Metabonomic analysis of hepatitis B virus-induced liver failure:identification of potential diagnostic biomarkers by fuzzy support vector machine

Hepatitis B virus （HBV）-induced liver failure is an emergent liver disease leading to high mortality. The severity of liver failure may be reflected by the profile of some metabolites. This study assessed the potential of using metabolites as biomarkers for liver failure by identifying metabolites with good discriminative performance for its phenotype. The serum samples from 24 HBV-indueed liver failure patients and 23 healthy volunteers were collected and analyzed by gas chromatography-mass spectrometry （GC-MS） to generate metabolite profiles. The 24 patients were further grouped into two classes according to the severity of liver failure. Twenty-five eommensal peaks in all metabolite profiles were extracted, and the relative area values of these peaks were used as features for each sample. Three algorithms, F-test, k-nearest neighbor （KNN） and fuzzy support vector machine （FSVM） combined with exhaustive search （ES）, were employed to identify a subset of metabolites （biomarkers） that best predict liver failure. Based on the achieved experimental dataset, 93.62% predictive accuracy by 6 features was selected with FSVM-ES and three key metabolites, glyeerie acid, cis-aeonitie acid and citric acid, are identified as potential diagnostic biomarkers.

Optimal Structural Design of the Midship of a VLCC Based on the Strategy Integrating SVM and GA

In this paper a hybrid process of modeling and optimization, which integrates a support vector machine （SVM） and genetic algorithm （GA）, was introduced to reduce the high time cost in structural optimization of ships. SVM, which is rooted in statistical learning theory and an approximate implementation of the method of structural risk minimization, can provide a good generalization performance in metamodeling the input-output relationship of real problems and consequently cuts down on high time cost in the analysis of real problems, such as FEM analysis. The GA, as a powerful optimization technique, possesses remarkable advantages for the problems that can hardly be optimized with common gradient-based optimization methods, which makes it suitable for optimizing models built by SVM. Based on the SVM-GA strategy, optimization of structural scantlings in the midship of a very large crude carrier （VLCC） ship was carried out according to the direct strength assessment method in common structural rules （CSR）, which eventually demonstrates the high efficiency of SVM-GA in optimizing the ship structural scantlings under heavy computational complexity. The time cost of this optimization with SVM-GA has been sharply reduced, many more loops have been processed within a small amount of time and the design has been improved remarkably.

Improving MapReduce Performance by Balancing Skewed Loads

MapReduce has emerged as a popular computing model used in datacenters to process large amount of datasets.In the map phase,hash partitioning is employed to distribute data that sharing the same key across data center-scale cluster nodes.However,we observe that this approach can lead to uneven data distribution,which can result in skewed loads among reduce tasks,thus hamper performance of MapReduce systems.Moreover,worker nodes in MapReduce systems may differ in computing capability due to(1) multiple generations of hardware in non-virtualized data centers,or(2) co-location of virtual machines in virtualized data centers.The heterogeneity among cluster nodes exacerbates the negative effects of uneven data distribution.To improve MapReduce performance in heterogeneous clusters,we propose a novel load balancing approach in the reduce phase.This approach consists of two components:(1) performance prediction for reducers that run on heterogeneous nodes based on support vector machines models,and(2) heterogeneity-aware partitioning(HAP),which balances skewed data for reduce tasks.We implement this approach as a plug-in in current MapReduce system.Experimental results demonstrate that our proposed approach distributes work evenly among reduce tasks,and improves MapReduce performance with little overhead.

