Chris Bowerman

University of Sunderland · Department of Computing, Engineering and Technology

In this paper, we investigate the benefits of machine learning approaches in predicting the spectra of meson bound states. A linear model (LM) approach is used to predict the spectra of some heavy mesons.

Facial expression recognition (FER) is an area of active research, both in computer science and in behavioural science. Across these domains there is evidence to suggest that humans and machines find it easier to recognise certain emotions, for example happiness, in comparison to others. Recent behavioural studies have explored human perceptions of...

The application of digital methods for content-based curation and dissemination of cultural heritage data offers unique advantages for physical sites at risk of damage. In areas affected by 2011 Arab spring, digital may be the only approach to create believable cultural experiences. We propose a framework incorporating computational methods such as...

In this paper, we categorized topology of terrorist networks into six because of their ideological, historical and practical similarities by showing them with real terrorist network examples.

Due to the interest by public audience and academic research, there has been a great interest in Terrorist Networks by the academicians, analysts and criminologists. Either to learn how to disrupt or to prevent their activities, structure of these networks are investigated. The final conclusion about their structure and topology came to the fact th...

This paper addresses the issue of providing resource reservation mechanism for OBS networks. We propose a linear prediction mechanism based on least mean square (LMS) method to reduce the burst delay at edge nodes. A reservation method is proposed to increase the reservation probability and to improve the delay reduction performance.

Four group detection models (e.g. GDM, OGDM, SoDM and ComDM) are developed based on crime data features. These detection models are compared more common baseline SNA group detection algorithms. It is intended to find out, whether these four crime data specific group detection models can perform better than widely used k-core and n-clique algorithms...

Detecting criminal networks from arrest data and offender demographics data made possible with our previous models such as GDM, OGDM, and SoDM and each of them proved successful on different types of criminal networks. To benefit from all features of police arrest data and offender demographics, a new combined model is developed and called as combi...

This volume contains the proceedings of the Fourth Colloquium on International Engineering Education, which took place in May 20, 2009 at San Diego State University, California. The transatlantic consortium “International Cooperation in Ambient Computing Education” (ICACE) organized the colloquium. The consortium, which was established to create a...

Detection of terrorist groups using crime data has few examples currently; this is because of lack of detailed crime data which contain terrorist groups’ attacks and activities. In this study, a novel prediction model; CPM is applied to a crime dataset which includes solved and unsolved terrorist events in Istanbul, Turkey between 2003 and 2005, ai...

In this study, a novel model is proposed to predict perpetuators of some terrorist events which are remain unsolved. The CPM learns from similarities between terrorist attacks and their crime attributes then puts them in appropriate clusters. Solved and unsolved attacks are gathered in the same - all linked to each other - ldquoumbrellardquo cluste...

Since discovery of organization structure of offender groups leads the investigation to terrorist cells or organized crime groups, detecting covert networks from crime data are important to crime investigation. Two models, GDM and OGDM, which are based on another representation model – OGRM are developed and tested on nine terrorist groups. GDM, wh...

A link mining study on a theft network is done in cooperation with Bursa Police Department in Turkey on more than 100,000 crimes and 6,000 persons. Group Detection Model (GDM) is based on co-occurrences of offenders in police arrest records for generating possible theft networks. Out of thousands of groups detected, only 63 ad-hoc theft groups are...

The production of electronic course content for delivery on virtual learning environments which employ the growing number of standards and specifications in this area are intended to enable the electronic teaching material to be re-used. This is accomplished by providing clearly defined approaches to describing and organising content so that the ma...

Improving the accuracy of assigning new email messages to small folders can reduce the likelihood of users creating duplicate folders for some topics. In this paper we presented a hybrid classification model, PERC, and use the Enron Email Corpus to investigate the performance of kNN, SVM and PERC in a simulation of a real­time situation. Our result...

The Kohonen self-organizing feature map (SOM) has several important properties that can be used within the data mining/knowledge discovery and exploratory data analysis process. A key characteristic of the SOM is its topology preserving ability to map a multi-dimensional input into a two dimensional form. This feature is used for classification and...

Proteomics is a field dedicated to the analysis and identification of proteins within an organism. Within proteomics, two-dimensional electrophoresis (2-DE) is currently unrivalled as a technique to separate and analyse proteins from tissue samples. The analysis of post-experimental data produced from this technique has been identified as an import...

The LOM (Learning Object Model) approach to courseware design seems to be driven by a desire to increase access to education as well as use technology to enable a higher staff – student ratio than is currently possible. The LOM standard involves the use of standard metadata descriptions of content and adaptive content engines to deliver the conglom...

This paper describes the text mining of personal document collections in order to learn the categories of the documents in the collection, and to assign a suitable text label to each category. In the first experiment we make use of a pre­ classified collection of documents from which we extract a text label for each category. In the second experime...

There has been little research into the use of hybrid neural data mining to improve robot performance or enhance their capability. This paper presents a novel neural data mining technique that analyses robot sensor data for imitation learning. Learning by imitation allows a robot to learn from observing either another robot or a human to gain skill...

