基于机器学习的图像分割算法研究

图像分割是计算机视觉研究中重要的一部分,其主要目的是在图像中将兴趣域目标与背景分割,关系到后续的目标识别、图像理解等操作的准确性.经过几十年的发展,许多优秀的图像分割的方法被提出.机器学习是当今时代的研究热点,基于深度卷积神经网络等机器学习的图像分割研究进展迅速.总结介绍了应用于图像分割的几种典型机器学习方法,分析比较了相关的分割原理步骤、优缺点和发展现状.最后分析了基于机器学习的图像分割算法的发展方向.     

Machine learning in control of functional electrical stimulationsystems for locomotion

Two machine learning techniques were evaluated for automatic design of a rule-based control of functional electrical stimulation (FES) for locomotion of spinal cord injured humans. The task was to learn the invariant characteristics of the relationship between sensory information and the FES-control signal by using off-line supervised training. Sensory signals were recorded using pressure sensors installed in the insoles of a subject's shoes and goniometers attached across the joints of the affected leg. The FES-control consisted of pulses corresponding to time intervals when the subject pressed on the manual push-button to deliver the stimulation during FES-assisted ambulation. The machine learning techniques used were the adaptive logic network (ALN) and the inductive learning algorithm (IL). Results to date suggest that, given the same training data, the IL learned faster than the ALN while both performed the test rapidly. The generalization was estimated by measuring the test errors and it was better with an ALN, especially if past points were used to reflect the time dimension. Both techniques were able to predict future stimulation events. An advantage of the ALN over the IL was that ALN's can be retrained with new data without losing previously collected knowledge. The advantages of the IL over the ALN were that the IL produces small, explicit, comprehensible trees and that the relative importance of each sensory contribution can be quantified     

基于双闭环控制的食盐自动装箱机控制系统设计

针对目前食盐装箱系统中自动化程度低、控制精度低等问题,设计了一套基于PLC的双闭环自动装箱机控制系统。在此详细介绍了系统的工艺流程,系统阐述了控制系统的I/O分配与接线,分析了控制流程,完成了控制系统的设计。该控制系统实现了控制过程的自动化,提高了系统的稳定性与可靠性。     

基于模糊控制的全自动洗衣机的设计

文章设计了一种全自动洗衣机,该洗衣机利用MC6805R3单片机模糊控制,能够实现自动对衣服的数量、质地和污染程度进行识别,通过模糊控制原理决定清洗衣服的过程,合理投入适量的洗衣剂,从而大大提高洗衣质量,也大大提高洗衣机的全自动化程度。     

三轴钻专用机床的PLC 控制系统

本文以三轴钻机床为研究对象,实现了机床的PLC控制系统设计。对PLC 控制系统中硬件的参数进行匹配,编写了机床定位模块的定位程序以及机床 PLC 的控制程序,实现了用 PLC 控制变频器对机床主轴无级调速,用定位模块对机床主轴的进给位置进行精确控制。     

Iterative learning contouring control for five-axis machine tools and industrial robots

The five-axis machine tool and industrial robot are two important systems in modern manufacturing systems. For accurate machining, the contouring control of these systems is essential. However, it is seldom studied in the literature. This is because of the unique features of such multi-axis motion systems: (1) they involve complicated kinematics; (2) not only contour error, but also orientation error should be minimized for the contouring control. In this paper, the iterative learning contouring control (ILCC) algorithm proposed previously by the authors will be applied to both the 5-axis machine tool and industrial robot. The control objective of the ILCC is the equivalent contour error, whose reduction is equivalent to the reduction of both contour error and orientation error. Moreover, the equivalent contour error can be easily constructed in the machine axis coordinates. Experiments on a commercial 5-axis machine tool and an industrial robot are conducted. It is found that either for the 5-axis machine tool or for the industrial robot, both the contour error and orientation error can monotonically converge almost at each time step, and the RMS contour error and orientation error can be reduced more than 90% after several learning iterations. The experimental results confirm the effectiveness of the proposed ILCC on the contouring control of both 5-axis machine tool and industrial robot.     

