Search

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance. [ABSTRACT FROM AUTHOR]

Digital public displays installed in various locations provide valuable information for the passers-by. However, the static characteristic of the digital public display limits the consumption of the displayed content to a small area. Personal mobile devices such as smartphones are now capable of interacting with digital public displays, which enables the passers-by to “take-away” the content and consume it on-the-go. This process requires device binding, content selection, and transfer between the two devices. In this paper, we propose a device binding method which utilizes the content brightness changing pattern as a unique content ID on the public display and an illuminance sensor on the mobile to bind and transfer between two devices. We conducted performance evaluations for binding algorithm robustness in different conditions. Also comparative studies among other binding interaction methods were conducted. Our results show that our proposed method performed stably across the various conditions and overall performance in interaction completion time and error rate was similar or superior to the existing methods. [ABSTRACT FROM AUTHOR]

Certificateless aggregate signature (CLAS) is a crucial cryptosystem. It can not only compress multiple signatures into a short signature, but also ensure the validity of each signature participating in the aggregation by verifying the validity of an resulting aggregate signature. Therefore, a secure and efficient CLAS scheme is very useful for resource-constrained environments because it greatly reduces the overall length of the signature and the verifier’s computational overhead. Cheng et al. presented an efficient CLAS scheme and proved its security in the random oracle model. However, we find that their scheme has security flaws. In this paper, we demonstrate that Cheng et al.’s CLAS scheme is vulnerable to coalition attacks from internal signers. To overcome these attacks, we present an improved CLAS scheme and prove that it is existentially unforgeable under the computational Diffie-Hellman assumption. In addition, our CLAS scheme can not only resist coalition attacks but also generate a very short aggregate signature. The performance analysis results show that our improved CLAS scheme is lower than the related CLAS schemes in terms of communication overhead and computation cost. [ABSTRACT FROM AUTHOR]

The accuracy and diversity of recommendation algorithms have always been the research hotspot of recommender systems. A good recommender system should not only have high accuracy and diversity, but also have adequate robustness against spammer attacks. However, the issue of recommendation robustness has received relatively little attention in the literature. In this paper, we systematically study the influences of different spammer behaviors on the recommendation results in various recommendation algorithms. We further propose an improved algorithm by incorporating the inner-similarity of user’s purchased items in the classic KNN approach. The new algorithm effectively enhances the robustness against spammer attacks and thus outperforms traditional algorithms in recommendation accuracy and diversity when spammers exist in the online commercial systems. [ABSTRACT FROM AUTHOR]

This paper describes an approach for improving the accuracy of memory-based collaborative filtering, based on the technique for order of preference by similarity to ideal solution (TOPSIS) method. Recommender systems are used to filter the huge amount of data available online based on user-defined preferences. Collaborative filtering (CF) is a commonly used recommendation approach that generates recommendations based on correlations among user preferences. Although several enhancements have increased the accuracy of memory-based CF through the development of improved similarity measures for finding successful neighbors, there has been less investigation into prediction score methods, in which rating/preference scores are assigned to items that have not yet been selected by a user. A TOPSIS solution for evaluating multiple alternatives based on more than one criterion is proposed as an alternative to prediction score methods for evaluating and ranking items based on the results from similar users. The recommendation accuracy of the proposed TOPSIS technique is evaluated by applying it to various common CF baseline methods, which are then used to analyze the MovieLens 100K and 1M benchmark datasets. The results show that CF based on the TOPSIS method is more accurate than baseline CF methods across a number of common evaluation metrics. [ABSTRACT FROM AUTHOR]

Advanced Metering Infrastructure (AMI) realizes a two-way communication of electricity data through by interconnecting with a computer network as the core component of the smart grid. Meanwhile, it brings many new security threats and the traditional intrusion detection method can’t satisfy the security requirements of AMI. In this paper, an intrusion detection system based on Online Sequence Extreme Learning Machine (OS-ELM) is established, which is used to detecting the attack in AMI and carrying out the comparative analysis with other algorithms. Simulation results show that, compared with other intrusion detection methods, intrusion detection method based on OS-ELM is more superior in detection speed and accuracy. [ABSTRACT FROM AUTHOR]

An understanding of how individuals shape and impact the evolution of society is vastly limited due to the unavailability of large-scale reliable datasets that can simultaneously capture information regarding individual movements and social interactions. We believe that the popular Indian film industry, “Bollywood”, can provide a social network apt for such a study. Bollywood provides massive amounts of real, unbiased data that spans more than 100 years, and hence this network has been used as a model for the present paper. The nodes which maintain a moderate degree or widely cooperate with the other nodes of the network tend to be more fit (measured as the success of the node in the industry) in comparison to the other nodes. The analysis carried forth in the current work, using a conjoined framework of complex network theory and random matrix theory, aims to quantify the elements that determine the fitness of an individual node and the factors that contribute to the robustness of a network. The authors of this paper believe that the method of study used in the current paper can be extended to study various other industries and organizations. [ABSTRACT FROM AUTHOR]

Modern computing architecture based on the separation of memory and processing leads to a well known problem called the von Neumann bottleneck, a restrictive limit on the data bandwidth between CPU and RAM. This paper introduces a new approach to computing we call AHaH computing where memory and processing are combined. The idea is based on the attractor dynamics of volatile dissipative electronics inspired by biological systems, presenting an attractive alternative architecture that is able to adapt, self-repair, and learn from interactions with the environment. We envision that both von Neumann and AHaH computing architectures will operate together on the same machine, but that the AHaH computing processor may reduce the power consumption and processing time for certain adaptive learning tasks by orders of magnitude. The paper begins by drawing a connection between the properties of volatility, thermodynamics, and Anti-Hebbian and Hebbian (AHaH) plasticity. We show how AHaH synaptic plasticity leads to attractor states that extract the independent components of applied data streams and how they form a computationally complete set of logic functions. After introducing a general memristive device model based on collections of metastable switches, we show how adaptive synaptic weights can be formed from differential pairs of incremental memristors. We also disclose how arrays of synaptic weights can be used to build a neural node circuit operating AHaH plasticity. By configuring the attractor states of the AHaH node in different ways, high level machine learning functions are demonstrated. This includes unsupervised clustering, supervised and unsupervised classification, complex signal prediction, unsupervised robotic actuation and combinatorial optimization of procedures–all key capabilities of biological nervous systems and modern machine learning algorithms with real world application. [ABSTRACT FROM AUTHOR]

