Candidate working set strategy based SMO algorithm in support vector machine

Sequential minimal optimization (SMO) is quite an efficient algorithm for training the support vector machine. The most important step of this algorithm is the selection of the working set, which greatly affects the training speed. The feasible direction strategy for the working set selection can decrease the objective function, however, may augment to the total calculation for selecting the working set in each of the iteration. In this paper, a new candidate working set (CWS) Strategy is presented considering the cost on the working set selection and cache performance. This new strategy can select several greatest violating samples from Cache as the iterative working sets for the next several optimizing steps, which can improve the efficiency of the kernel cache usage and reduce the computational cost related to the working set selection. The results of the theory analysis and experiments demonstrate that the proposed method can reduce the training time, especially on the large-scale datasets.

A novel bipolar time-spread echo hiding based watermarking method for stereo audio signals

In this paper, a novel bipolar time-spread (TS) echo hiding based watermarking method is proposed for stereo audio signals, to overcome the low robustness problem in the traditional TS echo hiding method. At the embedding, echo signals with opposite polarities are added to both channels of the host audio signal. This improves the imperceptibility of the watermarking scheme, since added watermarks have similar effects in both channels. Then decoding part is developed, in order to improve the robustness of the watermarking scheme against common attacks. Since these novel embedding and decoding methods utilize the advantage of two channels in stereo audio signals, it significantly reduces the interference of host signal at watermark extraction which is the main reason for error detection in the traditional TS echo hiding based watermarking under closed-loop attack. The effectiveness of the proposed watermarking scheme is theoretically analyzed and verified by simulations under common attacks. The proposed echo hiding method outperforms conventional TS echo hiding based watermarking when their perceptual qualities are similar.

Effective pseudonoise sequence and decoding function for imperceptibility and robustness enhancement in time-spread echo-based audio watermarking

This paper proposes an effective pseudonoise (PN) sequence and the corresponding decoding function for time-spread echo-based audio watermarking. Different from the traditional PN sequence used in time-spread echo hiding, the proposed PN sequence has two features. Firstly, the echo kernel resulting from the new PN sequence has frequency characteristics with smaller magnitudes in perceptually significant region. This leads to higher perceptual quality. Secondly, the correlation function of the new PN sequence has three times more large peaks than that of the existing PN sequence. Based on this feature, we propose a new decoding function to improve the robustness of time-spread echo-based audio watermarking. The effectiveness of the proposed PN sequence and decoding function is illustrated by theoretical analysis, simulation examples, and listening test.

Sequential fixed-width confidence bands for kernel regression estimation

We consider a random design model based on independent and identically distributed (iid) pairs of observations (Xi, Yi), where the regression function m(x) is given by m(x) = E(Yi|Xi = x) with one independent variable. In a nonparametric setting the aim is to produce a reasonable approximation to the unknown function m(x) when we have no precise information about the form of the true density, f(x) of X. We describe an estimation procedure of non-parametric regression model at a given point by some appropriately constructed fixed-width (2d) confidence interval with the confidence coefficient of at least 1−. Here, d(> 0) and 2 (0, 1) are two preassigned values. Fixed-width confidence intervals are developed using both Nadaraya-Watson and local linear kernel estimators of nonparametric regression with data-driven bandwidths.

The sample size was optimized using the purely and two-stage sequential procedure together with asymptotic properties of the Nadaraya-Watson and local linear estimators. A large scale simulation study was performed to compare their coverage accuracy. The numerical results indicate that the confidence bands based on the local linear estimator have the best performance than those constructed by using Nadaraya-Watson estimator. However both estimators are shown to have asymptotically correct coverage properties.

Sample size determination for kernel regression estimation using sequential fixed-width confidence bands

We consider a random design model based on independent and identically distributed pairs of observations (Xi, Yi), where the regression function m(x) is given by m(x) = E(Yi|Xi = x) with one independent variable. In a nonparametric setting the aim is to produce a reasonable approximation to the unknown function m(x) when we have no precise information about the form of the true density, f(x) of X. We describe an estimation procedure of non-parametric regression model at a given point by some appropriately constructed fixed-width (2d) confidence interval with the confidence coefficient of at least 1−. Here, d(> 0) and 2 (0, 1) are two preassigned values. Fixed-width confidence intervals are developed using both Nadaraya-Watson and local linear kernel estimators of nonparametric regression with data-driven bandwidths. The sample size was optimized using the purely and two-stage sequential procedures together with asymptotic properties of the Nadaraya-Watson and local linear estimators. A large scale simulation study was performed to compare their coverage accuracy. The numerical results indicate that the confi dence bands based on the local linear estimator have the better performance than those constructed by using Nadaraya-Watson estimator. However both estimators are shown to have asymptotically correct coverage properties.

