The challenges of the Big Data era has motivated many organizations to turn towards distributed, large-scale processing platforms to deal with their data. Map Reduce, and its open-source implementation, Hadoop, has grown to be highly popular with its successful programming model for simplified cluster processing. As a result, many organizations deploy their own Map Reduce/Hadoop clusters to store and process large amounts of useful data. This multicluster setting is gradually growing attention. Numerous previous works have researched on how to execute Map Reduce across geographically distributed data in this setting. However, an important class of applications have not been explored for multicluster Map Reduce: iterative computation. In this paper, we propose Fed Loop, a composite system aimed at providing iterative Map Reduce computation for geographically distributed data in multicluster settings. Fed Loop is capable of transparently executing both iterative and non-iterative Map Reduce jobs on either a single cluster or multiple clusters. For our performance evaluation, two well-known iterative algorithms was executed over 4 independent clusters (16 physical nodes in total) using Fed Loop: K-Means and Page Rank. Results helped us discover how different iterative applications may differ in execution efficiency for mutlicluster environments and how iterative multicluster computation systems like Fed Loop can be optimized.

In this paper, we present a novel multimodal emotion recognition technique that automatically learns decision-making parameters customized for each modality. Specifically, the process of decision-making is implemented in a multi-stage and collaborative fashion: Given a classifier for single modality, the classifier is regarded as a virtual expert since classification methods can make emotion recognition in accordance with certain expertise. Then, in the reputation equalization, the expert's classification capability is then quantitatively equalized to assure the reputation and/or confidence for each expert. To compromise decisions among experts, the final decision is obtained by calculating the weighted-sum of all the equalized reputation quantities, in such a way that the decision of one expert can be made in collaboration with that of the others. Moreover, to learn the proposed model parameters, the genetic algorithm is tailored and applied to alleviate the local minima problem during the process of finding an optimal solution. The experimental results have shown that the proposed collaborative decision-making model is effective in multimodal emotion recognition.

Abstract Summary: Recent advances in sequencing technologies have revolutionized genetic studies. Although high-coverage sequencing can uncover most variants present in the sequenced sample, low-coverage sequencing is appealing for its cost effectiveness. Here, we present AbCD (arbitrary coverage design) to aid the design of sequencing-based studies. AbCD is a user-friendly interface providing pre-estimated effective sample sizes, specific to each minor allele frequency category, for designs with arbitrary coverage (0.5–30×) and sample size (20–10 000), and for four major ethnic groups (Europeans, Africans, Asians and African Americans). In addition, we also present two software tools: ShotGun and DesignPlanner, which were used to generate the estimates behind AbCD. ShotGun is a flexible short-read simulator for arbitrary user-specified read length and average depth, allowing cycle-specific sequencing error rates and realistic read depth distributions. DesignPlanner is a full pipeline that uses ShotGun to generate sequence data and performs initial SNP discovery, uses our previously presented linkage disequilibrium-aware method to call genotypes, and, finally, provides minor allele frequency-specific effective sample sizes. ShotGun plus DesignPlanner can accommodate effective sample size estimate for any combination of high-depth and low-depth data (for example, whole-genome low-depth plus exonic high-depth) or combination of sequence and genotype data [for example, whole-exome sequencing plus genotyping from existing Genomewide Association Study (GWAS)]. Availability and implementation: AbCD, including its downloadable terminal interface and web-based interface, and the associated tools ShotGun and DesignPlanner, including documentation, examples and executables, are available at http://www.unc.edu/∼yunmli/AbCD.html. Contact: [email protected]

It is easy for a multi-layered perception (MLP) to fit a stratified spatial interpolation pattern whose form is close to open surface; while it is easy for a radial basis function network (RBFN) to fit a pocket (radial) spatial interpolation pattern whose form is close to closed surface. However, in the real world, the spatial interpolation pattern may consist of stratified and pocket patterns. Neither MLP nor RBFN can fit the pattern easily. To combine their advantages to fit the complex hybrid spatial interpolation patterns, in this article we propose a novel neural network, MLP–RBFN hybrid network (MRHN), whose hidden layer contains sigmoid and Gaussian units at the same time. Although there are two kinds of processing units in MRHN, in this study we used the principle of minimizing the error sum of squares to derive the supervised learning rules for all the network parameters. This research took rainfall distribution in Taiwan as a case study. The results show that (1) the prediction error of the testing dataset outside the training dataset demonstrated that MRHN was the most accurate among the three networks, RBFN was the next best, and MLP was the worst; (2) the MLP model seriously underestimated the values of high observed rainfall; (3) over-learning may be a serious shortcoming of using RBFN in spatial interpolation applications; (4) MRHN may have better generalization learning capacity than RBFN in spatial interpolation applications.

Recognizing human emotions from facial expressions is highly dependent on the quality of the referred facial expression features. Conventional methods often suffer from high computation time and serious influence of environment variations. In this paper, a triangular facial feature extraction method based on a Modified Active Shape Model (MASM) is proposed. This method features considering the interactions of all facial features, escaping from the affection of environment variations as well as noisy facial features, and reducing feature dimensions. MASM adopts the same shape representation and shape training procedures as ASM, but executes a different landmark searching procedure without using the gray level training procedure to avoid the affection from environment variations. Using the feature points extracted by MASM, two methods, one is based on statistical analysis and another one is derived from the genetic algorithm, are proposed to extract an optimal set of triangular facial features for emotion recognition. In the experiments with JAFFE database, a neural network classifier is employed to recognize emotions with those extracted triangular facial features. The experimental results show that based on the statistical analysis 65.1% recognition rate is achieved, and based on the genetic algorithm 70.2% recognition rate is achieved.