A non-invasive automatic broiler weight estimation and prediction method based on a machine learning algorithm was developed to address the issue of high labor costs and stress responses caused by the traditional broiler weighing method in large-scale broiler production. Machine learning algorithms are a data-driven strategy that enables computer systems to make predictions and judgments based on patterns and regularities that they have learned. To estimate the current weight of individual live broilers on farms, machine learning algorithms such as the Gaussian mixture model, Isolation Forest, and Ordering Points To Identify the Clustering Structure (OPTICS) are used to filter and extract data features using a two-stage clustering and noise reduction process. Real-time weight prediction was also achieved by combining polynomial fitting and the gray models and adjusting the model parameters based on prediction accuracy feedback. The symmetric mean absolute percentage error (SMAPE) value is a metric that is commonly used to evaluate the predictive performance of a model by comparing the degree of error between the model’s predicted value on the day of slaughter and the true value measured manually, and the results of the experiments on 111 datasets showed that 7.21% were less than or equal to 0.03, 28.83% were less than or equal to 0.1 and greater than 0.03, and 31.53% were less than or equal to 0.2 and greater than 0.1. This method can be used as a prediction scheme for broiler weight monitoring in a large-scale rearing environment, considering the cost of implementation and the accuracy of estimation.
The management of individual weights in broiler farming is not only crucial for increasing farm income but also directly linked to the revenue growth of integrated broiler companies, necessitating prompt resolution. This paper proposes a model to estimate daily average broiler weights using time and weight data collected through scales. In the proposed model, a method of self-adjusting weights in the bandwidth calculation formula is employed, and the daily average weight representative value is estimated using KDE. The focus of this study is to contribute to the individual weight management of broilers by intensively researching daily fluctuations in average broiler weight. To address this, weight and time data are collected and preprocessed through scales. The Gaussian kernel density estimation model proposed in this paper aims to estimate the representative value of the daily average weight of a single broiler using statistical estimation methods, allowing for self-adjustment of bandwidth values. When applied to the dataset collected through scales, the proposed Gaussian kernel density estimation model with self-adjustable bandwidth values confirmed that the estimated daily weight did not deviate beyond the error range of ±50 g compared with the actual measured values. The next step of this study is to systematically understand the impact of the broiler environment on weight for sustainable management strategies for broiler demand, derive optimal rearing conditions for each farm by combining location and weight data, and develop a model for predicting daily average weight values. The ultimate goal is to develop an artificial intelligence model suitable for weight management systems by utilizing the estimated daily average weight of a single broiler even in the presence of error data collected from multiple weight measurements, enabling more efficient automatic measurement of broiler weight and supporting both farms and broiler demand.
The weight information of broilers is important for understanding the growth progress of broilers and adjusting the breeding schedule, and predicting the broiler live weight at the time of shipment is an important task for producing high-quality broilers that meet consumer demand. To this end, we plan to analyze the broiler weight data automatically measured in a smart broiler house with an intelligent system and conduct a study to predict the weight until the time of shipment. To estimate the accurate daily body weight representative value of broiler body weight data, the K-means clustering method and the kernel density estimation method were applied, and the growth trends generated by each method were used as training data for the Prophet predictor, double exponential smoothing predictor, ARIMA predictor, and Gompertz growth model. The experimental results showed that the K-means + Prophet predictor model recorded the best prediction performance among the algorithm combinations proposed in this paper. The prediction results of the algorithm presented in this paper can analyze the growth progress of broilers in actual broiler houses and can be used as meaningful judgment data for adjusting the breeding schedule considering the time of shipment.
31 July 2022 in Journal of Digital Contents Society
Accurate prediction of broiler shipment weight is essential for optimizing production planning and meeting market demand. Previous studies have estimated representative daily weight values from load cell data using K-means clustering and kernel density estimation (KDE) and have applied forecasting models such as Prophet, ARIMA, and Gompertz. Among these, the combination of K-means and Prophet demonstrated the best performance. In this study, we propose an enhanced method integrating computer vision with load cell measurements. The YOLOv8n model localizes broilers in images, while a 5-pixel edge region, both inside and outside the weighing platform boundaries, filters invalid weight values. This enables accurate broiler counting on the weighing platform. The instantaneous population mean weight distribution is estimated by dividing the total measured weight by the detected broiler count. The representative daily weight values are then calculated through averaging. Additionally, we compare five outlier processing methods to evaluate their effectiveness in improving prediction accuracy. Experimental results show that our method achieves a prediction error of less than 50 g for broiler shipment weights, which will significantly improve farm operation efficiency and reduce feeding cost losses. This approach has already been deployed in selected farms and is ready for comprehensive implementation.
31 May 2018 in The Journal of Korean Institute of Information Technology
본 논문에서는 HSV의 색상과 에지 방향을 이용한 내용기반 영상 검색 방법을 제안한다. 제안된 알고리즘은 RGB 색상의 영상을 HSV 색상의 영상으로 변환한 뒤 색조(Hue)와 명도(Value)를 이용하여 에지 방향을 구한다. 색조와 명도, 그리고 에지 방향을 각각 양자화 한 후 모은 값을 영상의 특징벡터로 정의한다. 각 영상의 특징벡터는 데이터베이스에 저장한 후 질의로 입력된 영상의 특징벡터와 비교하여 유사영상들을 검색한다. 사용한 영상은 Corel 1000 데이터베이스의 영상 1000개이고, 이를 사용하여 검색 성능을 분석하였다. 실험한 결과 제안된 방법을 색상 정보만을 이용한 방법과 색상 차에 대한 히스토그램을 이용한 방법, 색상에 대한 코렐로 그램을 이용한 방법과 비교하였더니 상위 20개에 대한 평균 정확률에 대한 비교 결과 제안 방법이 각각 0.06, 0.01, 0.10 더 높게 나와 더 우수함을 알 수 있었다.