In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are...In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are combined to optimize the hidden layers' parameters which include the number of hidden layers and their node numbers.The classifier with dynamic thresholds is used to standardize the output for the first time, and it improves the robustness of the model to a high level.Finally, the classifier is applied to forecast box office revenue of a movie before its theatrical release.The comparison results with the MLP method show that the MLBP classifier model achieves more satisfactory results, and it is more reliable and effective to solve the problem.展开更多
The mining industry annually consumes trillions of British thermal units of energy,a large part of which is saveable.Diesel fuel is a significant source of energy in surface mining operations and haul trucks are the m...The mining industry annually consumes trillions of British thermal units of energy,a large part of which is saveable.Diesel fuel is a significant source of energy in surface mining operations and haul trucks are the major users of this energy source.Cross vehicle weight,truck velocity and total resistance have been recognised as the key parameters affecting the fuel consumption.In this paper,an artificial neural network model was developed to predict the fuel consumption of haul trucks in surface mines based on the gross vehicle weight,truck velocity and total resistance.The network was trained and tested using real data collected from a surface mining operation.The results indicate that the artificial neural network modelling can accurately predict haul truck fuel consumption based on the values of the haulage parameters considered in this study.展开更多
The paper presents an extension multi-laye r p erceptron model that is capable of representing and reasoning propositional know ledge base. An extended version of propositional calculus is developed, and its some prop...The paper presents an extension multi-laye r p erceptron model that is capable of representing and reasoning propositional know ledge base. An extended version of propositional calculus is developed, and its some properties is discussed. Formulas of the extended calculus can be expressed in the extension multi-layer perceptron. Naturally, semantic deduction of prop ositional knowledge base can be implement by the extension multi-layer perceptr on, and by learning, an unknown formula set can be found.展开更多
Acquisition of accurate channel state information （CSI） at transmitters results in a huge pilot overhead in massive multiple input multiple output （MIMO） systems due to the large number of antennas in the base sta...Acquisition of accurate channel state information （CSI） at transmitters results in a huge pilot overhead in massive multiple input multiple output （MIMO） systems due to the large number of antennas in the base station （BS）. To reduce the overwhelming pilot overhead in such systems, a structured joint channel estimation scheme employing compressed sensing （CS） theory is proposed. Specifically, the channel sparsity in the angular domain due to the practical scattering environment is analyzed, where common sparsity and individual sparsity structures among geographically neighboring users exist in multi-user massive MIMO systems. Then, by equipping each user with multiple antennas, the pilot overhead can be alleviated in the framework of CS and the channel estimation quality can be improved. Moreover, a structured joint matching pursuit （SJMP） algorithm at the BS is proposed to jointly estimate the channel of users with reduced pilot overhead. Furthermore, the probability upper bound of common support recovery and the upper bound of channel estimation quality using the proposed SJMP algorithm are derived. Simulation results demonstrate that the proposed SJMP algorithm can achieve a higher system performance than those of existing algorithms in terms of pilot overhead and achievable rate.展开更多
基金Supported by National Natural Science Foundation of China (No. 60573172)
文摘In this study, a Multi-Layer BP neural network(MLBP) with dynamic thresholds is employed to build a classifier model.As to the design of the neural network structure, theoretical guidance and plentiful experiments are combined to optimize the hidden layers' parameters which include the number of hidden layers and their node numbers.The classifier with dynamic thresholds is used to standardize the output for the first time, and it improves the robustness of the model to a high level.Finally, the classifier is applied to forecast box office revenue of a movie before its theatrical release.The comparison results with the MLP method show that the MLBP classifier model achieves more satisfactory results, and it is more reliable and effective to solve the problem.
基金CRC Mining and The University of Queensland for their financial support for this study
文摘The mining industry annually consumes trillions of British thermal units of energy,a large part of which is saveable.Diesel fuel is a significant source of energy in surface mining operations and haul trucks are the major users of this energy source.Cross vehicle weight,truck velocity and total resistance have been recognised as the key parameters affecting the fuel consumption.In this paper,an artificial neural network model was developed to predict the fuel consumption of haul trucks in surface mines based on the gross vehicle weight,truck velocity and total resistance.The network was trained and tested using real data collected from a surface mining operation.The results indicate that the artificial neural network modelling can accurately predict haul truck fuel consumption based on the values of the haulage parameters considered in this study.
文摘The paper presents an extension multi-laye r p erceptron model that is capable of representing and reasoning propositional know ledge base. An extended version of propositional calculus is developed, and its some properties is discussed. Formulas of the extended calculus can be expressed in the extension multi-layer perceptron. Naturally, semantic deduction of prop ositional knowledge base can be implement by the extension multi-layer perceptr on, and by learning, an unknown formula set can be found.
基金Project supported by the Fundamental Research Funds for the Cen- tral Universities （No. HIT.MKSTISP.2016 13） and the National Natural Science Foundation of China （No. 61671176）
文摘Acquisition of accurate channel state information （CSI） at transmitters results in a huge pilot overhead in massive multiple input multiple output （MIMO） systems due to the large number of antennas in the base station （BS）. To reduce the overwhelming pilot overhead in such systems, a structured joint channel estimation scheme employing compressed sensing （CS） theory is proposed. Specifically, the channel sparsity in the angular domain due to the practical scattering environment is analyzed, where common sparsity and individual sparsity structures among geographically neighboring users exist in multi-user massive MIMO systems. Then, by equipping each user with multiple antennas, the pilot overhead can be alleviated in the framework of CS and the channel estimation quality can be improved. Moreover, a structured joint matching pursuit （SJMP） algorithm at the BS is proposed to jointly estimate the channel of users with reduced pilot overhead. Furthermore, the probability upper bound of common support recovery and the upper bound of channel estimation quality using the proposed SJMP algorithm are derived. Simulation results demonstrate that the proposed SJMP algorithm can achieve a higher system performance than those of existing algorithms in terms of pilot overhead and achievable rate.
