Anomaly detection via a combination model in time series data

Since the time series data have the characteristics of a large amount of data and non-stationarity, we usually cannot obtain a satisfactory result by a single-model-based method to detect anomalies in time series data. To overcome this problem, in this paper, a combination-model-based approach is proposed by combining a similarity-measurement-based method and a model-based method for anomaly detection. First, the process of data representation is performed to generate a new data form to arrive at the purpose of reducing data volume. Furthermore, due to the anomalies being generally caused by changes in amplitude and shape, we take both the original time series data and their amplitude change data into consideration of the process of data representation to capture the shape and morphological features. Then, the results of data representation are employed to establish a model for anomaly detection. Compared with the state-of-the-art methods, experimental studies on a large number of datasets show that the proposed method can significantly improve the performance of anomaly detection with higher data anomaly resolution.

     

机器人系统全局渐近稳定非线性PD+轨迹跟踪控制

采用一类具有“小误差放大、大误差饱和”功能的非线性饱和函数来改进常用的线性比例微分加（ＰＤ＋）机器人系统动力学控制,以形成非线性ＰＤ＋（ＮＰＤ＋）控制,从而获得更快的响应速度和轨迹跟踪精度．应用Ｌｙａｐｕｎｏｖ直接稳定性理论和ＬａＳａｌｌｅ不变性原理证明了闭环系统的全局渐近稳定性．两自由度机器人系统数值仿真结果表明了所提出的ＮＰＤ＋控制具有良好的控制品质．     

Design and realization of hybrid ACO-based PID and LuGre friction compensation controller for three degree-of-freedom high precision flight simulator

Three degree-of-freedom (3-DOF) high precision flight simulator is a type of key hardware-in-loop equipment in the fields of aeronautics and astronautics. The conventional Proportional–Integral–Derivative (PID) is a widely used industrial controller that uses a combination of proportional, integral and derivative action on the control error to form the output of the controller. It is well known that the undesired phenomena caused by friction can lead to overall flight simulator performance degradation or instability. This paper presents a novel kind of hybrid Ant Colony Optimization (ACO)-based PID and LuGre friction compensation controller for 3-DOF high precision flight simulator. On the basis of introduction of the basic principles of ACO, the controlling scheme design for the 3-DOF high precision flight simulator is presented. Based on the popular LuGre friction model, a novel nonlinear friction compensation controller for 3-DOF high precision flight simulator is also developed. The proposed Lyapunov function proves the robust global convergence of the tracking error. The parameters tuning of PID can be summed up as the typical continual spatial optimization problem, grid-based searching strategy is adopted in the improved ACO algorithm, and self-adaptive control strategy for the pheromone decay parameter is also adopted. Modularization design is adopted in the 3-DOF high precision flight simulator. This software can process the position and status signals, and display them on the friendly interface. Double buffer mechanism is adopted in the communication protocol between lower Industrial Personal Computer (IPC) and upper IPC. The series experimental results have verified the feasibility and effectiveness of the proposed hybrid ACO-based PID and LuGre friction compensation controller.     

Synthesis of liveness enforcing supervisor for automated manufacturing systems using insufficiently marked siphons

A liveness enforcing supervisor synthesis technique is presented for Petri net modeling automated manufacturing systems. The insufficiently marked siphons are deployed to characterize the deadlock situations in an incidence matrix based way, which makes possible the study of the modeled systems from both structural and algebraic perspectives. The approach generates at each step a generalized mutual exclusion constraint which contains only markings for which liveness can be enforced. To avoid the explicit enumeration of all the set of strict minimal siphons, a set of mathematical programming formulations are established to implement the derivation of insufficiently marked siphons from the PT-transformation of the plant system. Further, a generalized elementary siphon control approach is involved such that the final supervisor can be structurally simplified. Several examples are used to illustrate these results.     

A cost matrix agent for shortest path routing in ad hoc networks

Wireless ad hoc networks do not rely on an existing infrastructure. They are organized as a network with nodes that act as hosts and routers to treat packets. With their frequent changes in topology, ad hoc networks do not rely on the same routing methods as for pre-established wired networks; they require routing methods for mobile wireless networks. To select a path from a source to a destination in dynamic ad hoc networks, an efficient and reliable routing method is very important. In this paper, we introduce a cost-matrix-based routing algorithm. An agent node creates topology information in the form of the adjacency-cost matrix which shows link costs of the network.Based on the adjacency-cost matrix, the minimum-cost matrix and the next-node matrices can be calculated. Based on the minimum-cost matrix and the next-node matrices, the minimum cost between source and destination nodes and between intermediate nodes on the minimum-cost paths can be calculated.The matrices are periodically distributed by the agent to the other nodes. Based on the minimum-cost matrix and the next-node matrices, each node decides the minimum-cost path to its destination. Because none of the nodes except the agent needs to gather network topology information, the control overhead of the proposed method is small compared with those of the general table-driven routing protocols.     

An integrated case-based reasoning and MCDM system for Web based tourism destination planning

The accelerating interaction between technology and tourism has changed radically the efficiency and effectiveness of tourism organizations, as well as how consumers interact with organizations. In this study, a Web based intelligent framework for travel agencies is proposed that offers customers a fast and reliable response service in a less costly manner. The proposed framework integrates case-based reasoning (CBR) system with a well-known multi criteria decision making (MCDM) technique, namely Analytic Hierarchy Process, to enhance the accuracy and speed in case matching in tourism destination planning. The integration of two techniques enables taking advantages of their strengths and complements each other’s weaknesses. A case study is performed to demonstrate how this framework can facilitate intelligent decision support by retrieving best-fitted responses for customers.     

Improving the generalization performance of RBF neural networks using a linear regression technique

In this paper we present a method for improving the generalization performance of a radial basis function (RBF) neural network. The method uses a statistical linear regression technique which is based on the orthogonal least squares (OLS) algorithm. We first discuss a modified way to determine the center and width of the hidden layer neurons. Then, substituting a QR algorithm for the traditional Gram–Schmidt algorithm, we find the connected weight of the hidden layer neurons. Cross-validation is utilized to determine the stop training criterion. The generalization performance of the network is further improved using a bootstrap technique. Finally, the solution method is used to solve a simulation and a real problem. The results demonstrate the improved generalization performance of our algorithm over the existing methods.     

Evidential grammars: A compositional approach for scene understanding. Application to multimodal street data

Automatic scene understanding from multimodal data is a key task in the design of fully autonomous vehicles. The theory of belief functions has proved effective for fusing information from several sensors at the superpixel level. Here, we propose a novel framework, called evidential grammars, which extends stochastic grammars by replacing probabilities by belief functions. This framework allows us to fuse local information with prior and contextual information, also modeled as belief functions. The use of belief functions in a compositional model is shown to allow for better representation of the uncertainty on the priors and for greater flexibility of the model. The relevance of our approach is demonstrated on multi-modal traffic scene data from the KITTI benchmark suite.     

机器人系统输出反馈重复学习轨迹跟踪控制

针对高度非线性多关节机器人的轨迹跟踪问题,提出一类输出反馈重复学习控制算法,使得在只有位置信息可测以及模型信息不确定的条件下即能获得良好的控制品质.非线性滤波器的引入解决了现实中速度信号较难获得的问题,重复学习控制策略实现了对周期性参考输入的渐近稳定跟踪.应用Lyapunov直接稳定性理论证明了闭环系统的全局渐近稳定性.三自由度机器人系统数值仿真结果表明了所提出的输出反馈重复学习控制的有效性.