Self-organising zooms for decentralised redundancy management in visual sensor networks

When visual sensor networks are composed of cameras which can adjust the zoom factor of their own lens, one must determine the optimal zoom levels for the cameras, for a given task. This gives rise to an important trade-off between the overlap of the different cameras’ fields of view, providing redundancy, and image quality. In an object tracking task, having multiple cameras observe the same area allows for quicker recovery, when a camera fails. In contrast having narrow zooms allow for a higher pixel count on regions of interest, leading to increased tracking confidence. In this paper we propose an approach for the self-organisation of redundancy in a distributed visual sensor network, based on decentralised multi-objective online learning using only local information to approximate the global state. We explore the impact of different zoom levels on these trade-offs, when tasking omnidirectional cameras, having perfect 360-degree view, with keeping track of a varying number of moving objects. We further show how employing decentralised reinforcement learning enables zoom configurations to be achieved dynamically at runtime according to an operator’s preference for maximising either the proportion of objects tracked, confidence associated with tracking, or redundancy in expectation of camera failure. We show that explicitly taking account of the level of overlap, even based only on local knowledge, improves resilience when cameras fail. Our results illustrate the trade-off between maintaining high confidence and object coverage, and maintaining redundancy, in anticipation of future failure. Our approach provides a fully tunable decentralised method for the self-organisation of redundancy in a changing environment, according to an operator’s preferences.

A spatiotemporal Data Envelopment Analysis (S-T DEA) approach:the need to assess evolving units

One of the major challenges in measuring efficiency in terms of resources and outcomes is the assessment of the evolution of units over time. Although Data Envelopment Analysis (DEA) has been applied for time series datasets, DEA models, by construction, form the reference set for inefficient units (lambda values) based on their distance from the efficient frontier, that is, in a spatial manner. However, when dealing with temporal datasets, the proximity in time between units should also be taken into account, since it reflects the structural resemblance among time periods of a unit that evolves. In this paper, we propose a two-stage spatiotemporal DEA approach, which captures both the spatial and temporal dimension through a multi-objective programming model. In the first stage, DEA is solved iteratively extracting for each unit only previous DMUs as peers in its reference set. In the second stage, the lambda values derived from the first stage are fed to a Multiobjective Mixed Integer Linear Programming model, which filters peers in the reference set based on weights assigned to the spatial and temporal dimension. The approach is demonstrated on a real-world example drawn from software development.

Evolutionary neural networks : models and applications

The scaling problems which afflict attempts to optimise neural networks (NNs) with genetic algorithms (GAs) are disclosed. A novel GA-NN hybrid is introduced, based on the bumptree, a little-used connectionist model. As well as being computationally efficient, the bumptree is shown to be more amenable to genetic coding lthan other NN models. A hierarchical genetic coding scheme is developed for the bumptree and shown to have low redundancy, as well as being complete and closed with respect to the search space. When applied to optimising bumptree architectures for classification problems the GA discovers bumptrees which significantly out-perform those constructed using a standard algorithm. The fields of artificial life, control and robotics are identified as likely application areas for the evolutionary optimisation of NNs. An artificial life case-study is presented and discussed. Experiments are reported which show that the GA-bumptree is able to learn simulated pole balancing and car parking tasks using only limited environmental feedback. A simple modification of the fitness function allows the GA-bumptree to learn mappings which are multi-modal, such as robot arm inverse kinematics. The dynamics of the 'geographic speciation' selection model used by the GA-bumptree are investigated empirically and the convergence profile is introduced as an analytical tool. The relationships between the rate of genetic convergence and the phenomena of speciation, genetic drift and punctuated equilibrium arc discussed. The importance of genetic linkage to GA design is discussed and two new recombination operators arc introduced. The first, linkage mapped crossover (LMX) is shown to be a generalisation of existing crossover operators. LMX provides a new framework for incorporating prior knowledge into GAs.Its adaptive form, ALMX, is shown to be able to infer linkage relationships automatically during genetic search.

Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson's disease symptom severity

The standard reference clinical score quantifying average Parkinson's disease (PD) symptom severity is the Unified Parkinson's Disease Rating Scale (UPDRS). At present, UPDRS is determined by the subjective clinical evaluation of the patient's ability to adequately cope with a range of tasks. In this study, we extend recent findings that UPDRS can be objectively assessed to clinically useful accuracy using simple, self-administered speech tests, without requiring the patient's physical presence in the clinic. We apply a wide range of known speech signal processing algorithms to a large database (approx. 6000 recordings from 42 PD patients, recruited to a six-month, multi-centre trial) and propose a number of novel, nonlinear signal processing algorithms which reveal pathological characteristics in PD more accurately than existing approaches. Robust feature selection algorithms select the optimal subset of these algorithms, which is fed into non-parametric regression and classification algorithms, mapping the signal processing algorithm outputs to UPDRS. We demonstrate rapid, accurate replication of the UPDRS assessment with clinically useful accuracy (about 2 UPDRS points difference from the clinicians' estimates, p < 0.001). This study supports the viability of frequent, remote, cost-effective, objective, accurate UPDRS telemonitoring based on self-administered speech tests. This technology could facilitate large-scale clinical trials into novel PD treatments.

Achievable performance gain of IEEE 802.11 multi-rate link adaptation algorithm with cross-layer design

Link quality-based rate adaptation has been widely used for IEEE 802.11 networks. However, network performance is affected by both link quality and random channel access. Selection of transmit modes for optimal link throughput can cause medium access control (MAC) throughput loss. In this paper, we investigate this issue and propose a generalised cross-layer rate adaptation algorithm. It considers jointly link quality and channel access to optimise network throughput. The objective is to examine the potential benefits by cross-layer design. An efficient analytic model is proposed to evaluate rate adaptation algorithms under dynamic channel and multi-user access environments. The proposed algorithm is compared to link throughput optimisation-based algorithm. It is found rate adaptation by optimising link layer throughput can result in large performance loss, which cannot be compensated by the means of optimising MAC access mechanism alone. Results show cross-layer design can achieve consistent and considerable performance gains of up to 20%. It deserves to be exploited in practical design for IEEE 802.11 networks.

A comparative evaluation of term recognition algorithms

Automatic Term Recognition (ATR) is a fundamental processing step preceding more complex tasks such as semantic search and ontology learning. From a large number of methodologies available in the literature only a few are able to handle both single and multi-word terms. In this paper we present a comparison of five such algorithms and propose a combined approach using a voting mechanism. We evaluated the six approaches using two different corpora and show how the voting algorithm performs best on one corpus (a collection of texts from Wikipedia) and less well using the Genia corpus (a standard life science corpus). This indicates that choice and design of corpus has a major impact on the evaluation of term recognition algorithms. Our experiments also showed that single-word terms can be equally important and occupy a fairly large proportion in certain domains. As a result, algorithms that ignore single-word terms may cause problems to tasks built on top of ATR. Effective ATR systems also need to take into account both the unstructured text and the structured aspects and this means information extraction techniques need to be integrated into the term recognition process.

A Bayesian formulation of search, control and the exploration/exploitation trade-off

A new approach to optimisation is introduced based on a precise probabilistic statement of what is ideally required of an optimisation method. It is convenient to express the formalism in terms of the control of a stationary environment. This leads to an objective function for the controller which unifies the objectives of exploration and exploitation, thereby providing a quantitative principle for managing this trade-off. This is demonstrated using a variant of the multi-armed bandit problem. This approach opens new possibilities for optimisation algorithms, particularly by using neural network or other adaptive methods for the adaptive controller. It also opens possibilities for deepening understanding of existing methods. The realisation of these possibilities requires research into practical approximations of the exact formalism.

Multi-party risk management helps manage cement plant construction in Thailand

Several parties (stakeholders) are involved in a construction project. The conventional Risk Management Process (RMP) manages risks from a single party perspective, which does not give adequate consideration to the needs of others. The objective of multi-party risk management is to assist decision-makers in managing risk systematically and most efficiently in a multi-party environment. Multi-party Risk Management Processes (MRMP) consist of risk identification, structuring, analysis and developing responses from all party perspectives. The MRMP has been applied to a cement plant construction project in Thailand to demonstrate its effectiveness.

