جستجوی مقالات مرتبط با کلیدواژه "artificial intelligence" در نشریات گروه "علوم دام"

Sistani cows are generally restless animals; therefore, controlling, treating, and weighing them is difficult. On the other hand, recording the weight of domestic animals, including Sistani cows, is inevitable, because it provides a good scale for management decisions in the herd such as balancing the diet, changing environmental conditions, or determining the time of slaughter of fattening animals. In addition to scales, various methods are commonly used to measure the body weight of large animals. Some of these methods include the use of weight-meters, appraisal assessments, and the use of mathematical models. One of the new methods for predicting livestock weight is artificial intelligence. Because some reports are indicating that artificial intelligence could facilitate the weighing process of animals, this study was performed to predict the body weight of Sistani cows using computer vision technology. The data required for this study were recorded in the Zahak breeding station located in Sistan and Baluchestan province of Iran. The recording operation involved the weighing and biometric measurement of about 190 Sistani cattle, including calves, heifers, and male and female animals, every three months during a year. At the time of weighing, images of the lateral view of each animal were taken and recorded using the CANON SX150IS digital camera. During this period, a total of 358 weight records of Sistani cows at different ages were recorded. The digital images were initially preprocessed using MATLAB software, and then some morphological features were extracted from each image. For predicting the weight of Sistani cows via the Artificial Neural Network (ANN), the extracted features of images were introduced to the ANN model as input and the weight of cows as output. The "feed-forward neural network", which was trained by the "error propagation" algorithm, was used to predict the weight of cows. The function used in the hidden layer of the ANN model was sigmoidal and in the output layer was linear. An ANN model which had the highest precision and lowest error was selected as the final model for predicting the animal weights. The criteria for selecting the best model were the highest determination coefficient (R2) and the lowest mean square error (MSE) compared to other available models. Out of 22 features extracted from each image, only 15 of them, which had a higher correlation with the body weight of cows at different ages, were selected as effective features. As result, equivalent diameter, major axis length, minor axis length, bounding box, convex area, filled area, area, perimeter, and the number of non-zero pixels of the image (NNZ) had the highest correlation with the cattle weights (P<0.01) and used as effective features to train the ANN model. The final ANN model had 15 neurons in the input layer including selected image features, 11 neurons in the hidden layer, and one neuron in the output layer including the weight of the cows. The precisions of the artificial neural network in the training, validation, and test phase were 0.974, 0.970, and 0.981, respectively. The results showed that the final ANN model had acceptable precision in all light, medium, and heavy-weight cows, and the size and the age of animals did not have a significant effect on the precision of the artificial neural network model. A correlation between the actual weight of Sistani cows and the weights predicted by the ANN model was 98.3%. The average error of the model in predicting the weight of cows was 1.11%. In the practical test, a 2.32 kg deviation was observed between the predictions of the ANN model and actual weights in Sistani cows. The accuracy of the ANN model for predicting the weight of Sistani cows in the present study is acceptable and within the range of the other reports. The proposed method based on image processing and ANN, had acceptable results in predicting the weight of Sistani cows. Given the difficulties of weighing Sistani cows as heavy livestock and sometimes the time-consuming process, it seems that the use of new technologies such as computer vision methods can be a good alternative to conventional weighing methods and facilitate and reduce recording costs of Sistani cows.

This research was conducted to investigate the possibility of using visual machine technology in measuring the body dimensions of Sistani cows. For this purpose, the record of body dimensions including length, shoulder height, hip height and chest circumference of 179 heads of livestock in Zahak Sistani cow breeding station, were measured at different time points, using a tape meter. At recording time, digital images were taken using the canon camera from the lateral view of cattle from distance of 2 meters. Digital image processing and feature extraction were performed using Graphical Unit Interference of MATLAB software. The feature of digital images as input and different body dimensions of cows as output of Artificial Neural Network(ANN) were used in the training and modeling phase. The results showed that, out of 22 features extracted from the images of Sistani cows, the 15 effective features, such as Equivalent Diameter, Major Axis Length, Minor Axis Length, Bounding Box, Convex Area, Filled Area, Area, Perimeter, and the number of white pixels of image (NNZ) had a significant correlation with the body dimensions of the Sistani cow(p<0.01). Body dimensions of Sistani cows including body length, shoulder height, hip height, and chest girths were estimated with accuracy of 0.98, 0.97, 0.97and 0.98%, by the ANNs model, respectively. The results of the present research showed that Artificial Intelligence Technology can act as a suitable alternative to biometric evaluation of Sistani cows and save time and relevant costs.

The poultry industry is very important in terms of supplying a significant portion of the country's food and protein needs. In this research, the energy consumption of broiler chickens has been evaluated. For this purpose, information was collected from 45 broiler chicken producers randomly collected in Mazandaran province. In this study, energy consumption and energy indices were calculated first and then, using artificial neural network, output energy modeling was considered as a function. The results of this study showed that total input and output energy in broiler chicken meat production was 153.79 and 27.45 GJ per 1000, respectively. In broiler chickens, the highest inputs were consumed with 61.48%. The energy ratio in the production of this product was also calculated to be 0.18. The artificial neural network results showed that the best structure for estimating the energy consumption of broiler chicken meat was estimated to be 5-12-1. The coefficient of explanation for the best structure for broiler chicken production was 0.99 for training data. Therefore, this model was selected as the best method for estimating the output energy based on input energy in the study area. In assessing the effectiveness of inputs on the outputs, the fossil fuel showed the highest sensitivity among the production inputs that reveals the needs for revision of the energy resources more than ever.

This study was conducted to introduce a method based on using digital image processing to estimate the weight of new born lambs of Zandi sheep. Data was collected from 115 new born lambs reared in the Zandi sheep breeding centre of Khojir, Tehran. Primarily, all lambs were weighted, and at the same time, several photos were taken from the side view of each lamb using a digital camera from a fixed imaging distance. Then, the features related to the lateral area of lambs were extracted from digital images using image processing tools (IPT) of MATLAB software. Afterwards, a suitable artificial neural network was designed to estimate the lamb's weight based on the features was extracted from digital images. The neural network was trained with the precision of 96.94 % to estimate the lamb's weight. In the test phase, there was a correlation equal to 90.11 percent between the actual weight of lambs and weights estimated by the artificial neural network (p