Spatially nested sampling schemes for spatial variance components: Scope for their optimization

Efficient designs for nested sampling are needed in many areas of science. In the geosciences they are used to discover the important spatial scales on which properties vary. However, while the practical advantages and disadvantages of various nested designs have been discussed, no attempt has been made to optimize nested sampling schemes. This paper shows how an optimal nested sampling design can be found by a method of numerical combinatorial optimization: simulated annealing. The sample design is optimized over a space of possible designs for a fixed sample size and predetermined levels (spatial scales). The objective function for optimization is based on the expected covariance matrix for errors in the estimates of variance components, and so depends on what those components are. By simulation it was shown that optimized sampling schemes can detect scale-dependent variance components with common requirements for statistical power on smaller total sample sizes than are required with commonly used spatially nested sample designs such as the balanced design. Although the optimized design depends on the underlying covariance structure, sampling designs can be identified that perform better than the commonly used ones over a wide range of conditions.     

A comparative analysis of performance improvement schemes for cache memories

There have been numerous techniques proposed in the literature that aim to improve the performance of cache memories by reducing cache conflicts. These techniques were proposed over the past decade and each proposal independently claimed to reduce conflict misses. However, because the published results used different benchmarks and different experimental setups, it is not easy to compare them. In this paper we report a side-by-side comparison of these techniques. We also evaluate the suitability of some of these techniques for caches with higher set associativities. In addition to evaluating techniques for their impact on cache misses and average memory access times, we also evaluate the techniques for their ability in reducing the non-uniformity of cache accesses.The conclusion of our work is that, each application may benefit from a different technique and no single scheme works universally well for all applications. We also observe that, for the majority of applications, XORing (XOR) and Odd-multiplier indexing schemes perform reasonably well. Among programmable associativity techniques, B-cache performs better than column-associative and adaptive-caches, but column-associative caches require very minimal extensions to hardware. Uniformity of cache accesses is improved most by B-cache technique while column-associative cache also improves cache access uniformities.Based on the observation that different techniques benefit different applications, we explored the use of multiple, programmable addressing mechanisms, each addressing scheme designed for a specific application. We include some preliminary data using multiple addressing schemes.     

Modelling multilevel data in multimedia: A hierarchical factor analysis approach

Multimedia content understanding research requires rigorous approach to deal with the complexity of the data. At the crux of this problem is the method to deal with multilevel data whose structure exists at multiple scales and across data sources. A common example is modeling tags jointly with images to improve retrieval, classification and tag recommendation. Associated contextual observation, such as metadata, is rich that can be exploited for content analysis. A major challenge is the need for a principal approach to systematically incorporate associated media with the primary data source of interest. Taking a factor modeling approach, we propose a framework that can discover low-dimensional structures for a primary data source together with other associated information. We cast this task as a subspace learning problem under the framework of Bayesian nonparametrics and thus the subspace dimensionality and the number of clusters are automatically learnt from data instead of setting these parameters a priori. Using Beta processes as the building block, we construct random measures in a hierarchical structure to generate multiple data sources and capture their shared statistical at the same time. The model parameters are inferred efficiently using a novel combination of Gibbs and slice sampling. We demonstrate the applicability of the proposed model in three applications: image retrieval, automatic tag recommendation and image classification. Experiments using two real-world datasets show that our approach outperforms various state-of-the-art related methods.     

Modelling of spatial point processes derived from a sequence of auto-Poisson lattice schemes

Spatial point processes form a set of statistical tools capable of modelling many environmental processes. They can deal with spatial interactions and dependencies between individuals which is an essential framework in environmental modelling. In this context, we focus on inhibitory pairwise interaction point processes that can be obtained as the limit of a suitable sequence of auto-Poisson lattice schemes. We review the limit theorems concerned, present a computer software (SPPA) and analyze the results of a Monte Carlo simulation study based on a particular pairwise interaction model.     

G1 rational blend interpolatory schemes: A comparative study

Interpolation of triangular meshes is a subject of great interest in many computer graphics related applications, as, for example, gaming and realtime rendering. One of the main approaches to interpolate the positions and normals of the mesh vertices is the use of parametric triangular Bézier patches. As it is well known, any method aiming at constructing a parametric, tangent plane (G¹) continuous surface has to deal with the vertex consistency problem. In this article, we propose a comparison of three methods appeared in the nineties that use a particular technique called rational blend to avoid this problem. Together with these three methods we present a new scheme, a cubic Gregory patch, that has been inspired by one of them. Our comparison includes an analysis of their computational costs on CPU and GPU, a study of their capabilities of approximating analytic surfaces and their response to different surface interrogation methods on arbitrary triangle meshes with a low triangle count that actually occur in their real-world use.     

