Sparse least square twin support vector machine with adaptive norm

By promoting the parallel hyperplanes to non-parallel ones in SVM, twin support vector machines (TWSVM) have attracted more attention. There are many modifications of them. However, most of the modifications minimize the loss function subject to the I ₂-norm or I ₁-norm penalty. These methods are non-adaptive since their penalty forms are fixed and pre-determined for any types of data. To overcome the above shortcoming, we propose l _p norm least square twin support vector machine (l _p LSTSVM). Our new model is an adaptive learning procedure with l _p -norm (0<p<1), where p is viewed as an adjustable parameter and can be automatically chosen by data. By adjusting the parameter p, l _p LSTSVM can not only select relevant features but also improve the classification accuracy. The solutions of the optimization problems in l _p LSTSVM are obtained by solving a series systems of linear equations (LEs) and the lower bounds of the solution is established which is extremely helpful for feature selection. Experiments carried out on several standard UCI data sets and synthetic data sets show the feasibility and effectiveness of the proposed method.     

Sparse Support Vector Machine with <Emphasis Type="Italic">L</Emphasis><Subscript><Emphasis Type="Italic">p</Emphasis></Subscript> Penalty for Feature Selection

We study the strategies in feature selection with sparse support vector machine (SVM). Recently, the socalled L _p -SVM (0 < p < 1) has attracted much attention because it can encourage better sparsity than the widely used L ₁-SVM. However, L _p -SVM is a non-convex and non-Lipschitz optimization problem. Solving this problem numerically is challenging. In this paper, we reformulate the L _p -SVM into an optimization model with linear objective function and smooth constraints (LOSC-SVM) so that it can be solved by numerical methods for smooth constrained optimization. Our numerical experiments on artificial datasets show that LOSC-SVM (0 < p < 1) can improve the classification performance in both feature selection and classification by choosing a suitable parameter p. We also apply it to some real-life datasets and experimental results show that it is superior to L ₁-SVM.     

A simplified multi-class support vector machine with reduced dual optimization

Support vector machine (SVM) was initially designed for binary classification. To extend SVM to the multi-class scenario, a number of classification models were proposed such as the one by Crammer and Singer (2001). However, the number of variables in Crammer and Singer’s dual problem is the product of the number of samples (l) by the number of classes (k), which produces a large computational complexity. This paper presents a simplified multi-class SVM (SimMSVM) that reduces the size of the resulting dual problem from l × k to l by introducing a relaxed classification error bound. The experimental results demonstrate that the proposed SimMSVM approach can greatly speed-up the training process, while maintaining a competitive classification accuracy.     

Effects of Increasing Oxygen Availability on Bicycle Ergometer Endurance Performance

In order to test the effects of increasing oxygen availability on bicycle ergometer endurance performance, 26 subjects completed two criterion endurance performance tests of 6'min duration, (designed to elicit 115% of [Vdot]_O2max) while breathing either room air or 100% oxygen. It was hypothesised that if oxygen availability is a limiting factor in endurance performance, one would expect increased work output in the hyperoxic condition, Hyperoxic conditions that do not result in increased work performance would support the cell as limiting. The results of the present study support the oxygen transport theory as the major limiting factor in aerobic endurance performance. Subjects turned substantially more pedal revolutions (17[sdot]3 revs :p < 0[sdot]01) and had significantly higher oxygen uptakes (650 to 780 cm³ greater: p < 0[sdot]01) in the 100% oxygen condition. In addition, there were no differences in estimated cardiac output between the two conditions while there were substantial differences in the estimated a-v O₂ difference (2[sdot]92 cm³ 100 cm^?3 higher in 100% oxygen, p < 0[sdot]01). The increase in work performance was, therefore, ascribed to increased cellular availability of oxygen during hyperoxia.     

Adaptive feature selection via a new version of support vector machine

This paper focuses on feature selection in classification. A new version of support vector machine (SVM) named p-norm support vector machine ( $p\in[0,1]$ ) is proposed. Different from the standard SVM, the p-norm $(p\in[0,1])$ of the normal vector of the decision plane is used which leads to more sparse solution. Our new model can not only select less features but also improve the classification accuracy by adjusting the parameter p. The numerical experiments results show that our p-norm SVM is more effective than some usual methods in feature selection.     

