In this report, a power series formulation of feature importance that explicitly identifies individual and interaction-type contributions is discussed.

This document presents the anthropometric percentile data captured in the 2015 Anthropometric Survey of the Royal Australian Navy (ASRAN) and provides information on how to apply the data and assess designs. Additional information presented includes information on RAN secular trend, personal equipment and clothing correction factors, and other allowances that need to be considered when applying the anthropometric data.

In 2015 an Anthropometric Survey of the Royal Australian Navy (ASRAN) was conducted providing comprehensive digital and manual anthropometric data (body size and shape) that can be used for the design of vessels, equipment, and clothing. This document has used that data to develop evidence based human factors engineering design guidance that can be used to tailor design solutions to optimise the fit between the Royal Australian Navy (RAN) population and Her Majesty's Australian (HMA) Surface Ships and Submarines, and their systems, subsystems, and facilities.

This paper is intended to contribute to both the dialogue around the use of AI in the ADF, as well as to provide a useful resource for ADF members to enhance their education and understanding about the technologies of artificial intelligence, with a particular focus on deep learning.

A general method used to quantify uncertainty in theoretical corrections to unsteady pressure measurements through tubes is documented in this report. This method is based on a wellvalidated theoretical model, which produces a transfer function that may be used for correcting unsteady pressure measurements through an Nt number of tubes and Nv number of volumes. The uncertainty estimation methods employed are in accordance with AIAA Standards. 

Body armour is used by police and military personnel to provide passive protection of the vital organs of the thorax and abdomen against ballistic, fragmentation and stab threats. Optimising the amount of coverage provided by body armour requires consideration of the trade-off between the passive protection afforded by the armour and its potential to hinder wearers' ability to actively protect themselves.

This study investigated information exchange and processing under the pressures and limitations of first respondents at the tactical edge to provide insight into transitioning reference information to a dynamic 'real-time' paradigm.

This report thus investigates the subject of factor screening, for stochastic simulation models, and overviews several solutions to this problem. In particular, sequential bifurcation will be shown to provide a very efficient approach to the problem of factor screening, in comparison to standard one factor at a time classication methods.

This work investigated a method for predicting future trends in peer-reviewed publication data related to science and technology. The developed method use non-linear regression to fit a particular type of s-shaped curve

There has been some work in recent years on investigating the use of machine learning (ML) techniques in order to assist software vulnerability discovery. Motivated by the spectacular success of deep learning (DL) approaches in fields such as computer vision and natural language processing, we propose to study the application of DL techniques to software vulnerability discovery.