arXiv subjects

Max A. Little

Publications and source records attributed to Max A. Little.

29 records · Page 2Linked to original sources

arXiv2019

Automatic Quality Control and Enhancement for Voice-Based Remote Parkinson's Disease Detection

The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algorithms in compensating this mismatch and improving the PD detection accuracy. Then, we propose two approaches to automatically control the quality of recordings by identifying the presence and type of short-term and long-term degradations and protocol violations in voice signals. Finally, we experiment with using the proposed quality control methods to inform the choice of enhancement algorithm. Experimental results using the voice recordings of the mPower mobile PD data set under different degradation conditions show the effectiveness of the quality control approaches in selecting an appropriate enhancement method and, consequently, in improving the PD detection accuracy. This study is a step towards the development of a remote PD detection system capable of operating in unseen acoustic environments.

eess.AS↗

arXiv2019

Adaptive probabilistic principal component analysis

Using the linear Gaussian latent variable model as a starting point we relax some of the constraints it imposes by deriving a nonparametric latent feature Gaussian variable model. This model introduces additional discrete latent variables to the original structure. The Bayesian nonparametric nature of this new model allows it to adapt complexity as more data is observed and project each data point onto a varying number of subspaces. The linear relationship between the continuous latent and observed variables make the proposed model straightforward to interpret, resembling a locally adaptive probabilistic PCA (A-PPCA). We propose two alternative Gibbs sampling procedures for inference in the new model and demonstrate its applicability on sensor data for passive health monitoring.

stat.ML↗

arXiv2019

Bayesian Pitch Tracking Based on the Harmonic Model

Fundamental frequency is one of the most important characteristics of speech and audio signals. Harmonic model-based fundamental frequency estimators offer a higher estimation accuracy and robustness against noise than the widely used autocorrelation-based methods. However, the traditional harmonic model-based estimators do not take the temporal smoothness of the fundamental frequency, the model order, and the voicing into account as they process each data segment independently. In this paper, a fully Bayesian fundamental frequency tracking algorithm based on the harmonic model and a first-order Markov process model is proposed. Smoothness priors are imposed on the fundamental frequencies, model orders, and voicing using first-order Markov process models. Using these Markov models, fundamental frequency estimation and voicing detection errors can be reduced. Using the harmonic model, the proposed fundamental frequency tracker has an improved robustness to noise. An analytical form of the likelihood function, which can be computed efficiently, is derived. Compared to the state-of-the-art neural network and non-parametric approaches, the proposed fundamental frequency tracking algorithm reduces the mean absolute errors and gross errors by 15\% and 20\% on the Keele pitch database and 36\% and 26\% on sustained /a/ sounds from a database of Parkinson's disease voices under 0 dB white Gaussian noise. A MATLAB version of the proposed algorithm is made freely available for reproduction of the results\footnote{An implementation of the proposed algorithm using MATLAB may be found in \url{https://tinyurl.com/yxn4a543}

cs.SD↗

arXiv2019

Probabilistic modelling of gait for remote passive monitoring applications

Passive and non-obtrusive health monitoring using wearables can potentially bring new insights into the user's health status throughout the day and may support clinical diagnosis and treatment. However, identifying segments of free-living data that sufficiently reflect the user's health is challenging. In this work we have studied the problem of modelling real-life gait which is a very indicative behaviour for multiple movement disorders including Parkinson's disease (PD). We have developed a probabilistic framework for unsupervised analysis of the gait, clustering it into different types, which can be used to evaluate gait abnormalities occurring in daily life. Using a unique dataset which contains sensor and video recordings of people with and without PD in their own living environment, we show that our model driven approach achieves high accuracy gait detection and can capture clinical improvement after medication intake.

eess.SP↗

arXiv2017

A unified algorithm framework for quality control of sensor data for behavioural clinimetric testing