Sensitivity of large-scale vegetation greenup and dormancy dates to climate change in the north−south transect of eastern China

Phenology event responses, based on vegetation types, are strong indicators of climate variability and the ability of the vegetation to adapt to future climate changes. However, the sensitivity of phenology events to climate change along either environmental or vegetation type gradients is rarely examined. Phenological curves of major vegetation types along the North?South Transect of Eastern China (NSTEC) have been developed using wavelet and smooth-spline methods based on the normalized difference vegetation index from 1982 to 2006. Spatial?temporal patterns, trends of greenup-onset dates, dormancy dates, and growing season lengths (GSLs) during the period of 1982?2006 are presented.

The greenup-onset dates were most significantly and negatively related to the temperature in cold and humid areas, but insignificantly and positively in semi-arid regions. However, dormancy date showed a positive correlation with temperature. In populations of the same vegetation type, distributed along thermal gradients of NSTEC, the phenology sensitivities to warming were different. Greenup sensitivities of cold temperate coniferous forest (CTCF) and temperate meadow steppe (TMS) increased significantly from??6.0 to 0 days °C^?1 (p < 0.001) and from about??2.0 to 2.0 days °C^?1 (p < 0.001), respectively. In contrast, temperate grass steppe (TGS) and temperate deciduous shrubland (TDS) showed a decreased trend of greenup sensitivity from 2.0 to??4.0 days °C^?1 (p < 0.001) and from 2.0 to??6.0 days °C^?1 (p < 0.001), respectively. For the dormancy date sensitivity, CTCF showed a decreasing trend from about 6.0 to 0 days °C^?1 (p < 0.001), and subtropical evergreen-broadleaved forest (SEBF) decreased from 5.0 to??5.0 days °C^?1 (p < 0.05).     

How do clinicians reconcile conditions and medications? The cognitive context of medication reconciliation

Medication omissions and dosing failures are frequent during transitions in patient care. Medication reconciliation (MR) requires bridging discrepancies in a patient’s medical history as a setting for care changes. MR has been identified as vulnerable to failure, and a clinician’s cognition during MR remains poorly described in the literature. We sought to explore cognition in MR tasks. Specifically, we sought to explore how clinicians make sense of conditions and medications. We observed 24 anesthesia providers performing a card-sorting task to sort conditions and medications for a fictional patient. We analyzed the spatial properties of the data using statistical methods. Most of the participants (58%) arranged the medications along a straight line (p < 0.001). They sorted medications by organ systems (Friedman’s χ ²(54) = 325.7, p < 0.001). These arrangements described the clinical correspondence between each two medications (Wilcoxon W = 192.0, p < 0.001). A cluster analysis showed that the subjects matched conditions and medications related to the same organ system together (Wilcoxon W = 1917.0, p < 0.001). We conclude that the clinicians commonly arranged the information into two groups (conditions and medications) and assigned an internal order within these groups, according to organ systems. They also matched between conditions and medications according to similar criteria. These findings were also supported by verbal protocol analysis. The findings strengthen the argument that organ-based information is pivotal to a clinician’s cognition during MR. Understanding the strategies and heuristics, clinicians employ through the MR process may help to develop practices to promote patient safety.     

Statistical model development and estimation of suspended particulate matter concentrations with Landsat 8 OLI images of Dongting Lake,China

Suspended particulate matter (SPM) is a dominant water constituent of case-II waters, and SPM concentration (C_SPM) is a key parameter describing water quality. This study, using Landsat 8 Operational Land Imager (OLI) images, aimed to develop the C_SPM retrieval models and further to estimate the C_SPM values of Dongting Lake. One Landsat 8 OLI image and 53 C_SPM measurements were employed to calibrate Landsat 8-based C_SPM retrieval models. The C_SPM values derived from coincident Landsat 8 OLI and Moderate Resolution Imaging Spectroradiometer (MODIS) images were compared to validate calibrated Landsat 8-based C_SPM models. After the best stable Landsat 8-based C_SPM retrieval model was further validated using an independent Landsat 8 OLI image and its coincident C_SPM measurements, it was applied to four Landsat 8 OLI images to retrieve the C_SPM values in the South and East Dongting Lake. Model calibration results showed that two exponential models of the red band explained 61% (estimated standard error (SE) = 7.96 mg l^–1) and 67% (SE = 6.79 mg l^–1) of the variation of C_SPM; two exponential models of the red:panchromatic band ratio obtained 81% (SE = 5.48 mg l^–1) and 77% (SE = 4.96 mg l^–1) fitting accuracy; and four exponential and quadratic models of the infrared band explained 72–83% of the variation of C_SPM (SE = 5.18–5.52 mg l^–1). By comparing the MODIS- and Landsat 8-based C_SPM values, an exponential model of the Landsat 8 OLI red band (C_SPM = 1.1034 × exp(23.61 × R)) obtained the best consistent C_SPM estimations with the MODIS-based model (r = 0.98, p < 0.01), and its further validation result using an independent Landsat 8 OLI image showed a significantly strong correlation between the measured and estimated C_SPM values at a significance level of 0.05 (r = 0.91, p < 0.05). The C_SPM spatiotemporal distribution derived from four Landsat 8 images revealed a clear spatial distribution pattern of C_SPM in the South and East Dongting Lake, which was caused by natural and anthropogenic factors together. This study confirmed the potential of Landsat 8 OLI images in retrieving C_SPM and provided a foundation for retrieving the spatial distribution of C_SPM accurately from this new data source in Dongting Lake.     

Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages

We analyze over 570 million Twitter messages from an eight month period and find that tracking a small number of keywords allows us to estimate influenza rates and alcohol sales volume with high accuracy. We validate our approach against government statistics and find strong correlations with influenza-like illnesses reported by the U.S. Centers for Disease Control and Prevention (r(14) = .964, p < .001) and with alcohol sales volume reported by the U.S. Census Bureau (r(5) = .932, p < .01). We analyze the robustness of this approach to spurious keyword matches, and we propose a document classification component to filter these misleading messages. We find that this document classifier can reduce error rates by over half in simulated false alarm experiments, though more research is needed to develop methods that are robust in cases of extremely high noise.     

Evolution strategies based adaptive Lp LS-SVM

Not only different databases but two classes of data within a database can also have different data structures. SVM and LS-SVM typically minimize the empirical ?-risk; regularized versions subject to fixed penalty (L₂ or L₁ penalty) are non-adaptive since their penalty forms are pre-determined. They often perform well only for certain types of situations. For example, LS-SVM with L₂ penalty is not preferred if the underlying model is sparse. This paper proposes an adaptive penalty learning procedure called evolution strategies (ES) based adaptive L_p least squares support vector machine (ES-based L_p LS-SVM) to address the above issue. By introducing multiple kernels, a L_p penalty based nonlinear objective function is derived. The iterative re-weighted minimal solver (IRMS) algorithm is used to solve the nonlinear function. Then evolution strategies (ES) is used to solve the multi-parameters optimization problem. Penalty parameterp, kernel and regularized parameters are adaptively selected by the proposed ES-based algorithm in the process of training the data, which makes it easier to achieve the optimal solution. Numerical experiments are conducted on two artificial data sets and six real world data sets. The experiment results show that the proposed procedure offer better generalization performance than the standard SVM, the LS-SVM and other improved algorithms.     

Stability of linear infinite-dimensional systems revisited

The paper is devoted to a study of stability questions for linear infinite-dimensional discrete-time and continuous-time systems. The concepts of power stability and l ^p Instability for a linear discrete-time system x _k+1 = Ax _k (where x _k ε X, X is a Banach space, A is linear and bounded) are introduced and studied. Relationships between these concepts and the inequality r(A) < 1, where r(A) denotes the spectral radius of A, are also given. The discrete-time results are used for a simple derivation of some well-known properties of exponentially stable and L^p-stable linear continuous-time systems described by [xdot](t) = Ax(t) (A generates here a strongly continuous semigroup of linear and bounded operators on X). Some remarks on norms related to stable systems are also included.     

Imbalanced data classification using second-order cone programming support vector machines

Learning from imbalanced data sets is an important machine learning challenge, especially in Support Vector Machines (SVM), where the assumption of equal cost of errors is made and each object is treated independently. Second-order cone programming SVM (SOCP-SVM) studies each class separately instead, providing quite an interesting formulation for the imbalanced classification task. This work presents a novel second-order cone programming (SOCP) formulation, based on the LP-SVM formulation principle: the bound of the VC dimension is loosened properly using the _l∞$l_{\infty }$-norm, and the margin is directly maximized using two margin variables associated with each class. A regularization parameter C is considered in order to control the trade-off between the maximization of these two margin variables. The proposed method has the following advantages: it provides better results, since it is specially designed for imbalanced classification, and it reduces computational complexity, since one conic restriction is eliminated. Experiments on benchmark imbalanced data sets demonstrate that our approach accomplishes the best classification performance, compared with the traditional SOCP-SVM formulation and with cost-sensitive formulations for linear SVM.     

