ORCID Profile
0000-0002-5300-6225
Current Organisation
Charles Darwin University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Research Square Platform LLC
Date: 03-08-2023
DOI: 10.21203/RS.3.RS-2968456/V2
Abstract: The development and introduction of AI language models have transformed the way humans and institutions interact with technology, enabling natural and intuitive communication between humans and machines. This paper conducts a competence-based analysis of an emerging AI language model’s task response to provide insight into its language proficiency, critical analysis and reasoning ability, and structure and relevance of the response. A multidisciplinary approach is adopted, drawing from fields such as Accounting, Education, Management, Social Work and Law, to evaluate the responses generated by the AI to higher education assignments. This paper offers insights into the strengths and limitations of language-based AI responses and identifies implications for the design and implementation of higher education assessments.
Publisher: Hindawi Limited
Date: 13-10-2022
DOI: 10.1155/2022/6000989
Abstract: Humans experience a variety of emotions throughout the course of their daily lives, including happiness, sadness, and rage. As a result, an effective emotion identification system is essential for electroencephalography (EEG) data to accurately reflect emotion in real-time. Although recent studies on this problem can provide acceptable performance measures, it is still not adequate for the implementation of a complete emotion recognition system. In this research work, we propose a new approach for an emotion recognition system, using multichannel EEG calculation with our developed entropy known as multivariate multiscale modified-distribution entropy (MM-mDistEn) which is combined with a model based on an artificial neural network (ANN) to attain a better outcome over existing methods. The proposed system has been tested with two different datasets and achieved better accuracy than existing methods. For the GAMEEMO dataset, we achieved an average accuracy ± standard deviation of 95.73% ± 0.67 for valence and 96.78% ± 0.25 for arousal. Moreover, the average accuracy percentage for the DEAP dataset reached 92.57% ± 1.51 in valence and 80.23% ± 1.83 in arousal.
Publisher: Research Square Platform LLC
Date: 25-05-2023
DOI: 10.21203/RS.3.RS-2968456/V1
Abstract: The development and introduction of AI language models have transformed the way humans and institutions interact with technology, enabling natural and intuitive communication between humans and machines. This paper conducts a competence-based analysis of an emerging AI language model’s task response to provide insight into its language proficiency, critical analysis and reasoning ability, and structure and relevance of the response. A multidisciplinary approach is adopted, drawing from fields such as Accounting, Education, Management, Social Work and Law, to evaluate the responses generated by the AI to higher education assignments. This paper offers insights into the strengths and limitations of language-based AI responses and identifies implications for the design and implementation of higher education assessments.
Publisher: Oxford University Press (OUP)
Date: 25-08-2016
DOI: 10.1002/BJS.10259
Abstract: The rising cost of healthcare is well documented. The purpose of this study was to determine the cost-effectiveness of pelvic exenteration (PE). Consecutive patients referred for consideration of PE between 2008 and 2011 were recruited into a prospective non-randomized study that compared quality of life (QoL) between patients who did or did not undergo PE. Information on QoL and cost (in Australian dollars, AUD) was collected at baseline, during admission and up to 24 months after discharge. QoL data were converted into a utility-based measure. Quality-adjusted life-years (QALYs) were calculated. Bottom-up costing was performed. The incremental cost-effectiveness ratio (ICER) was calculated per life-year saved and per QALY. There were 174 patients with sufficient data for analysis. Of these, 139 underwent PE. R0 was achieved in 78·4 per cent of patients. The survival rate at 24 months after PE was 74·8 per cent compared with 43 per cent in those without exenteration (P = 0·001). Treatment costs were significantly higher for patients who had PE compared with those who did not (mean AUD 137 407 versus 79 174 P & 0·001). The ICER was AUD 124 147 (95 per cent c.i. 71 585 to 261 876) per life-year saved and AUD 227 330 (109 974 to 1 100 449) per QALY. Curative PE (R0) was found to be more cost-effective than non-curative PE (R1/R2), with an ICER of AUD 101 518 (60 105 to 200 428) versus 390 712 (74 368 to 82 256 739) per life-year saved. Treatment of advanced pelvic cancers is expensive regardless of the treatment intent. For a cost difference of only AUD 58 000 (€38 264), PE offers a chance of cure, and improves survival and QoL.
Publisher: Queensland University of Technology
Date: 13-06-2023
DOI: 10.5204/IJCJSD.2641
Abstract: In Australia, one significant cause of the imprisonment and disadvantage of First Nations people relates to transport injustice. First Nations people face obstacles in becoming lawful road users, particularly in relation to acquiring driver licences, with driving unlicensed a common pathway into the criminal justice system. This paper identifies that while some programs focus on increasing driver licensing for First Nations people, there are significant limitations in terms of coverage and access. Further, very few ersionary or support programs proactively address the intersection between First Nations people’s driver licensing and the criminal justice system. Nevertheless, it is argued that scope does exist within some state and territory criminal justice programs to enhance transport justice by assisting First Nations people to secure driver licensing. This paper highlights the need for accessible, available and culturally safe driver licencing support programs in First Nations communities led by First Nations people.
No related grants have been discovered for Mark Brady.