Spatio-temporal metric learning for individual recognition from locomotion

Individual recognition from locomotion is a challenging task owing to large intra-class and small inter-class variations. In this article, we present a novel metric learning method for individual recognition from skeleton sequences. Firstly, we propose to model articulated body on Riemannian manifold to describe the essence of human motion, which can reflect biometric signatures of the enrolled individuals. Then two spatia-temporal metric learning approaches are proposed, namely Spatio-Temporal Large Margin Nearest Neighbor (ST-LMNN) and Spatio-Temporal Multi-Metric Learning (STMM), to learn discriminant bilinear metrics which can encode the spatio-temporal structure of human motion. Specifically, the ST-LMNN algorithm extends the bilinear model into classical Large Margin Nearest Neighbor method, which learns a low-dimensional local linear embedding in the spatial and temporal domain, respectively. To further capture the unique motion pattern for each individual, the proposed STMM algorithm learns a set of individual-specific spatio-temporal metrics, which make the projected features of the same person closer to its class mean than that of different classes by a large margin. Beyond that, we present a new publicly available dataset for locomotion recognition to evaluate the influence of both internal and external covariant factors. According to the experimental results from the three public datasets, we believe that the proposed approaches are both able to achieve competitive results in individual recognition.     

自动乒乓球发球机设计及其控制系统的探究

在我国乒乓球被视为"国球",它也是一项老少皆宜的健身运动项目,为了让学习者更好地练习乒乓球,根据乒乓球发球技术特点,我们发明了一种自动乒乓球发球机,本文针对自动乒乓球发球机设计及其控制系统进行了研究探索。     

高精度磨床电气系统加工恒温自动控制方法

由于系统内部的加工恒温控制精准度差,导致国内高精度磨床加工的凸轮轴精度达不到行业标准。基于此,提出高精度磨床电气系统加工恒温自动控制方法,对数字电位器和固态继电器的功率进行调节,控制交流调温模块。根据实验对比可知,本文提出的方法在恒温控制上远远优于传统方法,且可以确保温度维持在一个比较稳定而高的状态。     

A CNN-based chip for robot locomotion control

In this paper, the paradigm of emergent computation is applied to locomotion control in legged robots: the locomotion gait is the result of self-organization of a network of locally coupled nonlinear oscillators. This means to adopt the biological paradigm of central pattern generator (CPG), implemented by using cellular neural networks (CNNs). The whole control strategy is hybrid in the sense that the gait generation is accomplished by a fully analog CNN, while a simple logic unit modulates the behavior of the CNN-based CPG, so that the strategy is suitable to eventually include sensory feedback. The design of a VLSI chip implementing the CNN-based CPG and some experimental results on the chip are presented. The chip is designed using a switched-capacitor technique, fundamental to obtain in a simple and direct way some key features of the hybrid control discussed. The experimental results confirm the suitability of the approach.     

基于西门子S7-200PLC实现药片装瓶机自动控制

自动药片装瓶机,是对不同形状的药片进行计数、装瓶的专用设备。采用西门子S7-200PLC技术,实现装瓶机的启动、停止以及中途改变装填粒数的功能。在分析装瓶机系统工艺过程和控制要求的基础上,进行PLC硬件和软件设计,经上机模拟调试,调试结果与实际控制要求一致。本装瓶机控制系统具有药片数量显示功能、装瓶速度快、计数准确、线路简洁、控制灵活的优点。     

基于西门子S7-200PLC实现药片装瓶机自动控制

自动药片装瓶机,是对不同形状的药片进行计数、装瓶的专用设备.采用西门子S7-200PLC技术,实现装瓶机的启动、停止以及中途改变装填粒数的功能.在分析装瓶机系统工艺过程和控制要求的基础上,进行PLC硬件和软件设计,经上机模拟调试,调试结果与实际控制要求一致.本装瓶机控制系统具有药片数量显示功能、装瓶速度快、计数准确、线路简洁、控制灵活的优点.     

数学在自动控制中的应用

现代工业自动化控制中．通过PLC／DCS实现数字化控制越来越普遍。将一些典型的过程控制抽象为简单的数学算法,将数学模型应用于控制方法教学中,可使教学生动且具有实践性,同时也可增强学生对控制实现过程的理解。     

数学在自动控制中的应用

现代工业自动化控制中,通过PLC/DCS实现数字化控制越来越普遍.将一些典型的过程控制抽象为简单的数学算法,将数学模型应用于控制方法教学中,可使教学生动且具有实践性,同时也可增强学生对控制实现过程的理解.     

