Application of a Near-Optimal Reinforcement Learning Controller to a Robotics Problem in Manufacturing: A Hybrid Approach

Optimization theory provides a framework for determining the best decisions or actions with respect to some mathematical model of a process. This paper focuses on learning to act in a near-optimal manner through reinforcement learning for problems that either have no model or the model is too complex. One approach to solving this class of problems is via approximate dynamic programming. The application of these methods are established primarily for the case of discrete state and action spaces. In this paper we develop efficient methods of learning which act in complex systems with continuous state and action spaces. Monte-Carlo approaches are employed to estimate function values in an iterative, incremental procedure. Derivative-free line search methods are used to obtain a near-optimal action in the continuous action space for a discrete subset of the state space. This near-optimal control policy is then extended to the entire continuous state space via a fuzzy additive model. To compensate for approximation errors, a modified procedure for perturbing the generated control policy is developed. Convergence results under moderate assumptions and stopping criteria are established.     

Laser nanosources based on planar photonic crystals as new platforms for nanophotonic devices

Two-dimensional photonic crystal lasers have been fabricated on III–V semiconductor slabs. Tuning of the spontaneous emission in micro and nanocavities has been achieved by accurate control of the slab thickness. Different structures, some of them of new application to photonic crystal lasers, have been fabricated like the Suzuki-phase or the coupled-cavity ring-like resonators. Laser emission has been obtained by pulsed optical pumping. Optical characterization of the lasing modes have been performed showing one or more laser peaks centred around 1.55 μm. Far field characterization of the emission pattern has been realized showing different patterns depending on the geometrical shape of the structures. These kinds of devices may be used as efficient nanolaser sources for optical communications or optical sensors.     

综合网管中基于模型驱动的元数据管理

提出了一种基于模型驱动的元数据管理方案．方案采用了基于模型的形式化描述方法，统一了专业网管子系统间的元数据模式；通过引入模型驱动技术，从元模型的抽象层次消除了不同专业网管子系统之间存在的“信息孤岛”；方案还对综合网管环境下的元数据理论和交换机制进行了研究，并给出了元数据的管理框架以及元数据交换的Java接口映射．     

“后配额时代”中国纺织品服装出口预测

本文利用单整自回归移动平均模型,依据2000年1月至2004年12月中国纺织品服装出口额数据,对2005年和2006年中国纺织品服装出口走势进行预测分析。     

Integrated Groups and Smooth Distribution Groups

In this paper, we prove directly that α-times integrated groups define algebra homomorphisms. We also give a theorem of equivalence between smooth distribution groups and α-times integrated groups.     

A new type SVM-projected SVM

Support vector machine (SVM), developed by Vapnik et al., is a new and promising technique for classification and regression and has been proved to be competitive with the best available learning machines in many applications. However, the classification speed of SVM is substantially slower than that of other techniques with similar generalization ability. A new type SVM named projected SVM (PSVM), which is a combination of feature vector selection (FVS) method and linear SVM (LSVM), is proposed in present paper. In PSVM, the FVS method is first used to select a relevant subset (feature vectors, FVs) from the training data, and then both the training data and the test data are projected into the subspace constructed by FVs, and finally linear SVM(LSVM) is applied to classify the projected data. The time required by PSVM to calculate the class of new samples is proportional to the count of FVs. In most cases, the count of FVs is smaller than that of support vectors (SVs), and therefore PSVM is faster than SVM in running. Compared with other speeding-up techniques of SVM, PSVM is proved to possess not only speeding-up ability but also de-noising ability for high-noised data, and is found to be of potential use in mechanical fault pattern recognition.     

Surface roughness investigation of semi-conductor wafers

Conventionally, surface roughness is predominantly determined through the use of stylus instruments. However, there are certain limitations involved in the method, particularly when a test specimen, such as a silicon wafer, has a smooth mirror-like surface. Hence, it is necessary to explore alternative non-contact techniques. Light scattering has recently been gaining popularity as an optical technique to provide prompt and precise inspection of surface roughness. In this paper, the total integrated scattering (TIS) model is modified to retrieve parameters on surface micro-topography through light scattering. The applicability of the proposed modified TIS model is studied and compared with an atomic force microscope. Experimental results obtained show that the proposed technique is highly accurate for measuring surface roughness in the nanometer range.     

基于有限差分光束传播法的过渡波导功耗分析

为了在既定尺寸下减小斜坡波导和弯曲波导的功耗，设计了4种过渡波导形状函数。用有限差分光束传播法(FD-BPM)进行了模拟分析，发现过渡波导形状的选取与坡度和曲折角存在条件有关，并给出了条件表达式及其详细说明。     

Sum-fuzzy implementation of a choice function using artificial learning procedure with fixed fraction

In one if his paper Luo transformed the problem of sum-fuzzy rationality into artificial learning procedure and gave an algorithm which used the learning rule of perception. This paper extends the Luo method for finding a sum-fuzzy implementation of a choice function and offers an algorithm based on the artificial learning procedure with fixed fraction. We also present a concrete example which uses this algorithm.     

A method for determining optical constants, dimensions, and concentrations of “soft” absorbing particles in the brightening band region

We investigate the possibilities of creating a method for estimating the optical constants, dimensions, and concentrations of “soft” absorbing particles by applying a theoretical analysis of the angular dependence of the intergrated indicatrix, overall characteristics of light scattering, and absorption on the phase shift and diffraction parameter of particles in the brightening band region. We show that using the investigated optical characteristics, it is possible to determine the unknown parameters of a suspension from experimental data. Institute of Biophysics, Siberian Branch of the Russian Academy of Sciences, Akademgorodok, Krasnoyarsk, 660036, Russia. Translated from Zhurnal Prikladnoi Spektroskopii, Vol. 64, No. 6, pp. 807–812, November–December, 1997.