Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

Visual predictive control of spiral motion

This paper deals with constrained image-based visual servoing of circular and conical spiral motion about an unknown object approximating a single image point feature. Effective visual control of such trajectories has many applications for small unmanned aerial vehicles, including surveillance and inspection, forced landing (homing), and collision avoidance. A spherical camera model is used to derive a novel visual-predictive controller (VPC) using stability-based design methods for general nonlinear model-predictive control. In particular, a quasi-infinite horizon visual-predictive control scheme is derived. A terminal region, which is used as a constraint in the controller structure, can be used to guide appropriate reference image features for spiral tracking with respect to nominal stability and feasibility. Robustness properties are also discussed with respect to parameter uncertainty and additive noise. A comparison with competing visual-predictive control schemes is made, and some experimental results using a small quad rotor platform are given.

Force controlled hexapod walking

This thesis is a study on controlling methods for six-legged robots. The study is based on mathematical modeling and simulation. A new joint controller is proposed and tested in simulation that uses joint angles and leg reaction force as inputs to generate a torque, and a method to optimise this controller is formulated and validated. Simulation shows that hexapod can walk on flat ground based on PID controllers with just four target configurations and a set of leg coordination rules, which provided the basis for the design of the new controller.

Using qualitative mixed methods to study small health care organizations while maximising trustworthiness and authenticity

Background The primary health care sector delivers the majority of health care in western countries through small, community-based organizations. However, research into these healthcare organizations is limited by the time constraints and pressure facing them, and the concern by staff that research is peripheral to their work. We developed Q-RARA—Qualitative Rapid Appraisal, Rigorous Analysis—to study small, primary health care organizations in a way that is efficient, acceptable to participants and methodologically rigorous. Methods Q-RARA comprises a site visit, semi-structured interviews, structured and unstructured observations, photographs, floor plans, and social scanning data. Data were collected over the course of one day per site and the qualitative analysis was integrated and iterative. Results We found Q-RARA to be acceptable to participants and effective in collecting data on organizational function in multiple sites without disrupting the practice, while maintaining a balance between speed and trustworthiness. Conclusions The Q-RARA approach is capable of providing a richly textured, rigorous understanding of the processes of the primary care practice while also allowing researchers to develop an organizational perspective. For these reasons the approach is recommended for use in small-scale organizations both within and outside the primary health care sector.

Rethinking the value of simulation methods in the information systems research field : a call for reconstructing contribution for a broader audience

The impact of simulation methods for social research in the Information Systems (IS) research field remains low. A concern is our field is inadequately leveraging the unique strengths of simulation methods. Although this low impact is frequently attributed to methodological complexity, we offer an alternative explanation – the poor construction of research value. We argue a more intuitive value construction, better connected to the knowledge base, will facilitate increased value and broader appreciation. Meta-analysis of studies published in IS journals over the last decade evidences the low impact. To facilitate value construction, we synthesize four common types of simulation research contribution: Analyzer, Tester, Descriptor, and Theorizer. To illustrate, we employ the proposed typology to describe how each type of value is structured in simulation research and connect each type to instances from IS literature, thereby making these value types and their construction visible and readily accessible to the general IS community.

Is retinal shape different in Asians and Caucasians? Estimation from peripheral refraction and peripheral eye length methods

Purpose:Race appears to be associated with myopiogenesis, with East Asians showing high myopia prevalence. Considering structural variations in the eye, it is possible that retinal shapes are different between races. The purpose of this study was to quantify and compare retinal shapes between racial groups using peripheral refraction (PR) and peripheral eye lengths (PEL). Methods:A Shin-Nippon SRW5000 autorefractor and a Haag-Streit Lenstar LS900 biometer measured PR and PEL, respectively, along horizontal (H) and vertical (V) fields out to ±35° in 5° steps in 29 Caucasian (CA), 16 South Asian (SA) and 23 East Asian (EA) young adults (spherical equivalent range +0.75D to –5.00D in all groups). Retinal vertex curvature Rv and asphericity Q were determined from two methods: a) PR (Dunne): The Gullstrand-Emsley eye was modified according to participant’s intraocular lengths and anterior cornea curvature. Ray-tracing was performed at each angle through the stop, altering cornea asphericity until peripheral astigmatism matched experimental measurements. Retinal curvature and hence retinal co-ordinate intersection with the chief ray were altered until sagittal refraction matched its measurement. b) PEL: Ray-tracing was performed at each angle through the anterior corneal centre of curvature of the Gullstrand-Emsley eye. Ignoring lens refraction, retinal co-ordinates relative to the fovea were determined from PEL and trigonometry. From sets of retinal co-ordinates, conic retinal shapes were fitted in terms of Rv and Q. Repeated-measures ANOVA were conducted on Rv and Q, and post hoc t-tests with Bonferroni correction were used to compare races. Results:In all racial groups both methods showed greater Rv for the horizontal than for the vertical meridian and greater Rv for myopes than emmetropes. Rv was greater in EA than in CA (P=0.02), with Rv for SA being intermediate and not significantly different from CA and EA. The PEL method provided larger Rv than the PR method: PEL: EA vs CA 87±13 vs 83±11 m-1 (H), 79±13 vs 72±14 m-1 (V); PR: EA vs CA 79±10 vs 67±10 m-1 (H), 71±17 vs 66±12 m-1 (V). Q did not vary significantly with race. Conclusions:Estimates of Rv, but not of Q, varied significantly with race. The greater Rv found in EA than in CA and the comparatively high prevalence rate of myopia in many Asian countries may be related.

