Spatial Allocation of Material Flow Analysis: A Geographic Information System Application of Material Flow Analysis in Ireland

This study concerns the spatial allocation of material flows, with emphasis on construction material in the Irish housing sector. It addresses some of the key issues concerning anthropogenic impact on the environment through spatial temporal visualisation of the flow of materials, wastes and emissions at different spatial levels. This is presented in the form of a spatial model, Spatial Allocation of Material Flow Analysis (SAMFA), which enables the simulation of construction material flows and associated energy use. SAMFA parallels the Island Limits project (EPA funded under 2004-SD-MS-22-M2), which aimed to create a material flow analysis of the Irish economy classified by industrial sector. SAMFA further develops this by attempting to establish the material flows at the subnational geographical scale that could be used in the development of local authority (LA) sustainability strategies and spatial planning frameworks by highlighting the cumulative environmental impacts of the development of the built environment. By drawing on the idea of planning support systems, SAMFA also aims to provide a cross-disciplinary, integrative medium for involving stakeholders in strategies for a sustainable built environment and, as such, would help illustrate the sustainability consequences of alternative The pilot run of the model in Kildare has shown that the model can be successfully calibrated and applied to develop alternative material flows and energy-use scenarios at the ED level. This has been demonstrated through the development of an integrated and a business-as-usual scenario, with the former integrating a range of potential material efficiency and energysaving policy options and the latter replicating conditions that best describe the current trend. Their comparison shows that the former is better than the latter in terms of both material and energy use. This report also identifies a number of potential areas of future research and areas of broader application. This includes improving the accuracy of the SAMFA model (e.g. by establishing actual life expectancy of buildings in the Irish context through field surveys) and the extension of the model to other Irish counties. This would establish SAMFA as a valuable predicting and monitoring tool that is capable of integrating national and local spatial planning objectives with actual environmental impacts. Furthermore, should the model prove successful at this level, it then has the potential to transfer the modelling approach to other areas of the built environment, such as commercial development and other key contributors of greenhouse emissions. The ultimate aim is to develop a meta-model for predicting the consequences of consumption patterns at the local scale. This therefore offers the possibility of creating critical links between socio technical systems with the most important challenge of all the limitations of the biophysical environment.

Analysis of information leakage from encrypted Skype conversations

Voice over IP (VoIP) has experienced a tremendous growth over the last few years and is now widely used among the population and for business purposes. The security of such VoIP systems is often assumed, creating a false sense of privacy. This paper investigates in detail the leakage of information from Skype, a widely used and protected VoIP application. Experiments have shown that isolated phonemes can be classified and given sentences identified. By using the dynamic time warping (DTW) algorithm, frequently used in speech processing, an accuracy of 60% can be reached. The results can be further improved by choosing specific training data and reach an accuracy of 83% under specific conditions. The initial results being speaker dependent, an approach involving the Kalman filter is proposed to extract the kernel of all training signals.

Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

Background and aims: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.

Materials and methods: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: ‘semi-structured’ and ‘unstructured’. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.

Results: The best result of 99.4% accuracy – which included only one semi-structured report predicted as unstructured – was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.

Conclusions: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.