Optimalisasi K-MEDOID dalam Pengklasteran Mahasiswa Pelamar Beasiswa dengan CUBIC CLUSTERING CRITERION

Defiyanti, Sofi; Jajuli, Mohamad; Rohmawati, Nurul

doi:10.25077/teknosi.v3i1.2017.211-218

Cited by 19 publications

(19 citation statements)

References 6 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Beberapa penelitian tentang data mining seperti: [1] menunjukkan bahwa dengan penggunaan 2 cluster menghasilkan kelompok data dengan potensi yang dimiliki yaitu cluster 1 termasuk dalam potensi tinggi dengan hasil rata-rata brightness sebesar 344.470K dengan rata-rata confidence 87.08% dan cluster 2 masuk dalam potensi sedang dengan hasil rata-rata brightness sebesar 318.800K dengan rata-rata confidence sebesar 58,73%. Penelitian lainnya oleh (Defiyanti, Jajuli & W 2017). K-medoids merupakan salah satu metode pengelompokkan dalam data mining yang merupakan bagian dari partitional clustering.…”

Section: Pendahuluanunclassified

Implementasi Metode K-Medoids Clustering Dalam Pengelompokan Data Penyakit Alergi Pada Anak

Ningrum

Irawan

Lubis

2021

jurasik

View full text Add to dashboard Cite

Allergies are an abnormal response from the immune system. People who experience allergies have an immune system that reacts to a substance that is usually harmless in the environment. There are two limitations in this study, namely, seafood allergy and air allergy. In this study, the data used were sourced from the National Statistics Agency in 2011-2019. This study uses data mining techniques in data processing with the k-medoids clustering method. The k-medoids method is a clustering method that functions to split the dataset into several groups. The advantages of this method are able to overcome the weaknesses of the k-means method which is sensitive to outliers. Another advantage of this method is that the results of the clustering process do not depend on the order in which the dataset is entered. This method can be applied to data on the percentage of children affected by allergies by province, so that it can be seen the grouping of provinces based on this data. From this grouping data obtained 3 clusters namely low cluster (2 provinces), medium cluster (30 provinces) and high cluster (2 provinces) from the percentage of allergy immunization under five in each province. It is hoped that this research can provide information to the health department, especially the public health center regarding data grouping of Allergic Diseases in children in Indonesia which has an impact on equity in giving anti-allergic immunization to children in Indonesia

show abstract

Section: Pendahuluanunclassified

Implementasi Metode K-Medoids Clustering Dalam Pengelompokan Data Penyakit Alergi Pada Anak

Ningrum

Irawan

Lubis

2021

jurasik

View full text Add to dashboard Cite

show abstract

“…Clustering1atau1klusterisasi adalah salah1satu alat bantu1pada data mining yang bertujuan1mengelompokkan objek-objek ke dalam1cluster-cluster [1]. Dalam data mining ada dua jenis1metode…”

Section: Pendahuluanunclassified

Rekomendasi Grup Pada Website Alumni Teknik Informatika Universitas Muhammadiyah Malang

