Web Search has seen two big changes recently: rapid growth in mobile search traffic, and an increasing trend towards providing answer-like results for relatively simple information needs (e.g., [weather today]). Such results display the answer or relevant information on the search page itself without requiring a user to click. While clicks on organic search results have been used extensively to infer result relevance and search satisfaction, clicks on answer-like results are often rare (or meaningless), making it challenging to evaluate answer quality. Together, these call for better measurement and understanding of search satisfaction on mobile devices. In this paper, we studied whether tracking the browser viewport (visible portion of a web page) on mobile phones could enable accurate measurement of user attention at scale, and provide good measurement of search satisfaction in the absence of clicks. Focusing on answer-like results in web search, we designed a lab study to systematically vary answer presence and relevance (to the user's information need), obtained satisfaction ratings from users, and simultaneously recorded eye gaze and viewport data as users performed search tasks. Using this ground truth, we identified increased scrolling past answer and increased time below answer as clear, measurable signals of user dissatisfaction with answers. While the viewport may contain three to four results at any given time, we found strong correlations between gaze duration and viewport duration on a per result basis, and that the average user attention is focused on the top half of the phone screen, suggesting that we may be able to scalably and reliably identify which specific result the user is looking at, from viewport data alone.

Live SNG (Satellite News Gathering) services, featuring real-time streaming of high-quality video, are typically enabled via expensive SNG vehicles and satellite transmissions by TV companies. In this paper, we design a cost-effective solution to delivering live news broadcasting (LNB) service over emerging broadband wireless access technologies such as WiMAX. However, LNB is a bandwidth hungry service and may consume most of the uplink wireless resource. Besides, the conditions of the shared wireless access between mobile nodes and base stations (BSs) may vary with time and location, which affect the quality of service (QoS) of LNB service. To guarantee the QoS level of LNB service, we implement a novel system called i-SNG which uses multi-link SCTP to glue together more bandwidth from heterogeneous wireless networks such as WiMAX, 3.5G cellular, and WiFi, and to ensure fault tolerance for LNB. We share our experience in constructing an experimental test-bed for our proposed i-SNG system for LNB service. We apply a new multi-link SCTP patch over FreeBSD 7.1 in this test-bed. The experimental results show that i-SNG not only provides a cost-effective solution to LNB service, but also preserves the perceptual quality of LNB video streaming under different network conditions.

BACKGROUND: MicroRNAs (miRNAs) are short non-coding RNA molecules, which play an important role in post-transcriptional regulation of gene expression. There have been many efforts to discover miRNA precursors (pre-miRNAs) over the years. Recently, ab initio approaches have attracted more attention because they do not depend on homology information and provide broader applications than comparative approaches. Kernel based classifiers such as support vector machine (SVM) are extensively adopted in these ab initio approaches due to the prediction performance they achieved. On the other hand, logic based classifiers such as decision tree, of which the constructed model is interpretable, have attracted less attention. RESULTS: This article reports the design of a predictor of pre-miRNAs with a novel kernel based classifier named the generalized Gaussian density estimator (G2DE) based classifier. The G2DE is a kernel based algorithm designed to provide interpretability by utilizing a few but representative kernels for constructing the classification model. The performance of the proposed predictor has been evaluated with 692 human pre-miRNAs and has been compared with two kernel based and two logic based classifiers. The experimental results show that the proposed predictor is capable of achieving prediction performance comparable to those delivered by the prevailing kernel based classification algorithms, while providing the user with an overall picture of the distribution of the data set. CONCLUSION: Software predictors that identify pre-miRNAs in genomic sequences have been exploited by biologists to facilitate molecular biology research in recent years. The G2DE employed in this study can deliver prediction accuracy comparable with the state-of-the-art kernel based machine learning algorithms. Furthermore, biologists can obtain valuable insights about the different characteristics of the sequences of pre-miRNAs with the models generated by the G2DE based predictor.

This article presents a comprehensive study on the main characteristics of a novel optimization algorithm specifically designed for simulation of protein-ligand interactions. Though design of optimization algorithms has been a research issue extensively studied by computer scientists for decades, the emerging applications in bioinformatics such as simulation of protein-ligand interactions and protein folding introduce additional challenges due to (1) the high dimensionality nature of the problem and (2) the highly rugged landscape of the energy function. As a result, optimization algorithms that are not carefully designed to tackle these two challenges may fail to deliver satisfactory performance. This study has been motivated by the observation that the RAME (Rank-based Adaptive Mutation Evolutionary) optimization algorithm specifically designed for simulation of protein-ligand docking has consistently outperformed the conventional optimization algorithms by a significant degree. Accordingly, it is of interest to conduct a comprehensive investigation on the characteristics of the proposed algorithm and to learn how it will perform in the more general cases.The experimental results reveal that the RAME algorithm proposed in this article is capable of delivering superior performance to several alternative versions of the genetic algorithm in handling highly-rugged functions in the high-dimensional vector space. This article also reports experiments conducted to analyze the causes of the observed performance difference. The experiences learned provide valuable clues for how the proposed algorithm can be effectively exploited to tackle other computational biology problems.