Methods to improve the energy output of dye sensitized solar cell arrays

The work examined the operation and optimisation of dye-sensitised solar cell arrays, informing ways to improve performance through materials choices and geometrical design. Methods to improve the output of solar arrays under shading by external objects like trees or building were developed.

Statistical methods for electromyography data and associated problems

This thesis proposes three novel models which extend the statistical methodology for motor unit number estimation, a clinical neurology technique. Motor unit number estimation is important in the treatment of degenerative muscular diseases and, potentially, spinal injury. Additionally, a recent and untested statistic to enable statistical model choice is found to be a practical alternative for larger datasets. The existing methods for dose finding in dual-agent clinical trials are found to be suitable only for designs of modest dimensions. The model choice case-study is the first of its kind containing interesting results using so-called unit information prior distributions.

A continental-scale tool for acoustic identification of European bats

Summary 1. Acoustic methods are used increasingly to survey and monitor bat populations. However, the use of acoustic methods at continental scales can be hampered by the lack of standardized and objective methods to identify all species recorded. This makes comparable continent-wide monitoring difficult, impeding progress towards developing biodiversity indicators, transboundary conservation programmes and monitoring species distribution changes. 2. Here we developed a continental-scale classifier for acoustic identification of bats, which can be used throughout Europe to ensure objective, consistent and comparable species identifications. We selected 1350 full-spectrum reference calls from a set of 15 858 calls of 34 European species, from EchoBank, a global echolocation call library. We assessed 24 call parameters to evaluate how well they distinguish between species and used the 12 most useful to train a hierarchy of ensembles of artificial neural networks to distinguish the echolocation calls of these bat species. 3. Calls are first classified to one of five call-type groups, with a median accuracy of 97·6%. The median species-level classification accuracy is 83·7%, providing robust classification for most European species, and an estimate of classification error for each species. 4. These classifiers were packaged into an online tool, iBatsID, which is freely available, enabling anyone to classify European calls in an objective and consistent way, allowing standardized acoustic identification across the continent. 5. Synthesis and applications. iBatsID is the first freely available and easily accessible continental- scale bat call classifier, providing the basis for standardized, continental acoustic bat monitoring in Europe. This method can provide key information to managers and conservation planners on distribution changes and changes in bat species activity through time.

Human vs. machine : identification of bat species from their echolocation calls by humans and by artificial neural networks

Automated remote ultrasound detectors allow large amounts of data on bat presence and activity to be collected. Processing of such data involves identifying bat species from their echolocation calls. Automated species identification has the potential to provide more consistent, predictable, and potentially higher levels of accuracy than identification by humans. In contrast, identification by humans permits flexibility and intelligence in identification, as well as the incorporation of features and patterns that may be difficult to quantify. We compared humans with artificial neural networks (ANNs) in their ability to classify short recordings of bat echolocation calls of variable signal to noise ratios; these sequences are typical of those obtained from remote automated recording systems that are often used in large-scale ecological studies. We presented 45 recordings (1–4 calls) produced by known species of bats to ANNs and to 26 human participants with 1 month to 23 years of experience in acoustic identification of bats. Humans correctly classified 86% of recordings to genus and 56% to species; ANNs correctly identified 92% and 62%, respectively. There was no significant difference between the performance of ANNs and that of humans, but ANNs performed better than about 75% of humans. There was little relationship between the experience of the human participants and their classification rate. However, humans with <1 year of experience performed worse than others. Currently, identification of bat echolocation calls by humans is suitable for ecological research, after careful consideration of biases. However, improvements to ANNs and the data that they are trained on may in future increase their performance to beyond those demonstrated by humans.

Identification of New Zealand bats in flight from analysis of echolocation calls by artificial neural networks.

