Due to e-business' s variety of customers with different navigational patterns and demands, multiclass queuing network is a natural performance model for it. The open multi-class queuing network(QN) models are bas...Due to e-business' s variety of customers with different navigational patterns and demands, multiclass queuing network is a natural performance model for it. The open multi-class queuing network(QN) models are based on the assumption that no service center is saturated as a result of the combined loads of all the classes. Several formulas are used to calculate performance measures, including throughput, residence time, queue length, response time and the average number of requests. The solution technique of closed multi-class QN models is an approximate mean value analysis algorithm (MVA) based on three key equations, because the exact algorithm needs huge time and space requirement. As mixed multi-class QN models, include some open and some closed classes, the open classes should be eliminated to create a closed multi-class QN so that the closed model algorithm can be applied. Some corresponding examples are given to show how to apply the algorithms mentioned in this article. These examples indicate that multi-class QN is a reasonably accurate model of e-business and can be solved efficiently.展开更多
The discovery of pulsars is of great significance in the field of physics and astronomy.As the astronomical equipment produces a large number of pulsar data,an algorithm for automatically identifying pulsars becomes u...The discovery of pulsars is of great significance in the field of physics and astronomy.As the astronomical equipment produces a large number of pulsar data,an algorithm for automatically identifying pulsars becomes urgent.We propose a deep learning framework for pulsar recognition.In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the High Time Resolution Universe Medlat Training Data,there are two coping strategies in our framework:the smart under-sampling and the improved loss function.We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance.To our best knowledge,this is the first study that integrates these strategies and techniques in pulsar recognition.The experiment results show that our framework outperforms previous works with respect to either the training time or F 1 score.We can not only speed up the training time by 10×compared with the state-ofthe-art work,but also get a competitive result in terms of F1 score.展开更多
文摘Due to e-business' s variety of customers with different navigational patterns and demands, multiclass queuing network is a natural performance model for it. The open multi-class queuing network(QN) models are based on the assumption that no service center is saturated as a result of the combined loads of all the classes. Several formulas are used to calculate performance measures, including throughput, residence time, queue length, response time and the average number of requests. The solution technique of closed multi-class QN models is an approximate mean value analysis algorithm (MVA) based on three key equations, because the exact algorithm needs huge time and space requirement. As mixed multi-class QN models, include some open and some closed classes, the open classes should be eliminated to create a closed multi-class QN so that the closed model algorithm can be applied. Some corresponding examples are given to show how to apply the algorithms mentioned in this article. These examples indicate that multi-class QN is a reasonably accurate model of e-business and can be solved efficiently.
基金supported in part by Science and Technology Commission of Shanghai Municipality,China(Grant No.19ZR1463900)the National Key R&D Programme of China(Grant No.2018YFA0404603)。
文摘The discovery of pulsars is of great significance in the field of physics and astronomy.As the astronomical equipment produces a large number of pulsar data,an algorithm for automatically identifying pulsars becomes urgent.We propose a deep learning framework for pulsar recognition.In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the High Time Resolution Universe Medlat Training Data,there are two coping strategies in our framework:the smart under-sampling and the improved loss function.We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance.To our best knowledge,this is the first study that integrates these strategies and techniques in pulsar recognition.The experiment results show that our framework outperforms previous works with respect to either the training time or F 1 score.We can not only speed up the training time by 10×compared with the state-ofthe-art work,but also get a competitive result in terms of F1 score.