Constraints arise naturally in many scientific experiments/studies such as in, epidemiology, biology, toxicology, etc. and often researchers ignore such information when analyzing their data and use standard methods such as the analysis of variance (ANOVA). Such methods may not only result in a loss of power and efficiency in costs of experimentation but also may result poor interpretation of the data. In this paper we discuss constrained statistical inference in the context of linear mixed effects models that arise naturally in many applications, such as in repeated measurements designs, familial studies and others. We introduce a novel methodology that is broadly applicable for a variety of constraints on the parameters. Since in many applications sample sizes are small and/or the data are not necessarily normally distributed and furthermore error variances need not be homoscedastic (i.e. heterogeneity in the data) we use an empirical best linear unbiased predictor (EBLUP) type residual based bootstrap methodology for deriving critical values of the proposed test. Our simulation studies suggest that the proposed procedure maintains the desired nominal Type I error while competing well with other tests in terms of power. We illustrate the proposed methodology by re-analyzing a clinical trial data on blood mercury level. The methodology introduced in this paper can be easily extended to other settings such as nonlinear and generalized regression models. [ABSTRACT FROM AUTHOR]

This paper examines a biologically-inspired representation technique designed for the support of sensory-motor learning in developmental robotics. An interesting feature of the many topographic neural sheets in the brain is that closely packed receptive fields must overlap in order to fully cover a spatial region. This raises interesting scientific questions with engineering implications: e.g. is overlap detrimental? does it have any benefits? This paper examines the effects and properties of overlap between elements arranged in arrays or maps. In particular we investigate how overlap affects the representation and transmission of spatial location information on and between topographic maps. Through a series of experiments we determine the conditions under which overlap offers advantages and identify useful ranges of overlap for building mappings in cognitive robotic systems. Our motivation is to understand the phenomena of overlap in order to provide guidance for application in sensory-motor learning robots. [ABSTRACT FROM AUTHOR]

In 1979 Haralick famously introduced a method for analyzing the texture of an image: a set of statistics extracted from the co-occurrence matrix. In this paper we investigate novel sets of texture descriptors extracted from the co-occurrence matrix; in addition, we compare and combine different strategies for extending these descriptors. The following approaches are compared: the standard approach proposed by Haralick, two methods that consider the co-occurrence matrix as a three-dimensional shape, a gray-level run-length set of features and the direct use of the co-occurrence matrix projected onto a lower dimensional subspace by principal component analysis. Texture descriptors are extracted from the co-occurrence matrix evaluated at multiple scales. Moreover, the descriptors are extracted not only from the entire co-occurrence matrix but also from subwindows. The resulting texture descriptors are used to train a support vector machine and ensembles. Results show that our novel extraction methods improve the performance of standard methods. We validate our approach across six medical datasets representing different image classification problems using the Wilcoxon signed rank test. The source code used for the approaches tested in this paper will be available at: http://www.dei.unipd.it/wdyn/?IDsezione=3314&IDgruppo_pass=124&preview=. [ABSTRACT FROM AUTHOR]

This paper proposed a novel bionic selective visual attention mechanism to quickly select regions that contain salient objects to reduce calculations. Firstly, lateral inhibition filtering, inspired by the limulus’ ommateum, is applied to filter low-frequency noises. After the filtering operation, we use Artificial Bee Colony (ABC) algorithm based selective visual attention mechanism to obtain the interested object to carry through the following recognition operation. In order to eliminate the camera motion influence, this paper adopted ABC algorithm, a new optimization method inspired by swarm intelligence, to calculate the motion salience map to integrate with conventional visual attention. To prove the feasibility and effectiveness of our method, several experiments were conducted. First the filtering results of lateral inhibition filter were shown to illustrate its noise reducing effect, then we applied the ABC algorithm to obtain the motion features of the image sequence. The ABC algorithm is proved to be more robust and effective through the comparison between ABC algorithm and popular Particle Swarm Optimization (PSO) algorithm. Except for the above results, we also compared the classic visual attention mechanism and our ABC algorithm based visual attention mechanism, and the experimental results of which further verified the effectiveness of our method. [ABSTRACT FROM AUTHOR]

In some large-scale face recognition task, such as driver license identification and law enforcement, the training set only contains one image per person. This situation is referred to as one sample problem. Because many face recognition techniques implicitly assume that several (at least two) images per person are available for training, they cannot deal with the one sample problem. This paper investigates principal component analysis (PCA), Fisher linear discriminant analysis (LDA), and locality preserving projections (LPP) and shows why they cannot perform well in one sample problem. After that, this paper presents four reasons that make one sample problem itself difficult: the small sample size problem; the lack of representative samples; the underestimated intra-class variation; and the overestimated inter-class variation. Based on the analysis, this paper proposes to enlarge the training set based on the inter-class relationship. This paper also extends LDA and LPP to extract features from the enlarged training set. The experimental results show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Distributed hash tables (DHTs) are usually used in the open networking environment, where they are vulnerable to Sybil attacks. Pebble-Rotating Game (PRG) mixes the nodes of the honest and the adversarial randomly, and can resist the Sybil attack efficiently. However, the adversary may have some tricks to corrupt the rule of PRG. This paper proposes a set of mechanisms to make the rule of PRG be obliged to obey. A new joining node must ask the Certificate Authority (CA) for its signature and certificate, which records the complete process on how a node joins the network and obtains the legitimacy of the node. Then, to prevent the adversary from accumulating identifiers, any node can make use of the latest certificate to judge whether one identifier is expired with the help of the replacement property of RPG. This paper analyzes in details the number of expired certificates which are needed to store in every node, and gives asymptotic solution of this problem. The analysis and simulations show that the mean number of the certificates stored in each node are , where n is the size of the network. [ABSTRACT FROM AUTHOR]

