http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Study of Digit Recognition Algorithm for Meter based on Rough Set and Neural Network
Xiaochen Zhang,Yuanchang Zhong,Jiajia Shen,Kun Li,Congjun Feng 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.8
Due to the low recognition accuracy, the remote meter reading technology based on camera direct reading has been developed slowly. Although there is a variety of features data for recognizing digit in image using BP neural network, some of data cannot be used to recognize digit accurately. Moreover, the BP network has a slow rate of convergence, low accuracy and easily fall into local minimum. To solve the above questions, a new digit recognition algorithm of meter based on rough set and neural network which are optimized by genetic algorithm is proposed. The improved genetic rough set algorithm is used for reducing the data, and then the minimum feature attribute sets after reduction are input to genetic neural network for identifying digit. The experimental results show that the algorithm can effectively reduce the number of decision attributes and simplify the structure of the neural network with high identification accuracy and short training time, which improve the generalization ability and robustness of the neural network.
( Nianlong Jia ),( Wenjiang Feng ),( Yuanchang Zhong ),( Hong Kang ) 한국인터넷정보학회 2014 KSII Transactions on Internet and Information Syst Vol.8 No.11
Two-way relaying is an effective way of improving system spectral efficiency by making use of physical layer network coding. However, energy efficiency in OFDM-based bidirectional relaying with asymmetric traffic requirement has not been investigated. In this study, we focused on subcarrier transmission mode selection, bit loading, and power allocation in a multicarrier single amplified-and-forward relay system. In this scheme, each subcarrier can operate in two transmission modes: one-way relaying and two-way relaying. The problem is formulated as a mixed integer programming problem. We adopt a structural approximation optimization method that first decouples the original problem into two suboptimal problems with fixed subcarrier subsets and then finds the optimal subcarrier assignment subsets. Although the suboptimal problems are nonconvex, the results obtained for a single-tone system are used to transform them to convex problems. To find the optimal subcarrier assignment subsets, an iterative algorithm based on subcarrier ranking and matching is developed. Simulation results show that the proposed method can improve system performance compared with conventional methods. Some interesting insights are also obtained via simulation.