scholarly journals Analisa Hasil Pengelompokan Wilayah Kejadian Non-Kebakaran Menggunakan Agglomerative Hierachical Clustering di Semarang

2021 ◽  
Vol 15 (2) ◽  
pp. 63
Author(s):  
Desy Exasanti ◽  
Arief Jananto
Keyword(s):  
Hierarchical Clustering ◽  
Manhattan Distance ◽  
Agglomerative Hierarchical Clustering ◽  
Single Linkage ◽  
Bottom Up ◽  
Environment Analysis ◽  
Complete Linkage ◽  
Average Linkage

Abstrak−Klasterisasi merupakan metode pengelompokan dari data yang sudah diketahui label kelasnya untuk menemukan klaster baru dari hasil observasi. Dalam klasterisasi banyak metode yaitu metode terpusat, hirarki, kepadatan dan berbasis kisi, namun dalam penelitian yang dilakukan ini dipilih metode berbasis hirarki. Metode hirarki ini bekerja melakukan pengelompokan objek dengan membentuk hirarki klaster namun bukan berarti selalu digambarkan dengan hirarki dalam organsasi. Dipilihnya Agglomerative Hierarchical Clustering dimana merupakan jenis dari bawah ke atas atau biasa disebut (bottom-up) dalam metode ini objek yang akan diuji dianggap sebagai objek tunggal sebagai klaster dan lalu dilakukan iterasi untuk menemukan klaster-klaster yang lebih besar. Data yang akan digunakan adalah data non-kebakaran pada Dinas Pemadam Kebakaran Kota Semarang ynng mana akan dilakukan pengelompokan wilayah penanganan non-kebakaran. Dinas Pemadam Kebakaran melakukan penanganan bukan hanya kebakaran saja namun ada banyak hal yang sebenarnya dapat ditangani oleh petugas pemadam kebakaran, kejadian non-kebakaran ada beberapa seperti evakuasi reptil, evakuasi kucing, penyelamatan korban kecelakaan dan lain sebagainya. Dari data non-kebakaran dari 16 kecamatan di Kota Semarang pada tahun 2019 akan dilakukan uji menggunakan tiga algoritma yaitu Single Lingkage, Average Linkage dan Complete Linkage . Adapun dari algoritma Single Linkage dilakukan prosedur pemusatan dari jarak terkecil antar objek data, algoritma Average Linkage dilakukan prosedur dari jarak rata-rata objek data, sedangkan jika algoritma Complete Linkage dilakukan prosedur pemusatan dari jarak yang terbesar. Implementasi dan visualiasi dari data uji coba yang dilakukan di penilitian ini menggunakan tools WEKA 3.8.4, Wakaito Environment Analysis for Knowledge atau yang biasa dikenal dengan WEKA ini merupakan software yang menggunakan bahasa pemrograman java. Dari dataset 380 data diambil sampel 100 data untuk diuji mengunakan WEKA menggunakan metode perhtungan jarak Manhattan Distance dengan 3 cluster. Hasil dari data uji coba dapat divisualisasikan dengan visualisasi dendogram pada fitur visualize tree  dan jika dilakukan visualisasi dalam bentuk grafik dapat dilakukan menggunakan fitur visualize clusters assignment.

scholarly journals Comparison of Single Linkage, Complete Linkage, and Average Linkage Methods on Community Welfare Analysis in Cities and Regencies in East Java

2021 ◽  
Vol 18 (1) ◽  
pp. 130-140
Author(s):  
Yanuwar Reinaldi ◽  
Nurissaidah Ulinnuha ◽  
Moh. Hafiyusholeh
Keyword(s):  
Hierarchical Clustering ◽  
National Development ◽  
Clustering Methods ◽  
Single Linkage ◽  
Complete Linkage ◽  
Average Linkage ◽  
Linkage Methods ◽  
Silhouette Index ◽  
Linkage Method ◽  
Index Value

Community welfare is one of the important points for a region and is also the essence of national development. The welfare of the people in Indonesia is fairly unequal, especially in East Java. To be able to map an area to the welfare of its people in East Java, one way that can be used is to use clustering. The hierarchical clustering method is one of the clustering methods for grouping data. In hierarchical clustering, single linkage, complete linkage, and average linkage methods are suitable methods for grouping data, which will compare the best method to use. The results of the calculation show that the average linkage method with three clusters is the best calculation with a silhouette index value of 0.6054, with the 1st cluster there are 23 regions, namely the city/district with the highest community welfare, the 2nd cluster there are 11 regions, namely cities/districts with moderate social welfare, and in the third cluster there are 4 regions, namely cities/districts with the lowest community welfare.