Data classification is an intensively studied machine learning problem and there are two major categories of data classification algorithms, namely the logic based and the kernel based. The logic based classifiers, such as the decision tree and the rule-based classifier, feature the advantage of presenting a good summary about the distinctive characteristics of different classes of data. On the other hand, the kernel based classifiers, such as the neural network and the support vector machine (SVM), typically can deliver higher prediction accuracy than the logic based classifiers. However, the user of a kernel based classifier normally cannot get an overall picture about the distribution of the data set. For some applications, the overall picture of the distribution of the data set can provide valuable insights about the distinctive characteristics of different classes of data and therefore is highly desirable. In this article, aiming to close the gap between the logic based classifiers and the kernel based classifiers, we propose a novel approach to carry out density estimation based on a mixture model composed of a limited number of generalized Gaussian components. One favorite feature of the classifier constructed with the proposed approach is that a user can easily obtain an overall picture of the distributions of the data set by examining the eigenvectors and eigenvalues of the covariance matrices associated with the generalized Gaussian components. Experimental results show that the classifier constructed with the proposed approach is capable of delivering superior prediction accuracy in comparison with the conventional logic based classifiers and the EM (Expectation Maximization) based classifier. On the other hand, though it cannot match the prediction accuracy delivered by the SVM, the proposed classifier enjoys one major advantage due to providing the user with an overall picture of the underlying distributions.

From gene expression profiles, it is desirable to rebuild cellular dynamic regulation networks to discover more delicate and substantial functions in molecular biology, biochemistry, bioengineering and pharmaceutics. S-system model is suitable to characterize biochemical network systems and capable to analyze the regulatory system dynamics. However, inference of an S-system model of N-gene genetic networks has 2N(N+1) parameters in a set of non-linear differential equations to be optimized. This paper proposes an intelligent two-stage evolutionary algorithm (iTEA) to efficiently infer the S-system models of genetic networks from time-series data of gene expression. To cope with curse of dimensionality, the proposed algorithm consists of two stages where each uses a divide-and-conquer strategy. The optimization problem is first decomposed into N subproblems having 2(N+1) parameters each. At the first stage, each subproblem is solved using a novel intelligent genetic algorithm (IGA) with intelligent crossover based on orthogonal experimental design (OED). At the second stage, the obtained N solutions to the N subproblems are combined and refined using an OED-based simulated annealing algorithm for handling noisy gene expression profiles. The effectiveness of iTEA is evaluated using simulated expression patterns with and without noise running on a single-processor PC. It is shown that 1) IGA is efficient enough to solve subproblems; 2) IGA is significantly superior to the existing method SPXGA; and 3) iTEA performs well in inferring S-system models for dynamic pathway identification.

This paper proposes an efficient evolutionary divide-and-conquer approach (EDACA) to inferring S-system models of genetic networks from time-series data of gene expression. Inference of an S-system model has 2N(N+1) parameters to be optimized, where N is the number of genes in a genetic network. To cope with higher dimensionality, the proposed approach consists of two stages where each uses a divide-and-conquer strategy. The optimization problem is first decomposed into N subproblems having 2(N+1) parameters each. At the first stage, each subproblem is solved using a novel intelligent genetic algorithm (IGA) with intelligent crossover based on orthogonal experimental design (OED). The intelligent crossover divides two parents into n pairs of parameter groups, economically identifies the potentially better one of two groups of each pair, and systematically obtains a potentially good approximation to the best one of all 2/sup n/ combinations using at most 2n function evaluations. At the second stage, the obtained N solutions to the N subproblems are combined and refined using an OED-based simulated annealing algorithm (OSA) for handling noisy gene expression data. The effectiveness of EDACA is evaluated using simulated expression patterns with/without noise running on a single-CPU PC. It is shown that: 1) IGA is efficient enough to solve subproblems; 2) IGA is significantly superior to the existing method of using GA with simplex crossover; and 3) EDACA performs well in inferring S-system models of genetic networks from small-noise gene expression data.