Inverting recurrent neural networks for internal model control of nonlinear systems

In this paper, we show how a set of recently derived theoretical results for recurrent neural networks can be applied to the production of an internal model control system for a nonlinear plant. The results include determination of the relative order of a recurrent neural network and invertibility of such a network. A closed loop controller is produced without the need to retrain the neural network plant model. Stability of the closed-loop controller is also demonstrated.

The control of dynamical systems by neural networks

In this paper the use of neural networks for the control of dynamical systems is considered. Both identification and feedback control aspects are discussed as well as the types of system for which neural networks can provide a useful technique. Multi-layer Perceptron and Radial Basis function neural network types are looked at, with an emphasis on the latter. It is shown how basis function centre selection is a critical part of the implementation process and that multivariate clustering algorithms can be an extremely useful tool for finding centres.

Intelligent agents enabling negotiated control of pervasive environments

One of the important goals of the intelligent buildings especially in commercial applications is not only to minimize the energy consumption but also to enhance the occupant’s comfort. However, most of current development in the intelligent buildings focuses on an implementation of the automatic building control systems that can support energy efficiency approach. The consideration of occupants’ preferences is not adequate. To improve occupant’s wellbeing and energy efficiency in intelligent environments, we develop four types of agent combined together to form a multi-agent system to control the intelligent buildings. Users’ preferential conflicts are discussed. Furthermore, a negotiation mechanism for conflict resolution, has been proposed in order to reach an agreement, and has been represented in syntax directed translation schemes for future implementation and testing. Keywords: conflict resolution, intelligent buildings, multi-agent systems (MAS), negotiation strategy, syntax directed translation schemes (SDTS).

Strong structural controllability and the multi-link inverted pendulum

This technical note investigates the controllability of the linearized dynamics of the multilink inverted pendulum as the number of links and the number and location of actuators changes. It is demonstrated that, in some instances, there exist sets of parameter values that render the system uncontrollable and so usual methods for assessing controllability are difficult to employ. To assess the controllability, a theorem on strong structural controllability for single-input systems is extended to the multiinput case.

Change, rigidity & delay in the UK system of land-use development control

The British system of development control is time-consuming and uncertain in outcome. Moreover, it is becoming increasingly overloaded as it has gradually switched away from being centred on a traditional ‘is it an appropriate land-use?’ type approach to one based on multi-faceted inspections of projects and negotiations over the distribution of the potential financial gains arising from them. Recent policy developments have centred on improving the operation of development control. This paper argues that more fundamental issues may be a stake as well. Important market changes have increased workloads. Furthermore, the UK planning system's institutional framework encourages change to move in specific directions, which is not always helpful. If expectations of increased long-term housing supply are to be met more substantial changes to development control may be essential but hard to achieve.

A tutorial on pseudospectral methods for computational optimal control

[English] This paper is a tutorial introduction to pseudospectral optimal control. With pseudospectral methods, a function is approximated as a linear combination of smooth basis functions, which are often chosen to be Legendre or Chebyshev polynomials. Collocation of the differential-algebraic equations is performed at orthogonal collocation points, which are selected to yield interpolation of high accuracy. Pseudospectral methods directly discretize the original optimal control problem to recast it into a nonlinear programming format. A numerical optimizer is then employed to find approximate local optimal solutions. The paper also briefly describes the functionality and implementation of PSOPT, an open source software package written in C++ that employs pseudospectral discretization methods to solve multi-phase optimal control problems. The software implements the Legendre and Chebyshev pseudospectral methods, and it has useful features such as automatic differentiation, sparsity detection, and automatic scaling. The use of pseudospectral methods is illustrated in two problems taken from the literature on computational optimal control. [Portuguese] Este artigo e um tutorial introdutorio sobre controle otimo pseudo-espectral. Em metodos pseudo-espectrais, uma funcao e aproximada como uma combinacao linear de funcoes de base suaves, tipicamente escolhidas como polinomios de Legendre ou Chebyshev. A colocacao de equacoes algebrico-diferenciais e realizada em pontos de colocacao ortogonal, que sao selecionados de modo a minimizar o erro de interpolacao. Metodos pseudoespectrais discretizam o problema de controle otimo original de modo a converte-lo em um problema de programa cao nao-linear. Um otimizador numerico e entao empregado para obter solucoes localmente otimas. Este artigo tambem descreve sucintamente a funcionalidade e a implementacao de um pacote computacional de codigo aberto escrito em C++ chamado PSOPT. Tal pacote emprega metodos de discretizacao pseudo-spectrais para resolver problemas de controle otimo com multiplas fase. O PSOPT permite a utilizacao de metodos de Legendre ou Chebyshev, e possui caractersticas uteis tais como diferenciacao automatica, deteccao de esparsidade e escalonamento automatico. O uso de metodos pseudo-espectrais e ilustrado em dois problemas retirados da literatura de controle otimo computacional.

