An exact average symbol error rate analysis for the distributed dual-hop relay cooperative network with multiple relays in a Nakagami-m fading environment is presented.In the derivation of the moment generation functi...An exact average symbol error rate analysis for the distributed dual-hop relay cooperative network with multiple relays in a Nakagami-m fading environment is presented.In the derivation of the moment generation function of receiver Signal-to-Noise Ratio(SNR),the sectional integral method is used,instead of the cumulative density function method which is ordinarily used by the deduction of the outage probability of S-R-D link.The accurate symbol error rate of a dual-hop relay cooperative network is obtained with the closed-form Moment Genoration Function (MGF) expression.The correctness of the symbol error rate is verified through numerical simulations and is compared with other analytical methods.These deductions clearly show that the distributed cooperative diversity network presented has strong superiorities in overcoming severe fading and can achieve full diversity order.展开更多
Clinical examination data often have the features of carrying vague information,missing data and incomplete examination records,which lead to higher probabilities of misdiagnosis.A variational recursive-discriminant j...Clinical examination data often have the features of carrying vague information,missing data and incomplete examination records,which lead to higher probabilities of misdiagnosis.A variational recursive-discriminant joint model with fast weights(FWs)scheme is proposed.MIMIC-III data sets are trained and tested,and the results are used to diagnosing.Variational recurrent neural network(VRNN)with FWs can better obtain the temporal features with partly missing data,and discriminant neural network(DNN)is for decision.Moreover,layer regularization(LN)avoids the overflow of loss function and stabilize the dynamic parameters of each layer.For the simulations,10 laboratory tests were selected to predict 10 diseases,1600 samples and 400 samples were used for training and testing,respectively.The test accuracy of disease diagnosis without FWs is 72.55%,and that with FWs is 85.80%.Simulations reveal that the FWs mechanism can effectively optimize the system model,abstracting the features for diagnose,and significantly improve the accuracy of decision-making.展开更多
基金supported by Important National Science ＆ Technology Specific Projects under Grant No.CX01011the Important National Science ＆ Technology Specific Projects under Grant No.4101002+2 种基金the National Natural Science Foundation of China under Grants No.61002014,No.60972017,No.60972018the Excellent Young Teachers Program of MOE,PRC under Grant No.2009110120028the Research Fund for the Doctoral Program of Higher Education under Grants No.20091101110019,No.20070007019
文摘An exact average symbol error rate analysis for the distributed dual-hop relay cooperative network with multiple relays in a Nakagami-m fading environment is presented.In the derivation of the moment generation function of receiver Signal-to-Noise Ratio(SNR),the sectional integral method is used,instead of the cumulative density function method which is ordinarily used by the deduction of the outage probability of S-R-D link.The accurate symbol error rate of a dual-hop relay cooperative network is obtained with the closed-form Moment Genoration Function (MGF) expression.The correctness of the symbol error rate is verified through numerical simulations and is compared with other analytical methods.These deductions clearly show that the distributed cooperative diversity network presented has strong superiorities in overcoming severe fading and can achieve full diversity order.
基金supported by National Natural Science Foundation of China“Research on non-orthogonal multiple access technology for unauthorized transmission”(No.61771051)“Research on a new emergency positioning system for the integration of visible-light communication and MEMS inertial navigation”(No.61675025)
文摘Clinical examination data often have the features of carrying vague information,missing data and incomplete examination records,which lead to higher probabilities of misdiagnosis.A variational recursive-discriminant joint model with fast weights(FWs)scheme is proposed.MIMIC-III data sets are trained and tested,and the results are used to diagnosing.Variational recurrent neural network(VRNN)with FWs can better obtain the temporal features with partly missing data,and discriminant neural network(DNN)is for decision.Moreover,layer regularization(LN)avoids the overflow of loss function and stabilize the dynamic parameters of each layer.For the simulations,10 laboratory tests were selected to predict 10 diseases,1600 samples and 400 samples were used for training and testing,respectively.The test accuracy of disease diagnosis without FWs is 72.55%,and that with FWs is 85.80%.Simulations reveal that the FWs mechanism can effectively optimize the system model,abstracting the features for diagnose,and significantly improve the accuracy of decision-making.
