Rolling the dice: multidimensional visual exploration using scatterplot matrix navigation

Scatterplots remain one of the most popular and widely-used visual representations for multidimensional data due to their simplicity, familiarity and visual clarity, even if they lack some of the flexibility and visual expressiveness of newer multidimensional visualization techniques. This paper presents new interactive methods to explore multidimensional data using scatterplots. This exploration is performed using a matrix of scatterplots that gives an overview of the possible configurations, thumbnails of the scatterplots, and support for interactive navigation in the multidimensional space. Transitions between scatterplots are performed as animated rotations in 3D space, somewhat akin to rolling dice. Users can iteratively build queries using bounding volumes in the dataset, sculpting the query from different viewpoints to become more and more refined. Furthermore, the dimensions in the navigation space can be reordered, manually or automatically, to highlight salient correlations and differences among them. An example scenario presents the interaction techniques supporting smooth and effortless visual exploration of multidimensional datasets.     

VisGets: coordinated visualizations for web-based information exploration and discovery

In common Web-based search interfaces, it can be difficult to formulate queries that simultaneously combine temporal, spatial, and topical data filters. We investigate how coordinated visualizations can enhance search and exploration of information on the World Wide Web by easing the formulation of these types of queries. Drawing from visual information seeking and exploratory search, we introduce emph{VisGets} -- interactive query visualizations of Web-based information that operate with online information within a Web browser. VisGets provide the information seeker with visual overviews of Web resources and offer a way to visually filter the data. Our goal is to facilitate the construction of dynamic search queries that combine filters from more than one data dimension. We present a prototype information exploration system featuring three linked VisGets (temporal, spatial, and topical), and used it to visually explore news items from online RSS feeds.     

Voxel-based three-view hybrid parallel network for 3D object classification

Three-dimensional models are widely used in the fields of multimedia, computer graphics, virtual reality, entertainment, design, and manufacturing because of the rich information that preserves the surface, color and texture of real objects. Therefore, effective 3D object classification technology has become an urgent need. Previous methods usually directly convert classic 2D convolution into 3D form and apply it to objects with binary voxel representation, which may lose internal information that is essential for recognition. In this paper, we propose a novel voxel-based three-view hybrid parallel network for 3D shape classification. This method first obtains the depth projection views of the three-dimensional model from the front view, the top view and the side view, so as to preserve the spatial information of the three-dimensional model to the greatest extent, and output its predicted probability value for the category of the three-dimensional model, and then combining the three-view parallel network with voxel sub-network performs weight fusion, and then uses Softmax for classification. We conducted a series of experiments to verify the design of the network and achieved competitive performance in the 3D object classification tasks of ModelNet10 and ModelNet40.     

Multi-granularity hybrid parallel network simplex algorithm for minimum-cost flow problems

The Journal of Supercomputing - Minimum-cost flow problems widely exist in graph theory, computer science, information science, and transportation science. The network simplex algorithm is a fast...     

并联混合神经网络模型及应用研究

单一神经网络难以对复杂模型做出准确的预测,提出了一种并联型混合神经网络模型用于对复杂的系统进行预测,该模型由径向基函数网络、BP网络和控制模块组成。控制模块用于线性映射层,将两种单一神经网络的输出结合并得到最终的输出结果。详细地给出了混合模型的预测方法：首先,利用改进算法分别训练径向基函数网络和BP网络;其次,采用自适应遗传算法优化线性映射层以获得更好的预测精度;最后,利用两个实例比较单一神经网络和提出的混合网络的预测性能。实验表明,混合神经网络在预测精度上比单一网络具有更优的性能,同时,该混合模型为复杂系统提供了一种通用的预测工具。     

基于并行混合网络融入注意力机制的情感分析

针对传统卷积神经网络（CNN）不仅会忽略词的上下文语义信息而且最大池化处理时会丢失大量特征信息的问题，传统循环神经网络（RNN）存在的信息记忆丢失和梯度弥散问题，和CNN和RNN都忽略了词对句子含义的重要程度的问题，提出一种并行混合网络融入注意力机制的模型。首先，将文本用Glove向量化；之后，通过嵌入层分别用CNN和双向门限循环神经网络提取不同特点的文本特征；然后，再把二者提取得到的特征进行融合，特征融合后接入注意力机制判断不同的词对句子含义的重要程度。在IMDB英文语料上进行多组对比实验，实验结果表明，所提模型在文本分类中的准确率达到91.46%而其F1-Measure达到91.36%。     

