This paper analyzes the Keqiao Textile Index of China, which reflects China Textile City, the leading wholesale textile market in China. China Textile City is a textile entrepot with the most extensive scale and the largest line of business in China, and it is the largest specialized market for light textile in Asia as well. Thus, it is worthwhile to analyze this index. In this paper, 10 variables that represent the factors that significantly influence the Textile Index are selected from the set of possible variables that are deemed to be valid to the index. 6 variables are identified as nonlinear and 4 as linear by the nonparametric method. Then, varying-coefficient partially linear models are established, dividing the index into five terms: one nonparametric term and four linear terms. Each of the five terms comprises approximately 20% of the index, with the linear terms accounting for nearly 80%. Among the six nonparametric variables, cotton index A plays the most important role. The empirical and simulated results consistently show that the percent of each of the five terms would not vary substantially during the sample period if cotton index A were not more than twice the sample mean. Thus, textile prices can be regulated by properly adjusting the cotton price.
According to the characteristics of the constrained resource in distributed real-time data mining in the Internet of Things (IOT) environment, a distributed data mining method is researched in such environment. Based on the limits of computing ability, storage ability, battery energy resources, network bandwidth, and the Internet single point failure, the distributed network data mining method is researched, and the adaptive technology and peer-to-peer node method are adopted. The DRA-Kmeans algorithm of data mining based on the K-means algorithm is proposed, and the amount of data communication among the sites to reduce the number of iterations and clustering is reduced. Clustering efficiency is improved, and better clustering results and execution efficiency are achieved.
Observation providing information from above is important in in large-scale or dangerous rescue activity. This has been done from balloons or airplanes. Balloon observation requires a gas such as helium and takes a relatively long time to prepare, and while airplane observation can be prepared in a relatively short time and is highly mobile, flight time depends on the amount of fuel a plane can carry. We have proposed and developed a kite-based tethered flying robot that complements balloon and airplane observation while providing a short preparation time and long flight time . The objective of our research is autonomous flight information gathering consisting of a kite, a flight unit, a tether and a ground control unit with a line-winding machine. We propose fuzzy controllers for our robot that are inspired by kite flying.
In this paper, a hybrid genetic algorithm based on a chaotic migration strategy (HGABCM) for solving the flow shop scheduling problem with fuzzy delivery times is proposed. First, the initial population is divided into several sub-populations, and each sub-population is isolated and evolved. Next, these offspring are further optimized by a strategy that combines NEH heuristic algorithm proposed by M. Navaz, J.-E. Enscore, I. Ham in 1983 with a newly designed algorithm that has excellent local search capability, thereby enhancing the strategy’s local search capability. Then, the concept of a chaotic migration sequence is introduced to guide the ergodic process of the migration of individuals effectively so that information is exchanged sufficiently among sub-populations and the process of falling into a local optimal solution is thereby avoided. Finally, several digital simulations are provided to demonstrate the effectiveness of the algorithm proposed in this paper.
The effective self-guided genetic algorithm (SGGA) which we proposed is based on the characteristics of a hybrid flow shop scheduling problem. A univariate probability model based on workpiece permutation is introduced together with a bivariate probability model based on a similar workpiece blocks. An approach to updating a probability model parameters is given based on superior individuals. A novel probability calculation function is proposed taking advantages of statistical learning information provided by univariate and bivariate probabilistic model to calculate the probability of workpieces located in different positions. A method for evaluating the quality of individual candidates generated by GA crossover and mutation operators is suggested for selecting promising and excellent individual candidates as offspring. Simulation results show that the SGGA has excellent performance and robustness.
We propose a fully automated determination of the femoral coordinates in computerized tomography (CT) imaging based on epicondyles. The challenge point of this paper is that we take up how to calculate the femoral coordinate system (FCS), which is difficult to determine automatically. Our proposed method automatically determines the FCS based on anatomical reference points. We evaluated 10 subjects (six men and four women 28.9 ± 9.3 years old, three left-handed and seven right-handed) who had no history of joint injury. We examined the proposed method by comparing the expert and algorithm. The medial epicondyle was 1.41 ± 0.75 mm (p=0.42>0.05, student’s t test) in positioning accuracy. The lateral epicondyle was 1.36 ± 0.70 mm (p=0.42) in positioning accuracy. The origin was 0.87 ± 0.40 mm (p=0.71). in positioning accuracy. The lateral axis angle accuracy was 0.53 ± 0.84◦ (p=0.44). In short, the proposed method constructed patient-specific coordinate systems more accurately than expert manual.
