Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
116
result(s) for
"Marsland, Stephen"
Sort by:
Birdsong Denoising Using Wavelets
Automatic recording of birdsong is becoming the preferred way to monitor and quantify bird populations worldwide. Programmable recorders allow recordings to be obtained at all times of day and year for extended periods of time. Consequently, there is a critical need for robust automated birdsong recognition. One prominent obstacle to achieving this is low signal to noise ratio in unattended recordings. Field recordings are often very noisy: birdsong is only one component in a recording, which also includes noise from the environment (such as wind and rain), other animals (including insects), and human-related activities, as well as noise from the recorder itself. We describe a method of denoising using a combination of the wavelet packet decomposition and band-pass or low-pass filtering, and present experiments that demonstrate an order of magnitude improvement in noise reduction over natural noisy bird recordings.
Journal Article
Human behavior recognition technologies : intelligent applications for monitoring and security
\"This book takes an insightful glance into the applications and dependability of behavior detection and looks into the social, ethical, and legal implications of these areas\"--Provided by publisher.
Book
Incremental Learning of Human Activities in Smart Homes
Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.
Journal Article
Epidemic changepoint detection in the presence of nuisance changes
Many time series problems feature epidemic changes—segments where a parameter deviates from a background baseline. Detection of such changepoints can be improved by accounting for the epidemic structure, but this is currently difficult if the background level is unknown. Furthermore, in practical data the background often undergoes nuisance changes, which interfere with standard estimation techniques and appear as false alarms. To solve these issues, we develop a new, efficient approach to simultaneously detect epidemic changes and estimate unknown, but fixed, background level, based on a penalised cost. Using it, we build a two-level detector that models and separates nuisance and signal changes. The analytic and computational properties of the proposed methods are established, including consistency and convergence. We demonstrate via simulations that our two-level detector provides accurate estimation of changepoints under a nuisance process, while other state-of-the-art detectors fail. In real-world genomic and demographic datasets, the proposed method identified and localised target events while separating out seasonal variations and experimental artefacts.
Journal Article
Sounding out the nest
Monitoring breeding outcomes of cryptic nocturnal species such as the North Island brown kiwi (Apteryx mantelli) is an important aim for conservation management in New Zealand. While fitting male kiwi with radio transmitters enables incubation burrows to be found and monitored, it is invasive and expensive. Remote monitoring methods (without handling of birds) are preferable. Here we investigate the extent to which it is practical to find North Island brown kiwi incubation burrows based on remote monitoring, motivated by anecdotal reports that incubating males call close to their incubation burrow on first emergence. We test this observation, and then use it to demonstrate how a combination of acoustic recorders, human listening, and trail cameras can be deployed to locate the burrow with minimal disturbance, based on the male’s first call of the night. Our analysis of an incubating brown kiwi male’s first call in the evening as a function of distance from the burrow shows that for more than half the time monitored he called within 10 minutes of leaving his burrow and that on these nights, he was usually less than 35 m from it. Along with backtracking of kiwi footsteps, this enables the localisation of the burrow. We outline a workflow for the method based on our experience and discuss how it can be made more efficient and usable in the future. Our method facilitates the finding of nests, and hence of chicks, without the need for adult kiwi to be fitted with transmitters.
Journal Article
Sounding out the nest : unobtrusive localisation of North Island brown kiwi (Apteryx mantelli) incubation burrows
Investigates the extent to which it is practical to find North Island brown kiwi incubation burrows based on remote monitoring, motivated by anecdotal reports that incubating males call close to their incubation burrow on first emergence. Tests this observation, then uses it to demonstrate how a combination of acoustic recorders, human listening, and trail cameras can be deployed to locate the burrow with minimal disturbance, based on the male’s first call of the night. Outlines a workflow for the method based on the authors' experience and discusses how it can be made more efficient and usable in the future. Source: National Library of New Zealand Te Puna Matauranga o Aotearoa, licensed by the Department of Internal Affairs for re-use under the Creative Commons Attribution 3.0 New Zealand Licence.
Journal Article
The Measurement and Analysis of Shapes
A de Rham p-current can be viewed as a map (the current map) between the set of embeddings of a closed p-dimensional manifold into an ambient n-manifold and the set of linear functionals on differential p-forms. We demonstrate that, for suitably chosen Sobolev topologies on both the space of embeddings and the space of p-forms, the current map is continuously differentiable, with an image that consists of bounded linear functionals on p-forms. Using the Riesz representation theorem, we prove that each p-current can be represented by a unique co-exact differential form that has a particular interpretation depending on p. Embeddings of a manifold can be thought of as shapes with a prescribed topology. Our analysis of the current map provides us with representations of shapes that can be used for the measurement and statistical analysis of collections of shapes. We consider two special cases of our general analysis and prove that: (1) if p=n-1 then closed, embedded, co-dimension one surfaces are naturally represented by probability distributions on the ambient manifold and (2) if p=1 then closed, embedded, one-dimensional curves are naturally represented by fluid flows on the ambient manifold. In each case, we outline some statistical applications using an H˙1 and L2 metric, respectively.
Journal Article
K-Bit-Swap: a new operator for real-coded evolutionary algorithms
There have been a variety of crossover operators proposed for real-coded genetic algorithms (RCGAs). Such operators recombine values from pairs of strings to generate new solutions. In this article, we present a recombination operator for RCGAs that selects the string locations for change separately randomly in the parent and offspring, enabling solution parts to move within a string, and compare it to mainstream crossover operators in a set of experiments on a range of standard multidimensional optimization problems and a real-world clustering problem. We present two variants of the operator, either selecting bits uniformly at random in both strings or sampling the second bit from a normal distribution centered at the selected location in the first string. While the operator is biased toward exploitation of fitness space, the random selection of the second bit for swapping reduces this bias slightly. Statistical analysis of the experimental results using a nonparametric test shows the advantage of the new recombination operators on our test optimization functions.
Journal Article