scholarly journals Perbandingan Metode Single Linkage, Complete Linkage Dan Average Linkage dalam Pengelompokan Kecamatan Berdasarkan Variabel Jenis Ternak Kabupaten Sidoarjo

Jurnal INFORM ◽  
2019 ◽  
Vol 4 (2) ◽  
Author(s):  
Sulthan Fikri Mu'afa ◽  
Nurissaidah Ulinnuha
Keyword(s):  
Farm Animals ◽  
Single Linkage ◽  
Daily Lives ◽  
Food Ingredients ◽  
Complete Linkage ◽  
Material Sources ◽  
Average Linkage ◽  
Linkage Method ◽  
Livestock Products ◽  
Labor Resources

Livestock products are widely used by the community in their daily lives, for example as food ingredients, industrial material sources, labor resources, fertilizer sources and energy sources. This study aims to cluster livestock potential with data on livestock population in Sidoarjo Regency in 2017 with single linkage, complete linkage and average linkage method and comparing performance of the methods. In this cluster, the data will be grouped into 3 clusters. The results of the three clusters were obtained by sixteen sub-districts in the first cluster with the potential for low livestock and each one in the second and third clusters for single linkage and average linkage. While complete linkage obtained fifteen sub-districts in the first cluster with high potential for livestock, two sub-districts in the second cluster with the potential of medium livestock and one sub-district in the third cluster with the potential for high farm animals. In the comparison of the standard deviation ratio value, the smallest value of 0.222 is obtained by complete linkage, which shows that complete linkage is better than single linkage and average linkage in the case of subgrouping based on Sidoarjo regency livestock types.

scholarly journals PENCARIAN CLUSTER OPTIMUM PADA SINGLE LINKAGE, COMPLETE LINKAGE DAN AVERAGE LINKAGE

2019 ◽  
Vol 8 (3) ◽  
Author(s):  
Nur Asiska, Neva Satyahadewi, Hendra Perdana
Keyword(s):  
Global Optimum ◽  
Single Linkage ◽  
Complete Linkage ◽  
Average Linkage

Analisis cluster merupakan teknik multivariat yang digunakan untuk mengelompokkan objek/kasus (responden) menjadi kelompok-kelompok yang lebih kecil dimana setiap kelompok berisi objek/kasus yang mirip satu sama lain. Dalam analisis cluster dua prosedur yang digunakan untuk pengelompokan yaitu analisis cluster hierarki dan non-hierarki. Penentuan jumlah cluster optimum yang tepat untuk digunakan diperoleh melalui identifikasi pola pergerakan varian pada cluster yang mencapai global optimum. Penemuan posisi cluster yang mencapai global optimum pada pola pergerakan varian diperoleh melalui penerapan metode valley-tracing. Pada penelitian, digunakan penerapan analisis cluster hierarki untuk mengelompokkan kabupaten/kota di Kalimantan Barat berdasarkan indikator IPM. Dari hasil analisis pembentukan cluster optimum pada metode single linkage diperoleh cluster optimum sebanyak 4 cluster. Pada metode complete linkage diperoleh cluster optimum sebanyak 5 cluster. Metode average linkage menghasilkan cluster optimum sebanyak 5 cluster Kata Kunci : Analisis Multivariat, Analisis Cluster, Cluster Optimum 

scholarly journals PENGELOMPOKAN DESA/KELURAHAN DI KOTA DENPASAR MENURUT INDIKATOR PENDIDIKAN

2016 ◽  
Vol 5 (2) ◽  
pp. 38
Author(s):  
NI WAYAN ARIS APRILIA A.P ◽  
I GUSTI AYU MADE SRINADI ◽  
KARTIKA SARI
Keyword(s):  
Cluster Analysis ◽  
Data Analysis ◽  
The Other ◽  
Single Linkage ◽  
Complete Linkage ◽  
Hierarchical Method ◽  
Average Linkage ◽  
Different Characteristics

