Modeling energy partition patterns of growing pigs fed diets with different net energy levels based on machine learning.

The objectives of this study were to evaluate the energy partition patterns of growing pigs fed diets with different net energy (NE) levels based on machine learning methods, and to develop prediction models for the NE requirement of growing pigs. Twenty-four Duroc × Landrace × Yorkshire crossbred barrows with an initial body weight of 24.90 ±â€…0.46 kg were randomly assigned to 3 dietary treatments, including the low NE group (2,325 kcal/kg), the medium NE group (2,475 kcal/kg), and the high NE group (2,625 kcal/kg). The total feces and urine produced from each pig during each period were collected, to calculate the NE intake, NE retained as protein (NEp), and NE retained as lipid (NEl). A total of 240 sets of data on the energy partition patterns of each pig were collected, 75% of the data in the dataset was randomly selected as the training dataset, and the remaining 25% was set as the testing dataset. Prediction models for the NE requirement of growing pigs were developed using algorithms including multiple linear regression (MR), artificial neural networks (ANN), k-nearest neighbor (KNN), and random forest (RF), and the prediction performance of these models was compared on the testing dataset. The results showed pigs in the low NE group showed a lower average daily gain, lower average daily feed intake, lower NE intake, but greater feed conversion ratio compared to pigs in the high NE group in most growth stages. In addition, pigs in the 3 treatment groups did not show a significant difference in NEp in all growth stages, while pigs in the medium and high NE groups showed greater NEl compared to pig in the low NE group in growth stages from 25 to 55 kg (P < 0.05). Among the developed prediction models for NE intake, NEp, and NEl, the ANN models demonstrated the most optimal prediction performance with the smallest root mean square error (RMSE) and the largest R2, while the RF models had the worst prediction performance with the largest RMSE and the smallest R2. In conclusion, diets with varied NE concentrations within a certain range did not affect the NEp of growing pigs, and the models developed with the ANN algorithm could accurately achieve the NE requirement prediction in growing pigs.

Net energy (NE) can unify the energy value of the feed with the energy requirements of the pig more accurately and is the optimal system for accurately predicting the growth performance of pigs. The evaluation of the NE partition pattern is difficult and costly, thus, establishing a predicted model is a more efficient way. This study was conducted to evaluate the energy partition patterns of growing pigs fed diets with different NE levels based on machine learning methods. Diets with varied NE concentrations within a certain range did not affect the growth performance and NE requirement for lipid deposition in growing pigs. Among the 4 models developed to predict NE requirements, the artificial neural networks model had the highest accuracy, while the multiple linear regression model had the highest interpretability.

Oils with different degree of saturation: effects on ileal digestibility of fat and corresponding additivity and bacterial community in growing pigs.

BACKGROUND: Oils are important sources of energy in pig diets. The combination of oils with different degree of saturation contributes to improve the utilization efficiency of the mixed oils and may reduce the cost of oil supplemented. An experiment was conducted to evaluate the effects of oils with different degree of saturation on the fat digestibility and corresponding additivity and bacterial community in growing pigs. METHODS: Eighteen crossbred (Duroc × Landrace × Yorkshire) barrows (initial body weight: 29.3 ± 2.8 kg) were surgically fitted with a T-cannula in the distal ileum. The experimental diets included a fat-free basal diet and 5 oil-added diets. The 5 oil-added diets were formulated by adding 6% oil with different ratio of unsaturated to saturated fatty acids (U:S) to the basal diet. The 5 oils were palm oil (U:S = 1.2), canola oil (U:S = 12.0), and palm oil and canola oil were mixed in different proportions to prepare a combination of U:S of 2.5, 3.5 and 4.5, respectively. RESULTS: The apparent and standardized ileal digestibility (AID and SID) of fat and fatty acids increased linearly (P < 0.05) as the U:S of dietary oils increased except for SID of fat and C18:2. The AID and SID of fat and fatty acids differed among the dietary treatments (P < 0.05) except for SID of unsaturated fatty acids (UFA) and C18:2. Fitted one-slope broken-line analyses for the SID of fat, saturated fatty acids (SFA) and UFA indicated that the breakpoint for U:S of oil was 4.14 (R2 = 0.89, P < 0.01), 2.91 (R2 = 0.98, P < 0.01) and 3.84 (R2 = 0.85, P < 0.01), respectively. The determined SID of fat, C18:1, C18:2 and UFA in the mixtures was not different from the calculated SID of fat, C18:1, C18:2 and UFA. However, the determined SID of C16:0, C18:0 and SFA in the mixtures were greater than the calculated SID values (P < 0.05). The abundance of Romboutsia and Turicibacter in pigs fed diet containing palm oil was greater than that in rapeseed oil treatment group, and the two bacteria were negatively correlated with SID of C16:0, C18:0 and SFA (P < 0.05). CONCLUSIONS: The optimal U:S for improving the utilization efficiency of mixed oil was 4.14. The SID of fat and UFA for palm oil and canola oil were additive in growing pigs, whereas the SID of SFA in the mixture of two oils was greater than the sum of the values of pure oils. Differences in fat digestibility caused by oils differing in degree of saturation has a significant impact on bacterial community in the foregut.

Damage Indexing Method for Shear Critical Tubular Reinforced Concrete Structures based on Crack Image Analysis.

Image analysis techniques have been applied to measure the displacements, strain field, and crack distribution of structures in the laboratory environment, and present strong potential for use in structural health monitoring applications. Compared with accelerometers, image analysis is good at monitoring area-based responses, such as crack patterns at critical regions of reinforced concrete (RC) structures. While the quantitative relationship between cracks and structural damage depends on many factors, cracks need to be detected and quantified in an automatic manner for further investigation into structural health monitoring. This work proposes a damage-indexing method by integrating an image-based crack measurement method and a crack quantification method. The image-based crack measurement method identifies cracks locations, opening widths, and orientations. Fractal dimension analysis gives the flexural cracks and shear cracks an overall damage index ranging between 0 and 1. According to the orientations of the cracks analyzed by image analysis, the cracks can be classified as either shear or flexural, and the overall damage index can be separated into shear and flexural damage indices. These damage indices not only quantify the damage of an RC structure, but also the contents of shear and flexural failures. While the engineering significance of the damage indices is structure dependent, when the damage indexing method is used for structural health monitoring, the damage indices safety thresholds can further be defined based on the structure type under consideration. Finally, this paper demonstrates this method by using the results of two experiments on RC tubular containment vessel structures.

Measurement of Dynamic Responses from Large Structural Tests by Analyzing Non-Synchronized Videos.

Image analysis techniques have been employed to measure displacements, deformation, crack propagation, and structural health monitoring. With the rapid development and wide application of digital imaging technology, consumer digital cameras are commonly used for making such measurements because of their satisfactory imaging resolution, video recording capability, and relatively low cost. However, three-dimensional dynamic response monitoring and measurement on large-scale structures pose challenges of camera calibration and synchronization to image analysis. Without satisfactory camera position and orientation obtained from calibration and well-synchronized imaging, significant errors would occur in the dynamic responses during image analysis and stereo triangulation. This paper introduces two camera calibration approaches that are suitable for large-scale structural experiments, as well as a synchronization method to estimate the time difference between two cameras and further minimize the error of stereo triangulation. Two structural experiments are used to verify the calibration approaches and the synchronization method to acquire dynamic responses. The results demonstrate the performance and accuracy improvement by using the proposed methods.