J. Andrew Ware

Predicting the geo-temporal variations of crime and disorder

Traditional police boundaries—precincts, patrol districts, etc.—often fail to reflect the true distribution of criminal activity and thus do little to assist in the optimal allocation of police resources. This paper introduces methods for crime incident forecasting by focusing upon geographical areas of concern that transcend traditional policing boundaries. The computerised procedure utilises a geographical crime incidence-scanning algorithm to identify clusters with relatively high levels of crime (hot spots). These clusters provide sufficient data for training artificial neural networks (ANNs) capable of modelling trends within them. The approach to ANN specification and estimation is enhanced by application of a novel and noteworthy approach, the Gamma test (GT).

The use of spatial analytical techniques to explore patterns of fire incidence : A South Wales case study

The application of mapping and spatial analytical techniques to explore geographical patterns of crime incidence is well established. In contrast, the analysis of operational incident data routinely collected by fire brigades has received relatively less research attention, certainly in the UK academic literature. The aim of this paper is to redress this balance through the application of spatial analytical techniques that permit an exploration of the spatial dynamics of fire incidents and their relationships with socio-economic variables. By examining patterns for different fire incident types, including household fires, vehicle fires, secondary fires and malicious false alarms in relation to 2001 Census of Population data for an area of South Wales, we demonstrate the potential of such techniques to reveal spatial patterns that may be worthy of further contextual study. Further research is needed to establish how transferable these findings are to other geographical settings and how replicable the findings are at different geographical scales. The paper concludes by drawing attention to the current gaps in knowledge in analysing trends in fire incidence and proposes an agenda to advance such research using spatial analytical techniques.

Parallel Processing for Terrain Analysis in GIS: Visibility as a Case Study

The application of parallel processing to computationally intensive GIS problems has been advocated and illustrated by many researchers over the last twenty years. Despite this, GIS users have been slow to capitalize on the potential which the technology offers. Whilst today’s processors are adequate for the majority of GIS uses, some applications are too processor-intensive to be deemed viable for serial machines. This is particularly true of many digital terrain modelling applications, which has been the primary focus of parallel processing in GIS to date.This paper considers the problem of parallelizing line-of-sight (LOS) calculations in determining the visibility indices of entities such as elevation vertices in a digital terrain model (DTM). This is a requirement of site selection for a particular development, especially if visibility, or more specifically, visual intrusion is likely to be a key factor in gaining planning approval. To demonstrate the simplicity and applicability of parallelizing such GIS problems, this paper presents some parallel approaches in an efficient data organization, framework using a Transputer network. Speed-up performance can be increased by a factor of twelve using a simple network of twenty Transputers. As vast quantities of spatial data become available, particularly DTMs at larger scales and denser resolution, the demands for parallel processing will inevitably increase. It is hoped that the continued experiences of today’s researchers at applying parallel processing to well-defined problems will benefit the GIS users of tomorrow.

Optimum Work Roll Profile Selection in the Hot Rolling of Wide Steel Strip Using Computational Intelligence

The finishing train of a hot strip mill has been modelled by using a constant volume element model. The accuracy of the model has been increased by using an Artificial Neural Network (ANN). A non-linear Rank Based Geaetic Algorithm has been developed for the optimization of the work roll profiles in the finishing stands of the simulated hot strip mill. It has been compared with eight other experimental optimization algorithms: Random Walk, Hill Climbing, Simulated Annealing (SA) and five different Genetic Algorithms (GA). Finally, the work roll profiles have been optimized by the non-linear Rank Based Genetic Algorithm. The quality of the strip from the simulated mill was significantly improved.

