An Improved Gradient Projection-based Decomposition Technique for Support Vector Machines

In this paper we propose some improvements to a recent decomposition technique for the large quadratic program arising in training support vector machines. As standard decomposition approaches, the technique we consider is based on the idea to optimize, at each iteration, a subset of the variables through the solution of a quadratic programming subproblem. The innovative features of this approach consist in using a very effective gradient projection method for the inner subproblems and a special rule for selecting the variables to be optimized at each step. These features allow to obtain promising performance by decomposing the problem into few large subproblems instead of many small subproblems as usually done by other decomposition schemes. We improve this technique by introducing a new inner solver and a simple strategy for reducing the computational cost of each iteration. We evaluate the effectiveness of these improvements by solving large-scale benchmark problems and by comparison with a widely used decomposition package.     

Non-Parametric Regression Methods

The nature of the financial time series is complex, continuous interchange of stochastic and deterministic regimes. Therefore, it is difficult to forecast with parametric techniques. Instead of parametric models, we propose three techniques and compare with each other. Neural networks and support vector regression (SVR) are two universally approximators. They are data-driven non parametric models. ARCH/GARCH models are also investigated. Our assumption is that the future value of Istanbul Stock Exchange 100 index daily return depends on the financial indicators although there is no known parametric model to explain this relationship. This relationship comes from the technical analysis. Comparison shows that the multi layer perceptron networks overperform the SVR and time series model (GARCH).     

An improved max-flow-based lower bound for minimizing maximum lateness on identical parallel machines

In this paper, we introduce a new concept of semi-preemptive scheduling and we show how it can be used to derive a maximum-flow-based lower bound for the P|r_j|L_max which dominates the well-known preemptive lower bound. We show that, in some cases, the proposed bound strictly dominates the preemptive one while having the same complexity.     

Feature Selection using Fuzzy Support Vector Machines

The feature selection consists of obtaining a subset of these features to optimally realize the task without the irrelevant ones. Since it can provide faster and cost-effective learning machines and also improve the prediction performance of the predictors, it is a crucial step in machine learning. The feature selection methods using support machines have obtained satisfactory results, but the noises and outliers often reduce the performance. In this paper, we propose a feature selection approach using fuzzy support vector machines and compare it with the previous work, the results of experiments on the UCI data sets show that feature selection using fuzzy SVM obtains better results than using SVM.     

A mathematical model of the ring-spinning process

This paper develops a mathematical model of the ring-spinning process that takes into account its non-stationary nature. A complex system of differential equations is obtained, which from a mathematical point of view constitutes a ‘free-boundary’ problem. Its solution involves definition of suitable boundary conditions related to the mechanical characteristics of the process and of the spinning machine itself. The boundary conditions which determine the solution are pointed out. A numerical solution of the system of differential equations can be obtained by the Finite-Segments method, as shown in an example.     

OPTIMAL SETTING-UP OF KNITTING ELEMENTS AND ITS EFFECT ON TENSION VARIATION

The dynamic yarn tension variations during knitting cycle are very difficult to control and be-come one of barriers to knitting on modern warp knitting machine.Examination of experimentaldata and theoretical analysis show that the relative position of spring rail to knitting elements suchas needle,guide as well as their displacement has noticeable effect on tension variation so that theknitting condition can be much improved by rearrangement of the knitting elements and theirmovement within a knitting cycle.     

Electroencephalogram (EEG) time series classification: Applications in epilepsy

Epilepsy is among the most common brain disorders. Approximately 25–30% of epilepsy patients remain unresponsive to anti-epileptic drug treatment, which is the standard therapy for epilepsy. In this study, we apply optimization-based data mining techniques to classify the brain's normal and epilepsy activity using intracranial electroencephalogram (EEG), which is a tool for evaluating the physiological state of the brain. A statistical cross validation and support vector machines were implemented to classify the brain's normal and abnormal activities. The results of this study indicate that it may be possible to design and develop efficient seizure warning algorithms for diagnostic and therapeutic purposes. Research was partially supported by the Rutgers Research Council grant-202018, the NSF grants DBI-980821, CCF-0546574, IIS-0611998, and NIH grant R01-NS-39687-01A1.     

提高西德MNPJ型毛圈圆纬机压针三角与舌针使用寿命的研究

本文通过西德MNPJ型毛圈圆纬机编织过程的受力分析和机械润滑试验,提出了提高三角和舌针使用寿命的途径;同时又对该机三角系统的材料进行了研究,提出了自制三角系统的看法。     

Influence of two grinding methods on the uncertainty of determinations of heavy metals in atomic absorption spectrometry/electrothermal atomisation of plant samples

 Chemical analyses of trace elements are affected by relatively high analytical errors due to the different steps of the laboratory procedures: samples grinding, mineralisation and instrumental measurements. In the present communication, the influence of the grinding phase on the global uncertainty of Pb, Cd, Ni and Cr determinations in plant samples by the classical method of atomic absorption spectrometry/electrothermal atomisation (AAS-ETA) after dry ashing is quantified. Two grinding machines, a planetary mill with balls and jars of agate versus a stainless steel grinder were compared by analysing leaf samples of cucumber, strawberry, kiwivines, apple trees and grapevines from agricultural experimental plots under controlled conditions. Variance components due to the difference between grinding methods and experimental plots were estimated. Further, the simultaneous effects of the grinding methods on all considered metals have been evaluated by analysis of variance. With the stainless steel grinder, on average, higher levels of the considered heavy metals were obtained (up to 67% of the mean values). On average, the increments were similar for metals contained in steel (Ni and Cr) and those not contained (Pb and Cd). The true causes of these differences need further investigation to determine whether the higher metal detection is due to possible contamination, to a different grinding quality or to other reasons. Finally, the grinding methods did not seem to affect the combined uncertainty of the analyses. Received: 3 November 1997 · Accepted: 29 November 1997     

坐标测量机的空间误差检测及误差修正

如何简单、迅速地获取坐标测量机的机构误差,并对其进行软件修正,是近年来国内外学者研究的一个重要课题。本文研究了三坐标测量机的误差修正理论及用三维检具检测测量机误差的方法,提出了空间球检具晶格移位法误差检测原理和多项式拟合的误差函数获得方法,并将其应用于一台中型的坐标测量机的误差修正中,收到了满意的效果。