In this paper, we propose a novel and highly effective variationalbayesian expectation maximization-maximization (VBEM-M) inference method for log-linear cognitive diagnostic model (CDM). In the implementation of the...
详细信息
In this paper, we propose a novel and highly effective variationalbayesian expectation maximization-maximization (VBEM-M) inference method for log-linear cognitive diagnostic model (CDM). In the implementation of the variationalbayesian approach for the saturated log-linear CDM, the conditional variational posteriors of the parameters that need to be derived are in the same distributional family as the priors, the VBEM-M algorithm overcomes this problem. Our algorithm can directly estimate the item parameters and the latent attribute-mastery pattern simultaneously. In contrast, Yamaguchi and Okada’s (2020a) variational bayesian algorithm requires a transformation step to obtain the item parameters for the log-linear cognitive diagnostic model (LCDM). We conducted multiple simulation studies to assess the performance of the VBEM-M algorithm in terms of parameter recovery, execution time, and convergence rate. Furthermore, we conducted a series of comparative studies on the accuracy of parameter estimation for the DINA model and the saturated LCDM, focusing on the VBEM-M, VB, expectation-maximization, and Markov chain Monte Carlo algorithms. The results indicated that our method can obtain more stable and accurate estimates, especially for the small sample sizes. Finally, we demonstrated the utility of the proposed algorithm using two real datasets.
An intelligent industrial vehicle path-tracking hierarchical controller considering fully hydraulic steering time delay compensation is designed in this study. The upper decision layer uses variable constraint linear ...
详细信息
An intelligent industrial vehicle path-tracking hierarchical controller considering fully hydraulic steering time delay compensation is designed in this study. The upper decision layer uses variable constraint linear time-varying MPC for path-tracking control. The lower execution layer uses a time delay probability model and variational bayesian algorithm to estimate the optimal time-delay value and combines with proposed input-output moment equations for the steering system to advance the target steering wheel angle to realize the real-time compensation of steering time-delay disturbance by path tracking. The simulation and test results show that the lateral acceleration, center of mass sideslip angle, tire-slip angle, and tracking error of the intelligent industrial vehicle under different loads and working conditions are improved by 29.8%, 36.2%, 41.5%, and 43.2%, respectively.
Estimation and prediction of noise power are very important for communication anti-jamming and efficient allocation of spectrum resources in adaptive wireless communication and cognitive radio. In order to estimate an...
详细信息
ISBN:
(纸本)9781628411867
Estimation and prediction of noise power are very important for communication anti-jamming and efficient allocation of spectrum resources in adaptive wireless communication and cognitive radio. In order to estimate and predict the time-varying noise power caused by natural factors and jamming in the high frequency channel, variational bayesian algorithm and adaptive ARMA time series are proposed. Through establishing the time-varying noise power model, which controlled by the noise variance rate, the noise power can be estimated with variational bayesian algorithm, and the results show that the estimation error is related to observation interval. What's more, through the analysis of the correlation characteristics of the estimation power, noise power can be predicted based on adaptive ARMA time series, and the results show that it will be available to predict the noise power in next 5 intervals with the proportional error less than 0.2.
Hyper-spectral image fusion has been a hot topic in medical imaging and remote sensing. This paper proposes a bayesian fusion model which combines the panchromatic (PAN) image and the low spatial resolution hyper-spec...
详细信息
ISBN:
(纸本)9781479999880
Hyper-spectral image fusion has been a hot topic in medical imaging and remote sensing. This paper proposes a bayesian fusion model which combines the panchromatic (PAN) image and the low spatial resolution hyper-spectral (HS) image under the same framework. Sparsity constraint is introduced as double "spike-and-slab" priors, and anisotropic Gaussian noise is adopted for accuracy. To achieve reduction in computational complexity, we turn the anisotropic Gaussian distribution into isotropic one with modified linear transformation and propose a variationalbayesian expectation maximization (EM) algorithm to calculate the result. Experiment results show that our solution can achieve comparable performance in pan-sharpening to other state-of-art algorithms while largely reducing the computational complexity.
