FAST AND ACCURATE BILATERAL FILTERING USING GAUSS-POLYNOMIAL DECOMPOSITION

The bilateral filter is a versatile non-linear filter that has found diverse applications in image processing, computer vision, computer graphics, and computational photography. A common form of the filter is the Gaussian bilateral filter in which both the spatial and range kernels are Gaussian. A direct implementation of this filter requires O(sigma(2)) operations per pixel, where sigma is the standard deviation of the spatial Gaussian. In this paper, we propose an accurate approximation algorithm that can cut down the computational complexity to O(1) per pixel for any arbitrary sigma (constant-time implementation). This is based on the observation that the range kernel operates via the translations of a fixed Gaussian over the range space, and that these translated Gaussians can be accurately approximated using the so-called Gauss-polynomials. The overall algorithm emerging from this approximation involves a series of spatial Gaussian filtering, which can be efficiently implemented (in parallel) using separability and recursion. We present some preliminary results to demonstrate that the proposed algorithm compares favorably with some of the existing fast algorithms in terms of speed and accuracy.

A Data Dropout Compensation Algorithm Based on the Iterative Learning Control Methodology for Discrete-Time Systems

This paper deals with the convergence of a remote iterative learning control system subject to data dropouts. The system is composed by a set of discrete-time multiple input-multiple output linear models, each one with its corresponding actuator device and its sensor. Each actuator applies the input signals vector to its corresponding model at the sampling instants and the sensor measures the output signals vector. The iterative learning law is processed in a controller located far away of the models so the control signals vector has to be transmitted from the controller to the actuators through transmission channels. Such a law uses the measurements of each model to generate the input vector to be applied to its subsequent model so the measurements of the models have to be transmitted from the sensors to the controller. All transmissions are subject to failures which are described as a binary sequence taking value 1 or 0. A compensation dropout technique is used to replace the lost data in the transmission processes. The convergence to zero of the errors between the output signals vector and a reference one is achieved as the number of models tends to infinity.

Optimal H2 order-one reduction by solving eigenproblems for polynomial equations

A method is given for solving an optimal H2 approximation problem for SISO linear time-invariant stable systems. The method, based on constructive algebra, guarantees that the global optimum is found; it does not involve any gradient-based search, and hence avoids the usual problems of local minima. We examine mostly the case when the model order is reduced by one, and when the original system has distinct poles. This case exhibits special structure which allows us to provide a complete solution. The problem is converted into linear algebra by exhibiting a finite-dimensional basis for a certain space, and can then be solved by eigenvalue calculations, following the methods developed by Stetter and Moeller. The use of Buchberger's algorithm is avoided by writing the first-order optimality conditions in a special form, from which a Groebner basis is immediately available. Compared with our previous work the method presented here has much smaller time and memory requirements, and can therefore be applied to systems of significantly higher McMillan degree. In addition, some hypotheses which were required in the previous work have been removed. Some examples are included.

Accelerating Bayesian hierarchical clustering of time series data with a randomised algorithm.

We live in an era of abundant data. This has necessitated the development of new and innovative statistical algorithms to get the most from experimental data. For example, faster algorithms make practical the analysis of larger genomic data sets, allowing us to extend the utility of cutting-edge statistical methods. We present a randomised algorithm that accelerates the clustering of time series data using the Bayesian Hierarchical Clustering (BHC) statistical method. BHC is a general method for clustering any discretely sampled time series data. In this paper we focus on a particular application to microarray gene expression data. We define and analyse the randomised algorithm, before presenting results on both synthetic and real biological data sets. We show that the randomised algorithm leads to substantial gains in speed with minimal loss in clustering quality. The randomised time series BHC algorithm is available as part of the R package BHC, which is available for download from Bioconductor (version 2.10 and above) via http://bioconductor.org/packages/2.10/bioc/html/BHC.html. We have also made available a set of R scripts which can be used to reproduce the analyses carried out in this paper. These are available from the following URL. https://sites.google.com/site/randomisedbhc/.

Theoretical and experimental research on time-optimal trajectory planning and control of industrial robots

提出了一种用于工业机器人时间最优轨迹规划及轨迹控制的新方法，它可以确保在关节位移、速度、加速度以及二阶加速度边界值的约束下，机器人手部沿笛卡尔空间中规定路径运动的时间阳短。在这种方法中，所规划的关节轨迹都采用二次多项式加余弦函数的形式，不仅可以保证各关节运动的位移、速度 、加速度连续而且还可以保证各关节运动的二阶加速度连续。采用这种方法，既可以提高机器人的工作效率又可以延长机器人的工作寿命以PUMA560机器人为对象进行了计算机仿真和机器人实验，结果表明这种方法是正确的有效的。它为工业机器人在非线性运动学约束条件下的时间最优轨迹规划及控制问题提供了一种较好的解决方案。

Time-dependent Hyperstar algorithm for robust vehicle navigation in time-dependent stochastic road networks.