A hybrid genetic algorithm for the multi-depot vehicle routing problem

The distribution of finished products from depots to customers is a practical and challenging problem in logistics management. Better routing and scheduling decisions can result in higher level of customer satisfaction because more customers can be served in a shorter time. The distribution problem is generally formulated as the vehicle routing problem (VRP). Nevertheless, there is a rigid assumption that there is only one depot. In cases, for instance, where a logistics company has more than one depot, the VRP is not suitable. To resolve this limitation, this paper focuses on the VRP with multiple depots, or multi-depot VRP (MDVRP). The MDVRP is NP-hard, which means that an efficient algorithm for solving the problem to optimality is unavailable. To deal with the problem efficiently, two hybrid genetic algorithms (HGAs) are developed in this paper. The major difference between the HGAs is that the initial solutions are generated randomly in HGA1. The Clarke and Wright saving method and the nearest neighbor heuristic are incorporated into HGA2 for the initialization procedure. A computational study is carried out to compare the algorithms with different problem sizes. It is proved that the performance of HGA2 is superior to that of HGA1 in terms of the total delivery time.

Representation and parameterisation issues in genetic algorithms

A multi-chromosome GA (Multi-GA) was developed, based upon concepts from the natural world, allowing improved flexibility in a number of areas including representation, genetic operators, their parameter rates and real world multi-dimensional applications. A series of experiments were conducted, comparing the performance of the Multi-GA to a traditional GA on a number of recognised and increasingly complex test optimisation surfaces, with promising results. Further experiments demonstrated the Multi-GA's flexibility through the use of non-binary chromosome representations and its applicability to dynamic parameterisation. A number of alternative and new methods of dynamic parameterisation were investigated, in addition to a new non-binary 'Quotient crossover' mechanism. Finally, the Multi-GA was applied to two real world problems, demonstrating its ability to handle mixed type chromosomes within an individual, the limited use of a chromosome level fitness function, the introduction of new genetic operators for structural self-adaptation and its viability as a serious real world analysis tool. The first problem involved optimum placement of computers within a building, allowing the Multi-GA to use multiple chromosomes with different type representations and different operators in a single individual. The second problem, commonly associated with Geographical Information Systems (GIS), required a spatial analysis location of the optimum number and distribution of retail sites over two different population grids. In applying the Multi-GA, two new genetic operators (addition and deletion) were developed and explored, resulting in the definition of a mechanism for self-modification of genetic material within the Multi-GA structure and a study of this behaviour.

Multi-function controllers for a hydraulic pump

This project has been undertaken for Hamworthy Hydraulics Limited. Its objective was to design and develop a controller package for a variable displacement, hydraulic pump for use mainly on mobile earth moving machinery. A survey was undertaken of control options used in practice and from this a design specification was formulated, the successful implementation of which would give Hamworthy an advantage over its competitors. Two different modes for the controller were envisaged. One consisted of using conventional hydro-mechanics and the other was based upon a microprocessor. To meet short term customer prototype requirements the first section of work was the realisation of the hydro-mechanical system. Mathematical models were made to evaluate controller stability and hence aid their design. The final package met the requirements of the specification and a single version could operate all sizes of variable displacement pumps in the Hamworthy range. The choice of controller options and combinations totalled twenty-four. The hydro-mechanical controller was complex and it was realised that a micro-processor system would allow all options to be implemented with just one design of hardware, thus greatly simplifying production. The final section of this project was to determine whether such a design was feasible. This entailed finding cheap, reliable transducers, using mathematical models to predict electro-hydraulic interface stability, testing such interfaces and finally incorporating a micro-processor in an interactive control loop. The study revealed that such a system was technically possible but it would cost 60% more than its hydro-mechanical counterpart. It was therefore concluded that, in the short term, for the markets considered, the hydro-mechanical design was the better solution. Regarding the micro-processor system the final conclusion was that, because the relative costs of the two systems are decreasing, the electro-hydraulic controller will gradually become more attractive and therefore Hamworthy should continue with its development.

