Search

In this paper, a generalized nonlinear multi-regression model based on Choquet integral (NMRCI) is proposed and applied for estimation of non-additive systems that include outliers under inherent interaction among inputs. The parameters estimation for the proposed model is also performed via a modified algorithm based on particle swarm optimization with quantum-behavior (QPSO), named MQPSO. From the proposed model, the high breakdown regression estimator, a least trimmed squares (LTS) is applied to eliminate the influence caused by these observations that contain outliers. Besides, elitist crossover of genetic algorithm (GA) and adaptive decay of simulated annealing (SA) are used for conquering premature and controlling search policy, respectively. Hence, the proposed MQPSO algorithm which combines the mechanisms of GA, SA and LTS within the QPSO algorithm can deal with the proposed model with outliers. From simulation results, the proposed MQPSO readily corrects the deviation caused by outliers without losing precisions and swiftly achieves convergences on estimating the parameters of the proposed generalized NMRCI model for the non-additive systems with outliers.

This paper demonstrates that radial basis function networks (RBFNs) with support vector regression (SVR) and annealing robust learning algorithm (ARLA) can be used effectively for the identification of the nonlinear dynamic systems with outliers. When the RBFNs are used for the identification of the nonlinear dynamic system, the number of hidden nodes, the initial parameters of the kernel, and the initial weights of the network must be determined first, a SVR approach is proposed to solve the initial problem of RBFNs. That is, the SVR uses the quadratic programming optimization to determine the initial structure of the RBFNs. Besides, the new cost function for the system identification with outliers is also proposed. That is, the proposed annealing robust radial basis function networks (ARRBFNs) are trained by the ARLA, which uses the annealing concept in the cost function of the robust back-propagation learning algorithm, can overcome the error measurement caused by the outliers. Simulation results show the superiority of the proposed method with different SVR.

Charge trapping and related current-conduction mechanisms in metal–oxide–semiconductor (MOS) capacitors with La x Ta y dual-doped HfON dielectrics have been investigated under various post-deposition annealing (PDA). The results indicate that by La x Ta y incorporation into HfON dielectric enhances electrical and reliability characteristics, including equivalent-oxide-thickness (EOT), stress-induced leakage current (SILC), and trap energy level. The mechanisms related to larger positive charge generation in the gate dielectric bulk can be attributed to La x Ta y dual-doped HfON dielectric. The results of C – V measurement indicate that more negative charges are induced with increasing PDA temperature for the La x Ta y dual-doped HfON dielectric. The charge current transport mechanisms through various dielectrics have been analyzed with current–voltage ( I – V ) measurements under various temperatures. The current-conduction mechanisms of HfLaTaON dielectric at the low-, medium-, and high-electrical fields were dominated by Schottky emission (SE), Frenkel–Poole emission (F–P), and Fowler–Nordheim (F–N), respectively. A low trap energy level ( Φ trap ) involved in Frenkel–Pool conduction in an HfLaTaON dielectric was estimated to be around 0.142 eV. Although a larger amount of positive charges generated in the HfLaTaON dielectric was obtained, the Φ trap of these positive charges in the HfLaTaON dielectric are shallow compared with HfON dielectric.

In this study, an interval competitive agglomeration (ICA) clustering algorithm is proposed to overcome the problems of the unknown clusters number and the initialization of prototypes in the clustering algorithm for the symbolic interval-values data. In the proposed ICA clustering algorithm, both the Euclidean distance measure and the Hausdorff distance measure for the symbolic interval-values data are independently considered. Besides, the advantages of both hierarchical clustering algorithm and partitional clustering algorithm are also incorporated into the ICA clustering algorithm. Hence, the ICA clustering algorithm can be fast converges in a few iterations regardless of the initial number of clusters. Moreover, it is also converges to the same optimal partition regardless of its initialization. Experiments with simply data sets and real data sets show the merits and usefulness of the ICA clustering algorithm for the symbolic interval-values data.

This paper demonstrates an approach to predict the chaotic time series with outliers using annealing robust fuzzy neural networks (ARFNNs). A combination model that merges support vector regression (SVR), radial basis function networks (RBFNs) and simplified fuzzy inference system is used. The SVR has the good performances to determine the number of rules in the simplified fuzzy inference system and initial weights for the fuzzy neural networks (FNNs). Based on these initial structures, and then annealing robust learning algorithm (ARLA) can be used effectively to overcome outliers and adjust the parameters of structures. Simulation results show the superiority of the proposed method with different SVR for training and prediction of chaotic time series with outliers.