基于并行混合网络融入注意力机制的情感分析

针对传统卷积神经网络（CNN）不仅会忽略词的上下文语义信息而且最大池化处理时会丢失大量特征信息的问题,传统循环神经网络（RNN）存在的信息记忆丢失和梯度弥散问题,和CNN和RNN都忽略了词对句子含义的重要程度的问题,提出一种并行混合网络融入注意力机制的模型。首先,将文本用Glove向量化;之后,通过嵌入层分别用CNN和双向门限循环神经网络提取不同特点的文本特征;然后,再把二者提取得到的特征进行融合,特征融合后接入注意力机制判断不同的词对句子含义的重要程度。在IMDB英文语料上进行多组对比实验,实验结果表明,所提模型在文本分类中的准确率达到91.46%而其F1-Measure达到91.36%。     

Uncover: supporting city exploration with egocentric visualizations of location-based content

This paper describes the design and evaluation of Uncover: a mobile application that supports users in exploratory pedestrian behavior to gain situational awareness of their immediate environment. The design was based on guidelines derived from foraging theory and relies on egocentric views, which keep the virtual content automatically aligned with the real world. We carried out two studies with Uncover, which examine the successfulness of design choices aiming to support tourists’ city exploration while interfering with experiencing the surroundings as little as possible. A lab study tested the effect of different marker and background types on the time to recognize the direction with most content. The designs performing best were implemented in the final prototype, and a field study analyzed the exploration behavior tourists and visitors exhibited while using it. The study showed that supporting the exploration can be improved by enabling features that are either disabled by default or not available at all in commercial map applications, like egocentric orientation of the map, providing images of venues just by pointing to their direction, and displaying clusters of several venue types.     

VisDB: database exploration using multidimensional visualization

Discusses how the VisDB system supports the query specification process by representing the result visually. The main idea behind the system stems from the view of relational database tables as sets of multidimensional data where the number of attributes corresponds to the number of dimensions. In such a view, it is often unclear. In this system, each display pixel represents one database item. Pixels are arranged and colored to indicate the item's relevance to a user query and to give a visual impression of the resulting data set     

一种基于范围搜索的并行多维分类算法PRSMC

针对高速网络应用对基于范围查找的分组分类算法的要求以及高性能并行计算环境的特点,提出了一种高速多维分组分类算法——PRSMC(基于范围搜索的并行多维分类)算法。该算法具有较快的搜索速度和较强的并行性,特别适合在多CPU多核高性能计算机上实现。同时提出了算法的双缓冲并行实现技术,使得在软件环境中具有良好空间和时间性能。性能实验表明该算法具有良好的可扩展性,算法速度较同类基于区域划分的算法有较大提升,平均分类速率能达到1Mpkt/s左右。     

基于并行混合神经网络模型的短文本情感分析

针对传统的卷积神经网络（CNN）在进行情感分析任务时会忽略词的上下文语义以及CNN在最大池化操作时会丢失大量特征信息，从而限制模型的文本分类性能这两大问题，提出一种并行混合神经网络模型CA-BGA。首先，采用特征融合的方法在CNN的输出端融入双向门限循环单元（BiGRU）神经网络，通过融合句子的全局语义特征加强语义学习；然后，在CNN的卷积层和池化层之间以及BiGRU的输出端引入注意力机制，从而在保留较多特征信息的同时，降低噪声干扰；最后，基于以上两种改进策略构造出了并行混合神经网络模型。实验结果表明，提出的混合神经网络模型具有收敛速度快的特性，并且有效地提升了文本分类的F1值，在中文评论短文本情感分析任务上具有优良的性能。     

HARP: an open architecture for parallel matrix and signalprocessing

Describes and analyzes the Hybrid Array Ring Processor (HARP) architecture. The HARP is an application specific architecture built around a host processor, shared memory, and a set of memory mapped processing cells that are connected both into an open backplane and a bidirectional systolic ring. The architecture is analyzed through detailed simulation of a system implementation based on the Texas Instruments TMS34082 floating point RISC. A bus controller is designed that provides a tightly coupled DMA function that accelerates systolic communication and supports new interleaved transparent communications and reduced overhead message passing. The architecture is benchmarked with the matrix multiplication, FFT, QRD, and SVD algorithms     

Three-dimensional Petersen-torus network: a fixed-degree network for massively parallel computers

A two-dimensional (2D) Petersen-torus network is a mesh-class fixed-degree network designed using a Petersen graph, which has a maximum of 10 nodes when the degree is 3 and the diameter is 2 in a (d,k)-graph problem. Here, I propose a new three-dimensional (3D) Petersen-torus network that extends the 2D Petersen-torus network without increasing the degree. The 3D Petersen-torus has the same number of nodes (N). The 3D Petersen-torus is better than the well-known 3D torus and 3D honeycomb mesh in terms of diameter and network cost. The 3D Petersen-torus network is better than the hypercube-like and star graph-like networks in terms of extendibility. Hence, the proposed network may serve as the foundation for realizing a high-performance multicomputer. In this paper, the optimal routing algorithm, Hamilton cycle, and several basic attributes are discussed. Furthermore, a comparison with a mesh-class fixed-degree 3D network is made for degree, diameter, and network cost.     