Saputra

Wicaksono

Azhar

2020

View full text Add to dashboard Cite

AbstrakBelakangan ini hampir seluruh universitas yang ada di indonesia memiliki sistem informasi alumninya sendiri-sendiri. Sistem informasi alumni mampu memberikan informasi tentang kondisi alumninya setelah menyelesaikan masa perkuliahannya. Alumni merupakan aktor yang berperan penting dalam pendidikan. Saat ini jurusan Informatika Fakultas Teknik Universitas Muhammadiyah Malang telah memiliki website alumni. Permasalahannya belum adanya sistem yang memberikan alumni rekomendasi grup pada sistem, sehingga para alumni mampu saling bertukar informasi didalamnya. Dengan adanya data alumni dan juga di dukung dengan adanya tracer study, dapat di bentuk suatu rekomendasi grup dari data tracer study. K-medoid adalah metode pengelompokan data ke dalam sejumlah cluster tanpa adanya struktur hirarki antara satu dengan yang lainnya. Algoritma k-medoid memiliki nilai coefficient yang lebih tinggi di bandingkan dengan k-means dalam penelitian ini. Yang mana k-medoid mendapatkan nilai rata-rata Silhouette Score 0.7325888099 dalam pengujian dengan jumlah cluster 5 dan perulangan sebanyak 10 kali. Jika dibandingkan dengan k-means yang hanya memiliki nilai rata-rata Silhouette Score 0.6872873866.AbstractLately, Almost all universities in Indonesia have their own alumni information systems. The alumni information system is able to provide information about the condition of its alumni after collage graduation. Alumni are actors who play important role in education. Currently, the Department of Informatics, Faculty of Engineering, University of Muhammadiyah Malang has an alumni website. The problem is the absence of system that gives alumni group recommendation on the system, so that alumni are able to exchange information in this website. With the alumni data and also supported by the existence of a tracer study, it can be formed as group recommendation from the data tracer study. Clustering is one of tools in data mining that aims to group object into clusters. K-medoid is a method of grouping data into a number of clusters without hierarchical structure from one another. The k-medoid algorithm has higher coefficient value compared to k-means in this study. This K-medoid gets an average value of Silhouette Score 0.7325888099 in testing with the number of clusters 5 and repetitions 10 times. When compared with k-means which only has an average value of Silhouette Score 0.6872873866.

show abstract

“…Data mining berkaitan dengan bidang ilmuilmu lain, seperti database system, data warehousing, statistik, machine learning, information retrieval, dan komputasi tingkat tinggi. Selain itu, data mining didukung oleh ilmu lain seperti neural network, pengenalan pola, spatial data analysis, image database, signal processing [2]. Teknik data mining digunakan untuk memeriksa basis data berukuran besar sebagai cara untuk menemukan pola yang baru dan berguna [3].…”

Section: Pendahuluanunclassified

Penerapan Algoritma K-Medoids Untuk Mengelompokkan Penduduk 15 Tahun Keatas Menurut Lapangan Pekerjaan Utama

Pulungan¹,

Suhada²,

Suhendro³

2019

KOMIK

View full text Add to dashboard Cite

The main occupations in 15 years and above are on average not suitable for their age, which is done by adults but is done by people 15 years and older. Therefore, I do grouping data on population 15 years and above so that we know what their main jobs are. Here I use data mining with the K-Medoids method to classify the population of 15 years according to the main occupation, this research was conducted in Indonesia. The K-Medoids method is a method of collecting data with the classic clustering partitioning technique that groups datasets from n objects into K groups known a priori. A useful tool for determining k is a silhouette. It is stronger to be agreed upon and bigger than K-Means because it must add to the difference in the difference in the square of the euclidean distance. Attractions that can be determined as cluster objects are average differences for all objects in the cluster are minimal. That is the easiest point in the cluster. K-Medoids uses objects in a collection of objects to represent a cluster. The object chosen to represent a cluster is called medoid. Clusters are built by calculating the proximity they have between a medoid and non-medoid objects.Keywords: Data mining, K-Medoid, Main Job Fields 15 years and above

show abstract

Optimalisasi K-MEDOID dalam Pengklasteran Mahasiswa Pelamar Beasiswa dengan CUBIC CLUSTERING CRITERION

Cited by 19 publications

References 6 publications

Implementasi Metode K-Medoids Clustering Dalam Pengelompokan Data Penyakit Alergi Pada Anak

Implementasi Metode K-Medoids Clustering Dalam Pengelompokan Data Penyakit Alergi Pada Anak

Rekomendasi Grup Pada Website Alumni Teknik Informatika Universitas Muhammadiyah Malang

Penerapan Algoritma K-Medoids Untuk Mengelompokkan Penduduk 15 Tahun Keatas Menurut Lapangan Pekerjaan Utama

Contact Info

Product

Resources

About