Peter Summons

Automatic cell segmentation in microscopic color images using ellipse fitting and watershed

This paper presents an efficient and innovative method for the automated counting of cells in a microscopic image. The performance of watershed-based algorithms for the segmentation of clustered cells has been well demonstrated. The strength of our algorithm lies in the fact that it incorporates knowledge of color in the image. Our method uses the watershed transform with iterative shape alignment and is shown to be more accurate in retaining cell shape. We report a sensitivity of 97% and specificity of 96% when all color bands are used. Our methods could be of value to computer-based systems designed to objectively interpret microscopic images, since they provide a means for accurate cell segmentation.

Automated assessment and marking of spreadsheet concepts

An academic goal of a university is to ensure that student learning outcomes are achieved to their maximum potential. Attainment of academic goals however, can often be in conflict with attempts to realise administrative or business goals, as these may be perceived as being easily achieved through rationalisation of academic costs. The modern university must find a balance in the optimisation of these goals. This was recognised by (Cranitch 1991) “...with large numbers of students with different learning styles, there is a need to develop instructional arrangements that maximise student learning, while trying to minimise the cost in terms of time, effort and money”. Practically this may mean trying to maximise individual learning outcomes within very large classes, while trying to cope with the problems associated with large classes. One method of doing this is to reduce the logistic load or the management complexity of large classes, eg the PACE system (Oliver & Mitchell, 1996) for assessment management. Another is by automating some of the tasks related to student learning outcomes, eg the provision of consistent, adequate and timely feedback.

Authentication strategies for online assessments

An automatedmarking pilot scheme conductedat the University of Newcastle in 1997 has been extendedin collaborationwithDeakinUniversityto includedistancelearners.The workis being carried out under an Australian National Teaching Grant for 1998-99.This paper describesthe security and integrity strategies we adopt for automated assessmen~ and discusses the merits of authenticationstrategiesfor assessmentprocessesin the on-campusanddistancelearningscenarios.

Efficacy of the use of evidence‐based algorithmic guidelines in the acute care setting for pain assessment and management in older people: a critical review of the literature

AIM The aim of the literature review was to identify all examples of primary research using an algorithmic approach for the implementation of a clinical practice guideline relating to pain assessment and/or management within acute care, with a specific focus on older people. DESIGN Critical literature review. DATA SOURCES Inclusion criteria were; English language publications within the past 13 years; peer reviewed; research conducted within a hospital; about adult inpatients. Exclusion criteria; research located outside of a hospital context; quality improvement studies; rehabilitation studies and literature reviews. REVIEW METHODS Critical appraisal of the literature by using a qualitative interpretation of a translational approach. The literature was thematically mapped according to the criteria of credibility, transferability, plausibility and applicability. RESULTS No clinical practice guideline was found that directly related to both assessment and management of pain using an algorithm in acute care for older people. Five studies were found to have relevance and were critically evaluated. CONCLUSION A critique of the literature shows that an algorithmic approach is feasible for translation into a clinical practice guideline for assessment and management of pain in older people within the acute care setting. IMPLICATIONS FOR PRACTICE Implementation of any algorithmic approach requires consideration of the environment, culture and availability of resources.

An innovative approach to targeting pain in older people in the acute care setting.

Abstract This paper reports the findings of an exploratory pilot study which used mixed methods to determine (a) the feasibility of the study design for a larger multi site project and (b) whether a pain education promotion approach, termed ‘Targeting Pain’, using a multidisciplinary educational campaign and promotional media such as staff badges and ward signage, improves the detection and management of pain in older people in an acute care setting. Pre and post evaluation surveys and interviews were used to evaluate the approach. Findings showed an increase in pain assessment and documentation of pain by nursing staff, as well as an increase in the prescription of oral analgesics. However, the study indicated that the uptake regarding pain management from the education campaign was different between professional groups. Although there was a positive response by patients and staff to the use of staff badges, the ward signage failed to attract attention. The mixed methods approach used highlighted several areas that need to be improved for the next phase of the study.

Using a mobile device to enhance customer trust in the security of remote transactions

This paper presents a new scheme for online payment systems based on a mobile personal device and existing debit/credit card electronic payment protocols. The model focuses on trust to enhance the feeling of security in the use of debit/credit cards for online payment systems. A mobile personal device is used to control the payment process of customers in a transaction so as to give them the feeling of being in control of the payment process. The new model provides a way in which customer trust in controlling e-payment systems can be established, so that customers can trustfully participate in electronic commerce. We provide guidelines on how the trust of mobile devices can be applied to achieve mutual improvements between security and trust. Moreover, the model requirements are identified, and an analysis of these requirements against trust and security requirements in transactions is discussed.

Automated testing of databases and spreadsheets - the long and the short of it

Our introductory Information System subjects include the teaching and assessment of skills in word processing, spreadsheets, and databases. Having made pleasing progress with the automated generation and marking of the spreadsheet tests, we found that our move to automate the database testing highlighted some important distinctions between the two. In essence, spreadsheet testing is comparable to short-answer test and database to long-answer test, which require a markedly different approach.

Diabetic Retinopathy Classification Using C4.5

Early detection of diabetic retinopathy (DR) can prevent blindness and improve the quality of life. Practical detection requires a cost-effective screening over a large population. The presence of Microaneurysms (MAs) in a retinal image is the earliest sign of DR. This paper presents an efficient method to automatically detect MAs in a retinal image. The method is based on an advanced wavelet transform and the C4.5 algorithm (a categorization algorithm to distinguish DR and non-DR cases). It uses both the green and red channel data in RGB retinal images for detection of small sized MAs and obtains image feature parameters from the input image. A system was developed to implement the proposed method that displayed a sensitivity of 0.92 and a precision of 0.82.

Experiences of older people following the introduction of consumer-directed care to home care packages: A qualitative descriptive study

To explore the experiences of older people receiving home care package (HCP) support following the introduction of consumer‐directed care (CDC) by the Australian government on 1 July 2015.

EPICE an emotion fuzzy vectorial space for time modeling in medical decision

EPICE is a decision support system in medicine several knowledge bases that must cooperate together. The model takes into account the emotions of the patient and the physician involved in the care relationship during the evolution of the disease of the patient. The knowledge of clinical pictures are depicted with an object oriented time clinical model while the care relationship : the emotions of the patient and the caregivers are based on a psychological model. Both models rely on a fuzzy vectorial space that avoids fuzzification and denazification steps of the rule-based approaches and allows time modeling. We propose a fuzzy vectorial space to model the emotion felt by the patient during his care course and the relationship with the caregivers.