Support vector regression algorithm is applied to colleges recruiting students prediction in the paper. As colleges recruiting students prediction is a nonlinear regression problem,the input training data of colle...
详细信息
Support vector regression algorithm is applied to colleges recruiting students prediction in the paper. As colleges recruiting students prediction is a nonlinear regression problem,the input training data of colleges recruiting students are nonlinearly mapped into a high dimensional space in support vector regression model. The amount of colleges recruiting students of Sichuan province from 2000 to 2008 is used to prove the effectiveness of support vector regression ***,the forecasting curves of support vector regression method and BP neural network and the comparison of forecasting error for amount of colleges recruiting students between support vector regression method and BP neural network are given in this *** comparison results of forecasting error for amount of colleges recruiting students between support vector regression method and BP neural network indicate that support vector regression method has a higher forecasting accuracy than BP neural network.
Project evaluation and selection is a complex multiattribute decision-making problem. With the information uncertainty and inaccuracy considered, a new model for project evaluation and selection is proposed, which ...
详细信息
Project evaluation and selection is a complex multiattribute decision-making problem. With the information uncertainty and inaccuracy considered, a new model for project evaluation and selection is proposed, which combines the fuzzy analytic hierarchy process (AHP) and technique for order performance by similarity to ideal solution (TOPSIS). The hybrid method is based on interval-valued triangular fuzzy numbers. An index system for selecting the optimal project is established. The weights of criteria and sub-criteria are derived by fuzzy AHP. The relative closeness is drawn from the calculation of the distance between the alternatives and positive ideal solutions or negative ones. Also, the ranking of alternatives can be based on their relative closeness. Finally, a case study is given adopting the proposed method.
the site selection of the base station is regarded as one of the most important parts in the project of the wireless capacity expansion for Yulin Mobile. It is the essential factor in determining the better perfor...
详细信息
the site selection of the base station is regarded as one of the most important parts in the project of the wireless capacity expansion for Yulin Mobile. It is the essential factor in determining the better performance, the telephone traffic distribution as well. Mainly focusing on the current situation of the site selection of Yulin Mobil, this paper is trying to make a predictive analysis, moreover, we put forward a series of technical proposals, which is not only conclusive to the return of investment, the project implement in the construction of the Yulin Mobile, but also valuable to the promotion of the great task.
With the development of smart grid, the power communication service presents features of IP, broadband, and intelligence. The traditional transmission network based on Multi-Service Transport Plat (MSTP) cannot ad...
详细信息
With the development of smart grid, the power communication service presents features of IP, broadband, and intelligence. The traditional transmission network based on Multi-Service Transport Plat (MSTP) cannot adapt the evolution trend of allIP and ultra long-haul. The cost of Dense Wavelength Division Multiplexing (DWDM) technology also needs to be reduced. In this paper, a new framework of the next generation power communication transmission network based on Packet Transport Network (PTN) and Optical Transport Network (OTN) is proposed. Furthermore, strategies for interconnection and evolution of the current and future transmission network are discussed. The conclusion is that the PTN and OTN based network can solve the problems of traditional MSTP and DWDM network, so it is a suitable scheme for the next generation power communication transmission network.
In this paper, an improved algorithm based on the BM algorithm: BMD is proposed. BMD algorithm can reduce the space complexity and maintain the time complexity by reducing a pretreatment function and recording the ...
详细信息
ISBN:
(纸本)9781467306898
In this paper, an improved algorithm based on the BM algorithm: BMD is proposed. BMD algorithm can reduce the space complexity and maintain the time complexity by reducing a pretreatment function and recording the number of times that a bad char found in the pattern. Experiments indicate that the space complexity is reduced by 36% at most. Therefore, the improved algorithm can provide significant improvement in pattern matching performance when using in an IDS.
As the development of the data acquisition technology, the research of the uncertain data has been the center of people's attention, and at the same time, the cluster of the uncertain data has been in use wide...
详细信息
As the development of the data acquisition technology, the research of the uncertain data has been the center of people's attention, and at the same time, the cluster of the uncertain data has been in use widely. In this paper, after studying the cluster of the uncertain data, considering characters of the uncertain data, we propose a improved algorithm. We called it En-DBSCAN. In order to adapt the request of uncertain data's clustering we add probability factors and the theory of information entropy. The algorithm brings in a conception of probability radius to adjust uncertain data's scope of EPS neighborhood and information entropy to reduce center point's indeterminacy. Besides, this paper gives an analysis and confirmation about the algorithm.
On the basis of the research of massive signaling mining, obtain user track, analyze user behavior, mine user preference, and then utilize 3G mobile communications network technology to design a platform of mobile...
详细信息
On the basis of the research of massive signaling mining, obtain user track, analyze user behavior, mine user preference, and then utilize 3G mobile communications network technology to design a platform of mobile service support, which generalizes the signaling information for all types of customers and makes statistics, and reasons customized information intelligently, extracts effective data though technology of data mining, analyses user behavior and makes intelligent of processing, then selects services for the customer they need most automatically. It is personalized, precise and intelligent.
to realize the requirements translating industrial instruments to the digital, HART modem and HART PC software have been developed. When running the HART software on a PC, the signals are conversed by a HART modem...
详细信息
to realize the requirements translating industrial instruments to the digital, HART modem and HART PC software have been developed. When running the HART software on a PC, the signals are conversed by a HART modem to realize the functions of monitoring the intelligent electrical positioner, contlguration and so on. The data of HART 475 measured proves that the design conforms to the HART protocol standard, which communication is stable and reliable to meet the requirements of industrial field devices.
The mathematical model of a three-dimensional temperature field in the full 300 kA aluminum electrolysis cell was calculated with ANSYS. The calculated results revealed that the thermal gradients strongly concentr...
详细信息
The mathematical model of a three-dimensional temperature field in the full 300 kA aluminum electrolysis cell was calculated with ANSYS. The calculated results revealed that the thermal gradients strongly concentrated in the lateral freeze profile of the aluminum electrolysis cell, and the sharp temperature gradient in the insulating material under the cathode carbon block were also found, the temperature of liquid aluminum was between 1174-1233 K, the lowest temperature of bottom cell wall was about 322 K, which indicated that the temperature of the aluminum electrolysis cell bottom was overcooled, so the 300 kA aluminum electrolysis cell need to be redesigned to get the reasonable temperature field.
Driver fatigue detection is a challenging problem in intelligent transportation system. The detection accuracy suffered by different illumination. This paper proposed a fatigue detection method based on regional l...
详细信息
Driver fatigue detection is a challenging problem in intelligent transportation system. The detection accuracy suffered by different illumination. This paper proposed a fatigue detection method based on regional local binary patterns histogram (RLBPH) and support vector machine (SVM). Firstly, we division the face image into blocks, then using local binary patterns(LBP) operator to present each block and calculating the LBP histogram(LBPH) of each block, then combine them into a RLBPH to present the face image. We used the fatigue face sample RLBPH feature and normal face sample RLBPH feature to train the SVM to get its model and the parameters. We input the RLBPH feature of the testing sample to the trained models, thus can classify the RLBPH feature of the testing sample. In our experiments we observe that RLBPH features perform stably and robustly on different illumination, and yield promising performance in low-resolution images captured from webcam.
暂无评论