The use of smartphone and wearable sensing technology for objective, non-invasive and remote clinimetric testing of symptoms has considerable potential. However, the clinimetric accuracy achievable with such technology is highly reliant on separating the useful from irrelevant or confounded sensor data. Monitoring patient symptoms using digital sensors outside of controlled, clinical lab settings creates a variety of practical challenges, such as unavoidable and unexpected user behaviours. These behaviours often violate the assumptions of clinimetric testing protocols, where these protocols are designed to probe for specific symptoms. Such violations are frequent outside the lab, and can affect the accuracy of the subsequent data analysis and scientific conclusions. At the same time, curating sensor data by hand after the collection process is inherently subjective, laborious and error-prone. To address these problems, we report on a unified algorithmic framework for automated sensor data quality control, which can identify those parts of the sensor data which are sufficiently reliable for further analysis. Algorithms which are special cases of this framework for different sensor data types (e.g. accelerometer, digital audio) detect the extent to which the sensor data adheres to the assumptions of the test protocol for a variety of clinimetric tests. The approach is general enough to be applied to a large set of clinimetric tests and we demonstrate its performance on walking, balance and voice smartphone-based tests, designed to monitor the symptoms of Parkinson's disease.

eess.SP↗

arXiv2016

High Frequency Remote Monitoring of Parkinson's Disease via Smartphone: Platform Overview and Medication Response Detection

Objective: The aim of this study is to develop a smartphone-based high-frequency remote monitoring platform, assess its feasibility for remote monitoring of symptoms in Parkinson's disease, and demonstrate the value of data collected using the platform by detecting dopaminergic medication response. Methods: We have developed HopkinsPD, a novel smartphone-based monitoring platform, which measures symptoms actively (i.e. data are collected when a suite of tests is initiated by the individual at specific times during the day), and passively (i.e. data are collected continuously in the background). After data collection, we extract features to assess measures of five key behaviors related to PD symptoms -- voice, balance, gait, dexterity, and reaction time. A random forest classifier is used to discriminate measurements taken after a dose of medication (treatment) versus before the medication dose (baseline). Results: A worldwide study for remote PD monitoring was established using HopkinsPD in July, 2014. This study used entirely remote, online recruitment and installation, demonstrating highly cost-effective scalability. In six months, 226 individuals (121 PD and 105 controls) contributed over 46,000 hours of passive monitoring data and approximately 8,000 instances of structured tests of voice, balance, gait, reaction, and dexterity. To the best of our knowledge, this is the first study to have collected data at such a scale for remote PD monitoring. Moreover, we demonstrate the initial ability to discriminate treatment from baseline with 71.0(+-0.4)% accuracy, which suggests medication response can be monitored remotely via smartphone-based measures.

cs.CY↗

arXiv2014

Simple approximate MAP Inference for Dirichlet processes

The Dirichlet process mixture (DPM) is a ubiquitous, flexible Bayesian nonparametric statistical model. However, full probabilistic inference in this model is analytically intractable, so that computationally intensive techniques such as Gibb's sampling are required. As a result, DPM-based methods, which have considerable potential, are restricted to applications in which computational resources and time for inference is plentiful. For example, they would not be practical for digital signal processing on embedded hardware, where computational resources are at a serious premium. Here, we develop simplified yet statistically rigorous approximate maximum a-posteriori (MAP) inference algorithms for DPMs. This algorithm is as simple as K-means clustering, performs in experiments as well as Gibb's sampling, while requiring only a fraction of the computational effort. Unlike related small variance asymptotics, our algorithm is non-degenerate and so inherits the "rich get richer" property of the Dirichlet process. It also retains a non-degenerate closed-form likelihood which enables standard tools such as cross-validation to be used. This is a well-posed approximation to the MAP solution of the probabilistic DPM model.

stat.ML↗

arXiv2013

Highly comparative time-series analysis: The empirical structure of time series and their methods