An agent-based approach to value theory and wealth distribution in economics

Any attempt to model an economy requires foundational assumptions about the relations between prices, values and the distribution of wealth. These assumptions exert a profound influence over the results of any model. Unfortunately, there are few areas in economics as vexed as the theory of value. I argue in this paper that the fundamental problem with past theories of value is that it is simply not possible to model the determination of value, the formation of prices and the distribution of income in a real economy with analytic mathematical models. All such attempts leave out crucial processes or make unrealistic assumptions which significantly affect the results. There have been two primary approaches to the theory of value. The first, associated with classical economists such as Ricardo and Marx were substance theories of value, which view value as a substance inherent in an object and which is conserved in exchange. For Marxists, the value of a commodity derives solely from the value of the labour power used to produce it - and therefore any profit is due to the exploitation of the workers. The labour theory of value has been discredited because of its assumption that labour was the only ‘factor’ that contributed to the creation of value, and because of its fundamentally circular argument. Neoclassical theorists argued that price was identical with value and was determined purely by the interaction of supply and demand. Value then, was completely subjective. Returns to labour (wages) and capital (profits) were determined solely by their marginal contribution to production, so that each factor received its just reward by definition. Problems with the neoclassical approach include assumptions concerning representative agents, perfect competition, perfect and costless information and contract enforcement, complete markets for credit and risk, aggregate production functions and infinite, smooth substitution between factors, distribution according to marginal products, firms always on the production possibility frontier and firms’ pricing decisions, ignoring money and credit, and perfectly rational agents with infinite computational capacity. Two critical areas include firstly, the underappreciated Sonnenschein-Mantel- Debreu results which showed that the foundational assumptions of the Walrasian general-equilibrium model imply arbitrary excess demand functions and therefore arbitrary equilibrium price sets. Secondly, in real economies, there is no equilibrium, only continuous change. Equilibrium is never reached because of constant changes in preferences and tastes; technological and organisational innovations; discoveries of new resources and new markets; inaccurate and evolving expectations of businesses, consumers, governments and speculators; changing demand for credit; the entry and exit of firms; the birth, learning, and death of citizens; changes in laws and government policies; imperfect information; generalized increasing returns to scale; random acts of impulse; weather and climate events; changes in disease patterns, and so on. The problem is not the use of mathematical modelling, but the kind of mathematical modelling used. Agent-based models (ABMs), objectoriented programming and greatly increased computer power however, are opening up a new frontier. Here a dynamic bargaining ABM is outlined as a basis for an alternative theory of value. A large but finite number of heterogeneous commodities and agents with differing degrees of market power are set in a spatial network. Returns to buyers and sellers are decided at each step in the value chain, and in each factor market, through the process of bargaining. Market power and its potential abuse against the poor and vulnerable are fundamental to how the bargaining dynamics play out. Ethics therefore lie at the very heart of economic analysis, the determination of prices and the distribution of wealth. The neoclassicals are right then that price is the enumeration of value at a particular time and place, but wrong to downplay the critical roles of bargaining, power and ethics in determining those same prices.

A resource-based view of small export firms' social capital in a Southeast Asian country

This study empirically examines the social capital that facilitates the flow of export knowledge, thereby supporting the entrepreneurial stance of small export firms. By applying the VRIO (value, rarity, inimitability and organisation of firm resources) framework to the resource-based view (RBV) of the firm, this study suggests that superior performance is a function of resources that are valuable, rare, inimitable and sufficiently organised to develop and sustain the firm's competitive advantage. This study argues that small, resource-constrained export firms in a developing economy are able to adopt entrepreneurial tactics and reap positive rates of return by exploiting their relational capital to acquire export knowledge. A survey of 175 small export firms in the Philippines was conducted, and the data were analysed using structural equation modelling. The results suggest positive relationships between the firm's social capital and export knowledge. Export knowledge is associated with entrepreneurial orientation, which then correlates with export performance.

