A neural network-based detection and mitigation system for unintended acceleration

Modern vehicles are equipped with a growing number of electronic devices, which significantly improve the driving experience. However, the complicated architecture of electronic systems also increases the difficulty of fault diagnosis since process models are often unavailable. This paper presents a novel detection and mitigation system for vehicle related anomalies originating in unintended acceleration (UA), which has become one of the most complained-about vehicle problems in recent history. The detection system consists of several neural network-based models, which are created by analyzing historical vehicle data at specific moments such as acceleration peaks and gear shifting. These data-driven models describe the boundary of normal vehicle behavior in the data space. A priori knowledge of complete vehicle structures is not necessary for building them. The detection system combines these models to decide if a UA event has occurred. When a UA event is detected, a mitigation system cuts the engine power and adjusts the braking force accordingly. The whole system was validated in the Simulink/dSPACE environment. UA errors were simulated so that they occurred randomly when human subjects drove virtual cars in a simulated environment. Random noise of sensors were also considered and incorporated to add realism. Various traffic scenarios were included in tests. Test results show that the integrated system is capable of detecting UA in one second with high accuracy and reducing the risk of accidents.     

Decentralized neural identification and control for uncertain nonlinear systems: Application to planar robot

This paper presents a discrete-time decentralized neural identification and control for large-scale uncertain nonlinear systems, which is developed using recurrent high order neural networks (RHONN); the neural network learning algorithm uses an extended Kalman filter (EKF). The discrete-time control law proposed is based on block control and sliding mode techniques. The control algorithm is first simulated, and then implemented in real time for a two degree of freedom (DOF) planar robot.     

On “an improved approach for nonlinear system identification using neural networks”

Nonlinear system identification and prediction is a complex task, and often non-parametric models such as neural networks are used in place of intricate mathematics. To that cause, recently an improved approach to nonlinear system identification using neural networks was presented in Gupta and Sinha (J. Franklin Inst. 336 (1999) 721). Therein a learning algorithm was proposed in which both the slope of the activation function at a neuron, β, and the learning rate, η, were made adaptive. The proposed algorithm assumes that η and β are independent variables. Here, we show that the slope and the learning rate are not independent in a general dynamical neural nétwork, and this should be taken into account when designing a learning algorithm. Further, relationships between η and β are developed which helps reduce the number of degrees of freedom and computational complexity in an optimisation task of training a fully adaptive neural network. Simulation results based on Gupta and Sinha (1999) and the proposed approach support the analysis.     

A novel technique for optimal placement of piezoelectric actuators on smart structures

The problem of positioning of actuators and sensors on smart materials has been a point of interest in recent years. This is due to the fact that in many practical applications there are limitations in space, weight, etc. of the smart structures, which make the problem of positioning more complex. In addition, it is required that the actuators/sensors have the best possible performance. The development of smart structures technology in recent years has provided numerous opportunities for vibration control applications. The use of piezoelectric ceramics or polymers has shown great promise in the development of this technology. The employment of piezoelectric material as actuators in vibration control is beneficial because these actuators only excite the elastic modes of the structures without exciting the rigid-body modes. This is important since very often only elastic motions of the structures are needed to be controlled. The purpose of this paper is to introduce a novel approach developed for optimizing the location of piezoelectric actuators for vibration suppression of flexible structures. A flexible fin with bonded piezoelectric actuators is considered in this study. The frequency response function (FRF) of the system is then recorded and maximization of the FRF peaks is considered as the objective function of the optimization algorithm to find the optimal placement of the piezoelectric actuators on the smart fin. Three multi-layer perceptron neural networks are employed to perform surface fitting to the discrete data generated by the finite element method (FEM). Invasive weed optimization (IWO), a novel numerical stochastic optimization algorithm, is then employed to maximize the weighted summation of FRF peaks. Results indicate an accurate surface fitting for the FRF peak data and an optimal placement of the piezoelectric actuators for vibration suppression is achieved.     

Delay-dependent stability for uncertain cellular neural networks with discrete and distribute time-varying delays

In this paper, the problem of stability of uncertain cellular neural networks with discrete and distribute time-varying delays is considered. Based on the Lyapunov function method and convex optimization approach, a new delay-dependent stability criterion of the system is derived in terms of LMI (linear matrix inequality). In order to solve effectively the LMI as a convex optimization problem, the interior-point algorithm is utilized in this work. A numerical example is given to show the effectiveness of our results.     

Delay-dependent exponential stability for a class of neural networks with time delays and reaction-diffusion terms

In this paper, the exponential stability of a class of delayed neural networks described by nonlinear delay differential equations of the neutral type has been studied. By constructing appropriate Lyapunov functional and using the linear matrix inequality (LMI) optimization approach, a series of sufficient criteria is obtained ensuring the existence, uniqueness and global exponential stability of an equilibrium point of such a kind of delayed neural networks. These conditions are dependent on the size of the time delay and the measure of the space, which is usually less conservative than delay-independent and space-independent ones. And, these networks are generalized without assuming the boundedness and differentiability of the activate functions. The proposed LMI condition can be checked easily by recently developed algorithms. The results are new and improve the earlier work. Examples are provided to demonstrate the effectiveness and applicability of the proposed criteria.     

