Hisbel Arochena

A Portable Framework Design to Support User Context Aware Augmented Reality Applications

This paper describes a portable framework to support augmented reality applications with user context information. It combines users body responses with a virtual world by monitoring users physical activity and vital signs in order to reflect real body status in a virtual world. In this paper we present a design of our portable vital signs monitoring framework, which can be applied to support physiological or affective user context information in augmented reality applications. The pivotal part of our system consists of multiple sensor nodes, and a PDA/smart phone device that aggregates and analyses data before sending it to the virtual worlds controlling device as game play parameters. The malleability of the frameworks communications channels makes it compatible with most known game/ serious applications platforms.

A simple real-time QRS detection algorithm utilizing curve-length concept with combined adaptive threshold for electrocardiogram signal classification

QRS detection is a standard procedure in electrocardiogram (ECG) signal classification and analysis. Although there is a large number of methods published, some featuring high accuracy, the problem remains open. This is especially true with respect to high accuracy QRS detection in noisy ECGs such as long-term Holter monitoring during normal daily activity. In this paper a robust real-time QRS detector for noisy applications is proposed. It exploits a modified curve-length concept with combined adaptive threshold derived by basic mean, standard deviation and average peak-to-peak interval. The method was tested using the MIT-BIH arrhythmia database with an observed detection accuracy of 99.70%, sensitivity of 99.86%, positive prediction of 99.84%, and an average failed detection of 0.30%. The proposed approach compares favourably with published results for other QRS detectors, and proves superior to those having constant and manually entered threshold parameters.

Towards Total Knowledge Management for Healthcare: Clinical and Organizational Considerations

Knowledge Management (KM) has made a significant impact on the global healthcare sector. However, it is important to address the link between knowledge, information and engineering. Knowledge Engineering (KE) is often only a small part of a KM-based project, yet some KM practitioners favour wholly KE-biased Knowledge Management projects, disregarding a more necessary holistic stance. This paper analyses some current achievements in the KM field and provides a benchmark from which academics and practitioners can attempt to attain “Total Knowledge Management for Healthcare” (TKMh).

Knowledge management as a holistic tool for superior project management

The challenges encountered in project-based organisations have been addressed by many strategies. This paper intends to provide an empirical insight of knowledge and its application within project environs. This would instigate learning and innovation within Knowledge Management (KM) in project-based organisations. Based on two case studies, a simple understanding of knowledge, Knowledge Creation (KC) and its management are proposed. It further underlines the humanistic core of KM and a framework that can be utilised to align knowledge paths. Finally, the paper concludes with suggestions and recommendations for future research on KM in the realm of project management.

A knowledge-based primary care approach to increase breast screening attendance

The static rate of breast screening attendance in the UK has been of concern in the fight against breast cancer mortality. This paper highlights how primary care can play a vital role in addressing this issue. Knowledge created through prediction mechanisms and sharing them with care deliverers forms the core of this discussion. Knowledge-based alerts are employed to initiate interventions to increase the breast screening attendance. This paper highlights the various factors that are to be considered while deploying such initiatives in primary care setting and validates them through a questionnaire-based survey.

An algorithm for the prediction of attendance to a breast screening unit in the UK

Studying data from the Coventry, Solihull and Warwickshire Breast Screening Unit in the UK, this paper concentrates on a proposal of a predictive algorithm for attendance to the screening unit under study. A comparative assessment of the performance of the proposed algorithm with well-known methods of prediction is also discussed. From the results, it can be concluded that the proposed algorithm attains a similar predictive performance to the traditional Artificial Neural Network methods, with the bonus that it is better suited for this particular application. The performance of the Logistic Regression method in general, is inferior to that of the ANN methods for this application.

Physician intervention via knowledge management: using HL7 messaging to increase breast-screening uptake

Healthcare strategists have realised the relevance and importance of Knowledge Management (KM) for clinical and healthcare environments. There has been a huge thrust in Information Technology (IT) driven KM projects in healthcare. Projects related to Electronic Patient Record (EPR) have been the focus of many of the healthcare projects being carried out around the world. The synergy between overlapping technologies and the need for semantic interoperability of disparate systems have revolutionised how knowledge, information and data is being exchanged across the healthcare realm. This project addresses the issues of KM by leveraging the available IT tools and technologies within approved and dedicated standards (for example, HL7) to increase breast-screening attendance in a regional setting in the UK.

Comparison of two AI methods for colonic tissue image classification

Analysis of tissue is essential in dealing with a number of problems in cancer research. The identification of normal, dysplastic and cancerous colonic mucosa is an example of such a problem. In this paper, texture analysis techniques have been employed with the purpose of measuring characteristics of the tissue images. Those include histogram, grey-level difference statistics and co-occurrence matrix feature extraction algorithms. These characteristics are used as inputs for two different artificial intelligence approaches to address the image classification problem; a genetic algorithm and an artificial neural network. No significant differences have been found in the classifications obtained by both methodologies.

Analysis of attendance and screening variation in a UK breast cancer screening unit

The United Kingdom was reported in 1999, as the country with the third highest breast cancer death rate in the world. Nevertheless, the UK mortality has been falling dramatically since 1989. The country commenced implementation of a triannual National Breast Screening programme in 1987. A national programme is expected to start delivering mortality reductions after 5-7 years from full implementation. Successful mortality reductions are related to the performance of the screening test and rate of attendance for screening (compliance). The present work is focused on a statistical descriptive analysis of the attendance and screening variation of women invited for the preventive screening programme in a district based breast cancer-screening unit. The analysis includes appointments since 1989 from a data set of 147,432 women. Data was restricted to non-symptomatic women invited to screening. The unit has run up to four episodes achieving a screening of 80.6% of the invitations. An increase in the cases with screening variation has been observed as the number of episodes increased. However, and despite that, 99% of the women who attended for screening did so within 3 months of their initial invitation.

Blind study for the prediction of attendance to a UK breast cancer screening unit

This paper presents a blind study carried out in the Solihull, Coventry and Warwickshire Breast Cancer Screening Unit in the UK, aiming to evaluate the performance of the Artificial Intelligence Attendance algorithm (AI-ATT), in predicting attendance of women to screening invitations. Achieving a 76% accuracy on the blind data, it is concluded that this algorithm is a useful predictive tool, not only for the prediction of attendance of individuals, but also for the identification of possible non-attendees.