Single-linkage method to detect multiple outliers with different outlier scenarios in circular regression model

2019 ◽  
Author(s):  
Siti Zanariah Satari ◽  
Nur Faraidah Muhammad Di ◽  
Roslinazairimah Zakaria
Keyword(s):  
Regression Model ◽  
Single Linkage ◽  
Multiple Outliers ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Circular Regression

scholarly journals Egg production evaluation of laying hens by multivariate analysis

2017 ◽  
Vol 69 (3) ◽  
pp. 676-682
Author(s):  
P.B. Ferreira ◽  
P.R.N. Rorato ◽  
F.C.B. Mello ◽  
B. Bevilaqua ◽  
A. Macedo ◽  
...  
Keyword(s):  
Multivariate Analysis ◽  
Principal Components ◽  
Egg Production ◽  
Euclidean Distance ◽  
Nearest Neighbors ◽  
Single Linkage ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Highly Correlated ◽  
Santa Maria

ABSTRACT This study aimed to verify the existence of differences between hens from the Barred Plymouth Rock (PRB) breed and White Plymouth Rock (PRW) breed by multivariate analysis of weekly egg production and cumulative during the years of 1998 and 2010, from the Laboratório de Avicultura (LAVIC) of the Departamento de Zootecnia at the Universidade Federal de Santa Maria (UFSM). For the analysis of the univariate and multivariate variance, the experimental design was completely randomized with two treatments (breed) and 299 repetitions of the PRW breed and 350 of the PRB breed. The parameters analyzed were the weekly productions of eggs per bird from the 21st to the 50th week of age (P21, P22, ..., P50) and production of eggs accumulated being from the 21st to the 25th (PA1), 21st to the 30th (PA2), 21st to the 35th (PA3), 21st to the 40th (PA4), 21st to the 45th (PA5) and 21st to 50th (PA6). Analyzes of univariate and multivariate variance were conducted and the comparison of means were made by "T" Student and Wilks respectively (P < 0, 05). Based on the results, an analysis of the principal components was performed with parameters PA1, PA2, PA4, PA5 and PA6. With the average egg production per family accumulated, a cluster analysis using Euclidean distance and single linkage method (nearest neighbors) was performed. The first two principal components meet the total variation in egg production accumulated from the 21st to 25th, 21st to 30th, 21st to 40th, 21st to 45th and 21st to 50th weeks of age. Most of the phenotypic variation of the layers can be explained by the production of eggs accumulated from the 21st until the 40th week of age, and this variable is highly correlated with total egg production. Families from the PRW and PRB breed form seven distinct groups, but homogeneous by the similarity between them. This allows direct crossings between different groups, in the pursuit for heterosis.

scholarly journals Optimisation of Distribution Routes: A Case Study

2021 ◽  
Vol 23 (1) ◽  
pp. A62-A73
Author(s):  
Rudolf Kampf ◽  
Martina Hlatká ◽  
Patrik Gross
Keyword(s):  
Research Methods ◽  
Operational Research ◽  
Current Situation ◽  
Single Linkage ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Floor Coverings ◽  
A Company

This article focuses on optimisation of the distribution routes for a company that produces carpets, floor coverings and tapestries. The optimisation process is based on operational research methods including, without limitations, Mayer’s method and the single linkage method. The obtained results are subsequently compared to the current situation and evaluated in terms of time and costs. The conclusion provides the optimised economic solution.

scholarly journals The multiple outliers detection using agglomerative hierarchical methods in circular regression model

2017 ◽  
Vol 890 ◽  
pp. 012152 ◽  
Author(s):  
Siti Zanariah Satari ◽  
Nur Faraidah Muhammad Di ◽  
Roslinazairimah Zakaria
Keyword(s):  
Regression Model ◽  
Multiple Outliers ◽  
Outliers Detection ◽  
Circular Regression

scholarly journals Coleta e caracterização morfológica de populações de porongo – Lagenaria siceraria (Mol.) Standl. - Cucurbitaceae

2002 ◽  
Vol 24 (24) ◽  
pp. 91
Author(s):  
André Luís Lopes da Silva ◽  
Renato Aquino Záchia ◽  
Dilson Antônio Bisognin ◽  
Jean Carlos Budke
Keyword(s):  
Genetic Divergence ◽  
Dissimilarity Measure ◽  
Lagenaria Siceraria ◽  
Mature Fruit ◽  
Single Linkage ◽  
Municipal District ◽  
Heterogeneous Groups ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Santa Maria

Fruits of Lagenaria siceraria (Mol.) Standl. were collected in the municipal district of Santa Maria and Jaguarí (RS) with the objective of characterizing some local races used by the producers. Three populations of L. siceraria were characterized and classified as casco-grosso caciquense, casco-fino caciquense and casco-grosso precoce. It was made a morphologic characterization based on descriptors of mature fruit, seeking to verify the existent genetic divergence among these local races. The data were submitted the grouping analysis, as dissimilarity measure was used the distance of Mahalanobis (D²) and the used grouping methods were the "Método do vizinho mais próximo" (Single Linkage Method) and the method of Tocher, these methods obtained the populations in two heterogeneous groups. The porongo populations collected in Santa Maria didn't show genetic divergence being placed in the same group and the population collected in Jaguarí it was placed in another group.

