The factor that affects the milk production of dairy cows is the breeding of cows. Before the cows can be bred, the cows must show signs of estrus first. Farmers must detect estrus in time because the period of estrus...
详细信息
ISBN:
(数字)9783031585616
ISBN:
(纸本)9783031585609;9783031585616
The factor that affects the milk production of dairy cows is the breeding of cows. Before the cows can be bred, the cows must show signs of estrus first. Farmers must detect estrus in time because the period of estrus is It did not take long, so this research has developed the prediction of estrus in dairy cows using artificial intelligence methods, that is, using convolutional neural networks to help in the prediction. This research has a Comparison between the convolutional neural networks before adjusting the parameters, which achieved an accuracy of 95.082% and when using the artificial immunity system algorithm to adjust the parameters, the accuracy was 98.361%. The prediction used 4 types of dairy cow movements for prediction.
Faults or accidents may occur in a nuclear power plant (NPP), but it is hard for operators to recognize the situation and take effective measures quickly. So, online monitoring, diagnosis and prediction (OMDP) is used...
详细信息
Faults or accidents may occur in a nuclear power plant (NPP), but it is hard for operators to recognize the situation and take effective measures quickly. So, online monitoring, diagnosis and prediction (OMDP) is used to provide enough information to operators and improve the safety of NPPs. In this paper, distributed conservation equation (DCE) and artificial immunity system (AIS) are proposed for online monitoring and diagnosis. On this basis, quantitative simulation models and interactive database are combined to predict the trends and severity of faults. The effectiveness of OMDP in improving the monitoring and prediction of condensate and feed water system (CFWS) was verified through simulation tests. (C) 2015 Elsevier Ltd. All rights reserved.
The real-valued negative selection algorithm (RNS) has been a key algorithm of anomaly detection. However, the self set which is used to train detectors has some problems, such as the wrong samples;boundary invasion a...
详细信息
ISBN:
(纸本)9783642052521
The real-valued negative selection algorithm (RNS) has been a key algorithm of anomaly detection. However, the self set which is used to train detectors has some problems, such as the wrong samples;boundary invasion and the overlapping among the self samples. Due to the fact that the probability of most real-valued self vectors is near to Gaussian distribution, this paper proposes a new method which uses Gaussian distribution theory to optimize the self set before training stage. The method was tested by 2-dimensional synthetic data and real network data. Experimental results show that, the new method effectively solves the problems mentioned before.
暂无评论