摘要：A discrete observer-based repetitive control(RC) design method for a linear system with uncertainties was presented based on two-dimensional(2D) system theory. Firstly, a 2D discrete model was established to describe both the control behavior within a repetition period and the learning process taking place between periods. Next, by converting the designing problem of repetitive controller into one of the feedback gains of reconstructed variables, the stable condition was obtained through linear matrix inequality(LMI) and also the gain coefficient of repetitive system. Numerical simulation shows an exceptional feasibility of this proposal with remarkable robustness and tracking speed.

摘要：Knowledge about human beings is an integral part of any intelligent agent ofconsiderable significance. Delimiting, modeling and acquiring such knowledge are the centraltopics of this paper. Because of the tremendous complexity in knowledge of human beings, weintroduce a top-level ontology of human beings from the perspectives of psychology, sociology,physiology and pathology. This ontology is not only an explicit conceptualization of humanbeings, but also an efficient way of acquiring and organizing relevant knowledge.

摘要：This paper is concerned with the problem of the full-order observer design for a class of fractional-order Lipschitz nonlinear systems. By introducing a continuous frequency distributed equivalent model and using an indirect Lyapunov approach, the sufficient condition for asymptotic stability of the full-order observer error dynamic system is presented. The stability condition is obtained in terms of LMI, which is less conservative than the existing one. A numerical example demonstrates the validity of this approach.

摘要：The performance of the classical clustering algorithm is not always satisfied with the high-dimensional datasets, which make clustering method limited in many application. To solve this problem, clustering method with Projection Pursuit dimension reduction based on Immune Clonal Selection Algorithm (ICSA-PP) is proposed in this paper. Projection pursuit strategy can maintain consistent Euclidean distances between points in the low-dimensional embeddings where the ICSA is used to search optimizing projection direction. The proposed algorithm can converge quickly with less iteration to reduce dimension of some high-dimensional datasets, and in which space, K-mean clustering algorithm is used to partition the reduced data. The experiment results on UCI data show that the presented method can search quicker to optimize projection direction than Genetic Algorithm (GA) and it has better clustering results compared with traditional linear dimension reduction method for Principle Component Analysis (PCA).

摘要：Graphical representation is a very efficient tool for visual analysis of protein sequences. In this paper, a novel 2D graphical representation scheme is proposed on the basis of a newly introduced concept, named characteristic model of the protein sequences. After obtaining the 2D graphics of protein sequences, two numerical characterizations of them is designed as descriptors to analyze the nine DN5 protein sequences, simulation and analysis results show that, comparing with existing methods, our method is not only visible, intuitional, and simple, but also has no circuit or degeneracy, and even more important, since the storage space required by our method is constant and has nothing to do with the length of protein sequences, then it can keep excellent visual inspection for long protein sequences.

摘要：This paper presents a new model for edge extraction of MR images, based on curve evolution and edgeflow techniques. At first the model for curve evolution is constructed, which automatically detect boundaries, and change of topology in terms of the edgeflow fields, and then the numerical approximation of the model is introduced, which is based on semi-implicit scheme to speed up the proposed approach. Finally, the numerical implementation is present and the experimental results show that the proposed model successfully extracts the edge contours, regardless of the heavy noise.

摘要：Brain-like computer research and development have been growing rapidly in recent years. It is necessary to design large scale dynamical neural networks (more than 106 neurons) to simulate complex process of our brain. But such kind of task is not easy to achieve only based on the analysis of partial differential equations, especially for those complex neural models, e.g. Rose-Hindmarsh (RH) model. So in this paper, we develop a novel approach by combining fuzzy logical designing with Proximal Support Vector Machine Classifiers (PSVM) learning in the designing of large scale neural networks. Particularly, our approach can effectively simplify the designing process, which is crucial for both cognition science and neural science. At last, we conduct our approach on an artificial neural system with more than 108 neurons for haze-free task, and the experimental results show that texture features extracted by fuzzy logic can effectively increase the texture information entropy and improve the effect of haze-removing in some degree.

摘要：In this paper, we present a new scheme to segment a given image. This scheme utilizes neuro-fuzzy system to derive a proper set of contour pixels based on multi-scale images. We use these fuzzy derivatives to develop a new curve evolution model. The model automatically detect smooth boundaries, scaling the energy term, and change of topology according to the extracted con- tour pixels set. We present the numerical implementation and the experimental results based on the semi-implicit method. Experi- mental results show that one can obtains a high clualitv edge contour.

摘要：While Kinect was originally designed as a motion sensing input device of the gaming console Microsoft Xbox 360 for gaming purposes, it＇s easy-to-use, low-cost, reliability, speed of the depth measurement and relatively high quality of depth measurement make it can be used for 3D reconstruction. It could make 3D scanning technology more accessible to everyday users and turn 3D reconstruction models into much widely used asset for many applications. In this paper, we focus on Kinect 3D reconstruction.

摘要：先天性心脏病(CHD)是婴幼儿死亡主要原因。基于人工智能的先天性心脏病诊断网络(CHDNet)是一种基于超声心动图视频的二分类模型,用于判别超声心动图视频是否包含心脏缺陷。现有的CHDNet模型表现出与医学专家相当甚至更好的判别性能,但它们在训练集之外的样本上的不可靠性已成为模型部署的关键瓶颈。而这是当前大多数基于AI诊断方法的共性问题。为了克服这一挑战,本文我们提出了两种基本机制——贝叶斯推理和动态神经反馈——分别用于衡量和提高人工智能诊断的可靠性。贝叶斯推理允许神经网络模型输出CHD判别的可靠性而不仅仅是单一的判别结果,而动态神经反馈是一个计算神经反馈单元,允许神经网络将知识从输出层反馈给浅层,使神经网络有选择地激活相关神经元。为了评估这两种机制的有效性,我们在包含三种常见CHD缺陷的4151个超声心动图视频上训练了CHDNet,并在1037个超声心动图视频的内部测试集和从其他心血管成像设备新收集的692个外部视频集上对其进行了测试。每个超声心动图视频对应于一位患者和一次就诊。我们在多种代表性神经网络架构上展示了贝叶斯推理获得的可靠性如何解释和量化神经网络内部与外部测试集之间的性能显著差异,以及尽管输入被噪声破坏或使用外部测试集时,设计的反馈单元如何帮助神经网络保持高精度和可靠性。