This study proposes a hybrid robust approach for constructing Takagi-Sugeno-Kang (TSK) fuzzy models with outliers. The approach consists of a robust fuzzy C-regression model (RFCRM) clustering algorithm in the coarse-tuning phase and an annealing robust back-propagation (ARBP) learning algorithm in the fine-tuning phase. The RFCRM clustering algorithm is modified from the fuzzy C-regression models (FCRM) clustering algorithm by incorporating a robust mechanism and considering input data distribution and robust similarity measure into the FCRM clustering algorithm. Due to the use of robust mechanisms and the consideration of input data distribution, the fuzzy subspaces and the parameters of functions in the consequent parts are simultaneously identified by the proposed RFCRM clustering algorithm and the obtained model will not be significantly affected by outliers. Furthermore, the robust similarity measure is used in the clustering process to reduce the redundant clusters. Consequently, the RFCRM clustering algorithm can generate a better initialization for the TSK fuzzy models in the coarse-tuning phase. Then, an ARBP algorithm is employed to obtain a more precise model in the fine-tuning phase. From our simulation results, it is clearly evident that the proposed robust TSK fuzzy model approach is superior to existing approaches in learning speed and in approximation accuracy.

When a radial basis function network (RBFN) is used for identification of a nonlinear multi-input multi-output (MIMO) system, the number of hidden layer nodes, the initial parameters of the kernel, and the initial weights of the network must be determined first. For this purpose, a systematic way that integrates the support vector regression (SVR) and the least squares regression (LSR) is proposed to construct the initial structure of the RBFN. The first step of the proposed method is to determine the number of hidden layer nodes and the initial parameters of the kernel by the SVR method. Then the weights of the RBFN are determined by solving a simple minimization problem based on the concept of LSR. After initialization, an annealing robust learning algorithm (ARLA) is then applied to train the RBFN. With the proposed initialization approach, one can find that the designed RBFN has few hidden layer nodes while maintaining good performance. To show the feasibility and superiority of the annealing robust radial basis function networks (ARRBFNs) for identification of MIMO systems, several illustrative examples are included.

Silicon-oxide-nitride-oxide-silicon devices with nanoparticles (NPs) as charge trapping nodes (CTNs) are important to provide enhanced performance for nonvolatile memory devices. To study these topics, the TiO"xN"y metal oxide NPs embedded in the HfO"xN"y high-k dielectric as CTNs of the nonvolatile memory devices were investigated via the thermal synthesis using Ti thin-film oxidized in the mixed O"2/N"2 ambient. Well-isolated TiO"xN"y NPs with a diameter of 5-20nm, a surface density of ~3x10^1^1cm^-^2, and a charge trap density of around 2.33x10^1^2cm^-^2 were demonstrated. The writing characteristic measurements illustrate that the memory effect is mainly due to the hole trapping.

The back propagation (BP) algorithm for function approximation is multilayer feed-forward perceptions to learn parameters from sampling data. The BP algorithm uses the least squares method to obtain a set of weights minimizing the object function. One of main issues on the BP algorithm is to deal with data sets having variety of data distributions and bound with noises and outliers. In this paper, in order to overcome the problems of function approximation for a nonlinear system with noise and outliers, a robust fuzzy clustering method is proposed to greatly mitigate the influence of noise and outliers and then a fuzzy-based data sifter is used to partition the nonlinear system's domain into several piecewise linear subspaces to be represented by neural networks. There are two core ideas in the proposed method: (1) The robust fuzzy c-means algorithm is proposed to greatly mitigate the influence of data noise and outliers. (2) A fuzzy-based data sifter is proposed to locate good turning-points to partition a given nonlinear data domain into piecewise clusters so that a neural network can be constructed with fewer rules. Two experiments are illustrated and these results have shown that the proposed approach has good performance in various kinds of data domains with data noise and outliers.

The CoxNiyO hybrid metal oxide nanoparticles (HMONs) embedded in the HfOxNy high-k dielectric as charge trapping nodes of the nonvolatile memory devices have been formed via the chemical vapor deposition using the Co/Ni acetate calcined and reduced in the Ar/NH3 ambient. A charge trap density of 8.96 × 1011 cm−2 and a flatband voltage shift of 500 mV were estimated by the appearance of the hysteresis in the capacitance–voltage (C–V) measurements during the ±5 V sweep. Scanning electron microscopy image displays that the CoxNiyO HMONs with a diameter of ∼10–20 nm and a surface density of ∼1 × 1010 cm−2 were obtained. The mechanism related to the writing characteristics are mainly resulted from the holes trapping. Compared with those devices with the CoxNiyO HMONs formed by the dip-coated technique, memory devices with the CoxNiyO HMONs fabricated by the drop-coated technique show improved surface properties between the CoxNiyO HMONs and the HfON as well as electrical characteristics.

