基于本体学习与动态内容识别的信息抽取系统自优化研究

随着信息抽取技术的日益发展,信息抽取的准确性、效率、覆盖率以及维护成本等综合性能的提高成为有待突破的核心问题。提升信息抽取系统在运行过程中的自我优化能力是解决这个问题的关键。本文针对目前信息抽取系统优化中存在的人工参与过多、训练集要求过高等问题,提出一种基于本体学习与动态内容识别相结合的自优化方式,即通过动态内容识别结构化抽取结果,借助发掘的新概念促进本体学习,之后用新本体生成新抽取模式,循环迭代,最终实现信息抽取系统不断自优化。最后设计了系统实验方案并进行实验,实验结果证明在该自优化方案下抽取的准确性与覆盖率得到显著提升。

融合HOG+SVM与MFCC特征的自动优化物体识别系统研究

在与人交互情况下,针对物体识别系统通过反馈信息自动优化识别能力问题,提出一种结合梯度直方图(HOG)特征提取和支持向量机(SVM)进行特定物体识别的方法。运用Tensorflow训练语音识别模型反馈人机交互信息,使系统实现自优化。以手表类别作为识别对象,通过HOG特征描述对手表进行特征提取,通过二维主成分分析(2DPCA)和线性判别分析(LDA)对整体和局部特征进行降维,运用改进的空间金字塔匹配模型通过SVM对其分类,并运用非极大值抑制(NMS)确定区域,运用训练的梅尔倒谱(MFCC)特征语音识别模型对反馈信息进行识别,最终整合信息优化识别系统。实验表明,该系统对手表有较高的识别率,并能通过人机交流在较短时间内使系统实现自优化。

Optimal Decoupling Control Method and Its Application to a Ball Mill Coal-pulverizing System

Abstract-The conventional optimal tracking control method cannot realize decoupling control of linear systems with a strong coupling property. To solve this problem, in this paper, an optimal decoupling control method is proposed, which can simultaneousiy provide optimal performance. The optimal decoupling controller is composed of an inner-loop decoupling controller and an outer-loop optimal tracking controller. First, by introducing one virtual control variable, the original differential equation on state is converted to a generalized system on output. Then, by introducing the other virtual control variable, and viewing the coupling terms as the measurable disturbances, the generalized system is open-loop decoupled. Finally, for the decoupled system, the optimal tracking control method is used. It is proved that the decoupling control is optimal for a certain performance index. Simulations on a ball mill coal-pulverizing system are conducted. The results show the effectiveness and superiority of the proposed method as compared with the conventional optimal quadratic tracking （LQT） control method.

Allocation optimization of bicycle-sharing stations at scenic spots

Bicycle-sharing system is considered as a green option to provide a better connection between scenic spots and nearby metro/bus stations. Allocating and optimizing the layout of bicycle-sharing system inside the scenic spot and around its influencing area are focused on. It is found that the terrain, land use, nearby transport network and scenery point distribution have significant impact on the allocation of bicycle-sharing system. While the candidate bicycle-sharing stations installed at the inner scenic points, entrances/exits and metro stations are fixed, the ones installed at bus-stations and other passenger concentration buildings are adjustable. Aiming at minimizing the total cycling distance and overlapping rate, an optimization model is proposed and solved based on the idea of cluster concept and greedy heuristic. A revealed preference/stated preference （RP/SP） combined survey was conducted at Xuanwu Lake in Nanjing, China, to get an insight into the touring trip characteristics and bicycle-sharing tendency. The results reveal that 39.81% visitors accept a cycling distance of 1-3 km and 62.50% respondents think that the bicycle-sharing system should charge an appropriate fee. The sttrvey indicates that there is high possibility to carry out a bicycle-sharing system at Xuanwu Lake. Optimizing the allocation problem cluster by cluster rather than using an exhaustive search method significantly reduces the computing amount from O（2^43） to O（43 2）. The 500 m-radius-coverage rate for the alternative optimized by 500 m-radius-cluster and 800 m-radius-cluster is 89.2% and 68.5%, respectively. The final layout scheme will provide decision makers engineering guidelines and theoretical support.