Coping with delays for real-time gaze control (The Fall and Rise of the Smiths Regulator)

In this paper we describe how to cope with the delays inherent in a real time control system for a steerable stereo head/eye platform. A purposive and reactive system requires the use of fast vision algorithms to provide the controller with the error signals to drive the platform. The time-critical implementation of these algorithms is necessary, not only to enable short latency reaction to real world events, but also to provide sufficiently high frequency results with small enough delays that controller remain stable. However, even with precise knowledge of that delay, nonlinearities in the plant make modelling of that plant impossible, thus precluding the use of a Smith Regulator. Moreover, the major delay in the system is in the feedback (image capture and vision processing) rather than feed forward (controller) loop. Delays ranging between 40msecs and 80msecs are common for the simple 2D processes, but might extend to several hundred milliseconds for more sophisticated 3D processes. The strategy presented gives precise control over the gaze direction of the cameras despite the lack of a priori knowledge of the delays involved. The resulting controller is shown to have a similar structure to the Smith Regulator, but with essential modifications.

Sources of multi-decadal variability in Arctic sea ice extent

The observed dramatic decrease in September sea ice extent (SIE) has been widely discussed in the scientific literature. Though there is qualitative agreement between observations and ensemble members of the Third Coupled Model Intercomparison Project (CMIP3), it is concerning that the observed trend (1979–2010) is not captured by any ensemble member. The potential sources of this discrepancy include: observational uncertainty, physical model limitations and vigorous natural climate variability. The latter has received less attention and is difficult to assess using the relatively short observational sea ice records. In this study multi-centennial pre-industrial control simulations with five CMIP3 climate models are used to investigate the role that the Arctic oscillation (AO), the Atlantic multi-decadal oscillation (AMO) and the Atlantic meridional overturning circulation (AMOC) play in decadal sea ice variability. Further, we use the models to determine the impact that these sources of variability have had on SIE over both the era of satellite observation (1979–2010) and an extended observational record (1953–2010). There is little evidence of a relationship between the AO and SIE in the models. However, we find that both the AMO and AMOC indices are significantly correlated with SIE in all the models considered. Using sensitivity statistics derived from the models, assuming a linear relationship, we attribute 0.5–3.1%/decade of the 10.1%/decade decline in September SIE (1979–2010) to AMO driven variability.

Electrical stimulation for trunk control in paraplegia:A feasibility study

Paraplegic subjects lack trunk stability due to the loss of voluntary muscle control.This leads to a restriction of the volume of bi-manual workspace available,and hence has a detrimental impact on activities of daily living. Electrical Stimulation of paralysed muscles can be used to stabilize the trunk, but has never been applied in closed loop for this purpose. This paper describes the development of two closed loop controllers(PID and LQR),and their experimental evaluation on a human subject. Advantages and disadvantages of the two are discussed,considering a potential use of this technology during daily activities.

A microchannel neuroprosthesis for bladder control after spinal cord injury in rat

A severe complication of spinal cord injury is loss of bladder function (neurogenic bladder), which is characterized by loss of bladder sensation and voluntary control of micturition (urination), and spontaneous hyperreflexive voiding against a closed sphincter (detrusor-sphincter dyssynergia). A sacral anterior root stimulator at low frequency can drive volitional bladder voiding, but surgical rhizotomy of the lumbosacral dorsal roots is needed to prevent spontaneous voiding and dyssynergia. However, rhizotomy is irreversible and eliminates sexual function, and the stimulator gives no information on bladder fullness. We designed a closed-loop neuroprosthetic interface that measures bladder fullness and prevents spontaneous voiding episodes without the need for dorsal rhizotomy in a rat model. To obtain bladder sensory information, we implanted teased dorsal roots (rootlets) within the rat vertebral column into microchannel electrodes, which provided signal amplification and noise suppression. As long as they were attached to the spinal cord, these rootlets survived for up to 3 months and contained axons and blood vessels. Electrophysiological recordings showed that half of the rootlets propagated action potentials, with firing frequency correlated to bladder fullness. When the bladder became full enough to initiate spontaneous voiding, high-frequency/amplitude sensory activity was detected. Voiding was abolished using a high-frequency depolarizing block to the ventral roots. A ventral root stimulator initiated bladder emptying at low frequency and prevented unwanted contraction at high frequency. These data suggest that sensory information from the dorsal root together with a ventral root stimulator could form the basis for a closed-loop bladder neuroprosthetic. Copyright © 2013, American Association for the Advancement of Science

