Decision-tree induction to detect clinical mastitis with automatic milking

Kamphuis, C.; Mollenhorst, H.; Feelders, Ad; Pietersma, D.; Hogeveen, H.

doi:10.1016/j.compag.2009.08.012

Cited by 55 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A general complaint of dairy farmers working with an AMS is the relatively large number of false-positive alerts on the mastitis alert lists. Several detection models were developed with the aim of reducing the number of false-positive alerts (e.g., de Mol and Ouweltjes, 2001;Cavero et al, 2008;Kamphuis et al, 2010). The sensitivity (Se) and specificity (Sp) of these models, however, remain too low to substantially reduce the number of false-positive alerts and at the same time retain a sufficient detection of true cases.…”

Section: Introductionmentioning

confidence: 99%

Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Steeneveld

Gaag

Ouweltjes

et al. 2010

Journal of Dairy Science

Self Cite

View full text Add to dashboard Cite

Automatic milking systems (AMS) generate alert lists reporting cows likely to have clinical mastitis (CM). Dutch farmers indicated that they use non-AMS cow information or the detailed alert information from the AMS to decide whether to check an alerted cow for CM. However, it is not yet known to what extent such information can be used to discriminate between true-positive and false-positive alerts. The overall objective was to investigate whether selection of the alerted cows that need further investigation for CM can be made. For this purpose, non-AMS cow information and detailed alert information were used. During a 2-yr study period, 11,156 alerts for CM, including 159 true-positive alerts, were collected at one farm in the Netherlands. Non-AMS cow information on parity, days in milk, season of the year, somatic cell count history, and CM history was added to each alert. In addition, 6 alert information variables were defined. These were the height of electrical conductivity, the alert origin (electrical conductivity, color, or both), whether or not a color alert for mastitic milk was given, whether or not a color alert for abnormal milk was given, deviation from the expected milk yield, and the number of alerts of the cow in the preceding 12 to 96 h. Subsequently, naive Bayesian networks (NBN) were constructed to compute the posterior probability of an alert being truly positive based only on non-AMS cow information, based on only alert information, or based on both types of information. The NBN including both types of information had the highest area under the receiver operating characteristic curve (AUC; 0.78), followed by the NBN including only alert information (AUC = 0.75) and the NBN including only non-AMS cow information (AUC = 0.62). By combining the 2 types of information and by setting a threshold on the computed probabilities, the number of false-positive alerts on a mastitis alert list was reduced by 35%, and 10% of the true-positive alerts would not be identified. To detect CM cases at a farm with an AMS, checking all alerts is still the best option but would result in a high workload. Checking alerts based on a single alert information variable would result in missing too many true-positive cases. Using a combination of alert information variables, however, is the best way to select cows that need further investigation. The effect of adding non-AMS cow information on making a distinction between true-positive and false-positive alerts would be minor.

show abstract

Section: Introductionmentioning

confidence: 99%

Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Steeneveld

Gaag

Ouweltjes

et al. 2010

Journal of Dairy Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Estudos publicados (DE MOL;HOGEVEEN, 2001;NORBERG et al, 2004;KAMPHUIS et al, 2010;SUN et al, 2010) usam CE como diagnóstico de mastite, com uma grande variação de resultados de desempenho (HOGEVEEN, 2010).…”

Section: Métodos Automatizados Para O Diagnóstico De Mastiteunclassified

“…Há muitos estudos sendo realizados sobre a utiliza- (MI-LNER et al, 1996), no entanto, estes casos de mastite foram artificialmente induzidos, nas quais as medições foram feitas utilizando um aparelho portátil e não pelo equipamento em linha (KAMPHUIS et al, 2010 Para mensuração da CE existem dois tipos de equipamentos, um aparelho portátil e um equipamento acoplado a ordenhadeira automatizada. No sistema acoplado a medição da CE ocorre a cada ordenha por meio de softwares, e esses dados são armazenados em computadores, sendo que quando há uma variação individual, um sinal de alerta é disparado, indicando o animal que pode estar com mastite (JANZEKO-VIC, 2012).…”