Cluster analysis is one of data analysis used to classify objects in clusters which has objects with the same characteristics, whereas the other cluster has different characteristics. One part of the method of analysis cluster is hierarchy method. In a hierarchical method there are methods of linkage in the form of incorporation. Generally, methods of linkage is divided into 5 methods: single linkage, complete linkage, average linkage, Ward and centroid.  The purpose of this study was to determine the best method of linkage among the method of single linkage, complete linkage, average linkage, and Ward, using Euclidean and Pearson proximity distance. Base on the smallest value of CTM (Cluster Tightness Measure), the best method of linkage as a result of this research was average linkage in Pearson distance.

scholarly journals System for Determining Public Health Level Using the Agglomerative Hierarchical Clustering Method

Compiler ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 95
Author(s):  
Suhirman Suhirman ◽  
Hero Wintolo
Keyword(s):  
Mortality Rate ◽  
Hierarchical Clustering ◽  
Clustered Data ◽  
Infant Mortality Rate ◽  
Linkage Data ◽  
Agglomerative Hierarchical Clustering ◽  
Indicator Values ◽  
Complete Linkage ◽  
Health Level ◽  
Child Mortality Rate

Regions having higher level of welfare do not always have better indicator values than other regions having lower level of welfare. The problem is the lack of information related to the indicator values needed to determine the health level. Therefore, clustering using health data becomes necessary. Data were clustered to see the maximum or the minimum level of similarity. The clustered data were based on the similarity of four morality indicator values of the regional health level. Morality indicator values used in this research are infant mortality rate, child mortality rate, maternal mortality rate, and rough birth rate. The method used is Agglomerative Hierarchical Clustering (AHC) - Complete Linkage. Data were calculated using Euclidean Distance Equation, then Complete Linkage. Four clustered data were grouped into two clusters, healthy and/or unhealthy. The result, combining from all clusters into two large clusters to see healthy and unhealthy results.

scholarly journals Klasszikus klaszterező algoritmusok módosítása körút alapon

2021 ◽  
Vol 11 (4) ◽  
pp. 81-86
Author(s):  
Anita Agárdi
Keyword(s):  
Single Linkage ◽  
Complete Linkage ◽  
Average Linkage

Jelen cikkben a klasszikus klaszterező algoritmusok egy módosítását mutatom be. A cikkben egy olyan módszert mutatok be, amellyel a klaszterező algoritmusok maguk határozzák meg a klaszterhatárokat, azt, hogy hány csoportra bontsák az adatsor elemeit. A klaszterezés egy olyan adatbányászati módszer, ahol az egymással hasonló elemek azonos klaszterbe, míg az egymástól különböző elemek külön klaszterbe kerülnek. Jelen cikkben egy partíciós algoritmust (K-Means) és a hierarchikus módszereket (Single Linkage, Complete Linkage, Average Linkage, Ward, Centroid) mutatom be. A futási eredmények azt mutatják, hogy a klaszterezési algoritmusoknak többé-kevésbé sikerült kialakítaniuk a klasztereket anélkül, hogy bemenetként a klaszterszámot várnánk.

scholarly journals Penerapan Metode Angglomerative Hierarchical Clustering untuk Klasifikasi Kabupaten/Kota di Propinsi Jawa Timur Berdasarkan Kualitas Pelayanan Keluarga Berencana

CAUCHY ◽  
2015 ◽  
Vol 4 (1) ◽  
pp. 25
Author(s):  
Alfi Fadliana ◽  
Fachrur Rozi
Keyword(s):  
Hierarchical Clustering ◽  
Good Condition ◽  
Cluster Solution ◽  
Agglomerative Hierarchical Clustering ◽  
Clustering Methods ◽  
Cophenetic Correlation ◽  
Service Personnel ◽  
Medium Condition ◽  
Average Linkage ◽  
Hierarchical Clustering Methods

Agglomerative hierarchical clustering methods is cluster analysis method whose primary purpose is to group objects based on its characteristics, it begins with the individual objects until the objects are fused into a single cluster. Agglomerative hierarchical clustering methods are divided into single linkage, complete linkage, average linkage, and ward. This research compared the four agglomerative hierarchical clustering methods in order to get the best cluster solution in the case of the classification of regencies/cities in East Java province based on the quality of “Keluarga Berencana” (KB) services. The results of this research showed that based on calculation of cophenetic correlation coefficient, the best cluster solution is produced by average linkage method. This method obtained four clusters with the different characteristics. Cluster 1 has an “extremely bad condition” on the qualification of KB clinics and the competence of KB service personnel. Cluster 2 has a “good condition” on the qualification of KB clinics and “bad condition” on the competence of KB service personnel. Cluster 3 has a “bad condition” on the qualification of KB clinics and “medium condition” on the competence of KB service personnel. Cluster 4 have a “medium condition” on the qualification of KB clinics and a “good condition” on the competence of KB service personnel