Self-Optimizing Flexible Assembly Systems

Today＇s production systems are demanded to exhibit an increased flexibility and mutability in order to deal with dynamically changing conditions, objectives and an increasing number of product variants within industrial turbulent environments. Flexible automated systems are requested in order to improve dynamic production efficiency, e.g. robot-based hardware and PC-based controllers, but these usually induce a significantly higher production complexity, whereby the efforts for planning and programming, but also setups and reconfiguration, expand. In this paper a definition and some concepts of self-optimizing assembly systems are presented to describe possible ways to reduce the planning efforts in complex production systems. The concept of self-optimization in assembly systems will be derived from a theoretical approach and will be transferred to a specific application scenario---the automated assembly of a miniaturized solid state laser--where the challenges of unpredictable influences from e.g. component tolerances can be overcome by the help of self-optimization.

Dynamical Correction of Control Laws for Marine Ships’ Accurate Steering

The objective of this work is the analytical synthesis problem for marine vehicles autopilots design. Despite numerous known methods for a solution, the mentioned problem is very complicated due to the presence of an extensive population of certain dynamical conditions, requirements and restrictions, which must be satisfied by the appropriate choice of a steering control law. The aim of this paper is to simplify the procedure of the synthesis, providing accurate steering with desirable dynamics of the control system. The approach proposed here is based on the usage of a special unified multipurpose control law structure that allows decoupling a synthesis into simpler particular optimization problems. In particular, this structure includes a dynamical corrector to support the desirable features for the vehicle＇s motion under the action of sea wave disturbances. As a result, a specialized new method for the corrector design is proposed to provide an accurate steering or a trade-off between accurate steering and economical steering of the ship. This method guaranties a certain flexibility of the control law with respect to an actual environment of the sailing;its corresponding turning can be realized in real time onboard.

Adaptive bands filter bank optimized by genetic algorithm for robust speech recognition system

Perceptual auditory filter banks such as Bark-scale filter bank are widely used as front-end processing in speech recognition systems.However,the problem of the design of optimized filter banks that provide higher accuracy in recognition tasks is still open.Owing to spectral analysis in feature extraction,an adaptive bands filter bank (ABFB) is presented.The design adopts flexible bandwidths and center frequencies for the frequency responses of the filters and utilizes genetic algorithm (GA) to optimize the design parameters.The optimization process is realized by combining the front-end filter bank with the back-end recognition network in the performance evaluation loop.The deployment of ABFB together with zero-crossing peak amplitude (ZCPA) feature as a front process for radial basis function (RBF) system shows significant improvement in robustness compared with the Bark-scale filter bank.In ABFB,several sub-bands are still more concentrated toward lower frequency but their exact locations are determined by the performance rather than the perceptual criteria.For the ease of optimization,only symmetrical bands are considered here,which still provide satisfactory results.

Parametric optimization of friction stir welding process of age hardenable aluminum alloys-ANFIS modeling

A comparative approach was performed between the response surface method(RSM) and the adaptive neuro-fuzzy inference system(ANFIS) to enhance the tensile properties, including the ultimate tensile strength and the tensile elongation, of friction stir welded age hardenable AA6061 and AA2024 aluminum alloys. The effects of the welding parameters, namely the tool rotational speed, welding speed, axial load and pin profile, on the ultimate tensile strength and the tensile elongation were analyzed using a three-level, four-factor Box-Behnken experimental design. The developed design was utilized to train the ANFIS models. The predictive capabilities of RSM and ANFIS were compared based on the root mean square error, the mean absolute error, and the correlation coefficient based on the obtained data set. The results demonstrate that the developed ANFIS models are more effective than the RSM model.

Web-Based Synthetic Optimization Design System of Micro-Components

In order to meet the requirement of network synthesis optimization design for a micro component, a three-level information frame and functional module based on web was proposed. Firstly, the finite element method （FEM） was used to analyze the dynamic property of coupled-energy-domain of virtual prototype instances and to obtain some optimal information data. Secondly, the rough set theory （RST） and the genetic algorithm （GA） were used to work out the reduction of attributes and the acquisition of principle of optimality and to confirm key variable and restriction condition in the synthesis optimization design. Finally, the regression analysis （RA） and GA were used to establish the synthesis optimization design model and carry on the optimization design. A corresponding prototype system was also developed and the synthesis optimization design of a thermal actuated micro-pump was carded out as a demonstration in this paper.

Optimization Building Management

This paper demonstrates how achieving optimal integration between design and energy resources management can be particularly attractive in terms of energy consumption saving （cooling and heating） and lowering greenhouse gas emissions. The building automation system is based on innovative middleware framework which simplifies the modeling of a software for intelligent management of buildings and allows a multistandard and multiprotocol integration of sensors and actuators. The project has the target of underlining the economical opportunities and perspectives concerning the smart system adoption. Estimating the effects of home automation is essential to help its implementation, especially now that energy cost represents a consistent part of the house/building consumptions and will increase in the next few years. The results of the framework application in a residential building proves the validity of the proposed solution.

