On-line learning in neural networks

On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.

Packet voice/data in local broadcast networks

A local area network that can support both voice and data packets offers economic advantages due to the use of only a single network for both types of traffic, greater flexibility to changing user demands, and it also enables efficient use to be made of the transmission capacity. The latter aspect is very important in local broadcast networks where the capacity is a scarce resource, for example mobile radio. This research has examined two types of local broadcast network, these being the Ethernet-type bus local area network and a mobile radio network with a central base station. With such contention networks, medium access control (MAC) protocols are required to gain access to the channel. MAC protocols must provide efficient scheduling on the channel between the distributed population of stations who want to transmit. No access scheme can exceed the performance of a single server queue, due to the spatial distribution of the stations. Stations cannot in general form a queue without using part of the channel capacity to exchange protocol information. In this research, several medium access protocols have been examined and developed in order to increase the channel throughput compared to existing protocols. However, the established performance measures of average packet time delay and throughput cannot adequately characterise protocol performance for packet voice. Rather, the percentage of bits delivered within a given time bound becomes the relevant performance measure. Performance evaluation of the protocols has been examined using discrete event simulation and in some cases also by mathematical modelling. All the protocols use either implicit or explicit reservation schemes, with their efficiency dependent on the fact that many voice packets are generated periodically within a talkspurt. Two of the protocols are based on the existing 'Reservation Virtual Time CSMA/CD' protocol, which forms a distributed queue through implicit reservations. This protocol has been improved firstly by utilising two channels, a packet transmission channel and a packet contention channel. Packet contention is then performed in parallel with a packet transmission to increase throughput. The second protocol uses variable length packets to reduce the contention time between transmissions on a single channel. A third protocol developed, is based on contention for explicit reservations. Once a station has achieved a reservation, it maintains this effective queue position for the remainder of the talkspurt and transmits after it has sensed the transmission from the preceeding station within the queue. In the mobile radio environment, adaptions to the protocols were necessary in order that their operation was robust to signal fading. This was achieved through centralised control at a base station, unlike the local area network versions where the control was distributed at the stations. The results show an improvement in throughput compared to some previous protocols. Further work includes subjective testing to validate the protocols' effectiveness.

The impact of architecture on the performance of artificial neural networks

A number of researchers have investigated the impact of network architecture on the performance of artificial neural networks. Particular attention has been paid to the impact on the performance of the multi-layer perceptron of architectural issues, and the use of various strategies to attain an optimal network structure. However, there are still perceived limitations with the multi-layer perceptron and networks that employ a different architecture to the multi-layer perceptron have gained in popularity in recent years, particularly, networks that implement a more localised solution, where the solution in one area of the problem space does not impact, or has a minimal impact, on other areas of the space. In this study, we discuss the major architectural issues affecting the performance of a multi-layer perceptron, before moving on to examine in detail the performance of a new localised network, namely the bumptree. The work presented here examines the impact on the performance of artificial neural networks of employing alternative networks to the long established multi-layer perceptron. In particular, networks that impose a solution where the impact of each parameter in the final network architecture has a localised impact on the problem space being modelled are examined. The alternatives examined are the radial basis function and bumptree neural networks, and the impact of architectural issues on the performance of these networks is examined. Particular attention is paid to the bumptree, with new techniques for both developing the bumptree structure and employing this structure to classify patterns being examined.

Environmental and nature conservation : a facet study of concern for the quality of the natural environment

A multi-variate descriptive model of environmental and nature conservation attitudes and values is proposed and empirically supported. A mapping sentence is developed out of analysis of data from a series of Repertory Grid interviews addressing conservation employees' attitudes towards their profession's activities. The research is carried out within the meta-theoretical framework of Facet Theory. A mapping sentence is developed consisting of 9 facets. From the mapping sentence 3 questionnaires were constructed viewing the selective orientations towards environmental concern. A mapping sentence and facet model is developed for each study. Once the internal structure of this model had been established using Similarity Structure Analysis, the elements of the facets are subjected to Partial Order Scalogram Analysis with base coordinates. A questionnaire was statistically analysed to assess the relationship between facet elements and 4 measures of attitudes towards, and involvement with, conservation. This enabled the comparison of the relative strengths of attitudes associated with each facet element and each measure of conservation attitude. In general, the relationship between the social value of conservation and involvement pledges to conservation were monotonic; perceived importance of a conservation issue appearing predictive of personal involvement. Furthermore, the elements of the life area and scale facets were differentially related to attitude measures. The multi-variate descriptive model of environmental conservation values and attitudes is discussed in relation to its implications for psychological research into environmental concern and for environmental and nature conservation.

