Nawaz Khan

Performance Evaluation of Levenberg-Marquardt Technique in Error Reduction for Diabetes Condition Classification

Abstract This paper aims to provide a case study to classify diabetes medical condition amongst patients. The study examines the performance of the Levenberg-Marquardt (LM) algorithm on a single dataset, the Pima Indian Diabetes dataset, attempting to minimize error in classifying the patients as diabetes positive or negative. The learning algorithm is applied on dynamically constructed neural network to minimize the error by continuously training the network until the optimum efficiency level is obtained. The performance of the approach is verified by performing a comparison study. The comparison study involves testing of the dynamically constructed network and presents a critical analysis of the classification output. The performance of the network is measured in terms of sensitivity and specificity for different learning algorithms. The study reveals that the LM algorithm outperforms other techniques in these tests and consequently concludes it to be the best ANN learning rule in providing optimum output results when applied to a dynamically constructed neural network.

Interactive visualization for low literacy users: from lessons learnt to design

This paper aims to address the problems low literacy (LL) users face when searching for information online. The first part of this paper summarizes the problems that LL users face, and establishes a set of design principles for interfaces suitable for LL users. This is followed by a description of how these design principles are mapped to a novel interface for interactive data retrieval. The interface was realized into a working system and evaluated against a traditional web interface for both high literacy (HL) and LL users. The suitability of the designs was analyzed using performance data, subjective feedback and an observational analysis. The findings from the study suggest that LL users perform better and prefer the proposed designs over a traditional web interface.

Personalised Learning Materials Based on Dyslexia Types: Ontological Approach

Abstract In recent years, e-learning systems have played an increasingly important role in higher education and, in particular, in enhancing learning experiences for individuals who have learning difficulties. However, it appears that many of the people involved in the development and implementation of e-learning tools overlook the needs of dyslexic students. As such, these students lack access to the resources on offer to other students and this leads to a disability divide. In order for educational initiatives to be effective, learning experiences need to be tailored to the individual needs of each student and the materials and tools employed should be aligned with the students needs, capabilities and learning objectives. The objective of this research was to propose an ontology that will facilitate the development of learning methods and technologies that are aligned with dyslexia types and symptoms. The paper commences with a discussion of domain ontology and examines how learning objectives that take into consideration a students capabilities and needs can be matched with appropriate assistive technology in order to deliver effective e-learning experiences and educational resources that can be consistently employed. The ontology employed within this study was developed using Ontology Web Language (OWL), an information processing system that allows applications to handle both the content and the presentation of the information available on the web. Two characteristics were employed within this research to describe each resource: dyslexia type and the features of assistive technologies that were deemed to be most appropriate for educational experiences targeted at each dyslexia type.

True global optimality of the pressure vessel design problem: a benchmark for bio-inspired optimisation algorithms

The pressure vessel design problem is a well-known design benchmark for validating bio-inspired optimisation algorithms. However, its global optimality is not clear and there has been no mathematical proof put forward. In this paper, a detailed mathematical analysis of this problem is provided that proves that 6,059.714335048436 is the global minimum. The Lagrange multiplier method is also used as an alternative proof and this method is extended to find the global optimum of a cantilever beam design problem.

DAEL Framework: A New Adaptive E-learning Framework for Students with Dyslexia

Abstract This paper reports on an extensive study conducted on the existing frameworks and relevant theories that lead to a better understanding of the requirements of an e-learning tool for people with dyslexia. The DAEL framework has been developed with respect to four different dimensions: presentation, hypermediality, acceptability and accessibility, and user experience. However, there has been no research on the different types of dyslexia and the dyslexic users viewpoint as they affect application design. Therefore, in this paper a framework is proposed which would conform to the standards of acceptability and accessibility for dyslexic students. We hypothesise that an e-learning application, which will adopt itself according to individuals’ dyslexia types, will advantage the dyslexics’ individuals in their learning process.

Information seeking behaviour model as a theoretical lens: high and low literate users behaviour process analysed

Motivation -- The paper focuses on how information seeking behaviour model is used as a theoretical lens to analyse high and low literate users online behaviour which in turn will support interface design suggestions. Research approach -- Five high and five low literate users of a local charity which provides social service information participated to carry out four online information seeking tasks. Data were captured using think-aloud, video, observation and semi structured interview techniques. A data analysis on the study previously discovered eight information seeking behaviour strategies: Reading, Scanning, Focus, Satisfied, Verification, Recovery, Trajectories, Representation and Abandon. Several information seeking behaviour models were evaluated prior to selecting Ellis (1989) information seeking behaviour model which includes features such as: starting, chaining, browsing, differentiating, monitoring, extracting, verifying, and ending. The model is used as a theoretical lens to analyse the data combining with the previous findings to make interface design suggestions. The study will not validate the correctness or the features of Ellis model. Findings/Design -- The analysis uncovered two variations of Ellis model for the high and low literate users, and how the models were used to give interface design suggestions. Research limitations/Implications -- The small sample size of five high and five low literate participants, limited the possibility of generalizing the findings. Originality/Value -- The low and high literate users information seeking behaviour were analysed using Ellis model as a theoretical lens along with the previously identified information seeking behaviour strategies of these users. These finds of the refined models are used to suggest interface design to improve the low literate users online information seeking. Take away message -- The models will be used to suggest interface design recommend for low literate users. We hope the design suggestions will help improve the low literate users online information seeking.

An approach to develop human gene disorder database for intelligent variance analysis of genes and its products

Molecular biology databases presently exist in different formats, different sizes and in different data structures. These create a new challenge which is to make these databases interoperable. Currently, hyperlink text is attempting to link these databases but it is unable to resolve semantic conflicts of the data. Data interpretation through image visualization and smart query processing using object keying will ease the biological query many times. Our aim is to investigate and to develop a conceptual object model for a genetic disorder disease database which will interact with other heterogeneous public domain molecular biology databases for more meaningful information. The research focuses on issues such as data input, access, format, storage, searching using image key, semantics and interoperabilities when building such a specialized gene disorder database data model.

Cognitive Task Analysis of Low and High Literacy Users: Experiences in Using Grounded Theory and Emergent Themes Analysis

The purpose of this paper is to describe the advantages, experiences, observations and the findings made during the use of two different qualitative data analysis approaches: Grounded Theory and Emergent Themes Analysis. The study carried out evaluated low and high literacy user information seeking behaviour characteristics of UKs “Adviceguide” website. We discuss the use of more than one Cognitive Task Analysis (CTA) method, such as process tracing, observation and interviews, can overcame limitations of each method and optimise the outcomes.

Integration of biological data resources using image object keying

This paper presents a novel approach to integrate biological data from multiple resources into a single page using image object keying. In this interactive approach, a gel electrophoresis protein spot is selected by the user which initiates the retrieval of corresponding 3D structure of the protein. It provides a set of operators to access and to collect elements content of the biological data resources for integration. The approach utilises a number of tools, namely, meta data extractor, mapping linker, dispatcher and result integrator for unifying the data collected from multiple data sources.

Dyslexia adaptive e-learning system based on multi-layer architecture

The key shortcoming of traditional e-learning systems is that the learning they promote is not adaptive. This paper analyses the e-learning activity of individuals with dyslexia and proposes an innovative design for an e-learning system. This new system is user-centric and interactive based on information about the users learning preferences. The proposed system design employs a multi-layer architecture, including a presentation layer, an adaption layer, a learning management system layer, an application server layer and a database layer. The learning management system layer contains all the possible systems that provide resources to support the learning process, hence improving the systems reusability. The adaption layer provides the systems adaptive technique functionality, which makes it more intelligent and adaptive - the main objective of this research.