The integration of multi-source data to improve the classification of remotely sensed images

The number of remote sensing platforms and sensors rises almost every year, yet much work on the interpretation of land cover is still carried out using either single images or images from the same source taken at different dates. Two questions could be asked of this proliferation of images: can the information contained in different scenes be used to improve the classification accuracy and, what is the best way to combine the different imagery? Two of these multiple image sources are MODIS on the Terra platform and ETM+ on board Landsat7, which are suitably complementary. Daily MODIS images with 36 spectral bands in 250-1000 m spatial resolution and seven spectral bands of ETM+ with 30m and 16 days spatial and temporal resolution respectively are available. In the UK, cloud cover may mean that only a few ETM+ scenes may be available for any particular year and these may not be at the time of year of most interest. The MODIS data may provide information on land cover over the growing season, such as harvest dates, that is not present in the ETM+ data. Therefore, the primary objective of this work is to develop a methodology for the integration of medium spatial resolution Landsat ETM+ image, with multi-temporal, multi-spectral, low-resolution MODIS \Terra images, with the aim of improving the classification of agricultural land. Additionally other data may also be incorporated such as field boundaries from existing maps. When classifying agricultural land cover of the type seen in the UK, where crops are largely sown in homogenous fields with clear and often mapped boundaries, the classification is greatly improved using the mapped polygons and utilising the classification of the polygon as a whole as an apriori probability in classifying each individual pixel using a Bayesian approach. When dealing with multiple images from different platforms and dates it is highly unlikely that the pixels will be exactly co-registered and these pixels will contain a mixture of different real world land covers. Similarly the different atmospheric conditions prevailing during the different days will mean that the same emission from the ground will give rise to different sensor reception. Therefore, a method is presented with a model of the instantaneous field of view and atmospheric effects to enable different remote sensed data sources to be integrated.

Convergence and knowledge processing in multi-agent systems

Multi-agent systems are complex systems comprised of multiple intelligent agents that act either independently or in cooperation with one another. Agent-based modelling is a method for studying complex systems like economies, societies, ecologies etc. Due to their complexity, very often mathematical analysis is limited in its ability to analyse such systems. In this case, agent-based modelling offers a practical, constructive method of analysis. The objective of this book is to shed light on some emergent properties of multi-agent systems. The authors focus their investigation on the effect of knowledge exchange on the convergence of complex, multi-agent systems.

The effects of a lutein-based supplement on objective and subjective measures of retinal and visual function in eyes with age-related maculopathy - a randomised controlled trial

Lutein and zeaxanthin are lipid-soluble antioxidants found within the macula region of the retina. Links have been suggested between increased levels of these carotenoids and reduced risk for age-related macular disease (ARMD). Therefore, the effect of lutein-based supplementation on retinal and visual function in people with early stages of ARMD (age-related maculopathy, ARM) was assessed using multi-focal electroretinography (mfERG), contrast sensitivity and distance visual acuity. A total of fourteen participants were randomly allocated to either receive a lutein-based oral supplement (treated group) or no supplement (non-treated group). There were eight participants aged between 56 and 81 years (65·50 (sd 9·27) years) in the treated group and six participants aged between 61 and 83 years (69·67 (sd 7·52) years) in the non-treated group. Sample sizes provided 80 % power at the 5 % significance level. Participants attended for three visits (0, 20 and 40 weeks). At 60 weeks, the treated group attended a fourth visit following 20 weeks of supplement withdrawal. No changes were seen between the treated and non-treated groups during supplementation. Although not clinically significant, mfERG ring 3 N2 latency (P= 0·041) and ring 4 P1 latency (P= 0·016) increased, and a trend for reduction of mfERG amplitudes was observed in rings 1, 3 and 4 on supplement withdrawal. The statistically significant increase in mfERG latencies and the trend for reduced mfERG amplitudes on withdrawal are encouraging and may suggest a potentially beneficial effect of lutein-based supplementation in ARM-affected eyes. Copyright © 2012 The Authors.

The effect of load on agent-based algorithms for distributed task allocation

Multi-agent algorithms inspired by the division of labour in social insects and by markets, are applied to a constrained problem of distributed task allocation. The efficiency (average number of tasks performed), the flexibility (ability to react to changes in the environment), and the sensitivity to load (ability to cope with differing demands) are investigated in both static and dynamic environments. A hybrid algorithm combining both approaches, is shown to exhibit improved efficiency and robustness. We employ nature inspired particle swarm optimisation to obtain optimised parameters for all algorithms in a range of representative environments. Although results are obtained for large population sizes to avoid finite size effects, the influence of population size on the performance is also analysed. From a theoretical point of view, we analyse the causes of efficiency loss, derive theoretical upper bounds for the efficiency, and compare these with the experimental results.