In this paper we propose a new neural network architecture that deploys and extended Kalman filter (EKF) based learning algorithm. We used the new neural network for the prediction of speech signals. Simulation result...
In this paper we propose a new neural network architecture that deploys and extended Kalman filter (EKF) based learning algorithm. We used the new neural network for the prediction of speech signals. Simulation results show that the neural networks leads to better performance than the well known linear predictor coefficients (LPC) that uses Levinson-Durbin algorithm.
作者：
Sun, HongGuangSong, XiaoNaChen, YangQuanInstitute of Soft Matter Mechanics
Department of Engineering Mechanics Hohai University No. 1 XiKang Road Nanjing Jiangsu 210098 China School of Automation
Nanjing University of Science and Technology Nanjing Jiangsu 210094 China
Department of Electrical and Computer Engineering Utah State University 4120 Old Main Hill Logan UT 84322 United States
Differentiation and integration of non-integer order have drawn increasing attention in research community. Fractional order dynamic systems have been recognized as effective tools for characterizing the real-world ph...
详细信息
Wireless sensor networks are usually made up of a large number of sensor nodes. Such large networks require algorithms which can maintain their performance while the network size gets larger and larger. Clustering is ...
详细信息
Wireless sensor networks are usually made up of a large number of sensor nodes. Such large networks require algorithms which can maintain their performance while the network size gets larger and larger. Clustering is a very efficient method which can help many algorithms become scalable to networks of large sizes. Recently, irregular cellular learning automata is proposed as a suitable modeling tool for many sensor networkspsila applications and a clustering algorithm is given for proving this suitability. In this paper, we improve the proposed clustering algorithm which leads to more efficient clusters in terms of number of clusters, number of sparse clusters, and energy level of cluster heads.
The use of soft computing techniques in coherent communications phase synchronization provides an alternative to analytical or hard computing methods. The paper discusses a novel use of Adaptive Neuro-Fuzzy Inference ...
详细信息
The use of soft computing techniques in coherent communications phase synchronization provides an alternative to analytical or hard computing methods. The paper discusses a novel use of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for phase synchronization in coherent communications systems utilizing multiple phase shift keying (M-PSK) modulation. A brief overview of the M-PSK digital communications bandpass modulation technique is presented and its requisite need for phase synchronization is discussed. We briefly describe the hybrid platform developed by J.-S. Jang et al. (1997) that incorporates fuzzy/neural structures, namely the Adaptive Neuro-Fuzzy Interference Systems (ANFIS). We then discuss the application of ANFIS to phase estimation for M-PSK. The modeling of an implicit phase estimation scheme for M-PSK symbols with unknown structure are discussed. Performance results from simulation of the above scheme are presented.
Modified meshless methods are proposed by choosing trial and test functions from a variety of functional spaces. The accuracy of the proposed methods is evaluated for two ways of imposing essential boundary conditions...
详细信息
Geometries and dissociation energies of water molecules on Ga doped Al clusters were investigated using the first-principles density functional PW91 method. This work is divided into two parts: （i） the equilibrium s...
详细信息
Geometries and dissociation energies of water molecules on Ga doped Al clusters were investigated using the first-principles density functional PW91 method. This work is divided into two parts: （i） the equilibrium structures and stability of AlnGa （n=2-15） clusters and （ii） the interaction of H2O with stable AlnGa clusters. The results reveal that the most stable Al n Ga structures have similar configurations as the most stable host Al n+1 cluster except Al4Ga. Ga-doping causes a small change of the binding energies, fragmentation energies, and the second-order difference of the total energies in comparison with Al n+1 clusters. The adsorptions and dissociation of H2O molecule on AlnGa clusters are all exothermic. The dissociation energies can fully compensate for the dissociation barrier. Comparing with Al n+1 clusters, the dissociation barriers of H2O on the AlnGa clusters generally lower. The deformation extent of the AlnGa cluster configuration is larger than that of the Al n+1 cluster after the interaction of H2O with the clusters. Generally, the volumes of Aln+1 clusters get tight, the volumes of AlnGa clusters became expanded after dissociations of H2O on the clusters. This may be of the factors of gallium doped can make the activation of aluminum powers.
Current P2P applications are based on random connected overlays, which lead to generating a significant amount of inter-ISP traffic. Asking for more QoS requirements, such as a short delay and a stable streaming rate,...
详细信息
Current P2P applications are based on random connected overlays, which lead to generating a significant amount of inter-ISP traffic. Asking for more QoS requirements, such as a short delay and a stable streaming rate, few studies are dedicated to optimizing P2P live streaming applications, despite that recent work have proposed some solutions for P2P file distribution applications. In this paper, current traffic localization strategy is analyzed at first, and its two inherent flaws are revealed. Then we propose a novel strategy for ISP-friendly live streaming: based on a hybrid overlay, which is a two-tier structure, all ISPs are organized into an ISP-tree, and then local peers in each ISP form a mesh overlay. In each tier, a data scheduling is designed for inter-ISP traffic reduction and performance guarantee respectively. Compared with a famous live streaming strategy, R 2 , simulation results demonstrate that our strategy generates much less inter-ISP traffic and achieves a higher system performance.
This paper studies the problem of robust output feedback control of discrete time-delay systems with parameter uncertainties. The parameter uncertainties under consideration are time varying and norm bounded. A suffic...
详细信息
This paper studies the problem of robust output feedback control of discrete time-delay systems with parameter uncertainties. The parameter uncertainties under consideration are time varying and norm bounded. A sufficient condition for the existence of a dynamic output-feedback controller is presented in terms of linear matrix inequalities (LMIs). It is also shown that the set of dynamic output-feedback controller can be implicitly parameterized by the solutions (X, Y, R, S) to the LMIs. An example is given to demonstrate the potential of the proposed techniques.
In the study of ALM, how to improve the performance of multicast system is a hotspot. Theoretical study shows that network coding can improve the performance of network multicast. In this paper, in accordance with the...
详细信息
In the study of ALM, how to improve the performance of multicast system is a hotspot. Theoretical study shows that network coding can improve the performance of network multicast. In this paper, in accordance with the actual structure and features of HM-ALM, a cluster-oriented, and hybrid mesh ALM model, we select the deterministic linear coding strategy, and design the appropriate coding algorithm. The experimental results show that, using network coding in ALM system with hybrid mesh model can reduce transmission delay and enhance the system robustness with a certain amount of link redundancy.
暂无评论