This article presents a peer-to-peer (P2P) distributed variationalbayesian (P2PDVB) algorithm for density estimation and clustering in sensor networks. It is assumed that measurements of the nodes can be statisticall...
详细信息
This article presents a peer-to-peer (P2P) distributed variationalbayesian (P2PDVB) algorithm for density estimation and clustering in sensor networks. It is assumed that measurements of the nodes can be statistically modelled by a common Gaussian mixture model. The variational approach allows the simultaneous estimate of the component parameters and the model complexity. In this algorithm, each node independently calculates local sufficient statistics first by using local observations. A P2P averaging approach is then used to diffuse local sufficient statistics to neighbours and estimate global sufficient statistics in each node. Finally, each sensor node uses the estimated global sufficient statistics to estimate the model order as well as the parameters of this model. Because the P2P averaging approach only requires that each node communicate with its neighbours, the P2PDVB algorithm is scalable and robust. Diffusion speed and convergence of the proposed algorithm are also studied. Finally, simulated and real data sets are used to verify the remarkable performance of proposed algorithm.
Global navigation satellite system (GNSS) receivers meet numerous challenges in a high-orbit environment, including weak and discontinuous signal, and time-varying strength. To resolve these issues and enhance reliabi...
详细信息
Global navigation satellite system (GNSS) receivers meet numerous challenges in a high-orbit environment, including weak and discontinuous signal, and time-varying strength. To resolve these issues and enhance reliability, an innovative adaptive vector tracking loop (VTL) scheme is proposed. Non-linear models of the VTL filter are established to calculate code phase and carrier frequency errors accurately. Based on this, a deep analysis has been developed on the measurement noise. To reduce the impact of the interdependent noises among channels in VTL, an adaptive VTL algorithm assisted by the variationalbayesian (VB) learning network is proposed to estimate the measurement noise and maintain the error convergence in the time-varying noise or signal outage conditions. Further, the implementation steps of the adaptive algorithm have been designed in detail. In particular, the carrier-to-noise power ratio (C/N-0) estimation method is further employed to update the a prior probability density in case of change of tracking satellite. The simulation results indicate that the proposed VTL scheme with VB algorithm is a promising method to improve the accuracy and reliability of GNSS receivers significantly under a high-orbit degraded signal environment.
A novel online speaker clustering method suitable for real-time applications is proposed. Using an ergodic hidden Markov model, it employs incremental learning based on a variationalbayesian framework and provides pr...
详细信息
ISBN:
(纸本)9781424423538
A novel online speaker clustering method suitable for real-time applications is proposed. Using an ergodic hidden Markov model, it employs incremental learning based on a variationalbayesian framework and provides probabilistic (non-deterministic) decisions for each input utterance, directly considering the specific history of preceding utterances. It makes possible more robust cluster estimation and precise classification of utterances than do conventional online methods. Experiments on meeting-speech data show that the proposed method produces 70-80% fewer errors than a conventional method does.
作者:
Zhang, YugeXi An Jiao Tong Univ
Minist Educ Sch Informat & Commun Engn Key Lab Intelligent Networks & Network Secur Xian 710049 Shaanxi Peoples R China
Message authentication based on wireless physical layer channel information has gained significant attention in recent years. In existing studies, there are several channel based authentication methods to deal with th...
详细信息
ISBN:
(纸本)9781665443852
Message authentication based on wireless physical layer channel information has gained significant attention in recent years. In existing studies, there are several channel based authentication methods to deal with the single attacker scenario. However, in the real wireless environment, there may be several attackers and we do not know the exact number of the attackers. To solve the physical layer authentication problem in such a multi-attackers scenario, we propose a variational bayesian algorithm based authentication scheme using Gaussian mixture model. We show that even without having a complete prior knowledge and the number of the attackers, our algorithm can identify the received messages to determine whether they are from the legitimate transmitter or the attackers. We experimentally demonstrate the performance of our proposed method and show that the variational bayesian algorithm has a low miss detection rate.
暂无评论