关键词：
Almost periodic solution;Exponential dichotomy;Multidirectional associative memory neural networks;Multistability
摘要：
In this paper, the multiplicity of almost periodic solutions is studied for a multidirectional associative memory (MAM) neural network with almost periodic coefficients and continuously distributed delays. Under some assumptions on activation functions, some invariant subsets of the MAM neural network are constructed. The existence of multiple almost periodic solutions are obtained by using the theory of exponential dichotomy and Schauder's fixed point theorem. Furthermore, a sufficient condition is derived for the local exponential stability of some almost periodic solutions and their exponential attracting domains are also given. An example is given to illustrate the effectiveness of the results. (C) 2015 Elsevier B.V. All rights reserved.
摘要：
A multidirectional associative memory (MAM) neural network with periodic coefficients and distributed delays is studied. By constructing a Poincaré mapping, some sufficient conditions are obtained ensuring existence, uniqueness and the global exponential stability of a periodic solution of MAM neural network. The result is new to MAM neural networks. An example is given to illustrate the effectiveness of the result.
摘要：
Massive events can be produced today because of the rapid development of the Internet of Things (IoT). Complex event processing, which can be used to extract high-level patterns from raw data, has become an essential part of the IoT middleware. Prediction analytics is an important technology in supporting proactive complex event processing. In this paper, we propose the use of dynamic Bayesian model averaging to develop a high-accuracy prediction analytic method for large-scale IoT application. This method, which is based on a new multilayered adaptive dynamic Bayesian network model, uses Gaussian mixture models and expectation-maximization inference for basic Bayesian prediction. Bayesian model averaging is implemented by using Markov chain Monte Carlo approximation, and a novel dynamic Bayesian model averaging method is proposed based on event context clustering. Simulation experiments show that the proposed prediction analytic method has better accuracy compared to traditional methods. Moreover, the proposed method exhibits acceptable performance when implemented in large-scale IoT applications.
通讯机构：
[Jiang, Ping] C;Cent S Univ, Coll Mech & Elect Engn, Changsha 410083, Peoples R China.
关键词：
INERTIAL SENSOR;LASER;LOCALIZATION;MOBILE STATION
摘要：
To realize the precise localization of the working machinery in the paddy field, a 3-point laser localization system has been designed based on the experiments of Inertial Localization. This system is composed of the base station with the fixed distance and the moving station fixed on the carrier. The base stations mainly control the laser emission device to trace the corresponding laser receiving device, while the mobile station mainly collects the data of the sensors and calculates the position coordination. The experiment shows that the localization error is less than 10 cm on the test range of 50 meters, and the system is reliable localization.
关键词：
construction machine;multi-Agent technology;fuzzy;fault diagnosis
摘要：
The number of construction machinery faults is too much and its diagnosis are fuzzy and complex. We construct the fault hierarchy model by the means of hierarchy analysis and obtain all kinds of Possibility degree of faults factors through the triangular fuzzy complementary judgment matrix. Take the fault diagnosis of diesel engine fuel system, this paper establish intelligent fault diagnosis system, which has the ability of self-learning and self-correction using multi-agent technology.
