Physical activity recognition from accelerometer data using a multi-scale ensemble method

Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.

Measurement of energy expenditure of daily tasks among mothers of young children

There is currently some debate about whether the energy expenditure of domestic tasks is sufficient to confer health benefits. The aim of this study was therefore to measure the energy cost of five activities commonly undertaken by mothers of young children. Seven women with at least one child younger than five years of age spent 15 minutes in each of the following activities: sitting quietly, vacuum cleaning, washing windows, walking at moderate pace (approx 5km/hour), walking with a stroller and grocery shopping in a super-market. Each of the six 'trials' was completed on the same day, in random order. A carefully calibrated portable gas analyser was used to measure oxygen uptake during each activity, and data were converted to units of energy expenditure (METS). Vacuum cleaning, washing windows and walking with and without a stroller were found to be 'moderate intensity activities' (3 to 6 METs), but supermarket shopping did not reach this criterion. The MET values for these activities were similar to those reported in the Compendium of Physical Activities (Ainsworth et al., 2000). However, the energy expenditures of walking, both with and without a stroller, were higher than those reported in the Compendium. The findings suggest that some of the tasks associated with domestic caring duties are conducted at an intensity which is sufficient to confer some health benefit. Such benefits will only accrue however if the daily duration of these activities is sufficient to meet current guidelines.

Artificial neural networks to predict activity type and energy expenditure in youth

Previous studies have demonstrated that pattern recognition approaches to accelerometer data reduction are feasible and moderately accurate in classifying activity type in children. Whether pattern recognition techniques can be used to provide valid estimates of physical activity (PA) energy expenditure in youth remains unexplored in the research literature. Purpose: The objective of this study is to develop and test artificial neural networks (ANNs) to predict PA type and energy expenditure (PAEE) from processed accelerometer data collected in children and adolescents. Methods: One hundred participants between the ages of 5 and 15 yr completed 12 activity trials that were categorized into five PA types: sedentary, walking, running, light-intensity household activities or games, and moderate-to-vigorous intensity games or sports. During each trial, participants wore an ActiGraph GTIM on the right hip, and (V) Over dotO(2) was measured using the Oxycon Mobile (Viasys Healthcare, Yorba Linda, CA) portable metabolic system. ANNs to predict PA type and PAEE (METs) were developed using the following features: 10th, 25th, 50th, 75th, and 90th percentiles and the lag one autocorrelation. To determine the highest time resolution achievable, we extracted features from 10-, 15-, 20-, 30-, and 60-s windows. Accuracy was assessed by calculating the percentage of windows correctly classified and root mean square en-or (RMSE). Results: As window size increased from 10 to 60 s, accuracy for the PA-type ANN increased from 81.3% to 88.4%. RMSE for the MET prediction ANN decreased from 1.1 METs to 0.9 METs. At any given window size, RMSE values for the MET prediction ANN were 30-40% lower than the conventional regression-based approaches. Conclusions: ANNs can be used to predict both PA type and PAEE in children and adolescents using count data from a single waist mounted accelerometer.

Plasma-produced phase-pure cuprous oxide nanowires for methane gas sensing

Phase-selective synthesis of copper oxide nanowires is warranted by several applications, yet it remains challenging because of the narrow windows of the suitable temperature and precursor gas composition in thermal processes. Here, we report on the room-temperature synthesis of small-diameter, large-area, uniform, and phase-pure Cu2O nanowires by exposing copper films to a custom-designed low-pressure, thermally non-equilibrium, high-density (typically, the electron number density is in the range of 10 11-1013cm-3) inductively coupled plasmas. The mechanism of the plasma-enabled phase selectivity is proposed. The gas sensors based on the synthesized Cu2O nanowires feature fast response and recovery for the low-temperature (∼140°C) detection of methane gas in comparison with polycrystalline Cu2O thin film-based gas sensors. Specifically, at a methane concentration of 4%, the response and the recovery times of the Cu2O nanowire-based gas sensors are 125 and 147s, respectively. The Cu2O nanowire-based gas sensors have a potential for applications in the environmental monitoring, chemical industry, mining industry, and several other emerging areas.

