Veterinerlik Alanında Makine Öğrenmesi Uygulamaları Üzerine Bir Derleme

Cihan, Pınar; Kalipsiz, Oya

doi:10.9775/kvfd.2016.17281

Cited by 13 publications

(9 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In animal science and veterinary medicine, there are limited numbers of studies about fuzzy logic. Some of those studies are related with diseases prediction, assessment of risks, designing equipments and controllers [33,34] . Artificial intelligence approaches like Fuzzy Logic can be initiated the expert's vision since they are included the information of experts.…”

Section: Discussionmentioning

confidence: 99%

Yumurtacı Tavuklarda Yumurta Veriminin Tahminlenmesinde Bulanık Mantık Uygulaması

Gevrekçi¹,

Altintaş²,

Yeğenoğlu³

et al. 2018

Kafkas Univ Vet Fak Derg

View full text Add to dashboard Cite

Fuzzy logic has a great potential for researchers and it has been developed over the last two decades. In animal science, there are limited numbers of studies on fuzzy logic approach. This study was carried out to examine the Fuzzy logic applications for prediction of the egg production data. Egg production records were obtained from the commercial poultry farm in Izmir, Turkey. Egg production traits of brown laying hens at 22 to 40 weeks of age were analyzed with Fuzzy logic system. In this study, Fuzzy logic model was developed for the prediction of egg production values of three classes; top, middle and lower (bottom for the cage effect) production. For this purpose 120 data lines representing 4 inputs consisting of cage, age at sexual maturity (ASM), body weight at sexual maturity (BWSM), body weight at mature age (BW) and 1 output, egg production (EP) that collected daily and individually were used in a Fuzzy logic model. The similarities between predicted and original production records were investigated, the coefficient of determination (R 2) was found as 0.89 which was also shown the prediction's success rate. The probability of egg production at ASM of 168 days, BWSM of 1500 g and BW of 1820 g was found 98.97% while egg production's probability at ASM of 157 days, BWSM of 1720 g and BW of 1940 g was determined as 97.97%. These results were also concluded that layers reached at sexual maturity later have lower egg production. The results illustrated that Fuzzy model could provide an effective and accurate prediction for classifying egg production of laying hens. However, since the applications of fuzzy logic related to the prediction of egg production are limited, this work will be pioneered by future studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Yumurtacı Tavuklarda Yumurta Veriminin Tahminlenmesinde Bulanık Mantık Uygulaması

Gevrekçi¹,

Altintaş²,

Yeğenoğlu³

et al. 2018

Kafkas Univ Vet Fak Derg

View full text Add to dashboard Cite

show abstract

“…Nearest neighbour algorithms were first proposed for the supervised pattern recognition. Then, Troyanskaya et al [12] proposed the kNN and missing value imputation methods. The main idea is to measure the distance between each observation pair based on variables without missing values.…”

Section: A Imputation Methodsmentioning

confidence: 99%

“…SVD imputation algorithm was proposed by Troyanskaya et al [12]. The idea behind the algorithm is to estimate the missing values as a linear combination of the k most significant eigenvalues.…”

Section: A Imputation Methodsmentioning

confidence: 99%

“…In DNA microarray and biological researches, genetic data may be missing due to various reasons, such as scratched slide or contaminated samples. In medical diagnosis, the physician may request a test, which either provides the exact result or a test not relevant to the diagnosis or, in cases, where measuring is difficult/harmful, the features may be missing [12]- [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Heuristic Approach for Treating Missing Value: ABCimp

Cihan¹,

Ozger²

2019

ELEKTRON ELEKTROTECH

View full text Add to dashboard Cite

Missing values in datasets present an important problem for traditional and modern statistical methods. Many statistical methods have been developed to analyze the complete datasets. However, most of the real world datasets contain missing values. Therefore, in recent years, many methods have been developed to overcome the missing value problem. Heuristic methods have become popular in this field due to their superior performance in many other optimization problems. This paper introduces an Artificial Bee Colony algorithm based new approach for missing value imputation in the four real-world discrete datasets. At the proposed Artificial Bee Colony Imputation (ABCimp) method, Bayesian Optimization is integrated into the Artificial Bee Colony algorithm. The performance of the proposed technique is compared with other well-known six methods, which are Mean, Median, k Nearest Neighbor (k-NN), Multivariate Equation by Chained Equation (MICE), Singular Value Decomposition (SVD), and MissForest (MF). The classification error and root mean square error are used as the evaluation criteria of the imputation methods performance and the Naive Bayes algorithm is used as the classifier. The empirical results show that state-of-the-art ABCimp performs better than the other most popular imputation methods at the variable missing rates ranging from 3 % to 15 %.

show abstract

“…This makes analysis difficult for animals. For these reasons, it is known that the interdisciplinary study between the veterinary and the computer science fields is very low (Cihan et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Application of Small Ruminant Database and Data Analysis System (Desktop and Android Application)

Cihan

Kalipsiz

2018

Uluslararası Muhendislik Arastirma Ve Gelistirme Dergisi

Self Cite

View full text Add to dashboard Cite

In today's world, various information systems have been designed for helping the physicians in medicine field. By means of these systems, the data associated with the patients are stored, shared easily or the analysis about the patients can be done. In animal health, which is also as important as human health, it is seen that analyses about the illnesses are quite limited. In our opinion, one of the most important reasons for this is the lack of a system with which the data on the animals are stored and shared. Because of the lack of this kind of system, limited studies have been done on animal illnesses and alternative solutions could not be provided in detail for illnesses and deaths. Thus, the decrease in animals and animal productions has been rising day by day and the economy of the country has been affected negatively. In this study, a system has been provided in order to store, share and run data analysis regarding the records of animals. In addition, visual interfaces have been prepared to facilitate the database procedures.

show abstract

Veterinerlik Alanında Makine Öğrenmesi Uygulamaları Üzerine Bir Derleme

Cited by 13 publications

References 12 publications

Yumurtacı Tavuklarda Yumurta Veriminin Tahminlenmesinde Bulanık Mantık Uygulaması

Yumurtacı Tavuklarda Yumurta Veriminin Tahminlenmesinde Bulanık Mantık Uygulaması

A New Heuristic Approach for Treating Missing Value: ABCimp

Application of Small Ruminant Database and Data Analysis System (Desktop and Android Application)

Contact Info

Product

Resources

About