Echo state network （ESN） has become one of the most popular recurrent neural networks （RNN） for its good prediction performance of non-linear time series and simple training process. But several problems still pre...
详细信息
Echo state network （ESN） has become one of the most popular recurrent neural networks （RNN） for its good prediction performance of non-linear time series and simple training process. But several problems still prevent ESN from becoming a widely used tool. The most prominent problem is its high complexity with lots of random parameters. Aiming at this problem, a minimum complexity ESN model （MCESN） was proposed. In this paper, we proposed a new wavelet minimum complexity ESN model （WMCESN） to improve the prediction accuracy and increase the practical applicability. Our new model inherits the characters of minimum complexity ESN model using the fixed parameters and simple circle topology. We injected wavelet neurons to replace the original neurons in internal reservoir and designed a wavelet parameter matrix to reduce the computing time. By using different datasets, our new model performed better than the minimum complexity ESN model with normal neurons, but only utilized tiny time cost. We also used our own packets of transmission control protocol （TCP） and user datagram protocol （UDP） dataset to prove that our model can deal with the data packet bit prediction problem well.
Offiine network traffic analysis is very important for an in-depth study upon the understanding of network conditions and characteristics, such as user behavior and abnormal traffic. With the rapid growth of the amoun...
详细信息
Offiine network traffic analysis is very important for an in-depth study upon the understanding of network conditions and characteristics, such as user behavior and abnormal traffic. With the rapid growth of the amount of information on the Intemet, the traditional stand-alone analysis tools face great challenges in storage capacity and computing efficiency, but which is the advantages for Hadoop cluster. In this paper, we designed an offiine traffic analysis system based on Hadoop （OTASH）, and proposed a MapReduce-based algorithm for TopN user statistics. In addition, we studied the computing performance and failure tolerance in OTASH. From the experiments we drew the conclusion that OTASH is suitable for handling large amounts of flow data, and are competent to calculate in the case of single node failure.
A novel iterative channel estimation algorithm for orthogonal frequency-division multiplexing (OFDM) systems in fast time-varying environment is proposed. Instead of directly estimate the original channel taps, the pr...
详细信息
A novel iterative channel estimation algorithm for orthogonal frequency-division multiplexing (OFDM) systems in fast time-varying environment is proposed. Instead of directly estimate the original channel taps, the proposed estimation focus on the rest channel part from the original channel taps subtracted by the prior estimation results in the absence of any channel information. The initial results are obtained by time-domain least squares (LS) estimation by inserting zeros-padded training symbols between adjacent OFDM symbols. Monte Carlo simulations demonstrate the superiority of the proposed algorithm after a few iterations over the conventional methods based on complex-exponential basis expansion model (CE-BEM) or generalized complex-exponential basis expansion model (GCEBEM).
A channel estimation using Data-dependent Superimposed Training (DDST) over doubly selective channel is proposed for OFDM systems. Instead of using traditional pilot-assisted scheme, this scheme uses training superimp...
详细信息
Maximum like-lihood (ML) algorithm is the optimal detection scheme for the data detection of multiple-input multiple-output (MIMO) communication systems, but it has a high complexity in its preprocessing. For good per...
详细信息
Maximum like-lihood (ML) algorithm is the optimal detection scheme for the data detection of multiple-input multiple-output (MIMO) communication systems, but it has a high complexity in its preprocessing. For good performance and low complexity, a new Grover's Quantum Search (GS) based data detection algorithm for MIMO system is proposed. It can increase the probability amplitude of solutions while reducing the probability amplitude of non-solutions. By Grover's iterative process, the probability amplitude of solutions can reach maximum. So it can get the solutions after measurement with a high probability. The simulation results show that the proposed data detection algorithm for MIMO system has a very close to ML based data detection in Bit Error Rate (BER) performance, but it has lower complexity than ML based data detection algorithm.
Multi-Channel Multi-Radio can decrease the co-channel interference and increase the throughput in multi-hop wireless Ad Hoc networks. This paper presents an efficient cross-layer distributed routing algorithm for mult...
详细信息
Multi-Channel Multi-Radio can decrease the co-channel interference and increase the throughput in multi-hop wireless Ad Hoc networks. This paper presents an efficient cross-layer distributed routing algorithm for multi-radio multi-channel Mobile Ad Hoc networks, called MMRM, which jointly considers the link lifetime, link quality of different channels, and hop counts. By using WLH metric, the link lifetime is introduced to tradeoff with the shortest-path, which achieves more reliable path in the mobile environments. Channels with high link quality indication can be chosen hop-by-hop to obtain the best transmission quality. With a comparable complexity as the existing schemes, simulation results show that our proposal can achieve higher throughput and packet delivery ratio in the mobile multi-hop Ad Hoc networks.
Content-Centric networking (CCN) has shown possibilities to solve several problems of the Internet. Communications in CCN are based on contents instead of IP. Existing routing mechanisms in CCN are inefficient on the ...
详细信息
We propose an optimized time-varying channel estimation model for mobile orthogonal frequency division multiplexing (OFDM) systems applying superimposed training in time domain to assist the channel estimation. An ext...
详细信息
We propose an optimized time-varying channel estimation model for mobile orthogonal frequency division multiplexing (OFDM) systems applying superimposed training in time domain to assist the channel estimation. An extension line approximate method is proposed to fit the assumed linear timevarying channel. The performance of the proposed method is compared with the traditional one in terms of mean square error and results show better performance in scenarios of different SNR and maximum Doppler frequency.
Based on Complex-exponential Basis Expansion Model (CE-BEM) and Generalized Complex-exponential Basis Expansion Model (GCE-BEM), a novel basis expansion model is proposed for fast fading channel estimation. The order ...
详细信息
In this paper, a new broadband multiple-input multiple-output (MIMO) Rayleigh fading channel is proposed for vehicle-to-vehicle (V2V) communication system. Considering the scattering environment, we first propose a no...
详细信息
暂无评论