This work compares Co"xMo"yO, Co"xFe"yO and Fe"xMo"yO alloying metal oxide nanoparticles (AMONs) that were individually embedded in HfO"xN"y high-k dielectric as charge trapping nodes. They were formed by chemical vapor deposition using Co/Mo, Co/Fe and Fe/Mo acetate, respectively, calcined and reduced in Ar/NH"3 ambient. The effects of various pre-treatments on Co"xMo"yO, Co"xFe"yO and Fe"xMo"yO AMONs preparation were investigated. The results indicate that the larger charge trap density, larger memory window and better programming characteristics of Co"xMo"yO AMONs are attributable to their higher surface density and smaller diameter. The average collected charge in each Co"xMo"yO AMON is the smallest among three AMONs, revealing that a local leakage path is associated with the least charge loss. The main mechanism that governs the programming characteristics involves the trapping of holes.

In this study, CPBUM neural networks with annealing robust learning algorithm (ARLA) are proposed to improve the problems of conventional neural networks for modeling with outliers and noise. In general, the obtained training data in the real applications maybe contain the outliers and noise. Although the CPBUM neural networks have fast convergent speed, these are difficult to deal with outliers and noise. Hence, the robust property must be enhanced for the CPBUM neural networks. Additionally, the ARLA can be overcome the problems of initialization and cut-off points in the traditional robust learning algorithm and deal with the model with outliers and noise. In this study, the ARLA is used as the learning algorithm to adjust the weights of the CPBUM neural networks. It tunes out that the CPBUM neural networks with the ARLA have fast convergent speed and robust against outliers and noise than the conventional neural networks with robust mechanism. Simulation results are provided to show the validity and applicability of the proposed neural networks.

In this paper, the annealing robust radial basis function networks (ARRBFNs) are proposed to improve the problems of the robust radial basis function networks (RBFNs) for function approximation with outliers. Firstly, a support vector regression (SVR) approach is proposed to determine an initial structure of ARRBFNs in this paper. Because an SVR approach is equivalent to solving a linear constrained quadratic programming problem under a fixed structure of SVR, the number of hidden nodes, initial parameters and initial weights of the ARRBFNs are easily obtained. Secondly, the results of SVR are used as the initial structure in ARRBFNs. At the same time, an annealing robust learning algorithm (ARLA) is used as the learning algorithm for ARRBFNs, and applied to adjust the parameters as well as weights of ARRBFNs. That is, an ARLA is proposed to overcome the problems of initialization and the cut-off points in the robust learning algorithm. Hence, when an initial structure of ARRBFNs is determined by an SVR approach, the ARRBFNs with ARLA have fast convergence speed and are robust against outliers. Simulation results are provided to show the validity and applicability of the proposed ARRBFNs.

In this paper, the support vector interval regression networks (SVIRNs) are proposed for the interval regression analysis. The SVIRNs consist of two radial basis function networks. One network identifies the upper side of data interval, and the other network identifies the lower side of data intervals. Because the support vector regression (SVR) approach is equivalent to solving a linear constrained quadratic programming problem, the number of hidden nodes and the initial values of adjustable parameters can be easily obtained. Since the selection of a parameter e in the SVR approach may seriously affect the modeling performance, a two-step approach is proposed to properly select the e value. After the SVR approach with the selected e, an initial structure of SVIRNs can be obtained. Besides, outliers will not significantly affect the upper and lower bound interval obtained through the proposed two-step approach. Consequently, a traditional back-propagation (BP) learning algorithm can be used to adjust the initial structure networks of SVIRNs under training data sets without or with outliers. Due to the better initial structure of SVIRNs are obtained by the SVR approach, the convergence rate of SVIRNs is faster than the conventional networks with BP learning algorithms or with robust BP learning algorithms for interval regression analysis. Four examples are provided to show the validity and applicability of the proposed SVIRNs.

The research on theory and application of magnetic bearing system has received much attention in recent years. In order to overcome nonsystematic design and long training time in nonlinear adaptive inverse control, we propose a new method based on CPBUM neural network. The experimental results show that the proposed architecture provides a greater flexibility and better performance in controlling magnetic bearing system.