Composite materials impact damage detection using neural networks

This thesis considers two basic aspects of impact damage in composite materials, namely damage severity discrimination and impact damage location by using Acoustic Emissions (AE) and Artificial Neural Networks (ANNs). The experimental work embodies a study of such factors as the application of AE as Non-destructive Damage Testing (NDT), and the evaluation of ANNs modelling. ANNs, however, played an important role in modelling implementation. In the first aspect of the study, different impact energies were used to produce different level of damage in two composite materials (T300/914 and T800/5245). The impacts were detected by their acoustic emissions (AE). The AE waveform signals were analysed and modelled using a Back Propagation (BP) neural network model. The Mean Square Error (MSE) from the output was then used as a damage indicator in the damage severity discrimination study. To evaluate the ANN model, a comparison was made of the correlation coefficients of different parameters, such as MSE, AE energy, AE counts, etc. MSE produced an outstanding result based on the best performance of correlation. In the second aspect, a new artificial neural network model was developed to provide impact damage location on a quasi-isotropic composite panel. It was successfully trained to locate impact sites by correlating the relationship between arriving time differences of AE signals at transducers located on the panel and the impact site coordinates. The performance of the ANN model, which was evaluated by calculating the distance deviation between model output and real location coordinates, supports the application of ANN as an impact damage location identifier. In the study, the accuracy of location prediction decreased when approaching the central area of the panel. Further investigation indicated that this is due to the small arrival time differences, which defect the performance of ANN prediction. This research suggested increasing the number of processing neurons in the ANNs as a practical solution.

A legal perspective of integrated surface mining, solid waste landfill reclamation and land conservation

In the area of international environmental law this thesis proposes the formulation of one-step planning and permitting regulation for the integrated utilisation of new surface mines as depositories for municipal solid waste. Additionally, the utilisation of abandoned and currently operated surface mines is proposed as solid waste landfills as an integral step in their reclamation. Existing laws, litigation and issues in the United Kingdom, the U.S. and Canada are discussed because of their common legal system, language and heritage. The critical shortage of approved space for disposal of solid waste has caused an urgent and growing problem for both the waste disposal industry and society. Surface mining can serve three important environmental and societal functions inuring to the health and welfare of the public: (1) providing basic minerals for goods and construction; (20 sequentially, to provide critically needed, safe burial sites for society's wastes, and (3) to conserve land by dual purpose use and to restore derelict land to beneficial surface use. Currently, the first two functions are treated environmentally, and in regulation, as two different siting problems, yet they both are earth-disturbing and excavating industries requiring surface restoration. The processes are largely duplicative and should be combined for better efficiency, less earth disturbance, conservation of land, and for fuller and better reclamation of completed surface mines returning the surfaces to greater utility than present mined land reclamation procedures. While both industries are viewed by a developed society and its communities as "bad neighbours", they remain essential and critical for mankind's existence and welfare. The study offers successful examples of the integrated process in each country. The study argues that most non-fuel surface mine openings, if not already safe, can economically, through present containment technology, be made environmentally safe for use as solid waste landfills. Simultaneously, the procedure safeguards and monitors protection of ground and surface waters from landfill contamination.

Energy conservation measures on an industrial site

World and UK energy resources and use are reviewed and the role of energy conservation in energy policy identified. In considering various energy conservation measures, a distinction is made between energy intensive and non-intensive industries and also between direct and indirect uses of energy. Particular attention is given to the non-intensive user of energy. Energy use on one such industrial site has been studied to determine the most effective energy saving measures in the short term. Here it is estimated that over 65% of energy is consumed for indirect purposes, mainly for heating and lighting buildings. Emphasis is placed on energy auditing techniques and those energy saving measures requiring greater technical, economic and organisational resources to secure their implementation. Energy auditing techniques include the use of aerial thermography and snow formation surveys to detect heat losses. Qualitative and quantitative interpretations are carried out, but restricted mainly to evaluating building roof heat losses. From the energy auditing exercise, it is confirmed that the intermittent heating of buildings is the largest and most cost effective fuel saving measure. This was implemented on the site and a heat monitoring programme established to verify results. Industrial combined heat and power generation is investigated. A proposal for the site demonstrates that there are several obstacles to its successful implementation. By adopting an alternative financial rationale, a way of overcoming these obstacles is suggested. A useful by-product of the study is the classification of industrial sites according to the nature of industrial energy demand patterns. Finally, energy saving measures implemented on the site are quantlfied using comparative verification methods. Overall fuel savings of 13% are indicated. Cumulative savings in heating fuel amount to 26% over four years although heated area increased by approximately 25%.