scholarly journals Pengelompokkan Kecamatan Berdasarkan Potensi Pertanian di Kabupaten Halmahera Selatan dengan Analisis Gerombol

d'CARTESIAN ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 31
Author(s):  
Meilissa Harikadua ◽  
Djoni Hatidja ◽  
Charles E Mongi
Keyword(s):  
Cluster Analysis ◽  
Middle East ◽  
Secondary Data ◽  
Marine Fisheries ◽  
Single Linkage ◽  
North West ◽  
South West ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Cluster 2

This study aims to classify sub-districts based on the potential of agricultural, plantation, livestock, marine fisheries and forestry commodities in the area of South Halmahera Regency. The data used in this study are secondary data taken from the website of the Central Statistics Agency of South Halmahera Regency.The analysis used in this study is Cluster Analysis with a single linkage method and the results obtained are the formation of 3 cluster including Cluster 1 consisting of 28 districts namely: South Obi, Obi, West Obi, East Obi, North Obi, Bacan , South Mandioli, North Mandioli, Batang Lomang Islands, South East Bacan, Middle East Bacan, West Bacan, West Kasiruta, East Kasiruta, North West Bacan, Kayoa, West Kayoa, South Kayoa, North Kayoa, Makian Island, Makian Barat, Gane West, South West Gane, North West Gane, Joronga Islands, East Gane, Middle East Gane and South East Gane. Cluster 2 consisted of South Bacan sub-district and Cluster 3 consisted of East Bacan sub-district.

A Novel Parameter-Light Subspace Clustering Technique Based on Single Linkage Method

2019 ◽  
Vol 18 (01) ◽  
pp. 1950007
Author(s):  
Bhagyashri A. Kelkar ◽  
Sunil F. Rodd ◽  
Umakant P. Kulkarni
Keyword(s):  
Subspace Clustering ◽  
Numerical Data ◽  
High Dimensional ◽  
Not Given ◽  
Clustering Method ◽  
Single Linkage ◽  
Linkage Method ◽  
Benchmark Datasets ◽  
Single Linkage Method ◽  
Parameter Values

Subspace clustering is a challenging high-dimensional data mining task. There have been several approaches proposed in the literature to identify clusters in subspaces, however their performance and quality is highly affected by input parameters. A little research is done so far on identifying proper parameter values automatically. Other observed drawbacks are requirement of multiple database scans resulting into increased demand for computing resources and generation of many redundant clusters. Here, we propose a parameter light subspace clustering method for numerical data hereafter referred to as CLUSLINK. The algorithm is based on single linkage clustering method and works in bottom up, greedy fashion. The only input user has to provide is how coarse or fine the resulting clusters should be, and if not given, the algorithm operates with default values. The empirical results obtained over synthetic and real benchmark datasets show significant improvement in terms of accuracy and execution time.

scholarly journals Comparative Study of Clustering-Based Outliers Detection Methods in Circular-Circular Regression Model

2021 ◽  
Vol 50 (6) ◽  
pp. 1787-1798
Author(s):  
Siti Zanariah Satari ◽  
Nur Faraidah Muhammad Di ◽  
Yong Zulina Zubairi ◽  
Abdul Ghapor Hussin
Keyword(s):  
Comparative Study ◽  
Regression Model ◽  
Clustering Algorithms ◽  
Simulated Data ◽  
Stopping Rule ◽  
Detection Methods ◽  
Cluster Tree ◽  
Data Set ◽  
Multiple Outliers ◽  
Circular Regression

This paper is a comparative study of several algorithms for detecting multiple outliers in circular-circular regression model based on the clustering algorithms. Three measures of similarity based on the circular distance were used to obtain a cluster tree using the agglomerative hierarchical methods. A stopping rule for the cluster tree based on the mean direction and circular standard deviation of the tree height was used as the cutoff point and classifier to the cluster group that exceeded the stopping rule as potential outliers. The performances of the algorithms have been demonstrated using the simulation studies that consider several outlier scenarios with a certain degree of contamination. Application to real data using wind data and a simulated data set are given for illustrative purposes. Thus, it has been found that Satari’s algorithm (S-SL algorithm) performs well for any values of sample size n and error concentration parameter. The algorithms are good in identifying outliers which are not limited to one or few outliers only, but the presence of multiple outliers at one time.

scholarly journals Biogeography of Medically Important Insects using Quantitative Analysis

2020 ◽  
pp. 1-11
Author(s):  
Qi Shen ◽  
Zhixing You ◽  
Xiaojing Ma ◽  
Xiaocheng Shen
Keyword(s):  
Quantitative Analysis ◽  
Phytophagous Insects ◽  
Small Unit ◽  
Single Linkage ◽  
Average Group ◽  
The World ◽  
Distributional Information ◽  
Linkage Method ◽  
Single Linkage Method ◽  
Geographical Units

We summarized distributional information of medically important insects from 76 families and 4531 genera occurring worldwide. The continents were divided into 67 basic geographical units. Using a new similarity formula and a new clustering method for quantitative analysis, 67 basic geographical units were clustered into 7 large unit groups and 20 small unit groups. The results were superior to the traditional single linkage method, average group linkage method, or sum of squares method. The cluster results were similar with the result of mainly phytophagous insects 104,344 genera in the world, but were different from the Wallace’s mammal geographical division scheme. Based on these seemingly contradictory results, we infer that animals, insect and plants may have the same distribution pattern and that it is necessary to conduct precise quantitative analysis for animals and plants worldwide.

Sign in / Sign up

Export Citation Format

Share Document