The Quaternion LMS Algorithm for Adaptive Filtering of Hypercomplex Processes

The quaternion least mean square (QLMS) algorithm is introduced for adaptive filtering of three- and four-dimensional processes, such as those observed in atmospheric modeling (wind, vector fields). These processes exhibit complex nonlinear dynamics and coupling between the dimensions, which make their component-wise processing by multiple univariate LMS, bivariate complex LMS (CLMS), or multichannel LMS (MLMS) algorithms inadequate. The QLMS accounts for these problems naturally, as it is derived directly in the quaternion domain. The analysis shows that QLMS operates inherently based on the so called “augmented” statistics, that is, both the covariance $E{ {bf xx}^{H}}$ and pseudocovariance $E{ {bf xx}^{T}}$ of the tap input vector $ {bf x}$ are taken into account. In addition, the operation in the quaternion domain facilitates fusion of heterogeneous data sources, for instance, the three vector dimensions of the wind field and air temperature. Simulations on both benchmark and real world data support the approach.      

Automatic Parameter Optimization for Support Vector Regression for Land and Sea Surface Temperature Estimation From Remote Sensing Data

Land surface temperature (LST) and sea surface temperature (SST) are important quantities for many environmental models. Remote sensing is a source of information for their estimation on both regional and global scales. Many algorithms have been devised to estimate LST and SST from satellite data, most of which require a priori information about the surface and the atmosphere. A recently proposed approach involves the use of support vector machines (SVMs). Based on satellite data and corresponding in situ measurements, they generate an approximation of the relation between them, which can subsequently be used to estimate unknown surface temperatures from additional satellite data. Such a strategy requires the user to set several internal parameters. In this paper, a method is proposed for automatically setting these parameters to quasi-optimal values in the sense of minimum estimation errors. This is achieved by minimizing a functional correlated to regression errors (i.e., the “span-bound” upper bound on the leave-one-out (LOO) error) which can be computed by using only the training set, without need for a further validation set. In order to minimize this functional, Powell's algorithm is adopted, since it is applicable also to nondifferentiable functions. Experimental results yielded by the proposed method are similar in accuracy to those achieved by cross-validation and by a grid search for the parameter configuration which yields the best test-set accuracy. However, the proposed method gives a dramatic reduction in the computational time required, particularly when many training samples are available.      

FGBC-iDistance:fine-grained bit-code filter based high-dimensional index

In the high-dimensional vector retrieval,distance computation is a very time-consuming operation,the current research trend is to reduce the distance computation using divide and conquer algorithm.iDistance algorithm divides the vector space into subspace of clustering by pivot,BC-iDistance algorithm divides the subspace into 2 partitions in each dimension.A more fine-grained partition algorithm and index structure was proposed,each part corresponded with a unique FGBC code (fine-grained bit code),which realized the candidate sets filtered more precisely.The distance computation times of FGBC-iDistance can be reduced to $\frac{1}{2^{2d}}$ of iDistance.The distance computation frequency comparison:FGBC-iDistance≤BC-iDistance≤iDistance.The experiment results show that when the scope radius of the range query is 0.08,FGBC-iDistance distance computation times is about 20,000,which is far less than other algorithms,the running time is also reduced.     

Analysis and Hardware Architecture Design of Global Motion Estimation

Global motion estimation and compensation (GME/GMC) is an important video processing technique and has been applied to many applications including video segmentation, sprite/mosaic generation, and video coding. In MPEG-4 Advanced Simple Profile (ASP), GME/GMC is adopted to compensate camera motions. Since GME is important, many GME algorithms have been proposed. These algorithms have two common characteristics, huge computation complexity and ultra large memory bandwidth. Hence for realtime applications, a hardware accelerator of GME is required. However, there are many hardware design challenges of GME like irregular memory access and huge memory bandwidth, and only few hardware architectures have been proposed. In this paper, we first analyzed three typical algorithms of GME, and a fast GME algorithm is proposed. By using temporal prediction and skipping the redundant computation, 91% memory bandwidth and 80% iterations are saved, while the performance is kept, compared to Gradient Descent in MPEG-4 Verification Model. Based on our proposed algorithm, a hardware architecture of GME is also presented. A new scheduling, Reference-Based Scheduling, is developed to solve the irregular memory access problem. An interleaved memory arrangement is applied to satisfy the memory access requirement of interpolation. The total gate count of hardware implementation is 131 K with Artisan 0.18 um cell library, and the internal memory size is about 7.9 Kb. Its processing ability is MPEG-4 ASP@L3, which is 352×288 with 30 fps, at 30 MHz.