Ensemble learning is sophisticated machine learning use to solve many problems in practical applications. MultiBoosting, a cutting-edge learning approach in ensemble learning, is combined with AdaBoost and wagging. It retains AdaBoost’s bias reduction while adding wagging’s variance reduction to that already obtained by AdaBoost, thus reducing the total number of errors in classification. Data characteristics do not always follow traditional machine learning rules, however, so transfer learning acts to solve this problem. We propose a TrMultiBoosting algorithm, composed of MultiBoosting and state-of-the-art transfer learning algorithm TrAdaBoost for transfer learning. We use naive bayes as the basic learning algorithm. TrMultiBoosting has proven to present a decision committee with higher prediction accuracy on UCI data sets than either TrAdaBoost or MultiBoosting.
In this article, the linkage among the securities markets in returns, named “coexceedances,” is characterized by a new model. Considering that the positive and negative short-term liquidity shocks may cause very different influences on financial markets, the proposed model involves the asymmetric quantitative effects. Suitable explanatory variables are selected into our model after a fully consideration of factors which have potential effects on “coexceedances,” then the quantile technique is employed to estimate parameters. As an application, the asymmetric quantitative model of coexceedance is used to describe the contagion mechanism of the financial crisis. In the empirical study, we take some Asian markets as examples for analysis, and we find that during the financial crisis period, there are varied contagion effects among markets; and furthermore, other factors’ effects on “coexceedances” remarkably varied in each quantile. Our research may provide a reference for both the portfolio investors and the policy makers to forecast the risk and take the response to the financial crisis.
This study proposes weighted Lp-norm support vector regression (WLp-SVR) robust against both noise and outliers. Using Lp-norm enables WLp-SVR to select financial variables for creating the financial conditions index (FCI) reliably. We use a weighted sum method to construct a Chinese FCI. We then evaluate our FCI’s ability to forecast real output based on the Granger-causality and Engle-Granger cointegration tests. Regression results show that our FCI has strong predictive power in forecasting real output, indicating that our FCI is a potential leading indicator of the future state of the economy.
This paper proposes wavelet Lp-norm support vector regression (Lp-WSVR) to solve feature selection and regression problems effectively. Unlike conventional support vector regression (SVR), linear Lp-WSVR ensures that useful features are selected based on theoretical analysis. By using the wavelet kernel, Lp-WSVR approaches any curve in quadratic continuous integral space that leads to improving regression performance. Results of experiments show the superiority of Lp-WSVR in both feature selection and regression performances. Applying Lp-WSVR to Chinese real estate prices shows that the most significant and powerful factor contributing to Chinese housing prices is monetary growth.
Many of the trading strategies viewed as highly important by to financial market investors, we developed based on fundamental and technical analysis. We propose a stock trading strategy based on time-varying quantile analysis and apply it to the stock market in the People’s Republic of China. Comparing results for both the buy-and-hold strategy and a popular NARX-based neural network trading strategy showed that our strategy performed well.
E-commerce makes it possible to promote mass customization in practice. Manufacturers provide custom product which enables customers to select each components of the product from several variants according to their own preferences. Providing custom product increases the complexity of the inventory management, and the characteristics of inventory cost are different with those of common product. For custom product orders under e-commerce circumstances are significantly random and fluctuant, we research on this issue in the discrete system simulation method. We consider a same kind of product which is manufactured in either way of the common case and the custom case, design inventory cost simulation models for both situations supposing they adopt (s, S) inventory strategy. The results show that although the mass customization makes the inventory system more complicated, it could bring some benefits to inventory management. Compared with the inventory cost of common product, the inventory cost of custom product could be even lower and less sensitive about the product price, the change of purchase volumes and the order quantity. The conclusions could be suggestive for practice and provide confidence to manufacturers when they hesitate to supply custom products.
Applying nonparametric path-converged approach, the research innovatively provides the measurement of preference in technical efficiency by the ratio of labor elasticity to capital elasticity and further attempts to realize the optimization of preference in technical efficiency by a strategy of 30% abolishment of initial Drug Addition and a strategy with combination of smoothed governmental fiscal expenditure, which sheds fresh light on promoting hospitals’ efficiency in China from perspective of management engineering. With sample data of provincial public hospitals in Zhejiang Province during period of 200901-201306, the research obtains following conclusions. First, benchmark preference in technical efficiency shows production has shifted from physical capital preference to labor skilled preference in technical efficiency. Second, the changing trend of preference in technical efficiency validates initial Drug Addition and governmental fiscal expenditure pushes and restrains the labor skilled preference in technical efficiency respectively. Third, the strategy of 30% abolishment of Drug Addition will strengthen labor skilled preference in technical efficiency with less promotion intensity of initial Drug Addition. The strategy with combination of governmental fiscal expenditure restrains labor skilled preference in technical efficiency. The facts validate great urgency of raising payments for doctors and nurses so as to promoting efficiency effectively.