Identifying metaphorical language-use (e.g., sweet child) is one of the challenges facing natural language processing. This paper describes three novel algorithms for automatic metaphor identification. The algorithms are variations of the same core algorithm. We evaluate the algorithms on two corpora of Reuters and the New York Times articles. The paper presents the most comprehensive study of metaphor identification in terms of scope of metaphorical phrases and annotated corpora size. Algorithms’ performance in identifying linguistic phrases as metaphorical or literal has been compared to human judgment. Overall, the algorithms outperform the state-of-the-art algorithm with 71% precision and 27% averaged improvement in prediction over the base-rate of metaphors in the corpus. [ABSTRACT FROM AUTHOR]

: In computational science literature including, e.g., bioinformatics, computational statistics or machine learning, most published articles are devoted to the development of “new methods”, while comparison studies are generally appreciated by readers but surprisingly given poor consideration by many journals. This paper stresses the importance of neutral comparison studies for the objective evaluation of existing methods and the establishment of standards by drawing parallels with clinical research. The goal of the paper is twofold. Firstly, we present a survey of recent computational papers on supervised classification published in seven high-ranking computational science journals. The aim is to provide an up-to-date picture of current scientific practice with respect to the comparison of methods in both articles presenting new methods and articles focusing on the comparison study itself. Secondly, based on the results of our survey we critically discuss the necessity, impact and limitations of neutral comparison studies in computational sciences. We define three reasonable criteria a comparison study has to fulfill in order to be considered as neutral, and explicate general considerations on the individual components of a “tidy neutral comparison study”. R codes for completely replicating our statistical analyses and figures are available from the companion website http://www.ibe.med.uni-muenchen.de/organisation/mitarbeiter/020_professuren/boulesteix/plea2013. [ABSTRACT FROM AUTHOR]

One of the key aspects of computational systems biology is the investigation on the dynamic biological processes within cells. Computational models are often required to elucidate the mechanisms and principles driving the processes because of the nonlinearity and complexity. The models usually incorporate a set of parameters that signify the physical properties of the actual biological systems. In most cases, these parameters are estimated by fitting the model outputs with the corresponding experimental data. However, this is a challenging task because the available experimental data are frequently noisy and incomplete. In this paper, a new hybrid optimization method is proposed to estimate these parameters from the noisy and incomplete experimental data. The proposed method, called Swarm-based Chemical Reaction Optimization, integrates the evolutionary searching strategy employed by the Chemical Reaction Optimization, into the neighbouring searching strategy of the Firefly Algorithm method. The effectiveness of the method was evaluated using a simulated nonlinear model and two biological models: synthetic transcriptional oscillators, and extracellular protease production models. The results showed that the accuracy and computational speed of the proposed method were better than the existing Differential Evolution, Firefly Algorithm and Chemical Reaction Optimization methods. The reliability of the estimated parameters was statistically validated, which suggests that the model outputs produced by these parameters were valid even when noisy and incomplete experimental data were used. Additionally, Akaike Information Criterion was employed to evaluate the model selection, which highlighted the capability of the proposed method in choosing a plausible model based on the experimental data. In conclusion, this paper presents the effectiveness of the proposed method for parameter estimation and model selection problems using noisy and incomplete experimental data. This study is hoped to provide a new insight in developing more accurate and reliable biological models based on limited and low quality experimental data. [ABSTRACT FROM AUTHOR]

We live in an era of abundant data. This has necessitated the development of new and innovative statistical algorithms to get the most from experimental data. For example, faster algorithms make practical the analysis of larger genomic data sets, allowing us to extend the utility of cutting-edge statistical methods. We present a randomised algorithm that accelerates the clustering of time series data using the Bayesian Hierarchical Clustering (BHC) statistical method. BHC is a general method for clustering any discretely sampled time series data. In this paper we focus on a particular application to microarray gene expression data. We define and analyse the randomised algorithm, before presenting results on both synthetic and real biological data sets. We show that the randomised algorithm leads to substantial gains in speed with minimal loss in clustering quality. The randomised time series BHC algorithm is available as part of the R package BHC, which is available for download from Bioconductor (version 2.10 and above) via http://bioconductor.org/packages/2.10/bioc/html/BHC.html. We have also made available a set of R scripts which can be used to reproduce the analyses carried out in this paper. These are available from the following URL. https://sites.google.com/site/randomisedbhc/. [ABSTRACT FROM AUTHOR]

In this paper, we develop two automated authorship attribution schemes, one based on Multiple Discriminant Analysis (MDA) and the other based on a Support Vector Machine (SVM). The classification features we exploit are based on word frequencies in the text. We adopt an approach of preprocessing each text by stripping it of all characters except a-z and space. This is in order to increase the portability of the software to different types of texts. We test the methodology on a corpus of undisputed English texts, and use leave-one-out cross validation to demonstrate classification accuracies in excess of 90%. We further test our methods on the Federalist Papers, which have a partly disputed authorship and a fair degree of scholarly consensus. And finally, we apply our methodology to the question of the authorship of the Letter to the Hebrews by comparing it against a number of original Greek texts of known authorship. These tests identify where some of the limitations lie, motivating a number of open questions for future work. An open source implementation of our methodology is freely available for use at https://github.com/matthewberryman/author-detection. [ABSTRACT FROM AUTHOR]

Recommender systems are highly vulnerable to shilling attacks, both by individuals and groups. Attackers who introduce biased ratings in order to affect recommendations, have been shown to negatively affect collaborative filtering (CF) algorithms. Previous research focuses only on the differences between genuine profiles and attack profiles, ignoring the group characteristics in attack profiles. In this paper, we study the use of statistical metrics to detect rating patterns of attackers and group characteristics in attack profiles. Another question is that most existing detecting methods are model specific. Two metrics, Rating Deviation from Mean Agreement (RDMA) and Degree of Similarity with Top Neighbors (DegSim), are used for analyzing rating patterns between malicious profiles and genuine profiles in attack models. Building upon this, we also propose and evaluate a detection structure called RD-TIA for detecting shilling attacks in recommender systems using a statistical approach. In order to detect more complicated attack models, we propose a novel metric called DegSim’ based on DegSim. The experimental results show that our detection model based on target item analysis is an effective approach for detecting shilling attacks. [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization (PSO) is a meta-heuristic algorithm that has been shown to be successful in solving a wide variety of real and complicated optimization problems in engineering and computer science. This paper introduces a projection based PSO technique, named ProjPSO, to efficiently find different types of optimal designs, or nearly optimal designs, for mixture models with and without constraints on the components, and also for related models, like the log contrast models. We also compare the modified PSO performance with Fedorov's algorithm, a popular algorithm used to generate optimal designs, Cocktail algorithm, and the recent algorithm proposed by []. [ABSTRACT FROM AUTHOR]

