- Melbourne School of Population and Global Health - Research Publications
Melbourne School of Population and Global Health - Research Publications
Permanent URI for this collection
7 results
Filters
Reset filtersSettings
Statistics
Citations
Search Results
Now showing
1 - 7 of 7
-
ItemNo Preview AvailableData Governance and Social AnthropologyRose, J (European Association of Social Anthropologists, 2021-12-09)
-
ItemCollaborative Human-ML Decision Making Using Experts' Privileged Information under UncertaintyMaadi, M ; Khorshidi, HA ; Aickelin, U ( 2021-01-01)Machine Learning (ML) models have been widely applied for clinical decision making. However, in this critical decision making field, human decision making is still prevalent, because clinical experts are more skilled to work with unstructured data specially to deal with uncommon situations. In this paper, we use clinical experts' privileged information as an information source for clinical decision making besides information provided by ML models and introduce a collaborative human-ML decision making model. In the proposed model, two groups of decision makers including ML models and clinical experts collaborate to make a consensus decision. As decision making always comes with uncertainty, we present an interval modelling to capture uncertainty in the proposed collaborative model. For this purpose, clinical experts are asked to give their opinion as intervals, and we generate prediction intervals as the outputs of ML models. Using Interval Agreement Approach (IAA), as an aggregation function in our proposed collaborative model, pave the way to minimize loss of information through aggregating intervals to a fuzzy set. The proposed model not only can improve the accuracy and reliability of decision making, but also can be more interpretable especially when it comes to critical decisions. Experimental results on synthetic data shows the power of the proposed collaborative decision making model in some scenarios.
-
ItemNo Preview AvailableFeature Selection using Simulated Annealing with Optimal Neighborhood ApproachSyaiful, A ; Sartono, B ; Afendi, FM ; Anisa, R ; Salim, A (IOP Publishing Ltd, 2021-02-15)The one of the metaheuristic approaches that can be used was simulated annealing (SA) algorithm which inspired by annealing metallurgical process. This algorithm shows advantages in finding global optimum of given function which will be used in feature selection. In this study, we will trying to combine the neighborhood size and limited approach by using data simulation comparing between two function which is Akaike Index Criterion (AIC) function and Bayesian Index Criterion (BIC) function. The result of this experiment shows that the selected variables using optimal neighborhood size and limit the selected variable provide the result of goodness model around 98% of accuracy and specificity and 94% of sensitivity compared with simulated annealing algorithms without any modification using both AIC function and BIC function, and in the simulation also shows that BIC function give better result than AIC function.
-
ItemBuilding bridges, minding the gaps: involving the perspectives of older people in creating resilient healthcare infrastructure to disastersMerino, Y ; Vásquez, A ; Marinkovic, K (Lnu Press, 2020-01-14)
-
ItemNo Preview AvailableThe Spatiotemporal Signature of Indigenous Kinship NetworksRose, J (Royal Anthropological Institute of Great Britain and Ireland, 2020-09-15)The relationship between social anthropology and geography has been mediated by anthropology's specialised subfield of kinship analysis since the discipline's foundation in the 1870s. As this specialisation evolved with the incorporation of more formal modelling and analysis techniques from the 1960s, and especially with the incorporation of computing from the 1990s, both kinship analysis and geographic information systems have become more precise, with corresponding datasets growing to very large sizes. During the same period in Australia, social anthropology has been adopted by Commonwealth, state, and territory governments as a forensic discipline in the negotiation and litigation of Indigenous land rights via the Federal Court. This turn of events has spurred the development of the new methodology of spatio-temporal kinship network analysis (stKNA), a computer-based technique for modelling Indigenous kinship-based population networks as three-dimensional structures distributed over real geographic space and historical time. Using this methodology, forensic social anthropologists are able to demonstrate the kinship-based cohesion of Indigenous communities over large time-scales, together with their systemic association with the particular geographic regions to which they assert traditional ownership. This paper outlines the methodology of stKNA and its application in Australia.
-
ItemNo Preview AvailableIndigenous Australian Population Geometries: Tailoring Geospatial Data Structures for Enhanced Community Service DeliveryClinch, D ; Rose, J (Australasian eResearch Organisation, 2020)Data structures used by Australian federal government agencies for spatialising Indigenous geographic population distributions omit critical features necessary for effective service delivery. Currently, the Australian Statistical Geography Standard (ASGS) incorporates a so-called ‘Indigenous Structure’ derived from generic administrative geometries used for statistical purposes in wider population censuses. In this paper we present recent work on the development of an enhanced geometry, derived from linked geographic data and data structures, including Aboriginal community-controlled service providers, land councils, native title claims, language distribution maps, and other pertinent data assets. The objective of developing an enhanced Indigenous population geometry is to provide a maximally useful standard for the coordination and delivery of essential services into Indigenous communities. This work forms part of the core activity of the Indigenous Data Network (IDN) at the Melbourne School of Population and Global Health, University of Melbourne. Staffed by Indigenous and non-Indigenous experts in data science, geoscience, software engineering, population health, epidemiology and social and medical anthropology, the IDN is working to develop and implement best-practice national standards for Indigenous governance of Indigenous data.
-
ItemIMPROVING ACCURACY OF RECORD LINKAGE USING GRAPH STRUCTURES: RELEVANCE FOR HEALTH OUTCOMES RESEARCH?IJzerman, N ; Lin, P ; IJzerman, M ; Aickelin, U (ELSEVIER SCIENCE INC, 2020-05-01)