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.

The Catlin Seaview Survey – kilometre-scale seascape assessment, and monitoring of coral reef ecosystems

1.Marine ecosystems provide critically important goods and services to society, and hence their accelerated degradation underpins an urgent need to take rapid, ambitious and informed decisions regarding their conservation and management. 2.The capacity, however, to generate the detailed field data required to inform conservation planning at appropriate scales is limited by time and resource consuming methods for collecting and analysing field data at the large scales required. 3.The ‘Catlin Seaview Survey’, described here, introduces a novel framework for large-scale monitoring of coral reefs using high-definition underwater imagery collected using customized underwater vehicles in combination with computer vision and machine learning. This enables quantitative and geo-referenced outputs of coral reef features such as habitat types, benthic composition, and structural complexity (rugosity) to be generated across multiple kilometre-scale transects with a spatial resolution ranging from 2 to 6 m2. 4.The novel application of technology described here has enormous potential to contribute to our understanding of coral reefs and associated impacts by underpinning management decisions with kilometre-scale measurements of reef health. 5.Imagery datasets from an initial survey of 500 km of seascape are freely available through an online tool called the Catlin Global Reef Record. Outputs from the image analysis using the technologies described here will be updated on the online repository as work progresses on each dataset. 6.Case studies illustrate the utility of outputs as well as their potential to link to information from remote sensing. The potential implications of the innovative technologies on marine resource management and conservation are also discussed, along with the accuracy and efficiency of the methodologies deployed.

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.

Factors influencing robustness and effectiveness of conditional random fields in active learning frameworks

Active learning approaches reduce the annotation cost required by traditional supervised approaches to reach the same effectiveness by actively selecting informative instances during the learning phase. However, effectiveness and robustness of the learnt models are influenced by a number of factors. In this paper we investigate the factors that affect the effectiveness, more specifically in terms of stability and robustness, of active learning models built using conditional random fields (CRFs) for information extraction applications. Stability, defined as a small variation of performance when small variation of the training data or a small variation of the parameters occur, is a major issue for machine learning models, but even more so in the active learning framework which aims to minimise the amount of training data required. The factors we investigate are a) the choice of incremental vs. standard active learning, b) the feature set used as a representation of the text (i.e., morphological features, syntactic features, or semantic features) and c) Gaussian prior variance as one of the important CRFs parameters. Our empirical findings show that incremental learning and the Gaussian prior variance lead to more stable and robust models across iterations. Our study also demonstrates that orthographical, morphological and contextual features as a group of basic features play an important role in learning effective models across all iterations.

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.

Pollen image classification using the classifynder system: Algorithm comparison and a case study on New Zealand honey

We describe an investigation into how Massey University’s Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University’s pollen reference collection (2,890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set.We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. In addition to the Classifynder’s native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples.

A comparison of classification algorithms within the Classifynder pollen imaging system

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. © 2013 AIP Publishing LLC.

Wide area control of SVCs for first swing stabilisation and damping in longitudinal systems

A non-linear Kalman filter based control strategy for SVCs located in major load groups is presented. This focusses on the limitation and damping of inter-area modes. It does this through treating local modes as noise and uses a tunable nonlinear control algorithm to improve both first swing stability and system damping. Simulation on a four machine system shows that the Kalman filer can successfully lock on to a desired inter-area mode and obtain a 31% improvement in critical clearing time as well as improved damping.

Interpreting discovered patterns in terms of ontology concepts

Semantic Web offers many possibilities for future Web technologies. Therefore, it is a need to search for ways that can bring the huge amount of unstructured documents from current Web to Semantic Web automatically. One big challenge in searching for such ways is how to understand patterns by both humans and machine. To address this issue, we present an innovative model which interprets patterns to high level concepts. These concepts can explain the patterns' meanings in a human understandable way while improving the information filtering performance. The model is evaluated by comparing it against one state-of-the-art benchmark model using standard Reuters dataset. The results show that the proposed model is successful. The significance of this model is three fold. It gives a way to interpret text mining output, provides a technique to find concepts relevant to the whole set of patterns which is an essential feature to understand the topic, and to some extent overcomes information mismatch and overload problems of existing models. This model will be very useful for knowledge based applications.

Soil moisture variability in a temperate deciduous forest: insights from electrical resistivity and throughfall data

Hydrogeophysics is a growing discipline that holds significant promise to help elucidate details of dynamic processes in the near surface, built on the ability of geophysical methods to measure properties from which hydrological and geochemical variables can be derived. For example, bulk electrical conductivity is governed by, amongst others, interstitial water content, fluid salinity, and temperature, and can be measured using a range of geophysical methods. In many cases, electrical resistivity tomography (ERT) is well suited to characterize these properties in multiple dimensions and to monitor dynamic processes, such as water infiltration and solute transport. In recent years, ERT has been used increasingly for ecosystem research in a wide range of settings; in particular to characterize vegetation-driven changes in root-zone and near-surface water dynamics. This increased popularity is due to operational factors (e.g., improved equipment, low site impact), data considerations (e.g., excellent repeatability), and the fact that ERT operates at scales significantly larger than traditional point sensors. Current limitations to a more widespread use of the approach include the high equipment costs, and the need for site-specific petrophysical relationships between properties of interest. In this presentation we will discuss recent equipment advances and theoretical and methodological aspects involved in the accurate estimation of soil moisture from ERT results. Examples will be presented from two studies in a temperate climate (Michigan, USA) and one from a humid tropical location (Tapajos, Brazil).

Hydrological consequences of land-cover change: Quantifying the influence of plants on soil moisture with time-lapse electrical resistivity

Electrical resistivity of soils and sediments is strongly influenced by the presence of interstitial water. Taking advantage of this dependency, electrical-resistivity imaging (ERI) can be effectively utilized to estimate subsurface soil-moisture distributions. The ability to obtain spatially extensive data combined with time-lapse measurements provides further opportunities to understand links between land use and climate processes. In natural settings, spatial and temporal changes in temperature and porewater salinity influence the relationship between soil moisture and electrical resistivity. Apart from environmental factors, technical, theoretical, and methodological ambiguities may also interfere with accurate estimation of soil moisture from ERI data. We have examined several of these complicating factors using data from a two-year study at a forest-grassland ecotone, a boundary between neighboring but different plant communities.At this site, temperature variability accounts for approximately 20-45 of resistivity changes from cold winter to warm summer months. Temporal changes in groundwater conductivity (mean=650 S/cm =57.7) and a roughly 100-S/cm spatial difference between the forest and grassland had only a minor influence on the moisture estimates. Significant seasonal fluctuations in temperature and precipitation had negligible influence on the basic measurement errors in data sets. Extracting accurate temporal changes from ERI can be hindered by nonuniqueness of the inversion process and uncertainties related to time-lapse inversion schemes. The accuracy of soil moisture obtained from ERI depends on all of these factors, in addition to empirical parameters that define the petrophysical soil-moisture/resistivity relationship. Many of the complicating factors and modifying variables to accurately quantify soil moisture changes with ERI can be accounted for using field and theoretical principles.

Conclusion

This monograph provides an overview of recruitment learning approaches from a computational perspective. Recruitment learning is a unique machine learning technique that: (1) explains the physical or functional acquisition of new neurons in sparsely connected networks as a biologically plausible neural network method; (2) facilitates the acquisition of new knowledge to build and extend knowledge bases and ontologies as an artificial intelligence technique; (3) allows learning by use of background knowledge and a limited number of observations, consistent with psychological theory.