A commonly used strategy to improve search accuracy is through feedback techniques. Most existing work on feedback relies on positive information, and has been extensively studied in information retrieval. However, when a query topic is difficult and the results from the first-pass retrieval are very poor, it is impossible to extract enough useful terms from a few positive documents. Therefore, the positive feedback strategy is incapable to improve retrieval in this situation. Contrarily, there is a relatively large number of negative documents in the top of the result list, and it has been confirmed that negative feedback strategy is an important and useful way for adapting this scenario by several recent studies. In this paper, we consider a scenario when the search results are so poor that there are at most three relevant documents in the top twenty documents. Then, we conduct a novel study of multiple strategies for relevance feedback using both positive and negative examples from the first-pass retrieval to improve retrieval accuracy for such difficult queries. Experimental results on these TREC collections show that the proposed language model based multiple model feedback method which is generally more effective than both the baseline method and the methods using only positive or negative model. [ABSTRACT FROM AUTHOR]

Pattern recognition and classification are two of the key topics in computer science. In this paper a novel method for the task of pattern classification is presented. The proposed method combines a hybrid associative classifier (Clasificador Híbrido Asociativo con Traslación, CHAT, in Spanish), a coding technique for output patterns called one-hot vector and majority voting during the classification step. The method is termed as CHAT One-Hot Majority (CHAT-OHM). The performance of the method is validated by comparing the accuracy of CHAT-OHM with other well-known classification algorithms. During the experimental phase, the classifier was applied to four datasets related to the medical field. The results also show that the proposed method outperforms the original CHAT classification accuracy. [ABSTRACT FROM AUTHOR]

Protein-Protein Interaction (PPI) extraction is an important task in the biomedical information extraction. Presently, many machine learning methods for PPI extraction have achieved promising results. However, the performance is still not satisfactory. One reason is that the semantic resources were basically ignored. In this paper, we propose a multiple-kernel learning-based approach to extract PPIs, combining the feature-based kernel, tree kernel and semantic kernel. Particularly, we extend the shortest path-enclosed tree kernel (SPT) by a dynamic extended strategy to retrieve the richer syntactic information. Our semantic kernel calculates the protein-protein pair similarity and the context similarity based on two semantic resources: WordNet and Medical Subject Heading (MeSH). We evaluate our method with Support Vector Machine (SVM) and achieve an F-score of 69.40% and an AUC of 92.00%, which show that our method outperforms most of the state-of-the-art systems by integrating semantic information. [ABSTRACT FROM AUTHOR]

The Student's-t mixture model, which is heavily tailed and more robust than the Gaussian mixture model, has recently received great attention on image processing. In this paper, we propose a robust non-rigid point set registration algorithm using the Student's-t mixture model. Specifically, first, we consider the alignment of two point sets as a probability density estimation problem and treat one point set as Student's-t mixture model centroids. Then, we fit the Student's-t mixture model centroids to the other point set which is treated as data. Finally, we get the closed-form solutions of registration parameters, leading to a computationally efficient registration algorithm. The proposed algorithm is especially effective for addressing the non-rigid point set registration problem when significant amounts of noise and outliers are present. Moreover, less registration parameters have to be set manually for our algorithm compared to the popular coherent points drift (CPD) algorithm. We have compared our algorithm with other state-of-the-art registration algorithms on both 2D and 3D data with noise and outliers, where our non-rigid registration algorithm showed accurate results and outperformed the other algorithms. [ABSTRACT FROM AUTHOR]

In this paper, based on the gravity principle of classical physics, we propose a tunable gravity-based model, which considers tag usage pattern to weigh both the mass and distance of network nodes. We then apply this model in solving the problems of information filtering and network evolving. Experimental results on two real-world data sets, Del.icio.us and MovieLens, show that it can not only enhance the algorithmic performance, but can also better characterize the properties of real networks. This work may shed some light on the in-depth understanding of the effect of gravity model. [ABSTRACT FROM AUTHOR]

Variation of streamflow and sediment load in the Yellow River basin has received considerable attention due to its drastic reduction during the past several decades. This paper presents a detailed investigation on the changes of streamflow and sediment load from 1952 to 2011 using monthly observations at four gauging stations along the Yellow River. The results show significant decreasing trends for both streamflow and sediment load at all four gauging stations over the past 60 years. The wavelet transform demonstrated discontinuous periodicities from 1969 to 1973 and after 1986 due to the construction of large reservoirs and implementation of numerous soil and water conservations practices. The sediment rating curves with the power-law function was applied to investigate the relationship between discharge and sediment load. The results indicate distinct variations of the relationship between streamflow and sediment and implied significant hydro-morphological changes within different periods. The reducing sediment supply from the source region and the increased erosive power of the river are detected at Lanzhou station, while the decrease of the transport capacity at Toudaoguai is caused by severe siltation. Significant changes in the relationship between streamflow and sediment load are found at Huayuankou and Gaocun stations, which are largely induced by evident sediment income and trapping effects of large reservoirs. It is estimated that numerous reservoirs have strongly altered the regime and magnitude of streamflow and trapped large amount of sediment, leading to severe siltation and evident reduction of their total volumes. A decrease in precipitation, incoming water from the upper reaches, soil and water conservation measures as well as water consumption contribute most to the significant reduction of streamflow. The decrease of sediment load mainly resulted from various soil and water conservation measures and trapping in reservoirs from 1986 to 2011. [ABSTRACT FROM AUTHOR]

Time-course gene expression datasets, which record continuous biological processes of genes, have recently been used to predict gene function. However, only few positive genes can be obtained from annotation databases, such as gene ontology (GO). To obtain more useful information and effectively predict gene function, gene annotations are clustered together to form a learnable and effective learning system. In this paper, we propose a novel multi-instance hierarchical clustering (MIHC) method to establish a learning system by clustering GO and compare this method with other learning system establishment methods. Multi-label support vector machine classifier and multi-label K-nearest neighbor classifier are used to verify these methods in four yeast time-course gene expression datasets. The MIHC method shows good performance, which serves as a guide to annotators or refines the annotation in detail. [ABSTRACT FROM AUTHOR]