Chip-in-the-loop learning algorithm for Boltzmann machine

A new algorithm is presented for chip-in-the-loop learning of the synchronous Boltzmann machine, which has two distinct advantages: it allows optimal use of analogue circuit dynamic range, unlike the conventional learning algorithm, and it features a coherent dual weight representation, which improves learning efficiency     

英汉机器翻译中的短语自动识别算法

为了准确识别短语,设计了一种英汉机器翻译短语自动识别新算法。首先构建标记规模约为58万个英汉单词的短语语料库,为短语赋予基本的可搜索功能,保证翻译真实度;然后以短语中心点构造短语结构,改进标准GLR算法,在短语语料库的短语标记上识别短语词性,得到词性识别结果;最后通过解析线性表的句法功能校正词性识别结果中的英汉结构歧义,得到最终的识别结果。实验组织测评小组以打分方式对所设计的算法进行测评,测评结果证明算法的短语识别精度、识别速度和更新能力均很优秀。     

Machine learning techniques as a helpful tool toward determination of plaque vulnerability

Atherosclerotic cardiovascular disease results in millions of sudden deaths annually, and coronary artery disease accounts for the majority of this toll. Plaque rupture plays main role in the majority of acute coronary syndromes. Rupture has been usually associated with stress concentrations, which are determined mainly by tissue properties and plaque geometry. The aim of this study is develop a tool, using machine learning techniques to assist the clinical professionals on decisions of the vulnerability of the atheroma plaque. In practice, the main drawbacks of 3-D finite element analysis to predict the vulnerability risk are the huge main memories required and the long computation times. Therefore, it is essential to use these methods which are faster and more efficient. This paper discusses two potential applications of computational technologies, artificial neural networks and support vector machines, used to assess the role of maximum principal stress in a coronary vessel with atheroma plaque as a function of the main geometrical features in order to quantify the vulnerability risk.     

Linear control rules for production control of semiconductor fabs

We consider the problem of reducing the cycle time required for producing wafers at a given rate in high-volume single-product semiconductor fabs. Based on theoretical results, we propose a new method of input control that uses intersecting hyperplanes to decide when to release a new lot into the wafer fab. The release control rules constructed thus are said to belong to the class of linear control rules. We provide numerical examples to demonstrate that our method gives nearly optimal results for flowline and probabilistic reentrant flowline models. We then propose the linear control rule called descending control (DEC) and give a hybrid simulation-optimization procedure for determining DEC rules in real-life settings. We provide numerical results for the HP development fab model of Wein     

Relevance vector machine for automatic detection of clustered microcalcifications

Clustered microcalcifications (MC) in mammograms can be an important early sign of breast cancer in women. Their accurate detection is important in computer-aided detection (CADe). In this paper, we propose the use of a recently developed machine-learning technique--relevance vector machine (RVM)--for detection of MCs in digital mammograms. RVM is based on Bayesian estimation theory, of which a distinctive feature is that it can yield a sparse decision function that is defined by only a very small number of so-called relevance vectors. By exploiting this sparse property of the RVM, we develop computerized detection algorithms that are not only accurate but also computationally efficient for MC detection in mammograms. We formulate MC detection as a supervised-learning problem, and apply RVM as a classifier to determine at each location in the mammogram if an MC object is present or not. To increase the computation speed further, we develop a two-stage classification network, in which a computationally much simpler linear RVM classifier is applied first to quickly eliminate the overwhelming majority, non-MC pixels in a mammogram from any further consideration. The proposed method is evaluated using a database of 141 clinical mammograms (all containing MCs), and compared with a well-tested support vector machine (SVM) classifier. The detection performance is evaluated using free-response receiver operating characteristic (FROC) curves. It is demonstrated in our experiments that the RVM classifier could greatly reduce the computational complexity of the SVM while maintaining its best detection accuracy. In particular, the two-stage RVM approach could reduce the detection time from 250 s for SVM to 7.26 s for a mammogram (nearly 35-fold reduction). Thus, the proposed RVM classifier is more advantageous for real-time processing of MC clusters in mammograms.