Family Mobility : Reconciling Career Opportunities and Educational Strategy

Family mobility decisions reveal much about how the public and private realms of social life interact and change. This sociological study explores how contemporary families reconcile individual members’ career and education projects within the family unit over time and space, and unpacks the intersubjective constraints on workforce mobility. This Australian mixed methods study sampled Defence Force families and middle class professional families to illustrate how families’ educational projects are necessarily and deeply implicated in issues of workforce mobility and immobility, in complex ways. Defence families move frequently, often absorbing the stresses of moving through ‘viscous’ institutions as private troubles. In contrast, the selective mobility of middle class professional families and their ‘no go zones’ contribute to the public issue of poorly serviced rural communities. Families with different social, material and vocational resources at their disposal are shown to reflexively weigh the benefits and risks associated with moving differently. The book also explore how priorities shift as children move through educational phases. The families’ narratives offer empirical windows on larger social processes, such as the mobility imperative, the gender imbalance in the family’s intersubjective bargains, labour market credentialism, the social construction of place, and the family’s role in the reproduction of class structure.

Figure and ground

Critically responding to Heimo Zobernig's painted green carpet, a semi-permanent architectural intervention realised in the immediate aftermath of my survey show, I painted the windows of the predominantly glazed space red to effectively create a two-colour painting that envelops the viewer and adds a new dimension to the painterly tradition of hinterglasmalerei. The work created an immersive environment for viewers that aimed to promote an affectual experience through the intense saturation of the complimentary contrasts red and green.

Assessment of the effects of maternal exposure to heatwave on birth outcomes in Brisbane, Australia

Even though heatwave events have become more frequent and intense in most regions around the world, little is known about the impact of heatwave on birth outcomes. This thesis uses a population-based study design to investigate the relationship between maternal heatwave exposure and adverse birth outcomes in Brisbane, Australia. This study found that heatwave exposure at any stage of pregnancy can be harmful to fetal growth, and further increase the risk of adverse birth outcomes. Both short- and long-term effects of heatwave on adverse birth outcomes were found. The findings in this thesis may have significant public health implications.

Better half-dead than read? The Mezzomorto cases and their implications for literary culture in the 1930s

This article focusses on the two libel cases arising from Brian Penton's review of Vivian Crockett's novel Mezzomorto for the Bulletin in 1934, viewing them as points of entry into Australian literary politics in the 1930s, and as windows on to one of the most enduring and interesting feuds in Australian literary culture, that between P.R. 'Inky' Stephensen, self-styled 'Bunyip Critic,' and Brian Penton, arch exponent of 'destructive criticism' and scourge of parochial pretension. The cases are particularly interesting for what they reveal about the evolving positions of two influential figures in Australian writing of the 1930s and 1940s. They also play in to contemporary debates about the state and status of 'literature' in Australia. And while Penton's biographer Patrick Buckridge avers that the cases did not impact on any of the larger contemporary literary issues (meaning censorship and free speech), a case may be made for the significance of the libel actions in the context of attempts to establish an industrial and cultural presence for a diverse range of Australian writing.

Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

An open pit multistage mine production scheduling model for drilling, blasting and excavating operations

This paper proposes a new multi-resource multi-stage scheduling problem for optimising the open-pit drilling, blasting and excavating operations under equipment capacity constraints. The flow process is analysed based on the real-life data from an Australian iron ore mine site. The objective of the model is to maximise the throughput and minimise the total idle times of equipment at each stage. The following comprehensive mining attributes and constraints have been considered: types of equipment; operating capacities of equipment; ready times of equipment; speeds of equipment; block-sequence-dependent movement times of equipment; equipment-assignment-dependent operation times of blocks; distances between each pair of blocks; due windows of blocks; material properties of blocks; swell factors of blocks; and slope requirements of blocks. It is formulated by mixed integer programming and solved by ILOG-CPLEX optimiser. The proposed model is validated with extensive computational experiments to improve mine production efficiency at the operational level. The model also provides an intelligent decision support tool to account for the availability and usage of equipment units for drilling, blasting and excavating stages.