Numerous digitization and ontological initiatives have focused on translating biological knowledge from narrative text to machine-readable formats. In this paper, we describe two workflows for knowledge extraction and semantic annotation of text data objects featured in an online biodiversity aggregator, the Encyclopedia of Life. One workflow tags text with DBpedia URIs based on keywords. Another workflow finds taxon names in text using GNRD for the purpose of building a species association network. Both workflows work well: the annotation workflow has an F1 Score of 0.941 and the association algorithm has an F1 Score of 0.885. Existing text annotators such as Terminizer and DBpedia Spotlight performed well, but require some optimization to be useful in the ecology and evolution domain. Important future work includes scaling up and improving accuracy through the use of distributional semantics. [ABSTRACT FROM AUTHOR]

Protein subcellular localization prediction, as an essential step to elucidate the functions in vivo of proteins and identify drugs targets, has been extensively studied in previous decades. Instead of only determining subcellular localization of single-label proteins, recent studies have focused on predicting both single- and multi-location proteins. Computational methods based on Gene Ontology (GO) have been demonstrated to be superior to methods based on other features. However, existing GO-based methods focus on the occurrences of GO terms and disregard their relationships. This paper proposes a multi-label subcellular-localization predictor, namely HybridGO-Loc, that leverages not only the GO term occurrences but also the inter-term relationships. This is achieved by hybridizing the GO frequencies of occurrences and the semantic similarity between GO terms. Given a protein, a set of GO terms are retrieved by searching against the gene ontology database, using the accession numbers of homologous proteins obtained via BLAST search as the keys. The frequency of GO occurrences and semantic similarity (SS) between GO terms are used to formulate frequency vectors and semantic similarity vectors, respectively, which are subsequently hybridized to construct fusion vectors. An adaptive-decision based multi-label support vector machine (SVM) classifier is proposed to classify the fusion vectors. Experimental results based on recent benchmark datasets and a new dataset containing novel proteins show that the proposed hybrid-feature predictor significantly outperforms predictors based on individual GO features as well as other state-of-the-art predictors. For readers' convenience, the HybridGO-Loc server, which is for predicting virus or plant proteins, is available online at http://bioinfo.eie.polyu.edu.hk/HybridGoServer/. [ABSTRACT FROM AUTHOR]

Hundreds of millions of figures are available in biomedical literature, representing important biomedical experimental evidence. This ever-increasing sheer volume has made it difficult for scientists to effectively and accurately access figures of their interest, the process of which is crucial for validating research facts and for formulating or testing novel research hypotheses. Current figure search applications can't fully meet this challenge as the “bag of figures” assumption doesn't take into account the relationship among figures. In our previous study, hundreds of biomedical researchers have annotated articles in which they serve as corresponding authors. They ranked each figure in their paper based on a figure's importance at their discretion, referred to as “figure ranking”. Using this collection of annotated data, we investigated computational approaches to automatically rank figures. We exploited and extended the state-of-the-art listwise learning-to-rank algorithms and developed a new supervised-learning model BioFigRank. The cross-validation results show that BioFigRank yielded the best performance compared with other state-of-the-art computational models, and the greedy feature selection can further boost the ranking performance significantly. Furthermore, we carry out the evaluation by comparing BioFigRank with three-level competitive domain-specific human experts: (1) First Author, (2) Non-Author-In-Domain-Expert who is not the author nor co-author of an article but who works in the same field of the corresponding author of the article, and (3) Non-Author-Out-Domain-Expert who is not the author nor co-author of an article and who may or may not work in the same field of the corresponding author of an article. Our results show that BioFigRank outperforms Non-Author-Out-Domain-Expert and performs as well as Non-Author-In-Domain-Expert. Although BioFigRank underperforms First Author, since most biomedical researchers are either in- or out-domain-experts for an article, we conclude that BioFigRank represents an artificial intelligence system that offers expert-level intelligence to help biomedical researchers to navigate increasingly proliferated big data efficiently. [ABSTRACT FROM AUTHOR]

The number of available algorithms to infer a biological network from a dataset of high-throughput measurements is overwhelming and keeps growing. However, evaluating their performance is unfeasible unless a ‘gold standard’ is available to measure how close the reconstructed network is to the ground truth. One measure of this is the stability of these predictions to data resampling approaches. We introduce NetSI, a family of Network Stability Indicators, to assess quantitatively the stability of a reconstructed network in terms of inference variability due to data subsampling. In order to evaluate network stability, the main NetSI methods use a global/local network metric in combination with a resampling (bootstrap or cross-validation) procedure. In addition, we provide two normalized variability scores over data resampling to measure edge weight stability and node degree stability, and then introduce a stability ranking for edges and nodes. A complete implementation of the NetSI indicators, including the Hamming-Ipsen-Mikhailov (HIM) network distance adopted in this paper is available with the R package nettools. We demonstrate the use of the NetSI family by measuring network stability on four datasets against alternative network reconstruction methods. First, the effect of sample size on stability of inferred networks is studied in a gold standard framework on yeast-like data from the Gene Net Weaver simulator. We also consider the impact of varying modularity on a set of structurally different networks (50 nodes, from 2 to 10 modules), and then of complex feature covariance structure, showing the different behaviours of standard reconstruction methods based on Pearson correlation, Maximum Information Coefficient (MIC) and False Discovery Rate (FDR) strategy. Finally, we demonstrate a strong combined effect of different reconstruction methods and phenotype subgroups on a hepatocellular carcinoma miRNA microarray dataset (240 subjects), and we validate the analysis on a second dataset (166 subjects) with good reproducibility. [ABSTRACT FROM AUTHOR]

Multiple sequence alignment is a crucial task in a number of biological analyses like secondary structure prediction, domain searching, phylogeny, etc. MSAProbs is currently the most accurate alignment algorithm, but its effectiveness is obtained at the expense of computational time. In the paper we present QuickProbs, the variant of MSAProbs customised for graphics processors. We selected the two most time consuming stages of MSAProbs to be redesigned for GPU execution: the posterior matrices calculation and the consistency transformation. Experiments on three popular benchmarks (BAliBASE, PREFAB, OXBench-X) on quad-core PC equipped with high-end graphics card show QuickProbs to be 5.7 to 9.7 times faster than original CPU-parallel MSAProbs. Additional tests performed on several protein families from Pfam database give overall speed-up of 6.7. Compared to other algorithms like MAFFT, MUSCLE, or ClustalW, QuickProbs proved to be much more accurate at similar speed. Additionally we introduce a tuned variant of QuickProbs which is significantly more accurate on sets of distantly related sequences than MSAProbs without exceeding its computation time. The GPU part of QuickProbs was implemented in OpenCL, thus the package is suitable for graphics processors produced by all major vendors. [ABSTRACT FROM AUTHOR]

