Bacteria- or virus-infected chicken is conventionally detected by manual observation and conffrmed by a laboratory test, which may lead to late detection, signiffcant economic loss, and threaten human health. This paper reports on the development of an innovative technique to detect bacteria- or virus-infected chickens based on the optical chromaticity of the chicken comb. The chromaticity of the infected and healthy chicken comb was extracted and analyzed with International Commission on Illumination (CIE) XYZ color space. Logistic Regression, Support Vector Machines (SVMs), K-Nearest Neighbors (KNN), and Decision Trees have been developed to detect infected chickens using the chromaticity data. Based on the X and Z chromaticity data from the chromaticity analysis, the color of the infected chicken’s comb converged from red to green and yellow to blue. The development of the algorithms shows that Logistic Regression, SVM with Linear and Polynomial kernels performed the best with 95% accuracy, followed by SVM-RBF kernel, and KNN with 93% accuracy, Decision Tree with 90% accuracy, and lastly, SVM-Sigmoidal kernel with 83% accuracy. The iteration of the probability threshold parameter for Logistic Regression models has shown that the model can detect all infected chickens with 100% sensitivity and 95% accuracy at the probability threshold of 0.54. These works have shown that, despite using only the optical chromaticity of the chicken comb as the input data, the developed models (95% accuracy) have performed exceptionally well, compared to other reported results (99.469% accuracy) which utilize more sophisticated input data such as morphological and mobility features. This work has demonstrated a new feature for bacteria- or virus-infected chicken detection and contributes to the development of modern technology in agriculture applications.
1. Introduction
TTe increase in human population has forced poultry meat production to increase (1). However, mass production in the poultry industry may be more vulnerable to disease outbreaks in farmed animals due to the increased number of animals per area and prolonged usage of antibiotics (2). TTe World Bank reported a direct cost of $20 billion for disease outbreak events between 1988 to 2006, including public and animal health costs, compensation, production, and revenue costs. Plus, indirect losses, including animal product chain, trade, and tourism, were estimated to be more than $200 billion worldwide (3). For instance, the United States and China’s poultry industry recorded huge economic losses and threats to human health due to several poultry-related diseases such as the H7N9 avian inffuenza virus outbreak in 2013 , multistate foodborne outbreak of Salmonella Typhimurium , avian inffuenza outbreaks in 2022 , foodborne pathogens such as Campylobacter, Escherichia coli, Salmonella, and Norovirus, severe respiratory illness among poultry slaughter plant workers due to Chlamydia psittaci , andhuman infection with the inffuenza A (H5N6) virus of avian origin Although the viruses are preventable, curable, and controllable, there is still a continuous threat that they could start a pandemic if the viruses develop the ability to spread among humans effectively. TTerefore, early detection of diseases in poultry production is a primary concern to prevent a major outbreak that would affect the economy and human health.
Numerous disease detection methods have been proposed,developed, and widely applied to give early detection to prevent this catastrophe. TTe conventional method of detecting infected chickenwas using physical examination and laboratory tests. TTe physicalexamination is a way of seeing infected chicken through observationof clinical signs or changes in behavior and physical appearance of thechicken individually. TTe suspected chicken will be evicted from theffocks and undergo laboratory tests such as culture , polymerase chain reaction (PCR) , enzyme-linkedimmunosorbent assay (ELISA) and lateral ffow assay (LFA)). Biological samples such as blood, cloacal swabs, organs, andfeces were collected from the suspected chicken for the test. Apart from the requirement of trained personnel to conduct the tests, these methods are considered costly due to the equipment needed, such asa thermocycler, ELISA reader, PCR buffer, syringe, swab kit, and petridish for sampling and detecting the pathogen . Overall, these methods can detect infected chickens with high precision andspeciffcity. However, many other factors, such as cost and time takenfor detection, were compromised, which makes it almost impossible to be implemented, especially for large-scale poultry producers.