Synthesis and optimization of utility system using parameter adaptive differential evolution algorithm

Synthesis and optimization of utility system usually involve grassroots design, retrofitting and operation optimization, which should be considered in modeling process. This paper presents a general method for synthesis and optimization of a utility system. In this method, superstructure based mathematical model is established, in which different modeling methods are chosen based on the application. A binary code based parameter adaptive differential evolution algorithm is used to obtain the optimal con figuration and operation conditions of the system. The evolution algorithm and models are interactively used in the calculation, which ensures the feasibility of con figuration and improves computational ef ficiency. The capability and effectiveness of the proposed approach are demonstrated by three typical case studies.

Optimised Pattern Recognition for Robotic Weldment Geometry Measuring

Today, automated robot welding of components with low tolerances in series production is state-of-the-art. But turning to small batch production particularly of parts with high tolerances, engineering and construction of automated solutions is just at the beginning of providing economic efficiency. While weld seam tracking is well established for the described problem, geometric recognition of weldments is not yet solved satisfactorily. This paper will present an optimisation approach of a laser sensor guided and programmed robot welding system which was developed within the project ROPROF at the TU Dortmund. With this development, a working prototype of a robot weld system was built by a steel construction company as well as additional demonstration software showing the potential and transferability of adjusted geometric location of weldments for industrial applications.

Optimized Ewald sum for electrostatics in molecular self-assembly systems at interfaces

We extend the recent formulation of the Ewald sum for electrostatics in a two-dimensionally periodic three-dimensional multi- atom layer or two-dimensional single-atom layer system with a rectangular periodic boundary condition （J Chem Theory, Comput, 2014, 10： 534-542） to that with a parallelogrammic periodic boundary condition in general. Following the discussion of an efficient implementation of the formula, we suggest a simple setup of parameters using a relatively smaller screening factor and the associated larger real space cutoff distance to reach an optimized algorithm of an order N computational cost. The connection between the previous application of the Ewald sum to ionic crystal systems and the future application to mo- lecular self-assembly or disassembly systems on solid surfaces or at liquid-liquid interfaces ate illustrated to demonstrate the applicability of the present work to simulate the self-assembly process and to produce dynamical, structural and thermody- namic properties of experimental self-assembly systems of interest.

A new variational inequality formulation for unconfined seepage flow through fracture networks

Darcy's law only applying to the flow domain is extended to the entire fracture network domain including the dry domain.The partial differential equation(PDE) formulation for unconfined seepage flow problems for discrete fracture network is established,in which a boundary condition of Signorini's type is prescribed over the potential seepage surfaces.In order to reduce the difficulty in selecting trial functions,a new variational inequality formulation is presented and mathematically proved to be equivalent to the PDE formulation.The numerical procedure based on the VI formulation is proposed and the corresponding algorithm has been developed.Since a continuous penalized Heaviside function is introduced to replace a jump function in finite element analysis,oscillation of numerical integration for facture elements cut by the free surface is eliminated and stability of numerical solution is assured.The numerical results from two typical examples demonstrate,on the one hand the effectiveness and robustness of the proposed method,and on the other hand the capability of predicting main seepage pathways in fractured rocks and flow rates out of the drainage system,which is very important for performance assessments and design optimization of complex drainage system.

Optimization of the transmitted wavefront for the infrared adaptive optics system

The adaptive optics system for the second-generation Very Large Telescope-interferometer(VLTI)instrument GRAVITY consists of a novel cryogenic near-infrared wavefront sensor to be installed at each of the four unit telescopes of the Very Large Telescope(VLT).Feeding the GRAVITY wavefront sensor with light in the 1.4–2.4μm band,while suppressing laser light originating from the GRAVITY metrology system requires custom-built optical componets.In this paper,we present the development of a quantitative near-infraredpoint diffraction interferometric characterization technique,which allows measuring the transmitted wavefront error of the silicon entrance windows of the wavefront sensor cryostat.The technique can be readily applied to quantitative phase measurements in the near-infrared regime.Moreover,by employing a slightly off-axis optical setup,the proposed method can optimize the required spatial resolution and enable real time measurement capabilities.The feasibility of the proposed setup is demonstrated,followed by a theoretical analysis and experimental results.Our experimental results show that the phase error repeatability in the nanometer regime can be achieved.