The process of collecting and organizing sets of observations represents a common theme throughout the history of science. However, despite the ubiquity of scientists measuring, recording, and analyzing the dynamics of different processes, an extensive organization of scientific time-series data and analysis methods has never been performed. Addressing this, annotated collections of over 35 000 real-world and model-generated time series and over 9000 time-series analysis algorithms are analyzed in this work. We introduce reduced representations of both time series, in terms of their properties measured by diverse scientific methods, and of time-series analysis methods, in terms of their behaviour on empirical time series, and use them to organize these interdisciplinary resources. This new approach to comparing across diverse scientific data and methods allows us to organize time-series datasets automatically according to their properties, retrieve alternatives to particular analysis methods developed in other scientific disciplines, and automate the selection of useful methods for time-series classification and regression tasks. The broad scientific utility of these tools is demonstrated on datasets of electroencephalograms, self-affine time series, heart beat intervals, speech signals, and others, in each case contributing novel analysis techniques to the existing literature. Highly comparative techniques that compare across an interdisciplinary literature can thus be used to guide more focused research in time-series analysis for applications across the scientific disciplines.

physics.data-an↗

arXiv2011

Generalized Methods and Solvers for Noise Removal from Piecewise Constant Signals

Removing noise from piecewise constant (PWC) signals, is a challenging signal processing problem arising in many practical contexts. For example, in exploration geosciences, noisy drill hole records need separating into stratigraphic zones, and in biophysics, jumps between molecular dwell states need extracting from noisy fluorescence microscopy signals. Many PWC denoising methods exist, including total variation regularization, mean shift clustering, stepwise jump placement, running medians, convex clustering shrinkage and bilateral filtering; conventional linear signal processing methods are fundamentally unsuited however. This paper shows that most of these methods are associated with a special case of a generalized functional, minimized to achieve PWC denoising. The minimizer can be obtained by diverse solver algorithms, including stepwise jump placement, convex programming, finite differences, iterated running medians, least angle regression, regularization path following, and coordinate descent. We introduce novel PWC denoising methods, which, for example, combine global mean shift clustering with local total variation smoothing. Head-to-head comparisons between these methods are performed on synthetic data, revealing that our new methods have a useful role to play. Finally, overlaps between the methods of this paper and others such as wavelet shrinkage, hidden Markov models, and piecewise smooth filtering are touched on.

physics.data-an↗

arXiv2010

Steps and bumps: precision extraction of discrete states of molecular machines using physically-based, high-throughput time series analysis

We report new statistical time-series analysis tools providing significant improvements in the rapid, precision extraction of discrete state dynamics from large databases of experimental observations of molecular machines. By building physical knowledge and statistical innovations into analysis tools, we demonstrate new techniques for recovering discrete state transitions buried in highly correlated molecular noise. We demonstrate the effectiveness of our approach on simulated and real examples of step-like rotation of the bacterial flagellar motor and the F1-ATPase enzyme. We show that our method can clearly identify molecular steps, symmetries and cascaded processes that are too weak for existing algorithms to detect, and can do so much faster than existing algorithms. Our techniques represent a major advance in the drive towards automated, precision, highthroughput studies of molecular machine dynamics. Modular, open-source software that implements these techniques is provided at http://www.eng.ox.ac.uk/samp/members/max/software/

q-bio.QM↗

arXiv2010

Sparse bayesian step-filtering for high-throughput analysis of molecular machine dynamics

Nature has evolved many molecular machines such as kinesin, myosin, and the rotary flagellar motor powered by an ion current from the mitochondria. Direct observation of the step-like motion of these machines with time series from novel experimental assays has recently become possible. These time series are corrupted by molecular and experimental noise that requires removal, but classical signal processing is of limited use for recovering such step-like dynamics. This paper reports simple, novel Bayesian filters that are robust to step-like dynamics in noise, and introduce an L1-regularized, global filter whose sparse solution can be rapidly obtained by standard convex optimization methods. We show these techniques outperforming classical filters on simulated time series in terms of their ability to accurately recover the underlying step dynamics. To show the techniques in action, we extract step-like speed transitions from Rhodobacter sphaeroides flagellar motor time series. Code implementing these algorithms available from http://www.eng.ox.ac.uk/samp/members/max/software/.

q-bio.QM↗