Fingerprint singular points extraction based on orientation tensor field and Laurent series

Singular point(SP)extraction is a key component in automatic fingerprint identification system(AFIS).A new method was proposed for fingerprint singular points extraction,based on orientation tensor field and Laurent series.First,fingerprint orientation flow field was obtained,using the gradient of fingerprint image.With these gradients,fingerprint orientation tensor field was calculated.Then,candidate SPs were detected by the cross-correlation energy in multi-scale Gaussian space.The energy was calculated between fingerprint orientation tensor field and Laurent polynomial model.As a global descriptor,the Laurent polynomial coefficients were allowed for rotational invariance.Furthermore,a support vector machine(SVM)classifier was trained to remove spurious SPs,using cross-correlation coefficient as a feature vector.Finally,experiments were performed on Singular Point Detection Competition 2010(SPD2010)database.Compared to the winner algorithm of SPD2010 which has best accuracy of 31.90%,the accuracy of proposed algorithm is 45.34%.The results show that the proposed method outperforms the state-of-the-art detection algorithms by large margin,and the detection is invariant to rotational transformations.

Reservoir prediction using multi-wave seismic attributes

The main problems in seismic attribute technology are the redundancy of data and the uncertainty of attributes, and these problems become much more serious in multi-wave seismic exploration. Data redundancy will increase the burden on interpreters, occupy large computer memory, take much more computing time, conceal the effective information, and especially cause the ＂curse of dimension＂. Uncertainty of attributes will reduce the accuracy of rebuilding the relationship between attributes and geological significance. In order to solve these problems, we study methods of principal component analysis （PCA）, independent component analysis （ICA） for attribute optimization and support vector machine （SVM） for reservoir prediction. We propose a flow chart of multi-wave seismic attribute process and further apply it to multi-wave seismic reservoir prediction. The processing results of real seismic data demonstrate that reservoir prediction based on combination of PP- and PS-wave attributes, compared with that based on traditional PP-wave attributes, can improve the prediction accuracy.

Adaptive associative classification with emerging frequent patterns

In this paper, we propose an enhanced associative classification method by integrating the dynamic property in the process of associative classification. In the proposed method, we employ a support vector machine（SVM） based method to refine the discovered emerging ~equent patterns for classification rule extension for class label prediction. The empirical study shows that our method can be used to classify increasing resources efficiently and effectively.

Application of complete ensemble intrinsic time-scale decomposition and least-square SVM optimized using hybrid DE and PSO to fault diagnosis of diesel engines

Targeting the mode-mixing problem of intrinsic time-scale decomposition （ITD） and the parameter optimization problem of least-square support vector machine （LSSVM）, we propose a novel approach based on complete ensemble intrinsic time-scale decomposition （CEITD） and LSSVM optimized by the hybrid differential evolution and particle swarm optimization （HDEPSO） algorithm for the identification of the fault in a diesel engine. The approach consists mainly of three stages. First, to solve the mode-mixing problem of ITD, a novel CEITD method is proposed. Then the CEITD method is used to decompose the nonstationary vibration signal into a set of stationary proper rotation components （PRCs） and a residual signal. Second, three typical types of time-frequency features, namely singular values, PRCs energy and energy entropy, and AR model parameters, are extracted from the first several PRCs and used as the fault feature vectors. Finally, a HDEPSO algorithm is proposed for the parameter optimization of LSSVM, and the fault diagnosis results can be obtained by inputting the fault feature vectors into the HDEPSO-LSSVM classifier. Simulation and experimental results demonstrate that the proposed fault diagnosis approach can overcome the mode-mixing problem of ITD and accurately identify the fault patterns of diesel engines.

Using Kinect for real-time emotion recognition via facial expressions

Emotion recognition via facial expressions （ERFE） has attracted a great deal of interest with recent advances in artificial intelligence and pattern recognition. Most studies are based on 2D images, and their performance is usually computationally expensive. In this paper, we propose a real-time emotion recognition approach based on both 2D and 3D facial expression features captured by Kinect sensors. To capture the deformation of the 3D mesh during facial expression, we combine the features of animation units （AUs） and feature point positions （FPPs） tracked by Kinect. A fusion algorithm based on improved emotional profiles （IEPs） arid maximum confidence is proposed to recognize emotions with these real-time facial expression features. Experiments on both an emotion dataset and a real-time video show the superior performance of our method.