Using statistical textons for texture classification has shown great success recently. The maximal response 8 (Statistical_MR8), image patch (Statistical_Joint) and locally invariant fractal (Statistical_Fractal) are typical statistical texton algorithms and state-of-the-art texture classification methods. However, there are two limitations when using these methods. First, it needs a training stage to build a texton library, thus the recognition accuracy will be highly depended on the training samples; second, during feature extraction, local feature is assigned to a texton by searching for the nearest texton in the whole library, which is time consuming when the library size is big and the dimension of feature is high. To address the above two issues, in this paper, three binary texton counterpart methods were proposed, Binary_MR8, Binary_Joint, and Binary_Fractal. These methods do not require any training step but encode local feature into binary representation directly. The experimental results on the CUReT, UIUC and KTH-TIPS databases show that binary texton could get sound results with fast feature extraction, especially when the image size is not big and the quality of image is not poor. [ABSTRACT FROM AUTHOR]

The clinical notes in a given patient record contain much redundancy, in large part due to clinicians’ documentation habit of copying from previous notes in the record and pasting into a new note. Previous work has shown that this redundancy has a negative impact on the quality of text mining and topic modeling in particular. In this paper we describe a novel variant of Latent Dirichlet Allocation (LDA) topic modeling, Red-LDA, which takes into account the inherent redundancy of patient records when modeling content of clinical notes. To assess the value of Red-LDA, we experiment with three baselines and our novel redundancy-aware topic modeling method: given a large collection of patient records, (i) apply vanilla LDA to all documents in all input records; (ii) identify and remove all redundancy by chosing a single representative document for each record as input to LDA; (iii) identify and remove all redundant paragraphs in each record, leaving partial, non-redundant documents as input to LDA; and (iv) apply Red-LDA to all documents in all input records. Both quantitative evaluation carried out through log-likelihood on held-out data and topic coherence of produced topics and qualitative assessement of topics carried out by physicians show that Red-LDA produces superior models to all three baseline strategies. This research contributes to the emerging field of understanding the characteristics of the electronic health record and how to account for them in the framework of data mining. The code for the two redundancy-elimination baselines and Red-LDA is made publicly available to the community. [ABSTRACT FROM AUTHOR]

De novo sequencing is an important computational approach to determining the amino acid sequence of a peptide with tandem mass spectrometry (MS/MS). Most of the existing approaches use a graph model to describe a spectrum and the sequencing is performed by computing the longest antisymmetric path in the graph. The task is often computationally intensive since a given MS/MS spectrum often contains noisy data, missing mass peaks, or post translational modifications/mutations. This paper develops a new parameterized algorithm that can efficiently compute the longest antisymmetric partial path in an extended spectrum graph that is of bounded path width. Our testing results show that this algorithm can efficiently process experimental spectra and provide sequencing results of high accuracy. [ABSTRACT FROM AUTHOR]

Burn scar extraction using remote sensing data is an efficient way to precisely evaluate burn area and measure vegetation recovery. Traditional burn scar extraction methodologies have no well effect on burn scar image with blurred and irregular edges. To address these issues, this paper proposes an automatic method to extract burn scar based on Level Set Method (LSM). This method utilizes the advantages of the different features in remote sensing images, as well as considers the practical needs of extracting the burn scar rapidly and automatically. This approach integrates Change Vector Analysis (CVA), Normalized Difference Vegetation Index (NDVI) and the Normalized Burn Ratio (NBR) to obtain difference image and modifies conventional Level Set Method Chan-Vese (C-V) model with a new initial curve which results from a binary image applying K-means method on fitting errors of two near-infrared band images. Landsat 5 TM and Landsat 8 OLI data sets are used to validate the proposed method. Comparison with conventional C-V model, OSTU algorithm, Fuzzy C-mean (FCM) algorithm are made to show that the proposed approach can extract the outline curve of fire burn scar effectively and exactly. The method has higher extraction accuracy and less algorithm complexity than that of the conventional C-V model. [ABSTRACT FROM AUTHOR]

Disease module is a group of molecular components that interact intensively in the disease specific biological network. Since the connectivity and activity of disease modules may shed light on the molecular mechanisms of pathogenesis and disease progression, their identification becomes one of the most important challenges in network medicine, an emerging paradigm to study complex human disease. This paper proposes a novel algorithm, DiME (Disease Module Extraction), to identify putative disease modules from biological networks. We have developed novel heuristics to optimise Community Extraction, a module criterion originally proposed for social network analysis, to extract topological core modules from biological networks as putative disease modules. In addition, we have incorporated a statistical significance measure, B-score, to evaluate the quality of extracted modules. As an application to complex diseases, we have employed DiME to investigate the molecular mechanisms that underpin the progression of glioma, the most common type of brain tumour. We have built low (grade II) - and high (GBM) - grade glioma co-expression networks from three independent datasets and then applied DiME to extract potential disease modules from both networks for comparison. Examination of the interconnectivity of the identified modules have revealed changes in topology and module activity (expression) between low- and high- grade tumours, which are characteristic of the major shifts in the constitution and physiology of tumour cells during glioma progression. Our results suggest that transcription factors E2F4, AR and ETS1 are potential key regulators in tumour progression. Our DiME compiled software, R/C++ source code, sample data and a tutorial are available at http://www.cs.bham.ac.uk/~szh/DiME. [ABSTRACT FROM AUTHOR]