An evaluation of TCP over wired-to-wireless networks

To exploit the popularity of TCP as still the dominant sender and protocol of choice for transporting data reliably across the heterogeneous Internet, this thesis explores end-to-end performance issues and behaviours of TCP senders when transferring data to wireless end-users. The theme throughout is on end-users located specifically within 802.11 WLANs at the edges of the Internet, a largely untapped area of work. To exploit the interests of researchers wanting to study the performance of TCP accurately over heterogeneous conditions, this thesis proposes a flexible wired-to-wireless experimental testbed that better reflects conditions in the real-world. To exploit the transparent functionalities between TCP in the wired domain and the IEEE 802.11 WLAN protocols, this thesis proposes a more accurate methodology for gauging the transmission and error characteristics of real-world 802.11 WLANs. It also aims to correlate any findings with the functionality of fixed TCP senders. To exploit the popularity of Linux as a popular operating system for many of the Internet’s data servers, this thesis studies and evaluates various sender-side TCP congestion control implementations within the recent Linux v2.6. A selection of the implementations are put under systematic testing using real-world wired-to-wireless conditions in order to screen and present a viable candidate/s for further development and usage in the modern-day heterogeneous Internet. Overall, this thesis comprises a set of systematic evaluations of TCP senders over 802.11 WLANs, incorporating measurements in the form of simulations, emulations, and through the use of a real-world-like experimental testbed. The goal of the work is to ensure that all aspects concerned are comprehensively investigated in order to establish rules that can help to decide under which circumstances the deployment of TCP is optimal i.e. a set of paradigms for advancing the state-of-the-art in data transport across the Internet.

Combining temporal and spectral information with spatial mapping to identify differences between phonological and semantic networks:a magnetoencephalographic approach

Early, lesion-based models of language processing suggested that semantic and phonological processes are associated with distinct temporal and parietal regions respectively, with frontal areas more indirectly involved. Contemporary spatial brain mapping techniques have not supported such clear-cut segregation, with strong evidence of activation in left temporal areas by both processes and disputed evidence of involvement of frontal areas in both processes. We suggest that combining spatial information with temporal and spectral data may allow a closer scrutiny of the differential involvement of closely overlapping cortical areas in language processing. Using beamforming techniques to analyze magnetoencephalography data, we localized the neuronal substrates underlying primed responses to nouns requiring either phonological or semantic processing, and examined the associated measures of time and frequency in those areas where activation was common to both tasks. Power changes in the beta (14-30 Hz) and gamma (30-50 Hz) frequency bandswere analyzed in pre-selected time windows of 350-550 and 500-700ms In left temporal regions, both tasks elicited power changes in the same time window (350-550 ms), but with different spectral characteristics, low beta (14-20 Hz) for the phonological task and high beta (20-30 Hz) for the semantic task. In frontal areas (BA10), both tasks elicited power changes in the gamma band (30-50 Hz), but in different time windows, 500-700ms for the phonological task and 350-550ms for the semantic task. In the left inferior parietal area (BA40), both tasks elicited changes in the 20-30 Hz beta frequency band but in different time windows, 350-550ms for the phonological task and 500-700ms for the semantic task. Our findings suggest that, where spatial measures may indicate overlapping areas of involvement, additional beamforming techniques can demonstrate differential activation in time and frequency domains. © 2012 McNab, Hillebrand, Swithenby and Rippon.

Effect of the base station antenna beam tilting on energy consumption in cellular networks

The objective of this paper is to combine the antenna downtilt selection with the cell size selection in order to reduce the overall radio frequency (RF) transmission power in the homogeneous High-Speed Packet Downlink (HSDPA) cellular radio access network (RAN). The analysis is based on the concept of small cells deployment. The energy consumption ratio (ECR) and the energy reduction gain (ERG) of the cellular RAN are calculated for different antenna tilts when the cell size is being reduced for a given user density and service area. The results have shown that a suitable antenna tilt and the RF power setting can achieve an overall energy reduction of up to 82.56%. Equally, our results demonstrate that a small cell deployment can considerably reduce the overall energy consumption of a cellular network.