Probability-theoretical and possibility-theoretical algorithms for reducing multivariate data: A comparative analysis

A comparative analysis of probability-theoretical and possibility-theoretical methods for reducing multivariate data is carried out. Konstantin Sergeevich Sobolev. Born 1976. Graduated from the Moscow State University in 2000. Author of two papers. Ol’ga Vladimirovna Mondrus. Born 1981. Graduated from the Moscow State University in 2005. Author of two papers. Yurii P. Pyt’ev. Graduated from the Faculty of Physics, Moscow State University. Professor, Head of the Department of Computer Methods in Physics, Faculty of Physics, Moscow State University. Scientific Interests: mathematical methods of data analysis and interpretation, mathematical modeling of measuring-computing systems of superhigh resolution, and fuzzy and uncertain fuzzy mathematics. Author of more than 300 publications on mathematics, mathematical physics, and information science, including several monographs.     

Simultaneous analysis of coupled data blocks differing in size: A comparison of two weighting schemes

Research questions in several research domains imply the simultaneous analysis of different blocks of information that pertain to the same research objects. In personality psychology, for example, to study the relation between individual differences in behavior and cognitive-affective units that can account for these differences, two types of information pertaining to the same set of persons need to be analyzed simultaneously: (1) information about the situation-specific behavior profile of these persons, and (2) information about the cognitive-affective units these persons exhibit. When dealing with such coupled data blocks (i.e., different N-way N-mode data blocks that have one or more modes in common) it often happens that one data block is much larger in size than the other(s). In this case, the question arises whether the data entries or the data blocks should be considered as the units of information, in order to disclose the true structure underlying the coupled data blocks. To answer this question, two weighting schemes are compared that are obtained by applying weights in the overall objective function that is to be optimized in the data analysis, with each weight indicating the extent to which the corresponding data block influences the integrated analysis. In a simulation study it is showed that weighting the different data blocks such that each data entry influences the analysis to the same extent (i.e., data entries as units of information) outperforms a weighting scheme in which each data block has an equal influence on the analysis (i.e., data blocks as units of information). This superior performance is demonstrated for two global models for coupled data consisting of a three-way three-mode data block and a two-way two-mode data block that have one mode in common: (1) a multiway multiblock component model for coupled real-valued data, and (2) a simultaneous clustering model for coupled binary data.     

A Comparative Analysis of Different Arbitration Protocols for Multiple-Bus Multiprocessors

Earlier performance studies of multiple-bus multiprocessor systems assume a random selection of competing requests for bus assignment and ignore the effects of realistic bus arbitraion schemes on the performance of such systems.In this paper,we present performance analysis of the multiple-bus systems with different arbitration protocols.The priority protocols considered are random selection,fixed priority,rotating priority,round-robin and FIFO.Analytical models are developed for each of these five different priority protocols.Each of our analyses models exactly the behavior of the corresponding priority protocol with little computation cost.The analytical models are validated through extensive simulations and are them used to carry out performance analysis and comparison of different priority protocols.Numerical results obtained from our models show that the round-robin protocol performs the best amont the five protocols in the system with a few buses.     

A comparative study on spatial and spectral resolutions of satellite data in mapping mangrove forests

Mangrove forests in the western Waitemata Harbour, Auckland, New Zealand were mapped into lush and stunted categories from SPOT HRV and Landsat TM images at 10, 20 and 30m using the maximum likelihood method. It was found that the TM-generated results were the most accurate at 95% for lush mangroves and 87.5% for stunted mangroves. Their corresponding accuracy levels were lowered to 77.5% and 67.5% in the 20m SPOT XS-derived results. Both percentages were improved to 80 after the PAN band was incorporated in the classification at 10m. These results suggest that a high spectral resolution is more important in accurately mapping mangroves in a temperate zone than a fine spatial resolution because it enhances the interpretability of non-mangrove vegetation and thus increases its confusion with mangroves.     

A comparative experimental study of distributed storage engines for big spatial data processing using GeoSpark

