Comparing euclidean distance and nearest neighbor algorithm in an expert system for diagnosis of diabetes mellitus

Zubaedah, Reza; Xaverius, Fransiskus; Jayawardana, Hasanudin; Hidayat, Serli Hatul

doi:10.1016/j.enfcli.2019.07.121

Cited by 14 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The closer the distance, the higher the impact coefficient of the epidemic. Based on the theory of distance inverse weighting (Zubaedah et al, 2020), we still take Hubei as the center of the epidemic situation, according to the principle of outward diffusion and multi-step diffusion, we assign Hubei "epidemic index 1" and spread its epidemic index outward. The remaining 30 provinces or provincial municipalities in the country obtained the epidemic index 1/d ij , respectively.…”

Section: Epidemic Prediction Based On Spatial Euclidean Inverse Distancementioning

confidence: 99%

“…Boyda et al (2019) using GIS and spatial analysis methods, this paper reviewed and summarized the transmission of HIV in Africa. Due to the limitations of simple geographic information, Kurata & Bapat (2015) began to use the Euclidean distance matrix to measure the distance between two regions and generally used the Euclidean inverse distance to measure the proximity of two regions (Zubaedah et al, 2020;Lumijarvi, Laurikkala & Juhola, 2004). However, European inverse distance still cannot accurately reflect the strength of the relationship between the two regions, and hence, some economists have introduced economic distance into the spatial information system (Bastawrous & Suni, 2020;Najafi Alamdarlo, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Regional infectious risk prediction of COVID-19 based on geo-spatial data

Cheng

Zhao-zhou

Abba

et al. 2020

PeerJ

View full text Add to dashboard Cite

After the first confirmed case of the novel coronavirus disease (COVID-19) was found, it is of considerable significance to divide the risk levels of various provinces or provincial municipalities in Mainland China and predict the spatial distribution characteristics of infectious diseases. In this paper, we predict the epidemic risk of each province based on geographical proximity information, spatial inverse distance information, economic distance and Baidu migration index. A simulation study revealed that the information based on geographical economy matrix and migration index could well predict the spatial spread of the epidemic. The results reveal that the accuracy rate of the prediction is over 87.10% with a rank difference of 3.1. The results based on prior information will guide government agencies and medical and health institutions to implement responses to major public health emergencies when facing the epidemic situation.

show abstract

Section: Epidemic Prediction Based On Spatial Euclidean Inverse Distancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Regional infectious risk prediction of COVID-19 based on geo-spatial data

Cheng

Zhao-zhou

Abba

et al. 2020

PeerJ

View full text Add to dashboard Cite

show abstract

“…Seiring dengan kepopulerannya, kNN banyak digunakan untuk melakukan klasifikasi data dalam bidang sains dan teknik maupun ekonomi dan bisnis. Beberapa publikasi terkini yang menerapkan kNN meliputi: prediksi penyakit jantung [3], diagnosis penyakit diabetes [4], prediksi permintaan pasar [5], klasifikasi protein [6] dan desain radar detektor [7]. Selain itu, kNN juga banyak digunakan sebagai basis pengembangan algoritma machine learning yang lebih canggih [8][9][10][11][12].…”

Section: Pendahuluanunclassified

Evaluasi Implementasi Algoritma Machine Learning K-Nearest Neighbors (kNN) pada Data Spektroskopi Gamma Resolusi Rendah

Fajri¹,

Septian²,

Sanjaya³

2020

Fiziya

View full text Add to dashboard Cite

Abstrak Pada artikel ini kami mengevaluasi bagaimana implementasi algoritma machine learning k-Nearest Neighbors (kNN) pada data spektroskopi gamma beresolusi rendah. Penelitian ini bertujuan untuk mengetahui bagaimana performa kNN dalam mempelajari data tersebut. Kami melakukan berbagai variasi, yaitu: jumlah data training, jumlah data tes, jenis metric, dan nilai k untuk memperoleh performa terbaik dari algoritma ini. Data spektroskopi gamma diambil menggunakan sintilator NaI(Tl) Leybold Didactic dengan resolusi energi sebesar 10.9 keV per channel. Hasil variasi menunjukkan bahwa algoritma kNN memberikan hasil prediksi klasifikasi radioisotop yang sangat fluktuatif. Abstract In this paper we evaluate the implementation of a machine learning algorithm namely k-Nearest Neighbors (kNN) on low resolution gamma spectroscopy data. The aim is to provide the information of how well the algorithm performs on learning the data. We did the variation of number of training and test data, type of metric used, and values of k in order to see the best performance of the algorithm. The gamma spectroscopy data were taken using NaI(Tl) scintillator made by Leybold Didactic with resolution of 10.9 keV per channel. The variations show that the kNN algorithm produce significantly fluctuating accuracy to the prediction of radioisotope class.

show abstract

“…[5] , [6] , [10] , [11] , [12] , [13] , [20] , [22] , [24] , [29] , [31] ). The epidemic risk of each region is a function of factors such as geographic proximity, the population spatial distribution [32] , the economic development [3] and the migration index. Such information based on the geographic economy matrix and the migration index well could predict the spatial spread of the epidemic [5] .…”

Section: Introductionmentioning

confidence: 99%

The spreading of Covid-19 in Mexico: A diffusional approach

et al. 2021

View full text Add to dashboard Cite

In this work, we analyze the spreading of Covid-19 in Mexico using the spatial SEIRD epidemiologic model. We use the information of the 32 regions (States) that conform the country, such as population density, verified infected cases, and deaths in each State. We extend the SEIRD compartmental epidemiologic with diffusion mechanisms in the exposed and susceptible populations. We use the Fickian law with the diffusion coefficient proportional to the population density to encompass the diffusion effects. The numerical results suggest that the epidemiologic model demands time-dependent parameters to incorporate non-monotonous behavior in the actual data in the global dynamic. The diffusional model proposed in this work has great potential in predicting the virus spreading on different scales, i.e., local, national, and between countries, since the complete reduction in people mobility is impossible.

show abstract

Comparing euclidean distance and nearest neighbor algorithm in an expert system for diagnosis of diabetes mellitus

Cited by 14 publications

References 1 publication

Regional infectious risk prediction of COVID-19 based on geo-spatial data

Regional infectious risk prediction of COVID-19 based on geo-spatial data

Evaluasi Implementasi Algoritma Machine Learning K-Nearest Neighbors (kNN) pada Data Spektroskopi Gamma Resolusi Rendah

The spreading of Covid-19 in Mexico: A diffusional approach

Contact Info

Product

Resources

About