J-Circos : an interactive Circos plotter

Circos plots are graphical outputs that display three dimensional chromosomal interactions and fusion transcripts. However, the Circos plot tool is not an interactive visualization tool, but rather a figure generator. For example, it does not enable data to be added dynamically, nor does it provide information for specific data points interactively. Recently, an R-based Circos tool (RCircos) has been developed to integrate Circos to R, but similarly, Rcircos can only be used to generate plots. Thus, we have developed a Circos plot tool (J-Circos) that is an interactive visualization tool that can plot Circos figures, as well as being able to dynamically add data to the figure, and providing information for specific data points using mouse hover display and zoom in/out functions. J-Circos uses the Java computer language to enable it to be used on most operating systems (Windows, MacOS, Linux). Users can input data into JCircos using flat data formats, as well as from the GUI. J-Circos will enable biologists to better study more complex chromosomal interactions and fusion transcripts that are otherwise difficult to visualize from next-generation sequencing data.

Multi-action recognition via stochastic modelling of optical flow and gradients

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.

Fast and accurate business process drift detection

Business processes are prone to continuous and unexpected changes. Process workers may start executing a process differently in order to adjust to changes in workload, season, guidelines or regulations for example. Early detection of business process changes based on their event logs – also known as business process drift detection – enables analysts to identify and act upon changes that may otherwise affect process performance. Previous methods for business process drift detection are based on an exploration of a potentially large feature space and in some cases they require users to manually identify the specific features that characterize the drift. Depending on the explored feature set, these methods may miss certain types of changes. This paper proposes a fully automated and statistically grounded method for detecting process drift. The core idea is to perform statistical tests over the distributions of runs observed in two consecutive time windows. By adaptively sizing the window, the method strikes a trade-off between classification accuracy and drift detection delay. A validation on synthetic and real-life logs shows that the method accurately detects typical change patterns and scales up to the extent it is applicable for online drift detection.

RNASeqBrowser: A genome browser for simultaneous visualization of raw strand specific RNAseq reads and UCSC genome browser custom tracks

Background Strand specific RNAseq data is now more common in RNAseq projects. Visualizing RNAseq data has become an important matter in Analysis of sequencing data. The most widely used visualization tool is the UCSC genome browser that introduced the custom track concept that enabled researchers to simultaneously visualize gene expression at a particular locus from multiple experiments. Our objective of the software tool is to provide friendly interface for visualization of RNAseq datasets. Results This paper introduces a visualization tool (RNASeqBrowser) that incorporates and extends the functionality of the UCSC genome browser. For example, RNASeqBrowser simultaneously displays read coverage, SNPs, InDels and raw read tracks with other BED and wiggle tracks -- all being dynamically built from the BAM file. Paired reads are also connected in the browser to enable easier identification of novel exon/intron borders and chimaeric transcripts. Strand specific RNAseq data is also supported by RNASeqBrowser that displays reads above (positive strand transcript) or below (negative strand transcripts) a central line. Finally, RNASeqBrowser was designed for ease of use for users with few bioinformatic skills, and incorporates the features of many genome browsers into one platform. Conclusions The features of RNASeqBrowser: (1) RNASeqBrowser integrates UCSC genome browser and NGS visualization tools such as IGV. It extends the functionality of the UCSC genome browser by adding several new types of tracks to show NGS data such as individual raw reads, SNPs and InDels. (2) RNASeqBrowser can dynamically generate RNA secondary structure. It is useful for identifying non-coding RNA such as miRNA. (3) Overlaying NGS wiggle data is helpful in displaying differential expression and is simple to implement in RNASeqBrowser. (4) NGS data accumulates a lot of raw reads. Thus, RNASeqBrowser collapses exact duplicate reads to reduce visualization space. Normal PC’s can show many windows of NGS individual raw reads without much delay. (5) Multiple popup windows of individual raw reads provide users with more viewing space. This avoids existing approaches (such as IGV) which squeeze all raw reads into one window. This will be helpful for visualizing multiple datasets simultaneously. RNASeqBrowser and its manual are freely available at http://www.australianprostatecentre.org/research/software/rnaseqbrowser webcite or http://sourceforge.net/projects/rnaseqbrowser/ webcite