Disturbance observer-based control provides a promising approach to handle system disturbance and improve robustness. In this paper, a new fuzzy disturbance observer (FDO) is proposed into the SOS-based approach, where the polynomial fuzzy model is used to develop the system controller. Compared with other works published so far, the FDO mainly features two things: 1) the estimation error between the FDO and disturbance shrinks asymptotically to zero if the disturbance has a constant steady-state value; 2) parameters involved in the FDO is adjusted on the basis of the polynomial fuzzy model which is basically nonlinear. Finally, computer simulations are provided to illustrate the effectiveness of the proposed approach.
A hybrid particle swarm optimization (PSO) integrating neural network with fuzzy membership function (NEWFM) technique is proposed for epileptic seizure classification tasks based on brain electroencephalography (EEG) signals. By combining PSO and NEWFM, the proposed method obtains the optimal parameters from the EEG data training required to achieve the best accuracy in disease diagnosis. NEWFM, a model of neural networks, is expected to improve the accuracy by updating weights of fuzzy membership functions. The PSO, a swarm-inspired optimization algorithm, is used to obtain the optimal parameters from the NEWFM. A standard dataset comprising of 5 sets of epileptic seizure detection data, each consisting 100 single EEGs segments is employed to evaluate the proposed technique’s performance. Based on the experiments, the classification results show that the best accuracy of Z–S classification task is 99.5% with the optimal parameters of α=0.1 and β=0.1. For the ZNF–S classification task, the best accuracy is 97.73% with the optimal parameters of α=0.1 or 0.2 and β=0.2. Similar results for the ZNFO–S classification task is 97.64% with the optimal parameters set at α=0.1 or 0.2 and β=0.1.
We propose a unique time-varying identification approach to the market interest rate based on Taylor Rule for coordinating the monetary and exchange rate policies. The significant differences exist between real and market interest rates – 2001 and 2009 are high real interest rates, and 2004-2005 and 2010-2012 low real interest rates – that identify monetary and exchange rate policy conflicts in China. These conflicts derive from the indirect effect of monetary factor through interest rate inertia and expected output gap in 2001; the indirect effect of exchange rate factor through interest rates and inflation inertia in 2004-2005; the direct effects of monetary and the exchange rate factors and the indirect effects through interest rate and inflation inertia, and the expected inflation and output gap since 2009. Our empirical results provide decision support for the monetary and exchange rate policy for reforming Chinese market interest rates.
Based on weighted kernel density estimation and the nonparametric path identification model, this paper explores the impact of asset structure on solvency and risk exposure by insurance companies. To test the differences in solvency and risk exposure of admitted assets under stock and time deposit investment paths, we compared distributions under different investment paths to benchmark distribution. Our results suggest that both stock and time deposit investment impact positively on solvency, meaning that, all other things being equal, solvency increases when investment assets are expanded but risk increases simultaneously. The impact of stock investment is also greater than that of time deposit investment. The extent of these differences increased gradually over the year under the stock investment path, but reduced under the time deposit investment. Under the stock investment path, the value of the high quantiles of the distribution are likely to shift from that of low quantiles. Expected value and risk exposure under time deposit investment are not necessarily reduced, so regulators should both emphasize solvency indicators in daily supervision and also take into account changes in the investment structure, improve how admissible assets are calculated in case the insurance company increases the solvency margin by expanding high-risk investment.
In this paper, I design and develop a multiple description (MD) method which is based on fractal image coding procedure. In the encoder of MD, the IFS generated mappings are separated into different parts and encoded into different descriptions so that, on each description, a subset of these mappings can be involved. Meanwhile, a desired amount of redundancy is inserted into each description such that a satisfactory reconstruction quality will be ensured. In MD decoder, the redundancy and the mappings in one description are exploited to recover the missed mappings in the other description when only one description is received. Compared with the referenced methods, the the proposed MD coder can achieve better and more robust performance under various packet loss ratio circumstance.
On how to evaluate the performance of access control models, a method of N-dimensional security entropy is described in this paper. According to the definition and description of the information entropy in information theory, the definition of the One-dimensional Security Entropy is introduced and the one-dimensional security entropy in Discretionary-access Control model is discussed firstly. Then the N-dimensional security entropy is extended based on the unauthorized access, and by means of the N-dimensional security entropy, the quantitative security performance is measured in RBAC model. In order to measure the security of management information system with complex role level, an extension of RBAC access control (EXRBAC) model is presented in this paper, which could get quantitative analysis with N-dimensional security entropy methods. Through analyzing and comparing the security performance of these three access control models, it is shown that the EXRBAC model performance is improved in multi-class and multi-level roles condition.