustering dalam Pengelompokan Data Puskesmas pada Cakupan Imunisasi Dasar Lengkap

Saputra

Chusyairi²

2020

RESTI

View full text Add to dashboard Cite

The coverage of Health Care Center toward UCI (Universal Child Immunization) at Banyuwangi Regency in 2018 met the target 91%. Onfortunately with a high amount of immunization, the number of infant deaths reached 138 infants. Total number increased 111 from the previous year. A review of the complete basic immunization data needs to be done. In this research, a clustering method was proposed by comparing the K-Means and Fuzzy C-Means (FCM) algorithm in grouping Health Care Center data. Silhouette Coefficient and Standart Deviation were used to evaluate clusters that were perfomed to find out the accuracy in grouping data. The result showed that the FCM algorithm was better than K-Means based on Silhouette Coefficient results that were close to good, and the calculation of Standart Deviation had a smaller result that was 0.0918 than K-Means with the results of 0.0942. The Grouping of Heath Care Center data can be considered by the Health Department of Banyuwangi Regency in evaluating complete basic immunization services, especially in groups with poor immunization services to reduce infant and child mortality, so a disease that can be prevented with immunization become lower.

show abstract

“…A necessidade de um parâmetro k definido de forma explícita, costuma ser um problema tendo em vista que nem sempre se sabe quantos grupos existem a priori. Mesmo existindo outras possibilidades para descrever este método de particionamento de um conjunto de dados, de forma genérica o algoritmo K-Means pode ser descrito conforme fluxograma exibido na Figura 1 [34]. Figura 1.…”

Section: K-meansunclassified

Group Labeling Methodology Using Distance-based Data Grouping Algorithms

Filho

Machado

Veras

et al. 2020

RITA

View full text Add to dashboard Cite

Clustering algorithms are often used to form groups based on the similarity of their members. In this context, understanding a group is just as important as its composition. Identifying, or labeling groups can assist with their interpretation and, consequently, guide decision-making efforts by taking into account the features from each group. Interpreting groups can be beneficial when it is necessary to know what makes an element a part of a given group, what are the main features of a group, and what are the differences and similarities among them. This work describes a method for finding relevant features and generate labels for the elements of each group, uniquely identifying them. This way, our approach solves the problem of finding relevant definitions that can identify groups. The proposed method transforms the standard output of an unsupervised distance-based clustering algorithm into a Pertinence Degree (GP), where each element of the database receives a GP concerning each formed group. The elements with their GPs are used to formulate ranges of values for their attributes. Such ranges can identify the groups uniquely. The labels produced by this approach averaged 94.83% of correct answers for the analyzed databases, allowing a natural interpretation of the generated definitions.

show abstract

Implementation and comparison of K-means and fuzzy C-means algorithms for agricultural data

Cited by 22 publications

References 5 publications

Analysis of Online Consumer Behavior - Design of CRISP-DM Process Model

Analysis of Online Consumer Behavior - Design of CRISP-DM Process Model

Perbandingan Metode Clustering dalam Pengelompokan Data Puskesmas pada Cakupan Imunisasi Dasar Lengkap

Group Labeling Methodology Using Distance-based Data Grouping Algorithms

Contact Info

Product

Resources

About