Section: Métodos Automatizados Para O Diagnóstico De Mastiteunclassified

Métodos Automatizados De Diagnóstico De Mastite Em Vacas Leiteiras: Uma Revisão

Reis

Lopes

2015

ArqVet

View full text Add to dashboard Cite

REIS, E. M. B.; LOPES, M. A. Métodos automatizados de diagnóstico de mastite em vacas leiteiras: uma revisão. Arq. Ciênc. Vet. Zool. UNIPAR, Umuarama, v. 17, n. 3, p. 199-208, jul./set. 2014. RESUMO:A mastite é a infecção mais frequente dos animais destinados à produção de leite e que mais onera a pecuária leiteira. As perdas econômicas são causadas por diversos fatores: medicamentos, morte ou descarte precoce de animais, bem como em laticínios, pela queda na qualidade do produto final. Rotineiramente, quando se pretende verificar a incidência de mastite em vacas leiteiras utilizam-se os métodos convencionais e subjetivos, como a caneca telada e o California Mastitis Test. A automação na pecuária leiteira é uma inovação tecnológica que visa a minimizar os erros de manejo e otimizar os processos dentro da atividade, dentre os quais o diagnóstico precoce de casos subclínicos de mastite. O uso de sensores que utilizam parâmetros objetivos de mensuração tais como: condutividade elétrica, contagem de células somáticas, presença da enzima lactato desidrogenase, mensuração da cor e a homogeneidade podem ser a alternativa para detecção rápida e precisa de mastite em bovinos, especialmente quando se trata de sistemas automatizados, pois o diagnóstico precoce minimiza as perdas econômicas. Diante do exposto, objetivou-se realizar uma revisão bibliográfica sobre os métodos automatizados de detecção de mastite existentes atualmente. PALAVRAS-CHAVE: Automação. Bovinocultura Leiteira. Inovação Tecnológica. Zootecnia de Precisão. AUTOMATED DIAGNOSIS METHODS OF MASTITIS IN DAIRY MILK CATTLE: A REVIEWABSTRACT: The objective of this paper is to perform a bibliographic review on the currently existing automated methods for the detection of mastitis. Usually when one is supposed to verify the incidence of mastitis in dairy cows, conventional and subjective methods, such as the strip cup test and the California Mastitis Test, are used. Automation in dairy farming is a technological innovation aiming to minimize handling errors and to optimize the processes in the activity, among them, the early diagnosis of subclinical mastitis cases, through sensors using objective measuring parameters, such as electric conductivity, somatic cell count, presence of lactate dehydrogenase enzyme, color and homogeneity measurement. KEYWORDS: Automation. Dairy Cattle. Precision Dairy Farming. Technological Innovation. MÉTODOS AUTOMATIZADOS DE DIAGNOSIS DE MASTITIS EN VACAS LECHERAS: UNA REVISIÓNRESUMEN: Mastitis es la infección más frecuente en animales destinados a la producción de leche y más oneroso a la ganadería lechera. Las pérdidas económicas son causadas por diversos factores: medicamentos, muerte o descarte precoz de animales, así como en lacticinios, por la caída en la calidad del producto final. Rutinariamente, cuando se pretende verificar la incidencia de mastitis en vacas lecheras se utilizan los métodos convencionales y subjetivos, como la taza de red y el California Mastitis Test. La automatización en la ganadería lechera es una innovaci...

show abstract

“…Kamphuis ve ark. [3] , klinik mastitis'in tespitinde yaygın kullanılan bir veri madenciliği algoritması olan karar ağacı yöntemin-den yararlanmışlar ve yöntemin otomatik sağım sistemlerindeki modellerle benzerlik gösterdiği bilgisine ulaşmışlardır.…”

unclassified

A Data Mining Application in Animal Breeding: Determination of Some Factors in Japanese Quail Eggs Affecting Fertility

Küçükönder¹,

Üçkardeş²,

Narinç³

2014

Kafkas Univ Vet Fak Derg

View full text Add to dashboard Cite

ÖzetBu çalışmanın amacı, Japon bıldırcını yumurtalarının döllülük üzerine etkisi olan mevsim, seleksiyon ve yerleşim sıklığı faktörlerine göre veri madenciliği yöntemi ile sınıflandırılması ve bu faktörlerin etkisinin belirlenmesidir. Çalışmada seleksiyon yapılmış bir hattan ve rastgele çiftleştirilmiş bir kontrol hattından 3 farklı mevsimde (Yaz, Kış ve Sonbahar) elde edilen 180 dişi bıldırcın kullanılmıştır. İki farklı tip kafeste barındırılan (160-240 cm2/bıldırcın) bıldırcınlardan 12 haftalık yaşta bir hafta boyunca toplanan 1141 kuluçkalık yumurta çalışmanın materyalini oluşturmuştur. Araştırmada kullanılan sınıflandırma algoritmaları sırasıyla YSA, RBF Network, Naive Bayes, KStar, ve Ridor algoritmalarıdır. Söz konusu bu algoritmalara göre oluşturulan modellerin karşılaştırmasında Kappa istatistiği, Ortalama Mutlak Hata (OMH), Ortalama Hata Karekök (OHK), Göreli Mutlak Hata (GMH) ve Göreli Hata Karekök (GHK) performans kriterleri kullanılmıştır. Analizler sonucunda, yapılan karşılaştırmada performans kriter değerleri sırasıyla OMH: 0.002, OHK: 0.05, GMH: %1.07, GHK: %14.50 ve Kappa: 0.98 olan Ridor algoritmasına göre oluşturulan modelin en az hata ile sınıflandırma yaptığı görülmüştür. Yapılan bu çalışma ile %99.73 doğru sınıflandırma başarısı ile bıldırcın yumurtalarının genel olarak %85'inin döllü, %15'nin ise üreme kapasitelerinin düşük olduğu tespit edilmiştir. AbstractThe purpose of this study, classification with data mining methods according to the factors of season, selection, and frequency of settlement which have an effect on fertility in Japanese quail eggs, and is to determine the effect of these factors. In this study, 180 female quails in three different seasons (summer, winter and autumn) which were obtained from a selection line and a control line were used. 1141 hatching eggs collected from quails which were hosted on two different types of cages (160-240 cm2/quail) during a week at 12 weeks of age have formed the material of study. Classification algorithms used in the study are YSA, RBF Network, Naive Bayes, KStar, and Ridor algorythms, respectively. In the comparison of the models formed according to these algorithms, Kappa statistic, Mean Absolute Deviation (MAD), Mean Square Root Error (MSE), Relative Absolute Error (RAE), Relative Square Root Error (RSE) performance criteria were used. As a result of analysis, it has been seen in the comparison made that the model formed according to Ridor algorithm that has MAD: 0.002, MSE: 0.05, RAE: 1.07%, RSE: 14.50% and Kappa: 0.98 performance criteria values, respectively, has made the classification with minimum error. With this study conducted, it was determined that 85% of the quail eggs fertile and 15% of them has low reproduction capacity with the accurate classification success of 99.73%.

show abstract

Decision-tree induction to detect clinical mastitis with automatic milking

Cited by 55 publications

References 17 publications

Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Métodos Automatizados De Diagnóstico De Mastite Em Vacas Leiteiras: Uma Revisão

A Data Mining Application in Animal Breeding: Determination of Some Factors in Japanese Quail Eggs Affecting Fertility

Contact Info

Product

Resources

About