Posterior probability support vector machines (PPSVMs) prove robust against noises and outliers and need fewer storage support vectors (SVs). Gonen et al. (2008) extended PPSVMs to a multiclass case by both single-machine and multimachine approaches. However, these extensions suffer from low classification efficiency, high computational burden, and more importantly, unclassifiable regions. To achieve higher classification efficiency and accuracy with fewer SVs, a binary tree of PPSVMs for the multiclass classification problem is proposed in this letter. Moreover, a Fisher ratio separability measure is adopted to determine the tree structure. Several experiments on handwritten recognition datasets are included to illustrate the proposed approach. Specifically, the Fisher ratio separability accelerated binary tree of PPSVMs obtains overall test accuracy, if not higher than, at least comparable to those of other multiclass algorithms, while using significantly fewer SVs and much less test time.

A novel sifting method based on the concept of the ‘local centroids’ of a signal is developed for empirical mode decomposition (EMD), with the aim of reducing the mode-mixing effect and decomposing those modes whose frequencies are within an octave. Instead of directly averaging the upper and lower envelopes, as suggested by the original EMD method, the proposed technique computes the local mean curve of a signal by interpolating a set of ‘local centroids’, which are integral averages over local segments between successive extrema of the signal. With the ‘centroid’-based sifting, EMD is capable of separating intrinsic modes of oscillatory components with their frequency ratio ν even up to 0.8, thus greatly mitigating the effect of mode mixing and enhancing the frequency resolving power. Inspection is also made to show that the integral property of the ‘centroid’-based sifting can make the decomposition more stable against noise interference.

To overcome the failure in eliminating suspicious patterns or association rules existing in traditional association rules mining, we propose a novel method to mine item-item and between-set correlated association rules. First, we present three measurements: the association, correlation, and item-set correlation measurements. In the association measurement, the all-confidence measure is used to filter suspicious cross-support patterns, while the all-item-confidence measure is applied in the correlation measurement to eliminate spurious association rules that contain negatively correlated items. Then, we define the item-set correlation measurement and show its corresponding properties. By using this measurement, spurious association rules in which the antecedent and consequent item-sets are negatively correlated can be eliminated. Finally, we propose item-item and between-set correlated association rules and two mining algorithms, I&ISCoMine_AP and I&ISCoMine_CT. Experimental results with synthetic and real retail datasets show that the proposed method is effective and valid.

We describe a new tracking and predicting scheme applied to a lab-made ping pong robot. The robot has a monocular vision system comprised of a camera and a light. We propose an optimized strategy to calibrate the light center using the least square method. An ellipse fitting method is used to precisely locate the center of ball and shadow on the captured image. After the triangulation of the ball position in the world coordinates, a tracking algorithm based on a Kalman filter outputs an accurate estimation of the flight states including the ball position and velocity. Furthermore, a neural network model is constructed and trained to predict the following flight path. Experimental results show that this scheme can achieve a good predicting precision and success rate of striking an incoming ball. The robot can achieve a success rate of about 80% to return a flight ball of 5 m/s to the opposite court.

We propose a new scheme for transformer differential protection. This scheme uses different characteristics of the differential currents waveforms (DCWs) under internal fault and magnetizing inrush current conditions. The scheme is based on choosing an appropriate feature of the waveform and monitoring it during the post-disturbance instants. For this purpose, the signal feature is quantified by a discrimination function (DF). Discrimination between internal faults and magnetizing inrush currents is carried out by tracking the signs of three decision-making functions (DMFs) computed from the DFs for three phases. We also present a new algorithm related to the general scheme. The algorithm is based on monitoring the second derivative sign of DCW. The results show that all types of internal faults, even those accompanied by the magnetizing inrush, can be correctly identified from the inrush conditions about half a cycle after the occurrence of a disturbance. Another advantage of the proposed method is that the fault detection algorithm does not depend on the selection of thresholds. Furthermore, the proposed algorithm does not require burdensome computations.

Time moments have been introduced in automatic control because of the analogy between the impulse response of a linear system and a probability function. Pasek described a testing procedure for determining the DC parameters from the current response to a step in the armature voltage motor. In this paper, two identification algorithms developed based on the moments and Pasek’s methods are introduced and applied to the parameter identification of a DC motor. The simulation and experimental results are presented and compared, showing that the moments method makes the model closer to reality, especially in a transient regime.

The ranging accuracy of a pseudo-noise ranging system is mainly decided by range jitter and time delay discrimination. Many factors can affect the ranging accuracy, one of which is the chip rate. In digital signal processing, the time delay discrimination and autocorrelation function of sampled ranging sequences of different chip rates are very different. An approximation simulation model is established according to an in-phase quadrature (I/Q) correlator which is used to evaluate the time delay. Simulation results of the range jitter and time delay discrimination show that the chip rate which provides a non-integer sample-to-chip rate ratio can achieve a higher ranging accuracy, and some test results validate the simulation model. In some design missions, the simulation results may help to select an optimum sample-to-chip rate ratio to satisfy the design requirement on the ranging accuracy.

In this paper, we suggest applying tree structure on the sinusoidal parameters. The suggested sinusoidal coder is targeted to find the coded sinusoidal parameters obtained by minimizing a likelihood function in a least square (LS) sense. From a rate-distortion standpoint, we address the problem of how to allocate available bits among different frequency bands to code sinusoids at each frame. For further analyzing the quantization behavior of the proposed method, we assess the quantization performance with respect to other methods: the short-time Fourier transform (STFT) based coder commonly used for speech enhancement or separation, and the line spectral frequency (LSF) coder used in speech coding. Through extensive simulations, we show that the proposed quantizer leads to less spectral distortion as well as higher perceived quality for the re-synthesized signals based on the coded parameters in a model-based approach with respect to previous STFT-based methods. The proposed method lowers the complexity, and, due to its tree-structure, leads to a rapid search capability. It provides flexibility for use in many speaker-independent applications by finding the most likely frequency vectors selected from a list of frequency candidates. Therefore, the proposed quantizer can be considered an attractive candidate for model-based speech applications in both speaker-dependent and speaker-independent scenarios.

New video applications, such as 3D video and free viewpoint video, require efficient compression of multi-view video. In addition to temporal redundancy, exploiting the inter-view redundancy is crucial to improve the performance of multi-view video coding. In this paper, we present a novel method to construct the optimal inter-view prediction structure for multi-view video coding using simulated annealing. In the proposed model, the design of the prediction structure is converted to the arrangement of coding order. Then, a simulated annealing algorithm is employed to minimize the total cost for obtaining the best coding order. This method is applicable to arbitrary irregular camera arrangements. As experiment results reveal, the annealing process converges to satisfactory results rapidly and the generated optimal prediction structure outperforms the reference prediction structure of the joint multi-view video model (JMVM) by 0.1–0.8 dB PSNR gains.

In transform-domain distributed video coding (DVC), the correlation noises (denoted as N) between the source block and its temporal predictor can be modeled as Laplacian random variables. In this paper we propose that the noises (denoted as N′) between the source block and its co-located block in a reference frame can also be modeled as Laplacian random variables. Furthermore, it is possible to exploit the relationship between N and N′ to improve the performance of the DVC system. A practical scheme based on theoretical insights, the hash signature saving scheme, is proposed. Experimental results show that the proposed scheme saves on average 83.2% of hash signatures, 13.3% of bit-rate, and 3.9% of encoding time.