: Prediction and classification techniques have been well studied by machine learning researchers and developed for several real-word problems. However, the level of acceptance and success of prediction models are still below expectation due to some difficulties such as the low performance of prediction models when they are applied in different environments. Such a problem has been addressed by many researchers, mainly from the machine learning community. A second problem, principally raised by model users in different communities, such as managers, economists, engineers, biologists, and medical practitioners, etc., is the prediction models’ interpretability. The latter is the ability of a model to explain its predictions and exhibit the causality relationships between the inputs and the outputs. In the case of classification, a successful way to alleviate the low performance is to use ensemble classiers. It is an intuitive strategy to activate collaboration between different classifiers towards a better performance than individual classier. Unfortunately, ensemble classifiers method do not take into account the interpretability of the final classification outcome. It even worsens the original interpretability of the individual classifiers. In this paper we propose a novel implementation of classifiers combination approach that does not only promote the overall performance but also preserves the interpretability of the resulting model. We propose a solution based on Ant Colony Optimization and tailored for the case of Bayesian classifiers. We validate our proposed solution with case studies from medical domain namely, heart disease and Cardiotography-based predictions, problems where interpretability is critical to make appropriate clinical decisions. Availability: The datasets, Prediction Models and software tool together with supplementary materials are available at http://faculty.uaeu.ac.ae/salahb/ACO4BC.htm. [ABSTRACT FROM AUTHOR]

Increasing evidence has indicated that long non-coding RNAs (lncRNAs) are implicated in and associated with many complex human diseases. Despite of the accumulation of lncRNA-disease associations, only a few studies had studied the roles of these associations in pathogenesis. In this paper, we investigated lncRNA-disease associations from a network view to understand the contribution of these lncRNAs to complex diseases. Specifically, we studied both the properties of the diseases in which the lncRNAs were implicated, and that of the lncRNAs associated with complex diseases. Regarding the fact that protein coding genes and lncRNAs are involved in human diseases, we constructed a coding-non-coding gene-disease bipartite network based on known associations between diseases and disease-causing genes. We then applied a propagation algorithm to uncover the hidden lncRNA-disease associations in this network. The algorithm was evaluated by leave-one-out cross validation on 103 diseases in which at least two genes were known to be involved, and achieved an AUC of 0.7881. Our algorithm successfully predicted 768 potential lncRNA-disease associations between 66 lncRNAs and 193 diseases. Furthermore, our results for Alzheimer's disease, pancreatic cancer, and gastric cancer were verified by other independent studies. [ABSTRACT FROM AUTHOR]

The majority of next-generation sequencing short-reads can be properly aligned by leading aligners at high speed. However, the alignment quality can still be further improved, since usually not all reads can be correctly aligned to large genomes, such as the human genome, even for simulated data. Moreover, even slight improvements in this area are important but challenging, and usually require significantly more computational endeavor. In this paper, we present CUSHAW3, an open-source parallelized, sensitive and accurate short-read aligner for both base-space and color-space sequences. In this aligner, we have investigated a hybrid seeding approach to improve alignment quality, which incorporates three different seed types, i.e. maximal exact match seeds, exact-match k-mer seeds and variable-length seeds, into the alignment pipeline. Furthermore, three techniques: weighted seed-pairing heuristic, paired-end alignment pair ranking and read mate rescuing have been conceived to facilitate accurate paired-end alignment. For base-space alignment, we have compared CUSHAW3 to Novoalign, CUSHAW2, BWA-MEM, Bowtie2 and GEM, by aligning both simulated and real reads to the human genome. The results show that CUSHAW3 consistently outperforms CUSHAW2, BWA-MEM, Bowtie2 and GEM in terms of single-end and paired-end alignment. Furthermore, our aligner has demonstrated better paired-end alignment performance than Novoalign for short-reads with high error rates. For color-space alignment, CUSHAW3 is consistently one of the best aligners compared to SHRiMP2 and BFAST. The source code of CUSHAW3 and all simulated data are available at http://cushaw3.sourceforge.net. [ABSTRACT FROM AUTHOR]

With the proliferation of social networks and blogs, the Internet is increasingly being used to disseminate personal health information rather than just as a source of information. In this paper we exploit the wealth of user-generated data, available through the micro-blogging service Twitter, to estimate and track the incidence of health conditions in society. The method is based on two stages: we start by extracting possibly relevant tweets using a set of specially crafted regular expressions, and then classify these initial messages using machine learning methods. Furthermore, we selected relevant features to improve the results and the execution times. To test the method, we considered four health states or conditions, namely flu, depression, pregnancy and eating disorders, and two locations, Portugal and Spain. We present the results obtained and demonstrate that the detection results and the performance of the method are improved after feature selection. The results are promising, with areas under the receiver operating characteristic curve between 0.7 and 0.9, and f-measure values around 0.8 and 0.9. This fact indicates that such approach provides a feasible solution for measuring and tracking the evolution of health states within the society. [ABSTRACT FROM AUTHOR]

Posture segmentation plays an essential role in human motion analysis. The state-of-the-art method extracts sufficiently high-dimensional features from 3D depth images for each 3D point and learns an efficient body part classifier. However, high-dimensional features are memory-consuming and difficult to handle on large-scale training dataset. In this paper, we propose an efficient two-stage dimension reduction scheme, termed biview learning, to encode two independent views which are depth-difference features (DDF) and relative position features (RPF). Biview learning explores the complementary property of DDF and RPF, and uses two stages to learn a compact yet comprehensive low-dimensional feature space for posture segmentation. In the first stage, discriminative locality alignment (DLA) is applied to the high-dimensional DDF to learn a discriminative low-dimensional representation. In the second stage, canonical correlation analysis (CCA) is used to explore the complementary property of RPF and the dimensionality reduced DDF. Finally, we train a support vector machine (SVM) over the output of CCA. We carefully validate the effectiveness of DLA and CCA utilized in the two-stage scheme on our 3D human points cloud dataset. Experimental results show that the proposed biview learning scheme significantly outperforms the state-of-the-art method for human posture segmentation. [ABSTRACT FROM AUTHOR]

