This paper focuses on traffic flow forecasting approach based on soft computing tools. The soft computing tools used is Particle Swarm optimization (PSO) with Wavelet network Model(WNM). The forecast of short-term tra...
详细信息
This paper focuses on traffic flow forecasting approach based on soft computing tools. The soft computing tools used is Particle Swarm optimization (PSO) with Wavelet network Model(WNM). The forecast of short-term traffic flow in timely and accurate is one of important contents of intelligent transportation system research. The modelling of traffic characteristics and the prediction of future traffic flow are the first steps to efficient networkcontrol and management. The real traffic data is used to demonstrate that the PSO algorithm combined with WNM is effective for traffic flow forecasting. The simulation results demonstrate that the proposed model can improve prediction accuracy and outperforms other compared methods. A new hybrid model between wavelet analysis and a neural network: wavelet network model absorbs some merits of wavelet transform and artificial neural network.
Elliptic curve cryptography is a public key cryptosystem based on the elliptic curve discrete logarithm problem. The reason for the attractiveness of ECC is that there is no sub-exponential algorithm known to solve th...
详细信息
A new adaptive polarization mode dispersion PMD compensation method in 80Gbit/s optical communication is proposed. Through the control of DSP, the dithering particle swarm optimization (PSO) algorithm is used to extra...
详细信息
A new adaptive polarization mode dispersion PMD compensation method in 80Gbit/s optical communication is proposed. Through the control of DSP, the dithering particle swarm optimization (PSO) algorithm is used to extract the best degree of polarization (DOP), then the DOP is used to compensate three stage PMD of optical fiber.
Real-time traffic assignment for route guidance is put under the framework of model predictive control, which optimizes the routes based on the real-time feedback and prediction information of road network. In this fr...
Real-time traffic assignment for route guidance is put under the framework of model predictive control, which optimizes the routes based on the real-time feedback and prediction information of road network. In this framework, particle filter is utilized to estimate the statistic distribution of traffic flow of links without detection sensors based on the position and speed information of navigated vehicles on those links and the prior information of traffic flow of links with detection sensors. The chance constrains and Bayes-based route prediction are incorporated into the optimization model so that the stochastic characteristics of traffic needs, propagation and driver's decision-making behavior can be compensated in the route optimization. To check the chance constraints, the min-max characteristic points are used to fit the curve of stochastic traffic propagation process with stochastic needs to avoid the exponential increase of combination calculation. The genetic algorithm is utilized for the optimization with feasible-direction-search crossover and mutation to improve the evolution efficiency, combined with the traffic simulation in the mean sense with the compensation of stochastic parts of traffic flow data to evaluate the performance of real-time traffic assignment. The simulation results demonstrate the effectiveness of traffic navigation predictive control.
A RBF neural networkcontrol system optimized by Particle Swarm optimization is *** control system was constructed by two RBF neural network,one was used as identifier and the other was used as *** system parameters w...
详细信息
A RBF neural networkcontrol system optimized by Particle Swarm optimization is *** control system was constructed by two RBF neural network,one was used as identifier and the other was used as *** system parameters were optimized by PSO,RBF neural network identified the nonlinear controlled object,the obtained Jacobian information used into RBF *** results shows that the system optimized by PSO can get the ideal results of the control to the nonlinear objects,the system has good adaptive capacity and robustness.
It is significant to controlnetwork congestion by time series forecasting research for network flow. The hybrid method of particle swarm optimization algorithm and RBF neural network is applied to predict network flo...
详细信息
It is significant to controlnetwork congestion by time series forecasting research for network flow. The hybrid method of particle swarm optimization algorithm and RBF neural network is applied to predict network flow and gain the desirable network flow prediction results. In the hybrid method, particle swarm optimization algorithm is selected and adjusted to the connection weights and the center of radial basis function and the width of radial basis function. The network flow data are collected to search the prediction ability of particle swarm optimization algorithm and RBF neural network. Compared with the results of RBF neural network and BP neural network, particle swarm optimization algorithm and RBF neural network has better forecasting performance.
Taking advantage of the feature that the energy of the image would gather and spread on four components (LL2, LH2, HL2 and HH2) in the subimage after first-order CArdBAL2 multi-wavelet transform, propose an Informatio...
详细信息
Taking advantage of the feature that the energy of the image would gather and spread on four components (LL2, LH2, HL2 and HH2) in the subimage after first-order CArdBAL2 multi-wavelet transform, propose an Information Hiding Algorithm based on CArdBAL2 transform and DCT. According to the algorithm, LL2 is embedding module of robust parameters (odd-even verification data, scrambling optimization parameters and Hash value of information). Embed hiding Information in LH2 and HL2 with RAID4 and contrast detection data in HH2. Choose different DCT coefficient interval in LL2, LH2 and HL2. In aspect of information processing, using Logistic map and optimistic algorithm, improve the consistence of the embedded data bits’ order and the character of the sub-image. The algorithm can increase invisibility and robustness separately by 2.19% and 30.92% averagely. The algorithm has an obvious advantage against cutting. Its sensitivity of image tampering can reach to 98% or more and it has an excellent ability against steganalysis.
The high error rate of wireless link result in most of Packet loss rate that is caused by error of the wireless link,The standard TCP network will start congestion control before congestion ,result in the sharp decrea...
详细信息
The high error rate of wireless link result in most of Packet loss rate that is caused by error of the wireless link,The standard TCP network will start congestion control before congestion ,result in the sharp decrease of performance. In this paper,we propose an idea that adjust dynamic the size of TCP segment according to the error rate,and modify the *** function to implement this algorithm to improve the overall performance of TCP.
In the IMS-based NGN service platform, live streaming is an important value-added service. But the distribution of streaming media is a difficult problem because of its massive bandwidth requirement and real-time requ...
详细信息
In the IMS-based NGN service platform, live streaming is an important value-added service. But the distribution of streaming media is a difficult problem because of its massive bandwidth requirement and real-time requirement. Since IP multicast needs to update the whole network routers, this paper introduces P2P technology into live streaming system, which leverages the IPbased policy control and session-based QoS reservation mechanism of IMS. In the service system, the P2P cluster is constructed and managed in the central server deployed at the service plane without any modification to the standard IMS architecture. Several functional entities such as OMF, NRQF and P2P-enabled UE are extended based on the IMS-based IPTV architecture defined by ETSI TIAPAN. When the P2P-enabled UE initiates the service request, SCF as a SIP B2B UA is responsible for the session establishment among neighboring peers relying on the peer selected result from OMF. According to peer grouping judgment returned from NRQF, the OMF groups the UEs watching the same live channel into different peer clusters. Furthermore, this paper describes the session flows and QoS reserving procedure in the detail, and emphasizes the manageability of the P2P overlay.
Oven controlled crystal oscillators (OCXO) have been widely used in global positioning systems, communications, metering, telemetry control, spectrum, network analyzers and other electronic equipments as a source of t...
详细信息
Oven controlled crystal oscillators (OCXO) have been widely used in global positioning systems, communications, metering, telemetry control, spectrum, network analyzers and other electronic equipments as a source of time-frequency signal with high precision. Two most important performance indexes of a crystal oscillator are frequency stability and start-up characteristics. In this paper the marriage of hardware and software, practice of dual thermostatic bath and application of optimization technology in temperature control in duel temperature control system enable quicker start and further improve temperature control accuracy and the frequency stability of OCXO. This clever design optimization achieves lower power consumption, higher stability, even more compact size and quicker start.
暂无评论