Time-expanded and heterodyned echolocation calls of the New Zealand long-tailed Chalinolobus tuberculatus and lesser short-tailed bat Mystacina tuberculata were recorded and digitally analysed. Temporal and spectral parameters were measured from time-expanded calls and power spectra generated for both time-expanded and heterodyned calls. Artificial neural networks were trained to classify the calls of both species using temporal and spectral parameters and power spectra as input data. Networks were then tested using data not previously seen. Calls could be unambiguously identified using parameters and power spectra from time-expanded calls. A neural network, trained and tested using power spectra of calls from both species recorded using a heterodyne detector set to 40 kHz (the frequency with the most energy of the fundamental of C. tuberculatus call), could identify 99% and 84% of calls of C. tuberculatus and M. tuberculata, respectively. A second network, trained and tested using power spectra of calls from both species recorded using a heterodyne detector set to 27 kHz (the frequency with the most energy of the fundamental of M. tuberculata call), could identify 34% and 100% of calls of C. tuberculatus and M. tuberculata, respectively. This study represents the first use of neural networks for the identification of bats from their echolocation calls. It is also the first study to use power spectra of time-expanded and heterodyned calls for identification of chiropteran species. The ability of neural networks to identify bats from their echolocation calls is discussed, as is the ecology of both species in relation to the design of their echolocation calls.

Acoustic identification of 12 species of echolocating bat by discriminant function analysis and artificial neural networks

We recorded echolocation calls from 14 sympatric species of bat in Britain. Once digitised, one temporal and four spectral features were measured from each call. The frequency-time course of each call was approximated by fitting eight mathematical functions, and the goodness of fit, represented by the mean-squared error, was calculated. Measurements were taken using an automated process that extracted a single call from background noise and measured all variables without intervention. Two species of Rhinolophus were easily identified from call duration and spectral measurements. For the remaining 12 species, discriminant function analysis and multilayer back-propagation perceptrons were used to classify calls to species level. Analyses were carried out with and without the inclusion of curve-fitting data to evaluate its usefulness in distinguishing among species. Discriminant function analysis achieved an overall correct classification rate of 79% with curve-fitting data included, while an artificial neural network achieved 87%. The removal of curve-fitting data improved the performance of the discriminant function analysis by 2 %, while the performance of a perceptron decreased by 2 %. However, an increase in correct identification rates when curve-fitting information was included was not found for all species. The use of a hierarchical classification system, whereby calls were first classified to genus level and then to species level, had little effect on correct classification rates by discriminant function analysis but did improve rates achieved by perceptrons. This is the first published study to use artificial neural networks to classify the echolocation calls of bats to species level. Our findings are discussed in terms of recent advances in recording and analysis technologies, and are related to factors causing convergence and divergence of echolocation call design in bats.

Public space for street-scape theatrics : guerrilla spatial tactics and methods of urban hacking in Brisbane, Australia

It could be argued that architecture has an inherent social responsibility to enrich the urban and spatial environments for the city’s occupants. However how we define quality, and how ‘places’ can be designed to be fair and equitable, catering for individuals on a humanistic and psychological level, is often not clearly addressed. Lefebvre discusses the idea of the ‘right to the city’; the belief that public space design should facilitate freedom of expression and incite a sense of spatial ownership for its occupants in public/commercial precincts. Lefebvre also points out the importance of sensory experience in the urban environment. “Street-scape theatrics” are performative activities that summarise these two concepts, advocating the ‘right to the city’ by way of art as well as providing sensual engagement for city users. Literature discusses the importance of Street-scape Theatrics however few sources attempt to discuss this topic in terms of how to design these spaces/places to enhance the city on both a sensory and political level. This research, grounded in political theory, investigates the case of street music, in particular busking, in the city of Brisbane, Australia. Street culture is a notion that already exists in Brisbane, but it is heavily controlled especially in central locations. The study discusses how sensory experience of the urban environment in Brisbane can be enriched through the design for busking; multiple case studies, interviews, observations and thematic mappings provide data to gather an understanding of how street performers see and understand the built form. Results are sometime surprisingly incongruous with general assumptions in regards to street artist as well as the established political and ideological framework, supporting the idea that the best and most effective way of urban hacking is working within the system. Ultimately, it was found that the Central Business District in Brisbane, Australia, could adopt certain political and design tactics which attempt to reconcile systematic quality control with freedom of expression into the public/commercial sphere, realism upheld. This can bridge the gap between the micro scale of the body and the macro of the political economy through freedom of expression, thus celebrating the idiosyncratic nature of the city.

Multi-modal deformable medical image registration

Non-rigid image registration is an essential tool required for overcoming the inherent local anatomical variations that exist between images acquired from different individuals or atlases. Furthermore, certain applications require this type of registration to operate across images acquired from different imaging modalities. One popular local approach for estimating this registration is a block matching procedure utilising the mutual information criterion. However, previous block matching procedures generate a sparse deformation field containing displacement estimates at uniformly spaced locations. This neglects to make use of the evidence that block matching results are dependent on the amount of local information content. This paper presents a solution to this drawback by proposing the use of a Reversible Jump Markov Chain Monte Carlo statistical procedure to optimally select grid points of interest. Three different methods are then compared to propagate the estimated sparse deformation field to the entire image including a thin-plate spline warp, Gaussian convolution, and a hybrid fluid technique. Results show that non-rigid registration can be improved by using the proposed algorithm to optimally select grid points of interest.