Evaluation of nitrogen excretion equations for ryegrass pasture-fed dairy cows

Meta-Regression to Develop Predictive Equations for Urinary Nitrogen Excretion of Lactating Dairy Cows

Dairy cows' urinary nitrogen (N) excretion (UN; g/d) represents a significant environmental concern due to their contribution to nitrate leaching, nitrous oxide (a potent greenhouse gas), and ammonia emissions (contributor to N deposition). The first objective of the current study was to determine the adequacy of existing models to predict UN from total mixed ration (TMR)-fed and fresh forage (FF)-fed cows. Next, we aimed to develop equations to predict UN based on animal factors [milk urea nitrogen (MUN; mg/dL) and body weight (BW, kg)] and to explore how these equations are improved when dietary factors, such as diet type, dry matter intake (DMI), or dietary characteristics [neutral detergent fiber (NDF) and crude protein (CP) content], are considered. A dataset was obtained from 51 published experiments composed of 174 treatment means. The whole dataset was used to evaluate the mean and linear biases of three existing equations including diet type as an interaction term; all models had significant linear and mean biases and two of the three models had poor predictive capabilities as indicated by their large relative prediction error (RPE; root mean square error of prediction as a percent of the observed mean). Next, the complete data set was split into training and test sets, which were used to develop and to evaluate new models, respectively. The first model included MUN and BW, and there was a significant interaction between diet type and the coefficients. This model had the worst 1:1 agreement [Lin's concordance correlation coefficient (CCC) = 0.50] and largest RPE (24.7%). Models that included both animal and dietary factors performed the best, and when included in the model, the effect of diet type was no longer significant (p > 0.10). These models all had very good agreement (CCC ≥ 0.86) and relatively low RPE (≤13.1%). This meta-analysis developed precise and accurate equations to predict UN from dairy cows in both confined and pasture-based systems.

Machine-Learning-Based Uplink Throughput Prediction from Physical Layer Measurements

The uplink (UL) throughput prediction is indispensable for a sustainable and reliable cellular network due to the enormous amounts of mobile data used by interconnecting devices, cloud services, and social media. Therefore, network service providers implement highly complex mobile network systems with a large number of parameters and feature add-ons. In addition to the increased complexity, old-fashioned methods have become insufficient for network management, requiring an autonomous calibration to minimize utilization of the system parameter and the processing time. Many machine learning algorithms utilize the Long-Term Evolution (LTE) parameters for channel throughput prediction, mainly in favor of downlink (DL). However, these algorithms have not achieved the desired results because UL traffic prediction has become more critical due to the channel asymmetry in favor of DL throughput closing rapidly. The environment (urban, suburban, rural areas) affect should also be taken into account to improve the accuracy of the machine learning algorithm. Thus, in this research, we propose a machine learning-based UL data rate prediction solution by comparing several machine learning algorithms for three locations (Houston, Texas, Melbourne, Florida, and Batman, Turkey) and determine the best accuracy among all. We first performed an extensive LTE data collection in proposed locations and determined the LTE lower layer parameters correlated with UL throughput. The selected LTE parameters, which are highly correlated with UL throughput (RSRP, RSRQ, and SNR), are trained in five different learning algorithms for estimating UL data rates. The results show that decision tree and k-nearest neighbor algorithms outperform the other algorithms at throughput estimation. The prediction accuracy with the R2 determination coefficient of 92%, 85%, and 69% is obtained from Melbourne, Florida, Batman, Turkey, and Houston, Texas, respectively.