Chris Roadknight

An international cooperative programme indicates the widespread occurrence of ozone injury on crops

The UN/ECE ICP-Vegetation 1 routinely investigates the effects of ambient ozone pollution on crops throughout Europe. Each year, a series of co-ordinated ambient air experiments are conducted over a large area of Europe and a range of crop species are observed for the occurrence of injury following ozone episodes. In 1995 and 1996, ozone injury was observed at sites throughout Europe from United Kingdom (Nottingham) to the Russian Federation (Moscow) and from Sweden (Ostad) to Italy (Naples). The only site participating in the ICP-Vegetation where it was not observed was that at Finland (Jokioinen). Injury was identified on subterranean and white clover, French bean, soybean, tomato, and watermelon at one or more sites. Injury was also detected in gardens and on crops growing in commercial fields. Two short-term critical levels which incorporate ozone dose and air saturation vapour pressure deficit (VPD) were derived from the 1995 data. These were (i) an AOT40 2 of 200 ppb.h over 5 days when mean VPD (0930‐1630 h) is below 1.5 kPa and (ii) an AOT40 of 500 ppb.h over 5 days when mean VPD (0930‐1630 h) is above 1.5 kPa. In general, the 1996 data supported these critical levels although injury did occur on two occasions when the AOT40 was less than 50 ppb.h, and the VPD was less than 0.6 kPa. Thus, ICP-Vegetation experiments have shown that ozone injury can occur over much of Europe and that plants are most at risk in conditions of high atmospheric humidity. ©2000 Elsevier Science B.V. All rights reserved.

Modeling complex environmental data

Artificial neural networks (ANNs) are used to model the interactions that occur between ozone pollution, climatic conditions, and the sensitivity of crops and other plants to ozone. A number of generic methods for analysis and modeling are presented. These methods are applicable to the modeling and analysis of any data where an effect (in this case damage to plants) is caused by a number of variables that have a nonlinear influence. Multilayer perceptron ANNs are used to model data from a number of sources and analysis of the trained optimized models determines the accuracy of the models predictions. The models are sufficiently general and accurate to be employed as decision support systems by United Nations Economic Commission for Europe (UNECE) in determining the critical acceptable levels of ozone in Europe. Comparison is made of the accuracy of predictions for a number of modeling approaches. It is shown that the ANN approach is more accurate than other methods and that the use of principal components analysis on the inputs can improve the model. The validation of the models relies on more than simply an error measure on the test data. The relative importance of the causal agents in the model is established in the first instance by summing absolute weight values. This indicates whether the model is consistent with domain knowledge. The application of a range of conditions to the model then allows predictions to be made about the nonlinear influences of the individual principal inputs and of combinations of two inputs viewed as a three-dimensional graph. Equations are synthesized from the ANN to represent the model in an explicit mathematical form. Models are formed with essential parameters and other inputs are added as necessary, in order of decreasing priority, until an acceptable error level is reached. Secondary indicators substituting for primary indicators with which they are strongly correlated can be removed. From the synthesized equations both known and novel aspects of the process modeled can be identified. Known effects validate the model. Novel effects form the basis of hypotheses which can then be tested.

Provision of quality of service for active services

A novel approach to quality of service control in an active service network (application layer active network) is described. The approach makes use of a distributed genetic algorithm based on the unique methods that bacteria use to transfer and share genetic material. We have used this algorithm in the design of a robust adaptive control system for the active nodes in an active service network. The system has been simulated and results show that it can offer clear differentiation of active services. The algorithm places the right software, at the right place, in the right proportions; allows different time dependencies to be satisfied and simple payment related increases in performance.

Adaptive Management of an Active Service Network

The benefits of active services and networks cannot be realised unless the associated increase in system complexity can be efficiently managed. An adaptive management solution is required. Simulation results show that a distributed genetic algorithm, inspired by observations of bacterial communities, can offer many key management functions. The algorithm is fast and efficient, even when the demand for network services is varying rapidly.