Hierarchical Multiple Markov Chain Model for Unsupervised Texture Segmentation

In this paper, we present a novel multiscale texture model and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled, in turn, by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The “fragmentation” step allows one to find the elementary textures of the model, while the “reconstruction” step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural and remote sensing images.      

一种基于中心矩特征的SAR图像目标识别方法

合成孔径雷达自动目标识别是目前国内外模式识别领域的重点研究课题之一.本文给出了一种内存需求小,低计算复杂度且具有较好识别性能的SAR图像目标识别方法,先通过自适应阈值分割来获得目标图像,然后提取其中心矩特征,采用SVM来进行识别.基于美国MSTAR实测数据的识别试验验证了该方法的有效性.     

Signal Assignment to Hierarchical Memory Organizations for Embedded Multidimensional Signal Processing Systems

The storage requirements of the array-dominated and loop-organized algorithmic specifications running on embedded systems can be significant. Employing a data memory space much larger than needed has negative consequences on the energy consumption, latency, and chip area. Finding an optimized storage of the usually large arrays from these algorithmic specifications is an essential task of memory allocation. This paper proposes an efficient algorithm for mapping multidimensional arrays to the data memory. Similarly to , it computes bounding windows for live elements in the index space of arrays, but this algorithm is several times faster. More important, since this algorithm works not only for entire arrays, but also parts of arrays—like, for instance, array references or, more general, sets of array elements represented by lattices , this signal-to-memory mapping technique can be also applied in hierarchical memory architectures.      

Comparison of the Mean Time Between Failures for Two Systems Under Short Tests

A Sequential Probability Ratio Test (SPRT) is discussed, for comparison of two systems, one “basic” $(b)$, and the other “new” $(n)$, with exponentially distributed times between failures (TBF). The hypothesis that the mean $TBF_{n}/MTBF_{b}geq 1$ is checked, versus one that it is $≪$ 1. The paper deals with tests with a low Average Sample Number (ASN), having the advantage of economy in time requirement, and cost; and it is shown that the points of possible solutions in them are sparse. Criteria are proposed for assessment of the test quality, with a view to optimization of its parameters. We present a search algorithm for the truncation apex (TA), with dependences for the search domain, and for the position of the oblique test boundaries, serving jointly as the basis for our development of the test planning algorithm.      

Timetable Synchronization of Mass Rapid Transit System Using Multiobjective Evolutionary Approach

Users of mass rapid transit are often required to make transfers between different train lines to reach their destinations. Timetable synchronization minimizes delays during such transfers. This paper formulates a novel measure for timetable synchronization by means of a total passenger dissatisfaction index (TPDI); and the impact of such synchronization on the original unsynchronized timetable is accounted using a total deviation index ( $hbox{TD}_{V}$) that assigns penalties when deviations from the original timetable are incurred. Pareto fronts displaying the relationship between TPDI and $hbox{TD}_{V}$ are generated using the state-of-the-art nondominated sorting genetic algorithm 2 (NSGA 2). To further improve NSGA 2, three schemes---the use of a variant of the NSGA2 with differential evolution, a process we termed “seeding,” and finally a hybrid combination with local search techniques like heuristic hill climbing, tabu search, and simulated annealing---are proposed. Simulation results demonstrate that the “seeded” NSGA2-DE combined with the hill climbing heuristic produce the best results for the application. Solutions from the Pareto fronts are chosen for implementation to describe the different operating regions. A discussion section details the advantages and drawbacks of the proposed schemes.      

Large-Scale In Situ Fabrication of Voltage-Programmable Dual-Layer High-$kappa$ Dielectric Carbon Nanotube Memory Devices With High On/Off Ratio

In this letter, we report on measurements of carbon nanotube (CNT) field-effect transistors with high on/off ratio to be used as nonvolatile memory cells operating at room temperature. Thousands of memory devices have been realized using a complete in situ fabrication method. The self-aligned fabrication process allows large-scale production of CNT memory devices with high yield. The memory function is obtained by the threshold voltage shift due to the highly reproducible hysteresis in the transfer characteristics. The ratio of the current levels between a logical “1” and a “0” is about $hbox{10}^{6}$.