Cost function for sub-agent elements in multi-agent energy management system

Distributed generation plays a key role in reducing CO2 emissions and losses in transmission of power. However, due to the nature of renewable resources, distributed generation requires suitable control strategies to assure reliability and optimality for the grid. Multi-agent systems are perfect candidates for providing distributed control of distributed generation stations as well as providing reliability and flexibility for the grid integration. The proposed multi-agent energy management system consists of single-type agents who control one or more gird entities, which are represented as generic sub-agent elements. The agent applies one control algorithm across all elements and uses a cost function to evaluate the suitability of the element as a supplier. The behavior set by the agent's user defines which parameters of an element have greater weight in the cost function, which allows the user to specify the preference on suppliers dynamically. This study shows the ability of the multi-agent energy management system to select suppliers according to the selection behavior given by the user. The optimality of the supplier for the required demand is ensured by the cost function based on the parameters of the element.

A benchmark-driven modelling approach for evaluating deployment choices on a multi-core architecture

The complexity of current and emerging architectures provides users with options about how best to use the available resources, but makes predicting performance challenging. In this work a benchmark-driven model is developed for a simple shallow water code on a Cray XE6 system, to explore how deployment choices such as domain decomposition and core affinity affect performance. The resource sharing present in modern multi-core architectures adds various levels of heterogeneity to the system. Shared resources often includes cache, memory, network controllers and in some cases floating point units (as in the AMD Bulldozer), which mean that the access time depends on the mapping of application tasks, and the core's location within the system. Heterogeneity further increases with the use of hardware-accelerators such as GPUs and the Intel Xeon Phi, where many specialist cores are attached to general-purpose cores. This trend for shared resources and non-uniform cores is expected to continue into the exascale era. The complexity of these systems means that various runtime scenarios are possible, and it has been found that under-populating nodes, altering the domain decomposition and non-standard task to core mappings can dramatically alter performance. To find this out, however, is often a process of trial and error. To better inform this process, a performance model was developed for a simple regular grid-based kernel code, shallow. The code comprises two distinct types of work, loop-based array updates and nearest-neighbour halo-exchanges. Separate performance models were developed for each part, both based on a similar methodology. Application specific benchmarks were run to measure performance for different problem sizes under different execution scenarios. These results were then fed into a performance model that derives resource usage for a given deployment scenario, with interpolation between results as necessary.

Multi-attribute collaborative filtering recommendation based on improved group decision-making

Currently researchers in the field of personalized recommendations bear little consideration on users' interest differences in resource attributes although resource attribute is usually one of the most important factors in determining user preferences. To solve this problem, the paper builds an evaluation model of user interest based on resource multi-attributes, proposes a modified Pearson-Compatibility multi-attribute group decision-making algorithm, and introduces an algorithm to solve the recommendation problem of k-neighbor similar users. Considering the characteristics of collaborative filtering recommendation, the paper addresses the issues on the preference differences of similar users, incomplete values, and advanced converge of the algorithm. Thus the paper realizes multi-attribute collaborative filtering. Finally, the effectiveness of the algorithm is proved by an experiment of collaborative recommendation among multi-users based on virtual environment. The experimental results show that the algorithm has a high accuracy on predicting target users' attribute preferences and has a strong anti-interference ability on deviation and incomplete values.

Effects of a multi-session Cognitive Bias Modification program on interpretative biases and social anxiety symptoms in a sample of Iranian socially-anxious students

This study examines the effects of a multi-session Cognitive Bias Modification (CBM) program on interpretative biases and social anxiety in an Iranian sample. Thirty-six volunteers with a high score on social anxiety measures were recruited from a student population and randomly allocated into the experimental and control groups. In the experimental group, participants received 4 sessions of positive CBM for interpretative biases (CBM-I) over 2 weeks in the laboratory. Participants in the control condition completed a neutral task matched the active CBM-I intervention in format and duration but did not encourage positive disambiguation of socially ambiguous scenarios. The results indicated that after training the positive CBM-I group exhibited more positive (and less negative) interpretations of ambiguous scenarios and less social anxiety symptoms relative to the control condition at both 1 week post-test and 7 weeks follow-up. It is suggested that clinical trials are required to establish the clinical efficacy of this intervention for social anxiety.