Dynamic decision networks for decision-making in self-adaptive systems:a case study

Bayesian decision theory is increasingly applied to support decision-making processes under environmental variability and uncertainty. Researchers from application areas like psychology and biomedicine have applied these techniques successfully. However, in the area of software engineering and speci?cally in the area of self-adaptive systems (SASs), little progress has been made in the application of Bayesian decision theory. We believe that techniques based on Bayesian Networks (BNs) are useful for systems that dynamically adapt themselves at runtime to a changing environment, which is usually uncertain. In this paper, we discuss the case for the use of BNs, speci?cally Dynamic Decision Networks (DDNs), to support the decision-making of self-adaptive systems. We present how such a probabilistic model can be used to support the decision making in SASs and justify its applicability. We have applied our DDN-based approach to the case of an adaptive remote data mirroring system. We discuss results, implications and potential bene?ts of the DDN to enhance the development and operation of self-adaptive systems, by providing mechanisms to cope with uncertainty and automatically make the best decision.

Understanding supply chain disruption risk with the aid of social networks and information flows analysis

Supply Chain Risk Management (SCRM) has become a popular area of research and study in recent years. This can be highlighted by the number of peer reviewed articles that have appeared in academic literature. This coupled with the realisation by companies that SCRM strategies are required to mitigate the risks that they face, makes for challenging research questions in the field of risk management. The challenge that companies face today is not only to identify the types of risks that they face, but also to assess the indicators of risk that face them. This will allow them to mitigate that risk before any disruption to the supply chain occurs. The use of social network theory can aid in the identification of disruption risk. This thesis proposes the combination of social networks, behavioural risk indicators and information management, to uniquely identify disruption risk. The propositions that were developed from the literature review and exploratory case study in the aerospace OEM, in this thesis are:- By improving information flows, through the use of social networks, we can identify supply chain disruption risk. - The management of information to identify supply chain disruption risk can be explored using push and pull concepts. The propositions were further explored through four focus group sessions, two within the OEM and two within an academic setting. The literature review conducted by the researcher did not find any studies that have evaluated supply chain disruption risk management in terms of social network analysis or information management studies. The evaluation of SCRM using these methods is thought to be a unique way of understanding the issues in SCRM that practitioners face today in the aerospace industry.

Resource-aware configuration in smart camera networks

A recent trend in smart camera networks is that they are able to modify the functionality during runtime to better reflect changes in the observed scenes and in the specified monitoring tasks. In this paper we focus on different configuration methods for such networks. A configuration is given by three components: (i) a description of the camera nodes, (ii) a specification of the area of interest by means of observation points and the associated monitoring activities, and (iii) a description of the analysis tasks. We introduce centralized, distributed and proprioceptive configuration methods and compare their properties and performance. © 2012 IEEE.

Neurophysiological evaluation of convergent afferents innervating the human esophagus and area of referred pain on the anterior chest wall

Noxious stimuli in the esophagus cause pain that is referred to the anterior chest wall because of convergence of visceral and somatic afferents within the spinal cord. We sought to characterize the neurophysiological responses of these convergent spinal pain pathways in humans by studying 12 healthy subjects over three visits (V1, V2, and V3). Esophageal pain thresholds (Eso-PT) were assessed by electrical stimulation and anterior chest wall pain thresholds (ACW-PT) by use of a contact heat thermode. Esophageal evoked potentials (EEP) were recorded from the vertex following 200 electrical stimuli, and anterior chest wall evoked potentials (ACWEP) were recorded following 40 heat pulses. The fear of pain questionnaire (FPQ) was administered on V1. Statistical data are shown as point estimates of difference +/- 95% confidence interval. Pain thresholds increased between V1 and V3 [Eso-PT: V1-V3 = -17.9 mA (-27.9, -7.9) P < 0.001; ACW-PT: V1-V3 = -3.38 degrees C (-5.33, -1.42) P = 0.001]. The morphology of cortical responses from both sites was consistent and equivalent [P1, N1, P2, N2 complex, where P1 and P2 are is the first and second positive (downward) components of the CEP waveform, respectively, and N1 and N2 are the first and second negative (upward) components, respectively], indicating activation of similar cortical networks. For EEP, N1 and P2 latencies decreased between V1 and V3 [N1: V1-V3 = 13.7 (1.8, 25.4) P = 0.02; P2: V1-V3 = 32.5 (11.7, 53.2) P = 0.003], whereas amplitudes did not differ. For ACWEP, P2 latency increased between V1 and V3 [-35.9 (-60, -11.8) P = 0.005] and amplitudes decreased [P1-N1: V1-V3 = 5.4 (2.4, 8.4) P = 0.01; P2-N2: 6.8 (3.4, 10.3) P < 0.001]. The mean P1 latency of EEP over three visits was 126.6 ms and that of ACWEP was 101.6 ms, reflecting afferent transmission via Adelta fibers. There was a significant negative correlation between FPQ scores and Eso-PT on V1 (r = -0.57, P = 0.05). These data provide the first neurophysiological evidence of convergent esophageal and somatic pain pathways in humans.

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.