Latest Trend and Challenges in Machine Learning– and Deep Learning–Based Computational Techniques in Poultry Health and Disease Management: A Review

Abstract

To determine the flock’s economic worth, free-range chicken growers must determine the gender, bird movement, behavior, disease detection, and lameness of the chickens. However, because of the complex environmental background and the fluctuating chicken population, it is difficult for farmers to effectively and properly measure those characteristics. Manual estimation is also inaccurate and time-consuming because probable identification occurs in their life cycle. Therefore, the industry benefits from automated systems that can produce findings quickly and precisely in managing health and diseases. The advancement of machine learning (ML)– and deep learning (DL)–based algorithms are boons for poultry health and disease management. This study reviews the literature using ML and DL techniques in prediction, classification, and disease detection in various metrics, namely, poultry health and disease management. We have considered the research article published from 2010 to 2023 in this study, which uses ML- and DL-based computation techniques in poultry welfare metrics such as gender identification, tracking of poultry, analysis of broiler chicken behavior, detection of poultry diseases, lameness and broiler weight, and stress monitoring. In addition, this review explores the most recent developments, difficulties, strategies, and databases used in image preprocessing feature extraction and classification. The review addresses these challenges and discusses the approaches and techniques researchers employ to tackle them in the field of poultry management and disease detection.