With increasing numbers of GPS-equipped mobile devices, we are witnessing a deluge of spatial information that needs to be effectively and efficiently managed. Even though there are several distributed spatial data processing systems such as GeoSpark (Apache Sedona), the effects of underlying storage engines have not been well studied for spatial data processing. In this paper, we evaluate the performance of various distributed storage engines for processing large-scale spatial data using GeoSpark, a state-of-the-art distributed spatial data processing system running on top of Apache Spark. For our performance evaluation, we choose three distributed storage engines having different characteristics: (1) HDFS, (2) MongoDB, and (3) Amazon S3. To conduct our experimental study on a real cloud computing environment, we utilize Amazon EMR instances (up to 6 instances) for distributed spatial data processing. For the evaluation of big spatial data processing, we generate data sets considering four kinds of various data distributions and various data sizes up to one billion point records (38.5GB raw size). Through the extensive experiments, we measure the processing time of storage engines with the following variations: (1) sharding strategies in MongoDB, (2) caching effects, (3) data distributions, (4) data set sizes, (5) the number of running executors and storage nodes, and (6) the selectivity of queries. The major points observed from the experiments are summarized as follows. (1) The overall performance of MongoDB-based GeoSpark is degraded compared to HDFS- and S3-based GeoSpark in our experimental settings. (2) The performance of MongoDB-based GeoSpark is relatively improved in large-scale data sets compared to the others. (3) HDFS- and S3-based GeoSpark are more scalable to running executors and storage nodes compared to MongoDB-based GeoSpark. (4) The sharding strategy based on the spatial proximity significantly improves the performance of MongoDB-based GeoSpark. (5) S3- and HDFS-based GeoSpark show similar performances in all the environmental settings. (6) Caching in distributed environments improves the overall performance of spatial data processing. These results can be usefully utilized in decision-making of choosing the most adequate storage engine for big spatial data processing in a target distributed environment.

     

Design-based spatial sampling: Theory and implementation

Various sampling techniques are widely used in environmental, social and resource surveys. Spatial sampling techniques are more efficient than conventional sampling when surveying spatially distributed targets such as CO₂ emissions, soil pollution, a population distribution, disaster distribution, and disease incidence, where spatial autocorrelation and heterogeneity are prevalent. However, despite decades of development in theory and practice, there are few computer programs for spatial sampling. We investigated the three-fold relationship between targets, sampling strategies and statistical methods in spatial contexture. Accordingly, the information flow of the spatial sampling process was reconstructed and optimized. SSSampling, a computer program for design-based spatial sampling, has been developed from the theoretical basis. Three typical applications of the software, namely sampling design, optimal statistical inference and precision assessment, are demonstrated as case studies.     

A spatial sampling criterion for sonar obstacle detection

A spatial sampling criterion for sonar systems that allows all obstacles within a given radius from the sensor to be detected is described. The environment considered is a two-dimensional floor plan that is extended into the third dimension, in which the scanning is performed in the horizontal plane. In this environment, edgelike reflectors, such as edges of doors or doorways, and oblique surfaces are the most difficult to detect. By considering the physics of sound propagation, the sonar scanning density required to detect these objects is determined. An experimental verification is included. The limitations of detecting objects with sonar in a more general environment are discussed. These results can be used to determine the necessary spacing in a transducer ring array and the maximum step size that a mobile robot can translate without danger of collision     

A comparative analysis of different gender pair combinations in pair programming

Over the last decade, there has been a steady stream of pair programming studies. However, one significant area of pair programming that has not received its due attention is gender. Considering the fact that pair programming is one of the major human-centric software development paradigms, this is a gap that needs to be addressed. This empirical study conducted quantitative and qualitative analyses of different gender pair combinations within pair programming context. Using a pool of university programming course students as the experiment participants, the study examined three gender pair types: female–female, female–male, and male–male. The result revealed that there was no significant gender difference in the pair programming coding output. But there were significant differences in the levels of pair compatibility and communication between the same gender pair type: female–female and male–male, and the mixed gender pair type, female–male. The post-experiment comments provide additional insights and details about gender in pair interactions.     

Evaluating the precision of eight spatial sampling schemes in estimating regional means of simulated yield for two crops

We compared the precision of simple random sampling (SimRS) and seven types of stratified random sampling (StrRS) schemes in estimating regional mean of water-limited yields for two crops (winter wheat and silage maize) that were simulated by fourteen crop models. We found that the precision gains of StrRS varied considerably across stratification methods and crop models. Precision gains for compact geographical stratification were positive, stable and consistent across crop models. Stratification with soil water holding capacity had very high precision gains for twelve models, but resulted in negative gains for two models. Increasing the sample size monotonously decreased the sampling errors for all the sampling schemes. We conclude that compact geographical stratification can modestly but consistently improve the precision in estimating regional mean yields. Using the most influential environmental variable for stratification can notably improve the sampling precision, especially when the sensitivity behavior of a crop model is known.     

A probabilistic spatial data model

Spatial information in autonomous robot tasks is uncertain due to measurement errors, the dynamic nature of the world, and an incompletely known environment. We present a probabilistic spatial data model capable of describing relevant spatial data, such as object location, shape, composition, and other parameters, in the presence of uncertainty. Uncertain spatial information is modeled through continuous probability distributions on values of attributes. The data model is designed to support our visual tracking and navigation prototype.     

Graphical data analysis in comparative experimental studies

We discuss a clustering method of sample means as an alternative to the multiple comparison procedure in analysis of variance. In particular we review six of such methods that appeared in the literature and also investigate their characteristics in an illustrative example. Small-scaled simulation studies are carried out to compare their performances.