A new pose accuracy compensation method for parallel manipulators based on hybrid artificial neural network

Neural Computing and Applications - The pose accuracy of parallel manipulators is one of the most important performance indices in advanced industrial applications. The modeling and estimation of...     

Information visualizations for knowledge acquisition: The impact of dimensionality and color coding

Information visualizations – interactive graphical representations of large amounts of abstract data which do not have a natural visual representation – have mainly been used to support information retrieval. This article investigates whether information visualizations are also suitable for fostering knowledge acquisition as well as how information visualizations, from a cognitive perspective, have to be designed to be efficient learning tools. An experimental study provided evidence that information visualizations support knowledge acquisition. In addition, with regard to the appropriate design, the empirical results showed that two-dimensional information visualizations are better suited for supporting processes of knowledge acquisition than three-dimensional ones and that color-coded information visualizations slightly increase performance in a knowledge test compared to monochromatic ones.     

Methodology for modelling SPMD hybrid parallel computation

This research defines and analyzes a methodology for deriving a performance model for SPMD hybrid parallel applications. Hybrid parallelism combines shared memory and message passing computing models. This work extends the current practice of application performance modelling by development of a methodology for hybrid applications with these procedures.

• Creation of a model based on complexity analysis of an application code and its data structures.
• Enhancement of a static complexity model by dynamic factors to capture execution time phenomena, such as memory hierarchy effects.
• Quantitative analysis of model characteristics and the effects of perturbations in measured parameters.

These research results are presented in the context of a hybrid parallel implementation of a sparse linear algebra kernel. A model for this kernel is derived and analyzed using the methodology. Application of the model on two large parallel computing platforms provides case studies for the methodology. Operating system issues, machine balance factor, and memory hierarchy effects on model accuracy are examined. Copyright © 2007 John Wiley & Sons, Ltd.     

A parallel hybrid metaheuristic for bicluster editing

The bicluster editing problem (BEP) consists of editing (adding or removing) the edges of a bipartite graph G in order to transform it into a vertex‐disjoint union of complete bipartite subgraphs, in such a way that the sum of the weights of the edited edges is minimum. In this paper, we propose five parallel strategies for the implementation of a hybrid metaheuristic for the BEP, consisting of a GRASP with VNS as local search. Computational experiments show near‐linear speedups on Linux cluster with 64 processors and better solutions than those of the sequential approach.     

Gemini: an optical interconnection network for parallel processing

The Gemini interconnect is a dual technology (optical and electrical) interconnection network designed for use in tightly-coupled multicomputer systems. It consists of a circuit-switched optical data path in parallel with a packet-switched electrical control/data path. The optical path is used for transmission of long data messages and the electrical path is used for switch control and transmission of short data messages. The paper describes the architecture of the interconnection network and related communications protocols. Fairness issues associated with network operation are addressed and a discrete-event simulation model of the entire system is described. Network performance characteristics derived from the simulation model are presented. The results show significant performance benefits when using virtual output queuing and quantify the tradeoffs between throughput and fairness in the system     

A parallel network for visual cognition

The authors describe a parallel dynamical system designed to integrate model-based and data-driven approaches to image recognition in a neural network, and study one component of the system in detail. That component is the translation-invariant network of probabilistic cellular automata (PCA), which combines feature-detector outputs and collectively performs enhancement and recognition functions. Recognition is a novel application of the PCA. Given a model of the target object, conditions on the PCA weights are obtained which must be satisfied for object enhancement and noise rejection to occur, and engineered weights are constructed. For further refinement of the weights, a training algorithm derived from optimal control theory is proposed. System operation is illustrated with examples derived from visual, infrared, and laser-radar imagery.     

一种基于MapReduce的OpenFlow网络属性并行验证算法

针对OpenFlow网络中流表配置错误引起转发回路、路由黑洞和访问控制规则失效等问题,提出一种并行的基于MapReduce的OpenFlow网络属性验证算法。通过在Map阶段划分规则等价类,在Reduce阶段为规则等价类构建基于交换机端口谓词的网络转发图并分析可达性,实现对网络属性的并行验证。同时,通过采用原子谓词将传统可达性分析中的规则匹配域多维集合运算转换为整数集合运算,以进一步提高可达性分析效率。此外,基于原子谓词的谓词表达方式可消除交换机端口谓词集合中的冗余项,降低存储开销。最后,通过理论分析和仿真实验验证了算法的正确性及在时间和存储开销方面的优越性。