Key Results: Differential Ratio data mining was used to perform knowledge discovery within the 2-DE proteomics data, incorporating the spatial and temporal components. How does the work advance the state-of-the-art?: Development of data mining technique that performs automatic discovery of interesting trends within large spatio-temporal data incorp...

In this paper, we take a mildly critical look at the ''new model'' of learning on which electronic learning systems are built by looking at key projects, discussing current research and highlighting both strengths and weaknesses. We shall then draw the discussion together by making reference to lessons from the past and using this to point to sugge...

nclude BRIDGE, CALLE, ALICE-chan, the McGill language-learning environment, and the GPARS suite. The BRIDGE tutor makes use of a Government-Binding parser in a multimedia tutoring system in classroom use, and its NLP component and authoring components are examined in some detail. In the ALICE-chan system, students answer questions by typing in Roma...

this article. Huckvale et al. 1997 already 44 provide a list of good introductory books, so that it will suffice here to point to two series of books which have been translated into all the major European languages: the Dummies series for absolute beginners, published by IDG Books, and the Nutshell series of introductions and references published b...

The Computer Aided Learning (CAL) working group of the SOCRATES thematic network in Speech Communication Science have studied how the Internet is being used and could be used for the provision of self-study materials for education. In this paper we follow up previous recommendations for the design of Internet tutorials with recommendations for thei...

Introduction 1.1 Aims of the Working Group The working group in Computer-Aided Learning and Use of the Internet aims: q to bring together information about resources and tools for computeraided learning (CAL) in the field q to promote the use of the Internet to disseminate information and teaching materials q to make suggestions of areas of resourc...

It is argued that to say that “any ICT application worthy of the name” must be pedagogically driven (Nicholson & Mulhern, 2001, p. 149) is too strong a statement, inasmuch as CALL system architecture holds issues not only for language learners but also for the development of CALL as a research discipline. A system at Sunderland University illustrat...

Much research has recently been conducted into the use of models for the economic design of multiple control charts (EDCC). Control chart models generally assume that most process variables are constant and only a limited number of the major variables are varied to reach a local optimum. In the economic design of multiple control charts (EDMCC), mu...

The selection of operators and parameters for genetic algorithms (GA) depends upon the situation, and the choice is usually left to the users. Identifying the optimum selection is very time consuming and, therefore, it is important to develop a system which can assist the users in their selections. In our fuzzy Taguchi controller, we present a hybr...

Questions in traditional print-based materials Questions in on-line materials: a new approach A first example: simple questions A second example: series of MC questions Principles of good HCI-design Some practical experiences Real-life examples Conclusions References and Bibliography Abstract This paper provides the JavaScript code for asking quest...

This paper describes an accurate and robust text alignment system for structurally different languages. Among structurally different languages such as Japanese and English, there is a limitation on the amount of word correspondences that can be statistically ...

The number of different words expected on the basis of the urn model to appear in, for example, the first half of a text, is known to overestimate the observed number of different words. This paper examines the source of this overestimation bias. It ...

AdriaensG. and HahnU. (eds.), Parallel Natural Language Processing. Norwood, NJ: Ablex, 1994. $79.50. ISBN 0 89391 869 5 - Volume 1 Issue 1 - Chris Bowerman

Much research has been undertaken recently in the areas of ICASE and reverse engineering. Both approaches have their problems and drawbacks: inflexibility and a blind manipulation of entities. Such problems can be overcome by incorporating intelligence into the tools. We propose a new type of ICASE tool: Knowledge-Based ICASE (KB-CASE) whose blackb...

The open-ended nature of writing at university level constitutes a problem for traditional frame-based CALL. Traditional CALL cannot cope well with open ended language use since it relies on being able to recognise fixed expressions. The types of such systems are mentioned, and the fact that writing cannot be satisfactorily handled in such a way is...

The history of computer-aided language learning (CALL) dates back some 40 years. During this period two main types of system have been developed: frame-based and intelligent. These two types of programs are examined in turn below.

The Computer Aided Learning working group of the SOCRATES thematic network in Speech Communica-tion Sciences have studied how the Internet is being used and could be used for the provision of self-study materials. In this paper we build on our findings and make recommendations that should be useful to any current or potential author of tutorial mat...

The need to extract and subsequently represent meaning-ful knowledge from biomedical data sets is a rapidly growing area of research. Often, such data sets offer further challenges than more traditional analysis, since many domains contain data that is inherently multi-dimensional and contains spatial and/or temporal ele-ments. This may be further...

The growth of biomedical databases has seen a demand for data mining techniques to efficiently and effectively analyse the data contained within. One important consideration is the need to include expert's opinions within the knowledge discovery process. However, this can be difficult to accomplish when such heuristics are presented in loosely defi...

Navigating websites with mobile devices, such as a mobile phone, is cumbersome as a user's ability to access and process available information is easily impeded. Websites on mobile devices are not designed to provide navigation that is easy to follow, consistent and intuitive, therefore users tend to not use mobile devices for internet browsing pur...