Gene selection and prediction for cancer classification using support vector machines with a reject option

In cancer classification based on gene expression data, it would be desirable to defer a decision for observations that are difficult to classify. For instance, an observation for which the conditional probability of being cancer is around 1/2 would preferably require more advanced tests rather than an immediate decision. This motivates the use of a classifier with a reject option that reports a warning in cases of observations that are difficult to classify. In this paper, we consider a problem of gene selection with a reject option. Typically, gene expression data comprise of expression levels of several thousands of candidate genes. In such cases, an effective gene selection procedure is necessary to provide a better understanding of the underlying biological system that generates data and to improve prediction performance. We propose a machine learning approach in which we apply the l₁ penalty to the SVM with a reject option. This method is referred to as the l₁ SVM with a reject option. We develop a novel optimization algorithm for this SVM, which is sufficiently fast and stable to analyze gene expression data. The proposed algorithm realizes an entire solution path with respect to the regularization parameter. Results of numerical studies show that, in comparison with the standard l₁ SVM, the proposed method efficiently reduces prediction errors without hampering gene selectivity.     

Towards a practical remote-sensing model of suspended sediment concentrations in turbid waters using MERIS measurements

A new empirical index, termed the normalized suspended sediment index (NSSI), is proposed to predict total suspended sediment (TSS) concentrations in inland turbid waters using Medium Resolution Imaging Spectrometer (MERIS) full-resolution (FR) 300 m data. The algorithm is based on the normalized difference between two MERIS spectral bands, 560 and 760 nm. NSSI shows its potential in application to our study region – Poyang Lake – the largest freshwater lake in China. An exponential function (R² = 0.90, p < 0.01) accurately explained the variance in the in situ data and showed better performance for the TSS range 10–524 mg l^?1. The algorithm was then validated with TSS estimates using an atmospheric-corrected MERIS FR image. The validation showed that the NSSI algorithm was a more robust TSS algorithm than the band-ratio algorithms. Findings of this research imply that NSSI can be successfully used on MERIS images to obtain TSS in Poyang Lake. This work provided a practical remote-sensing approach to estimate TSS in the optically and hydrologically complex Poyang Lake and the method can be easily extended to other similar waters.     

The effects of clinical information presentation on physicians' and nurses' decision-making in ICUs

This research evaluated physicians' agreement about patients' diagnoses and nurses' ability to detect patient change using traditional charts (TC) and a work domain analysis-based paper prototype (PP) and also sought to determine whether differences persisted when the PP was represented as an electronic prototype (EP). Nurses' change detection improved using the PP and EP compared to TC (PP vs TC, t_(df=6) = 1.94, p < 0.03; EP vs TC, t_(df=6) = 3.14, p < 0.01) and detection was better using the EP compared with the PP (t_(df=6) = 5.96, p < 0.001). Physicians were more likely to agree about failed physiological systems using the EP compared with the PP (t_(df=10) = 3.14, p < 0.01), but agreement about patient diagnoses was higher using the PP compared with the EP (t_(df=10) = 2.23; p < 0.02). These results are attributed to information grouping around physiological functions and the direct association of cause-and-effect relations in clinical information design.     

Pathological brain detection in MRI scanning via Hu moment invariants and machine learning

Abstract

Background: We proposed a new automatic and rapid computer-aided diagnosis system to detect pathological brain images obtained in the scans of magnetic resonance imaging (MRI). Methods: For simplification, we transformed the problem to a binary classification task (pathological or normal). It consisted of two steps: first, Hu moment invariants (HMI) were extracted from a specific MR brain image; then, seven HMI features were fed into two classifiers: twin support vector machine (TSVM) and generalised eigenvalue proximal SVM (GEPSVM). Results: Then, a 5 × 5-fold cross validation on a data set containing 90 MR brain images, demonstrated that the proposed methods “HMI + GEPSVM” and “HMI + TSVM” achieved classification accuracy of 98.89%, higher than eight state-of-the-art methods: “DWT + PCA + BP-NN”, “DWT + PCA + RBF-NN”, “DWT + PCA + PSO-KSVM”, “WE + BP-NN”, “WE + KSVM”, “DWT + PCA + GA-KSVM”, “WE + PSO-KSVM” and “WE + BBO-KSVM”. Conclusion: The proposed methods are superior to other methods on pathological brain detection (p < 0.05).     

