Fitness assessment of document model

Document classification is a supervised machine learning process, where predefined category labels are assigned to documents based on the hypothesis derived from training set of labelled documents. Documents cannot be directly interpreted by a computer system unless they have been modelled as a collection of computable features. Rogati and Yang [M. Rogati and Y. Yang, Resource selection for domain-specific cross-lingual IR, in SIGIR 2004: Proceedings of the 27th annual international conference on Research and Development in Information Retrieval, ACM Press, Sheffied: United Kingdom, pp. 154-161.] pointed out that the effectiveness of document classification system may vary in different domains. This implies that the quality of document model contributes to the effectiveness of document classification. Conventionally, model evaluation is accomplished by comparing the effectiveness scores of classifiers on model candidates. However, this kind of evaluation methods may encounter either under-fitting or over-fitting problems, because the effectiveness scores are restricted by the learning capacities of classifiers. We propose a model fitness evaluation method to determine whether a model is sufficient to distinguish positive and negative instances while still competent to provide satisfactory effectiveness with a small feature subset. Our experiments demonstrated how the fitness of models are assessed. The results of our work contribute to the researches of feature selection, dimensionality reduction and document classification.

A reflexive course for Masters students to understand and plan their own continuing professional development

Continuing Professional Development (CPD) is seen as a vital part of a professional engineer’s career, by professional engineering institutions as well as individual engineers. Factors such as ever-changing workforce requirements and rapid technological change have resulted in engineers no longer being able to rely just on the skills they learnt at university or can pick up on the job; they must undergo a structured professional development with clear objectives to develop further professional knowledge, values and skills. This paper presents a course developed for students undertaking a Master of Engineering or Master of Project Management at the University of Queensland. This course was specifically designed to help students plan their continuing professional development, while developing professional skills such as communication, ethical reasoning, critical judgement and the need for sustainable development. The course utilised a work integrated learning pedagogy applied within a formal learning environment, and followed the competency based chartered membership program of Engineers Australia, the peak professional body of engineers in Australia. The course was developed and analysed using an action learning approach. The main research question was “Can extra teaching and learning activities be developed that will simulate workplace learning?” The students continually assessed and reflected upon their current competencies, skills and abilities, and planed for the future attainment of specific competencies which they identified as important to their future careers. Various evaluation methods, including surveys before and after the course, were used to evaluate the action learning intervention. It was found that the assessment developed for the course was one of the most important factors, not only in driving student learning, as is widely accepted, but also in changing the students’ understandings and acceptance of the need for continuous professional development. The students also felt that the knowledge, values and skills they developed would be beneficial for their future careers, as they were developed within the context of their own professional development, rather than to just get through the course. © 2005, American Society for Engineering Education

A cost-effectiveness analysis of heroin detoxification methods in the Australian National Evaluation of Pharmacotherapies for Opioid Dependence (NEPOD)

This economic evaluation was part of the Australian National Evaluation of Pharmacotherapies for Opioid Dependence (NEPOD) project. Data from four trials of heroin detoxification methods, involving 365 participants, were pooled to enable a comprehensive comparison of the cost-effectiveness of five inpatient and outpatient detoxification methods. This study took the perspective of the treatment provider in assessing resource use and costs. Two short-term outcome measures were used-achievement of an initial 7-day period of abstinence, and entry into ongoing post-detoxification treatment. The mean costs of the various detoxification methods ranged widely, from AUD $491 (buprenorphine-based outpatient); to AUD $605 for conventional outpatient; AUD $1404 for conventional inpatient; AUD $1990 for rapid detoxification under sedation; and to AUD $2689 for anaesthesia per episode. An incremental cost-effectiveness analysis was carried out using conventional outpatient detoxification as the base comparator. The buprenorphine-based outpatient detoxification method was found to be the most cost-effective method overall, and rapid opioid detoxification under sedation was the most costeffective inpatient method.

Evaluation and comparison of mammalian subcellular localization prediction methods

Background: Determination of the subcellular location of a protein is essential to understanding its biochemical function. This information can provide insight into the function of hypothetical or novel proteins. These data are difficult to obtain experimentally but have become especially important since many whole genome sequencing projects have been finished and many resulting protein sequences are still lacking detailed functional information. In order to address this paucity of data, many computational prediction methods have been developed. However, these methods have varying levels of accuracy and perform differently based on the sequences that are presented to the underlying algorithm. It is therefore useful to compare these methods and monitor their performance. Results: In order to perform a comprehensive survey of prediction methods, we selected only methods that accepted large batches of protein sequences, were publicly available, and were able to predict localization to at least nine of the major subcellular locations (nucleus, cytosol, mitochondrion, extracellular region, plasma membrane, Golgi apparatus, endoplasmic reticulum (ER), peroxisome, and lysosome). The selected methods were CELLO, MultiLoc, Proteome Analyst, pTarget and WoLF PSORT. These methods were evaluated using 3763 mouse proteins from SwissProt that represent the source of the training sets used in development of the individual methods. In addition, an independent evaluation set of 2145 mouse proteins from LOCATE with a bias towards the subcellular localization underrepresented in SwissProt was used. The sensitivity and specificity were calculated for each method and compared to a theoretical value based on what might be observed by random chance. Conclusion: No individual method had a sufficient level of sensitivity across both evaluation sets that would enable reliable application to hypothetical proteins. All methods showed lower performance on the LOCATE dataset and variable performance on individual subcellular localizations was observed. Proteins localized to the secretory pathway were the most difficult to predict, while nuclear and extracellular proteins were predicted with the highest sensitivity.