Performance-guided neural network for rapidly self-organising active network management

We present a neural network for real-time learning and mapping of patterns using an external performance indicator. In a non-stationary environment where new patterns are introduced over time, the learning process utilises a novel snap-drift algorithm that performs fast, convergent, minimalist learning (snap) when the overall network performance is poor and slower, more cautious learning (drift) when the performance is good. Snap is based on a modified form of Adaptive Resonance Theory (CGIP 37(1987)54); and drift is based on Learning Vector Quantization (LVQ) (Proc. IJCNN 1(1990a)545). The two are combined within a semi-supervised learning system that shifts its learning style whenever it receives a significant change in performance feedback. The learning is capable of rapid re-learning and re-stabilisation, according to changes in external feedback or input patterns. We have incorporated this algorithm into the design of a modular neural network system, Performance-guided Adaptive Resonance Theory (P-ART) (Proc. IJCNN 2(2003)1412; Soft computing systems: Design, Management and application, IOS Press, Netherland, 2002; pp. 21-31). Simulation results show that the system discovers alternative solutions in response to significant changes in the input patterns and/or in the environment, which may require similar patterns to be treated differently over time. The simulations involve attempting to optimise the selection of network services in a non-stationary, real-time active computer network environment, in which the factors influencing the required selections are subject to change.

File popularity characterisation

A key determinant of the effectiveness of a web cache is the locality of the files requested. In the past this has been difficult to model, as locality appears to be cache specific. We show that locality can be characterised with a single parameter, which primarily varies with the topological position of the cache, and is largely independent of the culture of the cache users. Accurate cache models can therefore be built without any need to consider cultural effects that are hard to predict.

Linking cache performance to user behaviour

The performance of HTTP cache servers varies dramatically from server to server. Much of the variation is independent of cache size and network topology and thus appears to be related to differences in the user communities. Analysis of a range of user traces shows that, just like caches, individual users have highly variable hit rates, Zipf locality curves and show strong signs of long range dependency. In order to predict cache performance we propose a simple model which treats a cache as an aggregation of single users, and each user as a small cache.

Snap-drift: real-time, performance-guided learning

A novel approach for real-time learning and mapping of patterns using an external performance indicator is described. The learning makes use of the snap-drift algorithm based on the concept of fast, convergent, minimalist learning (snap) when the overall network performance has been poor and slower, cautious learning (drift towards user request input patterns) when the performance has been good, in a non-stationary environment where new patterns are being introduces over time. Snap is based on adaptive resonance; and drift is based on learning vector quantization (LVQ). The two are combined in a semi-supervised system that shifts its learning style whenever it receives a change in performance feedback. The learning is capable of rapidly relearning and reestablishing, according to changes in feedback or patterns. We have used this algorithm in the design of a modular neural network system, known as performance-guided adaptive resonance theory (P-ART). Simulation results show that it discovers alternative solutions in response to a significantly changed situation, in terms of the input vectors (patterns) and/or of the environment, which may require the patterns to be treated differently over time.

Real–Time Data Management on a Wireless Sensor Network

A multi-layered algorithm is proposed that provides a scalable and adaptive method for handling data on a wireless sensor network. Statistical tests, local feedback, and global genetic style material exchange ensure limited resources such as battery and bandwidth which are used efficiently by manipulating data at the source and important features in the time series are not lost when compression needs to be made. The approach leads to a more ‘hands off’ implementation which is demonstrated by a real world oceanographic deployment of the system.

Variations in cache behavior

HTTP cache servers reduce network traffic by storing popular files nearer to the client and have been implemented worldwide. Their reported performance on key metrics such as hit rate varies greatly. In order to optimise the design of the cache network this variation needs to be understood. The variation in hit rate across a number of caches is investigated and is shown to be partly stochastic (i.e caused by insufficient sample size) and partly fractal (i.e deterministic in origin).