Existence and global exponential stability of a periodic solution for a discrete-time interval general BAM neural networks

In this paper, a discrete-time interval general BAM bidirectional associative memory neural networks model is considered. By employing the theory of coincidence degree and using Halanay-type inequality technique we establish new sufficient conditions ensuring the existence and global exponential stability of periodic solutions for the discrete-time interval general BAM bidirectional neural networks. The results obtained generalize and improve known results in [23]. An example is provided to show the correctness of our analysis.     

A flow and routing control policy for communication networks with multiple competitive users

This paper is concerned with deriving an optimal flow and routing control policy for two-node parallel link communication networks with multiple competing users. The model assumes that each user has a flow demand which needs to be optimally selected and routed on the network links. The flow and routing control policy for each user seeks to maximize the user's total throughput and minimize its expected delay. To derive such a policy, we consider a utility function for each user that combines these two objectives in an additive fashion with preference constants that can be adjusted to reflect the user's own preferences between maximizing throughput and minimizing delay. Additionally, we provide each user with the ability to make these preferences link-dependent to reflect the user's preferences for certain links over others in the network. A condition that depends on the link capacities and preference constants is derived to guarantee the existence and uniqueness of a non-symmetric flow and routing control policy solution which satisfies the Nash equilibrium of non-cooperative game theory. The Nash equilibrium is a desirable solution for such networks because it insures that no user can improve its utility by unilaterally deviating from its Nash control policy. We discuss in detail several interesting properties of this equilibrium and in particular, its relationship to the users’ preference constants. Two illustrative examples are also presented.     

基于Zigbee和LabVIEW的新型城市照明监控系统

基于CC2530模块、Zigbee协议栈和LabVIEW编程设计了一种新型城市照明监控系统。该系统由自组织网络支撑,根据能量均衡的原则设计系统的基本架构;基于Zigbee协议栈进行功能定制,从而采集光照强度和链路质量强度,并为各节点设置自定义标签和睡眠周期;利用LabVIEW编程开发监控中心客户端。该系统首先由各监控节点采集信息,然后将这些信息发送给路由器或基站,最后上传给监控中心客户端,从而实现了城市照明系统精准、快速地监控与维护,此外,客户端还能在节点出现异常时报警。     

Design and comparison of LQG/LTR and H∞ controllers for a VSTOL flight control system

In this paper two robust controllers for a multivariable vertical short take-off and landing (VSTOL) aircraft system are designed and compared. The aim of these controllers is to achieve robust stability margins and good performance in step response of the system. LQG/LTR method is a systematic design approach based on shaping and recovering open-loop singular values while mixed-sensitivity H_∞ method is established by defining appropriate weighting functions to achieve good performance and robustness. Comparison of the two controllers show that LQG method requires rate feedback to increase damping of closed-loop system, while H_∞ controller by only proper choose the weighting functions, meets the same performance for step response. Output robustness of both controllers is good but H_∞ controller has poor input stability margin. The net controller order of H_∞ is higher than the LQG/LTR method and the control effort of them is in the acceptable range.     

创新系统研究30年:发展历程与研究展望

本文对30年来创新系统研究的发展进行了分析，涵盖了国家创新系统（NIS），区域创新系统（RIS），产业创新系统（SIS）以及技术创新系统（TIS）。文章按照创新系统研究的演化历程，分析了每个创新系统方法的理论起源，考察了引用最多的案例研究，分析了空间边界和分析单元，探讨了基本组成要素功能和分类方法，以厘清创新系统研究的理论体系，并在此基础上提出了每个创新系统研究方法需要进一步的研究。最后，对创新系统今后的研究进行了展望：加强创新系统方法的指向性和规范性导向；对创新系统分析框架内的最新方法进行整合，开展全球创新系统研究；加强对新兴经济体国家的研究，进一步证明创新系统理论在不同国家情境下的适用性。     

An integrated holistic model for an eHealth system: A national implementation approach and a new cloud-based security model

Although its structure and strategies are rapidly evolving, the impact of the eHealth on the healthcare services is evident. Implementing eHealth systems on a national level can drastically enhance the health practices and services provided to the patients and community. Hence, the engineering of a new model and a holistic framework for eHealth systems becomes a necessity in order to have an effective implementation of these systems. The vast and rapid development in computers, communication, and Internet technologies has significantly affected the contemporary health systems. However, the complexity of the healthcare environment, the abundance of information, the compatibility and the lack of unified eHealth framework creates real challenges to present efficient and attractive eHealth model that encompasses all these elements. Furthermore, the security of the health records and the secure access to the information add a new dimension of complexity. This work presents a new model and an integrated framework for an efficient implementation of eHealth systems at the national level. The proposed model and framework successfully incorporate all the success factors of efficient eHealth system along with a new security model to access the health records.     

A study of the information needs of the users of a folk music library and the implications for the design of a digital library system

A qualitative study of user information needs is reported, based on a purposive sample of users and potential users of the Vaughan Williams Memorial Library, a small specialist folk music library in North London. The study set out to establish what the users’ (both existing and potential) information needs are, so that the library’s online service may take them into account with its design. The information needs framework proposed by Nicholas [Nicholas, D. (2000) Assessing information needs: tools, techniques and concepts for the internet age. London: ASLIB] is used as an analytical tool to achieve this end. The demographics of the users were examined in order to establish four user groups: Performer, Academic, Professional and Enthusiast. Important information needs were found to be based on social interaction, and key resources of the library were its staff, the concentration of the collection and the library’s social nature. A collection of broad design requirements are proposed based on the analysis and this study also provides some insights into the issue of musical relevance, which are discussed.