Modelling based design of a pilot-scale membrane bioreactor for combined nutrient removal from domestic wastewater

A three stage-treatment of domestic wastewater including anaerobic, anoxic and aerobic phases is employed in this study while a clarifier unit is replaced with a submerged membrane in the aerobic unit. The effects of operational parameters on the performance of a pilot scale submerged membrane bioreactor (SMBR) namely hydraulic retention time (HRT), ratio of return activated sludge (QRS), ratio of internal recycle (QIR), solid retention time (SRT) and dissolved oxygen (DO) are evaluated by simulations, using a hybrid model composed of TUDP model, oxygen transfer model, biofouling model due to extra-cellular polymeric substances (EPS) and turbulent shear model. The results showed that anaerobic HRT of 3 hours, anoxic HRT of 6 hours, QRS of 20% and QIR of 300 % are satisfactory in obtaining a high removal efficiency (>90%) of COD, NH4-N, P04-P as well as a less sludge production. An increase of sludge production causes an increase in EPS, which fouls the membrane surface and increase the cleaning cycle of membrane. Operation of 5MBR system at 2 mg/I of DO and 30 days of SRT can extend the membrane cleaning cycle dramatically. The membrane cleaning cycle however is strongly dependent on the initial and terminal specific fluxes and displays inverse power relationships to those fluxes.

Energy efficiency methods in electrified railways based on recovery of regenerated power

Various attempts have been made to minimise energy consumption of rail vehicles by means of regenerative power from electric braking of traction motors. This paper describes energy efficiency methods in electrified railways based on recovery of energy. Direct recovery methods that return regenerative power to electrified networks, and recovery methods based on energy storage systems are elaborated. The benefits of developing recovery methods and advantages of energy storage systems are discussed.

A fast kernel dimension reduction algorithm with applications to face recognition

This paper presents a novel dimensionality reduction algorithm for kernel based classification. In the feature space, the proposed algorithm maximizes the ratio of the squared between-class distance and the sum of the within-class variances of the training samples for a given reduced dimension. This algorithm has lower complexity than the recently reported kernel dimension reduction(KDR) for supervised learning. We conducted several simulations with large training datasets, which demonstrate that the proposed algorithm has similar performance or is marginally better compared with KDR whilst having the advantage of computational efficiency. Further, we applied the proposed dimension reduction algorithm to face recognition in which the number of training samples is very small. This proposed face recognition approach based on the new algorithm outperforms the eigenface approach based on the principle component analysis (PCA), when the training data is complete, that is, representative of the whole dataset.

Identification of nonlinear fMRI models using Auxiliary Particle Filter and kernel smoothing method

Hemodynamic models have a high potential in application to understanding the functional differences of the brain. However, full system identification with respect to model fitting to actual functional magnetic resonance imaging (fMRI) data is practically difficult and is still an active area of research. We present a simulation based Bayesian approach for nonlinear model based analysis of the fMRI data. The idea is to do a joint state and parameter estimation within a general filtering framework. One advantage of using Bayesian methods is that they provide a complete description of the posterior distribution, not just a single point estimate. We use an Auxiliary Particle Filter adjoined with a kernel smoothing approach to address this joint estimation problem.

Pricing innovations in consumption growth: a re-evaluation of the recursive utility model

We re-evaluate the cross-sectional asset pricing implications of the recursive utility function of Epstein and Zin, 1989 and Epstein and Zin, 1991, using innovations in future consumption growth in our tests. Our empirical specification helps explain the size, value and momentum effects. Specifically, we find that (і) the beta associated with news about consumption growth has a systematic pattern: beta decreases along the size dimension and increases along the book-to-market and momentum dimensions, (іі) innovation in consumption growth is significantly priced in asset returns using both the Fama and MacBeth (1973) and the stochastic discount factor approaches, and (ііі) the model performs better than both the CAPM and Fama–French model.

Directed search, coordination failure, and seller profits: an experimental comparison of posted pricing with single and multiple prices

We experimentally examine posted pricing and directed search. In one treatment, capacity-constrained sellers post fixed prices, which buyers observe before choosing whom to visit. In the other, firms post both “single-buyer” (applied when one buyer visits) and “multibuyer” (when multiple buyers visit) prices. We find, based on a 2 × 2 (two buyers and two sellers) market and a follow-up experiment with 3 and 2 × 3 markets, that multibuyer prices can be lower than single-buyer prices or prices in the one-price treatment. Also, allowing the multibuyer price does not affect seller profits and increases market frictions.

Face recognition from face motion manifolds using robust kernel resistor-average distance

In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97–100% are consistently achieved on databases of 35– 90 people.

A hierarchical cloud pricing system

Cloud computing is experiencing phenomenal growth and there are now many vendors offering their cloud services. In cloud computing, cloud providers cooperate together to offer their computing resource as a utility and software as a service to customers. The demands and the price of cloud service should be negotiated between providers and users based on the Service Level Agreement (SLA). In order to help cloud providers achieving an agreeable price for their services and maximizing the benefits of both cloud providers and clients, this paper proposes a cloud pricing system consisting of hierarchical system, M/M/c queuing model and pricing model. Simulation results verify the efficiency of our proposed system.