An Introduction to Self-Organizing Maps

Asan, Umut; Ercan, Seçil

doi:10.2991/978-94-91216-77-0_14

Cited by 45 publications

(21 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The neuron with the smallest distance (best-matching unit, BMU) is then selected and the weights from this BMU and the neighbours are updated according to a Gaussian function ( Çinar and Merdun, 2009 ). Nearby neurons in the output layer represents similar properties and neurons located farther away from each other have dissimilar properties ( Asan and Ercan, 2012 ).…”

Section: Methodsmentioning

confidence: 99%

“…This technique projects high-dimensional data into a lower-dimensional space with the purpose of grouping samples with similar characteristics and finding possible patterns ( Brereton, 2012 ; Doan et al, 2020 ). It has outstanding visualisation capabilities, it is ease to implement and robust to missing data ( Asan and Ercan, 2012 ; Vesanto, 1999 ). In the context of the COVID-19 pandemic, SOM has been used to find similarities in the transmission dynamics among cities, regions or countries worldwide ( Galvan et al, 2021 ; Hartono, 2020 ; Melin et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distinct weather conditions and human mobility impacts on the SARS-CoV-2 outbreak in Colombia: Application of an artificial neural network approach

Herrera

Gontijo

Enríquez-Delgado

et al. 2021

International Journal of Hygiene and Environmental Health

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Distinct weather conditions and human mobility impacts on the SARS-CoV-2 outbreak in Colombia: Application of an artificial neural network approach

Herrera

Gontijo

Enríquez-Delgado

et al. 2021

International Journal of Hygiene and Environmental Health

View full text Add to dashboard Cite

“…SOM memiliki sejumlah keunggulan, diantaranya: (1) SOM tidak memerlukan asumsi tentang distribusi variabel dan juga tidak memerlukan independensi di antara variabel, (2) SOM lebih mudah diimplementasikan dan mampu memecahkan masalah nonlinier dengan kompleksitas sangat tinggi, (3) SOM efektif dalam menangani data noise dan data missing, berdimensi sangat kecil, serta sampel dengan ukuran tidak terbatas [17].…”

Section: Self-organizing Mapunclassified

Self-Organizing Map Menggunakan Davies-Bouldin Index dalam Pengelompokan Wilayah Indonesia Berdasarkan Konsumsi Pangan

Kartikasari

2021

Jambura J. Math

View full text Add to dashboard Cite

ABSTRAKKecukupan konsumsi pangan merupakan salah satu penunjang terbentuknya sumber daya manusia unggul yang menjadi fokus kebijakan pembangunan di Indonesia. Agar konsumsi pangan terpenuhi, salah satu cara yang dapat dilakukan adalah melakukan pengelompokan wilayah berdasarkan konsumsi pangan. Penelitian ini bertujuan untuk mengelompokkan wilayah Indonesia berdasarkan konsumsi pangan berdasarkan data konsumsi kalori per kapita sehari dari berbagai komoditas pangan. Pengelompokan wilayah dilakukan dengan metode self-organizing map (SOM) dengan terlebih dahulu ditentukan jumlah cluster optimum menggunakan nilai Davies-Bouldin Index (DBI) terkecil. Hasil penelitian menunjukkan bahwa hasil cluster optimum yang terbentuk sejumlah 4 cluster dengan jumlah anggota untuk cluster 1 sebanyak 22 provinsi, cluster 2 sebanyak 10 provinsi, cluster 3 sebanyak 1 provinsi, dan cluster 4 sebanyak 1 provinsi.ABSTRACTAdequate food consumption is one of the supports for forming superior human resources, which is the focus of development policies in Indonesia. To fulfill food consumption, one way to be done is to group regions based on food consumption. This study aims to classify regions of Indonesia based on food consumption based on average daily per capita calorie consumption data from various food commodities. Regional grouping is done using the self-organizing map (SOM) method by first determining the optimum number of clusters using the smallest Davies-Bouldin Index (DBI) value. The results showed that the optimum cluster results were 4 clusters with the number of members for cluster 1 as many as 22 provinces, cluster 2 as many as 10 provinces, cluster 3 as many as 1 province, and cluster 4 as many as 1 province.

show abstract

“…Considering the dimensionality reducing capability, SOM is similar to the statistical equivalent of Principal Component Analysis, whereas Baccao et al (Bação et al, 2005) suggest SOM as a possible substitute for K-means clustering when the neighbourhood is not considered. Besides, in comparison to statistical techniques, SOM offers three main advantages due to its nonparametric nature: (i) it works independent of variable's distributions, (ii) it is computationally efficient to non-linear problems and (iii) it caters for noise or missing data more effectively (Asan and Ercan, 2012).…”

Section: Unsupervised Classification Using Som and K-meansmentioning

confidence: 99%

Contextual Contact Tracing based on Stochastic Compartment Modeling and Spatial Risk Assessment

Mahmood

Mateu

Orallo

2021

Preprint

View full text Add to dashboard Cite

The current situation of COVID-19 highlights the paramount importance of infectious disease surveillance, which necessitates early monitoring for effective response. Policymakers are interested in data insights identifying high-risk areas as well as individuals to be quarantined, especially as the public gets back to their normal routine. We investigate both requirements by the implementation of disease outbreak modeling and exploring its induced dynamic spatial risk in form of risk assessment, along with its real-time integration back into the disease model. This paper implements a contact tracing-based stochastic compartment model as a baseline, to further modify the existing setup to include the spatial risk. This modification of each individual-level contact's intensity to be dependent on its spatial location has been termed as Contextual Contact Tracing. The results highlight that the inclusion of spatial context tends to send more individuals into quarantine which reduces the overall spread of infection. With a simulated example of an induced spatial high-risk, it is highlighted that the new spatio-SIR model can act as a tool to empower the analyst with a capability to explore disease dynamics from a spatial perspective. We conclude that the proposed spatio-SIR tool can be of great help for policymakers to know the consequences of their decision prior to their implementation.

show abstract

An Introduction to Self-Organizing Maps

Cited by 45 publications

References 34 publications

Distinct weather conditions and human mobility impacts on the SARS-CoV-2 outbreak in Colombia: Application of an artificial neural network approach

Distinct weather conditions and human mobility impacts on the SARS-CoV-2 outbreak in Colombia: Application of an artificial neural network approach

Self-Organizing Map Menggunakan Davies-Bouldin Index dalam Pengelompokan Wilayah Indonesia Berdasarkan Konsumsi Pangan

Contextual Contact Tracing based on Stochastic Compartment Modeling and Spatial Risk Assessment

Contact Info

Product

Resources

About