Nearest Prototype and Nearest Neighbor Clustering with Twofold Memberships Based on Inductive Property

2013 ◽  
Vol 17 (4) ◽  
pp. 504-510
Author(s):  
Satoshi Takumi ◽  
◽  
Sadaaki Miyamoto
Keyword(s):  
Hierarchical Clustering ◽  
Nearest Neighbor ◽  
Classification Rules ◽  
Agglomerative Hierarchical Clustering ◽  
Single Linkage ◽  
Natural Classification ◽  
Nearest Neighbor Classification ◽  
Voronoi Regions ◽  
Inductive Property ◽  
Neighbor Classification

The aim of this paper is to study methods of twofold membership clustering using the nearest prototype and nearest neighbor. The former uses theK-means, whereas the latter extends the single linkage in agglomerative hierarchical clustering. The concept of inductive clustering is moreover used for the both methods, which means that natural classification rules are derived as the results of clustering, a typical example of which is the Voronoi regions inK-means clustering. When the rule of nearest prototype allocation inK-means is replaced by nearest neighbor classification, we have inductive clustering related to the single linkage in agglomerative hierarchical clustering. The former method usesK-means or fuzzyc-means with noise clusters, whereby twofold memberships are derived; the latter method also derives two memberships in a different manner. Theoretical properties of the both methods are studied. Illustrative examples show implications and significances of this concept.

scholarly journals Pengelompokan Artikel Berita Berbahasa Indonesia dengan Agglomerative Clustering

2018 ◽  
Author(s):  
Yudi Wibisono ◽  
Masayu Leylia Khodra
Keyword(s):  
Cosine Similarity ◽  
Agglomerative Clustering ◽  
Single Linkage ◽  
Inverse Document Frequency ◽  
Complete Linkage ◽  
Term Frequency ◽  
Average Linkage ◽  
Document Frequency ◽  
Average Group

Makalah ini mengaplikasikan agglomerative clustering untuk pengelompokan artikel berita berbahasa Indonesia untuk sistem aggregator berita. Agglomerative clustering merupakan teknik clustering hirarki dengan keunggulan jumlah cluster tidak perlu ditentukan, dan kualitas cluster tidak bergantung pada inisialisasi awal anggota cluster. Empat linkage diimplementasikan yaitu single linkage, complete linkage, average linkage, dan average-group linkage. Clustering dilakukan dengan menggunakan fitur leksikal, pembobotan term-frequency inverse document-frequency (tf.idf), cosine similarity, dan minimum anggota cluster adalah tiga. Dengan menggunakan 104 artikel berbahasa Indonesia yang telah dilabeli, kualitas cluster terbaik dihasilkan agglomerative clustering dengan menggunakan complete linkage dan kemiripan minimum 0.3 (purity rata-rata 0.888 dan lima cluster) dan 0.4 (purity rata-rata 0.938 dan empat cluster). Hasil eksperimen juga menunjukkan bahwa complete linkage menghasilkan purity rata-rata terbaik dan konsisten dibandingkan jenis linkage lainnya, dan nilai purity akan semakin tinggi jika parameter min_sim diperbesar, tetapi hal tersebut menyebabkan jumlah cluster yang dihasilkan semakin kecil.

Agglomerative Hierarchical Clustering Without Reversals on Dendrograms Using Asymmetric Similarity Measures

2012 ◽  
Vol 16 (7) ◽  
pp. 807-813
Author(s):  
Satoshi Takumi ◽  
◽  
Sadaaki Miyamoto
Keyword(s):  
Hierarchical Clustering ◽  
Similarity Measures ◽  
Real Data ◽  
Agglomerative Hierarchical Clustering ◽  
Average Linkage ◽  
Linkage Methods ◽  
Asymmetric Similarity

Algorithms of agglomerative hierarchical clustering using asymmetric similarity measures are studied. Two different measures between two clusters are proposed, one of which generalizes the average linkage for symmetric similarity measures. Asymmetric dendrogram representation is considered after foregoing studies. It is proved that the proposed linkage methods for asymmetric measures have no reversals in the dendrograms. Examples based on real data show how the methods work.

Sign in / Sign up

Export Citation Format

Share Document