The vehicle navigation problem studied in Bell (2009) is revisited and a time-dependent reverse Hyperstar algorithm is presented. This minimises the expected time of arrival at the destination, and all intermediate nodes, where expectation is based on a pessimistic (or risk-averse) view of unknown link delays. This may also be regarded as a hyperpath version of the Chabini and Lan (2002) algorithm, which itself is a time-dependent A* algorithm. Links are assigned undelayed travel times and maximum delays, both of which are potentially functions of the time of arrival at the respective link. The driver seeks probabilities for link use that minimise his/her maximum exposure to delay on the approach to each node, leading to the determination of the pessimistic expected time of arrival. Since the context considered is vehicle navigation where the driver is not making repeated trips, the probability of link use may be interpreted as a measure of link attractiveness, so a link with a zero probability of use is unattractive while a link with a probability of use equal to one will have no attractive alternatives. A solution algorithm is presented and proven to solve the problem provided the node potentials are feasible and a FIFO condition applies for undelayed link travel times. The paper concludes with a numerical example.

Genetic Algorithm Search for Predictive Patterns in Multidimensional Time Series

Based on an algorithm for pattern matching in character strings, we implement a pattern matching machine that searches for occurrences of patterns in multidimensional time series. Before the search process takes place, time series are encoded in user-designed alphabets. The patterns, on the other hand, are formulated as regular expressions that are composed of letters from these alphabets and operators. Furthermore, we develop a genetic algorithm to breed patterns that maximize a user-defined fitness function. In an application to financial data, we show that patterns bred to predict high exchange rates volatility in training samples retain statistically significant predictive power in validation samples.

Evaluation of an algorithm to guide patients with type 1 diabetes treated with continuous subcutaneous insulin infusion on how to respond to real-time continuous glucose levels:A randomized controlled trial

OBJECTIVE - To evaluate an algorithm guiding responses of continuous subcutaneous insulin infusion (CSII)-treated type 1 diabetic patients using real-time continuous glucose monitoring (RT-CGM). RESEARCH DESIGN AND METHODS - Sixty CSII-treated type 1 diabetic participants (aged 13-70 years, including adult and adolescent subgroups, with A1C =9.5%) were randomized in age-, sex-, and A1C-matched pairs. Phase 1 was an open 16-week multicenter randomized controlled trial. Group A was treated with CSII/RT-CGM with the algorithm, and group B was treated with CSII/RT-CGM without the algorithm. The primary outcome was the difference in time in target (4-10 mmol/l) glucose range on 6-day masked CGM. Secondary outcomes were differences in A1C, low (=3.9 mmol/l) glucose CGM time, and glycemic variability. Phase 2 was the week 16-32 follow-up. Group A was returned to usual care, and group B was provided with the algorithm. Glycemia parameters were as above. Comparisons were made between baseline and 16 weeks and 32 weeks. RESULTS - In phase 1, after withdrawals 29 of 30 subjects were left in group A and 28 of 30 subjects were left in group B. The change in target glucose time did not differ between groups. A1C fell (mean 7.9% [95% CI 7.7-8.2to 7.6% [7.2-8.0]; P <0.03) in group A but not in group B (7.8% [7.5-8.1] to 7.7 [7.3-8.0]; NS) with no difference between groups. More subjects in group A achieved A1C =7% than those in group B (2 of 29 to 14 of 29 vs. 4 of 28 to 7 of 28; P = 0.015). In phase 2, one participant was lost from each group. In group A, A1C returned to baseline with RT-CGM discontinuation but did not change in group B, who continued RT-CGM with addition of the algorithm. CONCLUSIONS - Early but not late algorithm provision to type 1 diabetic patients using CSII/RT-CGM did not increase the target glucose time but increased achievement of A1C =7%. Upon RT-CGM cessation, A1C returned to baseline. © 2010 by the American Diabetes Association.

A mixed cost-function adaptive algorithm for ADSL time-domain equalization

We propose a mixed cost-function adaptive initialization algorithm for the time domain equalizer in a discrete multitone (DMT)-based asymmetric digital subscriber line. Using our approach, a higher convergence rate than that of the commonly used least-mean square algorithm is obtained, whilst attaining bit rates close to the optimum maximum shortening SNR and the upper bound SNR. Furthermore, our proposed method outperforms the minimum mean-squared error design for a range of time domain equalizer (TEQ) filter lengths. The improved performance outweighs the small increase in computational complexity required. A block variant of our proposed algorithm is also presented to overcome the increased latency imposed on the feedback path of the adaptive system.