Settlement location and population density estimation in rugged terrain using information derived from Landsat ETM and SRTM data

It is useful to have a disaggregated population database at uniform grid units in disaster situations. This study presents a method for settlement location probability and population density estimations at a 90 m resolution for northern Iraq using the Shuttle Radar Topographic Mission (SRTM) digital terrain model and Landsat Enhanced Thematic Mapper satellite imagery. A spatial model each for calculating the probability of settlement location and for estimating population density is described. A randomly selected subset of field data (equivalent to 50%) is first analysed for statistical links between settlement location probability and population density; and various biophysical features which are extracted from Landsat or SRTM data. The model is calibrated using this subset. Settlement location probability is attributed to the distance from roads and water bodies and land cover. Population density can be estimated based upon land cover and topographic features. The Landsat data are processed using a segmentation and subsequent feature–based classification approach making this method robust to seasonal variations in imagery and therefore applicable to a time series of images regardless of acquisition date. The second half of the field data is used to validate the model. Results show a reasonable estimate of population numbers (r = 0.205, p<0.001) for both rural and urban settlements. Although there is a strong overall correlation between the results of this and the LandScan model (r = 0.464, p<0.001), this method performs better than the 1 km resolution LandScan grid for settlements with fewer than 1000 people, but is less accurate for estimating population numbers in urban areas (LandScan rural r = 0.181, p<0.001; LandScan urban r = 0.303, p<0.001). The correlation between true urban population numbers is superior to that of LandScan however when the 90 m grid values are summed using a filter which corresponds to the LandScan spatial resolution (r = 0.318, p<0.001).     

Texture classification using features derived from random field models

This paper presents a new feature extraction method for classifying a texture image into one of the l possible classes C_i, i=1,…,l. It is assumed that the given M × M image characterized by a set of intensity levels, {y(s₁,S₂), 0≤s_s,s₂≤M?1}, is a realization of an underlying random field model, known as the Simultaneous Autoregressive Model (SAR). This model is characterized by a set of parameters φ whose probability density function p_i(φ), depends on the class to which the image belongs. First it is shown that the maximum likelihood estimate (M.L.E.) $\text{φ}{}^1$, of φ is an appropriate feature vector for classification purposes. The optimum Bayes classifier which minimizes the average probability of classification error, is then designed using $\text{φ}{}^1$. Finally the efficiency of the feature vector is demonstrated through experimental results obtained with some natural texture data and a simpler quadratic mean classifier.     

A fast algorithm for computing a longest common increasing subsequence

Let A=〈a₁,a₂,…,am〉 and B=〈b₁,b₂,…,bn〉 be two sequences, where each pair of elements in the sequences is comparable. A common increasing subsequence of A and B is a subsequence 〈ai₁=bj₁,ai₂=bj₂,…,ail=bjl〉, where i₁<i₂<?<il and j₁<j₂<?<jl, such that for all 1?k<l, we have aik<aik+1. A longest common increasing subsequence of A and B is a common increasing subsequence of the maximum length. This paper presents an algorithm for delivering a longest common increasing subsequence in O(mn) time and O(mn) space.     

A variant of Wiener’s attack on RSA

Wiener’s attack is a well-known polynomial-time attack on a RSA cryptosystem with small secret decryption exponent d, which works if d < n ^0.25, where n = pq is the modulus of the cryptosystem. Namely, in that case, d is the denominator of some convergent p _m /q _m of the continued fraction expansion of e/n, and therefore d can be computed efficiently from the public key (n, e). There are several extensions of Wiener’s attack that allow the RSA cryptosystem to be broken when d is a few bits longer than n ^0.25. They all have the run-time complexity (at least) O(D ²), where d = Dn ^0.25. Here we propose a new variant of Wiener’s attack, which uses results on Diophantine approximations of the form |α ? p/q| <  c/q ², and “meet-in-the-middle” variant for testing the candidates (of the form rq _m+1 +  sq _m ) for the secret exponent. This decreases the run-time complexity of the attack to O(D log D) (with the space complexity O(D)).