Purpose: This paper describes a novel method to automatically segment the human brainstem into midbrain and pons, called LABS: Landmark-based Automated Brainstem Segmentation. LABS processes high-resolution structural magnetic resonance images (MRIs) according to a revised landmark-based approach integrated with a thresholding method, without manual interaction. Methods: This method was first tested on morphological T1-weighted MRIs of 30 healthy subjects. Its reliability was further confirmed by including neurological patients (with Alzheimer's Disease) from the ADNI repository, in whom the presence of volumetric loss within the brainstem had been previously described. Segmentation accuracies were evaluated against expert-drawn manual delineation. To evaluate the quality of LABS segmentation we used volumetric, spatial overlap and distance-based metrics. Results: The comparison between the quantitative measurements provided by LABS against manual segmentations revealed excellent results in healthy controls when considering either the midbrain (DICE measures higher that 0.9; Volume ratio around 1 and Hausdorff distance around 3) or the pons (DICE measures around 0.93; Volume ratio ranging 1.024–1.05 and Hausdorff distance around 2). Similar performances were detected for AD patients considering segmentation of the pons (DICE measures higher that 0.93; Volume ratio ranging from 0.97–0.98 and Hausdorff distance ranging 1.07–1.33), while LABS performed lower for the midbrain (DICE measures ranging 0.86–0.88; Volume ratio around 0.95 and Hausdorff distance ranging 1.71–2.15). Conclusions: Our study represents the first attempt to validate a new fully automated method for in vivo segmentation of two anatomically complex brainstem subregions. We retain that our method might represent a useful tool for future applications in clinical practice. [ABSTRACT FROM AUTHOR]

A synchrotron X-ray microscope is a powerful imaging apparatus for taking high-resolution and high-contrast X-ray images of nanoscale objects. A sufficient number of X-ray projection images from different angles is required for constructing 3D volume images of an object. Because a synchrotron light source is immobile, a rotational object holder is required for tomography. At a resolution of 10 nm per pixel, the vibration of the holder caused by rotating the object cannot be disregarded if tomographic images are to be reconstructed accurately. This paper presents a computer method to compensate for the vibration of the rotational holder by aligning neighboring X-ray images. This alignment process involves two steps. The first step is to match the “projected feature points” in the sequence of images. The matched projected feature points in the - plane should form a set of sine-shaped loci. The second step is to fit the loci to a set of sine waves to compute the parameters required for alignment. The experimental results show that the proposed method outperforms two previously proposed methods, Xradia and SPIDER. The developed software system can be downloaded from the URL, http://www.cs.nctu.edu.tw/~chengchc/SCTA or http://goo.gl/s4AMx. [ABSTRACT FROM AUTHOR]

Image encryption is an important and effective technique to protect image security. In this paper, a novel image encryption algorithm combining Julia sets and Hilbert curves is proposed. The algorithm utilizes Julia sets’ parameters to generate a random sequence as the initial keys and gets the final encryption keys by scrambling the initial keys through the Hilbert curve. The final cipher image is obtained by modulo arithmetic and diffuse operation. In this method, it needs only a few parameters for the key generation, which greatly reduces the storage space. Moreover, because of the Julia sets’ properties, such as infiniteness and chaotic characteristics, the keys have high sensitivity even to a tiny perturbation. The experimental results indicate that the algorithm has large key space, good statistical property, high sensitivity for the keys, and effective resistance to the chosen-plaintext attack. [ABSTRACT FROM AUTHOR]

The part-based method has been a fast rising framework for object detection. It is attracting more and more attention for its detection precision and partial robustness to the occlusion. However, little research has been focused on the problem of occlusion overlapping of the part regions, which can reduce the performance of the system. This paper proposes a part-based probabilistic model and the corresponding inference algorithm for the problem of the part occlusion. The model is based on the Bayesian theory integrally and aims to be robust to the large occlusion. In the stage of the model construction, all of the parts constitute the vertex set of a fully connected graph, and a binary variable is assigned to each part to indicate its occlusion status. In addition, we introduce a penalty term to regularize the argument space of the objective function. Thus, the part detection is formulated as an optimization problem, which is divided into two alternative procedures: the outer inference and the inner inference. A stochastic tentative method is employed in the outer inference to determine the occlusion status for each part. In the inner inference, the gradient descent algorithm is employed to find the optimal positions of the parts, in term of the current occlusion status. Experiments were carried out on the Caltech database. The results demonstrated that the proposed method achieves a strong robustness to the occlusion. [ABSTRACT FROM AUTHOR]

In this paper, a numerical method for the solution of a strongly coupled reaction-diffusion system, with suitable initial and Neumann boundary conditions, by using cubic B-spline collocation scheme on a uniform grid is presented. The scheme is based on the usual finite difference scheme to discretize the time derivative while cubic B-spline is used as an interpolation function in the space dimension. The scheme is shown to be unconditionally stable using the von Neumann method. The accuracy of the proposed scheme is demonstrated by applying it on a test problem. The performance of this scheme is shown by computing and error norms for different time levels. The numerical results are found to be in good agreement with known exact solutions. [ABSTRACT FROM AUTHOR]

Automatic text categorization is one of the key techniques in information retrieval and the data mining field. The classification is usually time-consuming when the training dataset is large and high-dimensional. Many methods have been proposed to solve this problem, but few can achieve satisfactory efficiency. In this paper, we present a method which combines the Latent Dirichlet Allocation (LDA) algorithm and the Support Vector Machine (SVM). LDA is first used to generate reduced dimensional representation of topics as feature in VSM. It is able to reduce features dramatically but keeps the necessary semantic information. The Support Vector Machine (SVM) is then employed to classify the data based on the generated features. We evaluate the algorithm on 20 Newsgroups and Reuters-21578 datasets, respectively. The experimental results show that the classification based on our proposed LDA+SVM model achieves high performance in terms of precision, recall and F1 measure. Further, it can achieve this within a much shorter time-frame. Our process improves greatly upon the previous work in this field and displays strong potential to achieve a streamlined classification process for a wide range of applications. [ABSTRACT FROM AUTHOR]

Two-way selection is a common phenomenon in nature and society. It appears in the processes like choosing a mate between men and women, making contracts between job hunters and recruiters, and trading between buyers and sellers. In this paper, we propose a model of two-way selection system, and present its analytical solution for the expectation of successful matching total and the regular pattern that the matching rate trends toward an inverse proportion to either the ratio between the two sides or the ratio of the state total to the smaller group's people number. The proposed model is verified by empirical data of the matchmaking fairs. Results indicate that the model well predicts this typical real-world two-way selection behavior to the bounded error extent, thus it is helpful for understanding the dynamics mechanism of the real-world two-way selection system. [ABSTRACT FROM AUTHOR]