The semi-automated classification of sedimentary organic matter in palynological preparations

The capture, analysis and classification of sedimentary organic matter in palynological preparations have been semi-automated. First, the morphological and textural discriminatory features used in classification schemes are measured using a computer-controlled stage and a digital camera mounted on a microscope in combination with Halcon image analysis algorithms. Second, the Exhaustive CHi-square Automatic Interaction Detector classification tree algorithm is applied to all feature measurements to establish their saliency as classification discriminators. Thirdly, the results of the classification tree algorithm are used to determine the inputs used by the actual classifier, which consists of a series of artificial neural networks (ANNs). The Gamma test (GT) is introduced as a tool to help facilitate the best use of limited data and to ensure that the ANNs are not over trained. The results show that the system developed is able to achieve an average correct classification rate of 87%. This is encouraging enough to prompt further research that could result in a commercially viable system. In the future, work will concentrate on refining the image capture component of the system and increasing the size of those databases that have been shown both empirically and by the GT to be too small to facilitate the construction of accurate classifiers.

A genetic algorithm approach to cartographic map generalisation

Rendering map data at scales smaller than their source can give rise to map displays exhibiting graphic conflict, such that objects are either too small to be seen or too close to each other to be distinguishable. Furthermore, scale reduction will often require important features to be exaggerated in size, sometimes leading to overlapping features. Cartographic map generalisation is the process by which any graphic conflict that arises during scaling is resolved. In this paper, we show how a Genetic Algorithm (GA) approach was used to resolve spatial conflict between objects after scaling, achieving near optimal solutions within practical time constraints.

Parallel distributed viewshed analysis

1. ABSTRACT The paper describes a number of distributed approaches to implementing a parallel vklbility a]g~rithm for Viewshed analysis. The problem can be simplified by considering a range of domain partitioning strategies for optimizing tie proc=sor worldoads. The best approaches are shown to work 22 times faster across a network of 24 processors. Such strategies allow traditional GIS functionality to be extended into new problem areas or to higher resolution spatial data using existing computing resources. Ke~~vords Intervisilility and viewshed analysis, digital terrain modeliig, DEhL parallel computing, distributed computing

Layered Neural Networks as Universal Approximators

The paper considers Itos results on the approximation capability of layered neural networks with sigmoid units in two layers. First of all the paper recalls one of Itos main results. Then the results of Ito regarding Heaviside function as sigmoid functions are extended using a signum function. For Heaviside functions a layered neural network implementation is presented that is also valid for signum functions. The focus of paper is on the implementation of Itos appoximators as four layer feed-forward neural networks.

Direct mapping of X3D scenes to MPEG-7 descriptions

Content description is an important step in multimedia indexing and search applications. While, in the past, a large volume of research has been devoted to image, audio, and video data, 3D scenes have received relatively little attention. In this paper, we present a methodology for the automatic description of 3D scenes, based on textual metadata but also their shape, structure, color, animation, lighting, viewpoint, texture and interactivity content. Our system accepts 3D scenes as input, written in the open X3D standard for web graphics, and automatically builds MPEG-7 descriptions. In order to fully model 3D content, we draw upon our previous work, where we have extended the MPEG-7 standard with multiple 3D-specific descriptors. Here, we further extend MPEG-7, and present our approach for automatic descriptor extraction. We take advantage of the fact that both X3D and MPEG-7 are written in XML, and base our automatic extraction system on eXtensible Stylesheet Language Transformations (XSLT). We have incorporated our system into a large-scale platform for VR advertising over the web, where the benefits of automatic annotation can be twofold: authors are offered better access to stored 3D material, for editing and reuse, and end users can be provided with advertisements whose semantic content matches their profile.

Adaptive contrast enhancement based on highly overlapped interpolation

Conventional pointwise adaptive contrast enhancement is very effective in adjusting the contrast of medical images with large regional brightness differences. However, the pointwise algorithm is computationally intensive, thus limiting its practical application. Two existing stepwise algorithms cut down the computational overhead by adopting regional interpolation and averaging techniques respectively. Based on these two stepwise algorithms, we describe an adaptive contrast enhancement in which a new kind of variable image filter suitable for array multiplication is employed. Experiments show that the new algorithm can avoid the generation of blocking effects and effectively reduce image distortion in enhancement. Moreover, the speed of the algorithm can be adjusted according to different requirements.