Hidden Markov Models for Time Series

Zucchini, Walter; MacDonald, Iain L.; Langrock, Roland

doi:10.1201/b20790

Cited by 336 publications

(222 citation statements)

References 0 publications

Supporting

Mentioning

189

Contrasting

Order By: Relevance

“…Hidden Markov models (HMMs) have proven to be effective in modelling time series data [64]. They are a good fit for recognising activities from sensor-generated data in the sense that they are capable of recovering a series of latent states from a series of observations.…”

Section: Recognition Methodsmentioning

confidence: 99%

Using Sensors to Study Home Activities

Jiang

Pozza

Gunnarsdóttir

et al. 2017

JSAN

View full text Add to dashboard Cite

Abstract:Understanding home activities is important in social research to study aspects of home life, e.g., energy-related practices and assisted living arrangements. Common approaches to identifying which activities are being carried out in the home rely on self-reporting, either retrospectively (e.g., interviews, questionnaires, and surveys) or at the time of the activity (e.g., time use diaries). The use of digital sensors may provide an alternative means of observing activities in the home. For example, temperature, humidity and light sensors can report on the physical environment where activities occur, while energy monitors can report information on the electrical devices that are used to assist the activities. One may then be able to infer from the sensor data which activities are taking place. However, it is first necessary to calibrate the sensor data by matching it to activities identified from self-reports. The calibration involves identifying the features in the sensor data that correlate best with the self-reported activities. This in turn requires a good measure of the agreement between the activities detected from sensor-generated data and those recorded in self-reported data. To illustrate how this can be done, we conducted a trial in three single-occupancy households from which we collected data from a suite of sensors and from time use diaries completed by the occupants. For sensor-based activity recognition, we demonstrate the application of Hidden Markov Models with features extracted from mean-shift clustering and change points analysis. A correlation-based feature selection is also applied to reduce the computational cost. A method based on Levenshtein distance for measuring the agreement between the activities detected in the sensor data and that reported by the participants is demonstrated. We then discuss how the features derived from sensor data can be used in activity recognition and how they relate to activities recorded in time use diaries.

show abstract

Section: Recognition Methodsmentioning

confidence: 99%

Using Sensors to Study Home Activities

Jiang

Pozza

Gunnarsdóttir

et al. 2017

JSAN

View full text Add to dashboard Cite

show abstract

“…An HMM is also referred to as a dependent finite mixture model (Gollery, 2008;MacDonald & Zucchini, 1997;Visser & Speekenbrink, 2010;Zucchini & MacDonald, 2009). HMMs have been used in various applications like speech recognition, EEG analysis, psychology, economics, and genetics.…”

Section: Using a Hidden Markov Model To Describe The Hand Movement Sementioning

confidence: 99%

“…The fundamental assumption is, at any point in time, the observations are distributed as mixtures given an r number of latent/hidden states, and time-dependencies between observations are due to time-dependencies between the hidden states following a first-order Markov process (Visser & Speekenbrink, 2010). A first-order Markov process assumes that, given a sequence of a discrete random variable, the occurrence at time t+1 is conditioned upon the most recent value of the random variable at time t (Zucchini & MacDonald, 2009). This property is a relaxation of the independence assumption, and can be displayed as a direct graph where any future observation is dependent only on the present observation (see Figure 6a).…”

Section: Using a Hidden Markov Model To Describe The Hand Movement Sementioning

confidence: 99%

A Measurement Model of Gestures in an Embodied Learning Environment: Accounting for Temporal Dependencies

2017

View full text Add to dashboard Cite

ABSTRACT:Interactive learning environments with body-centric technologies lie at the intersection of the design of embodied learning activities and multimodal learning analytics. Sensing technologies can generate large amounts of fine-grained data automatically captured from student movements. Researchers can use these fine-grained data to create a high-resolution picture of the activity that takes place during these student-computer interactions and explore whether the sequence of movements has an effect on learning. We present a use-case modelling of temporal data in an interactive learning environment with hand gestures, and discuss some validity threats if temporal dependencies are not accounted for. In particular, we assess how, if ignored, the temporal dependencies in the measurement of hand gestures might affect the goodness of fit of the statistical model and would affect the measurement of the similarity between elicited and enacted movement. Our findings show that accounting for temporality is crucial for finding a meaningful fit to the data. In using temporal analytics, we are able to create a high-resolution picture of how sensorimotor coordination correlates with learning gains in our learning system.

show abstract

“…In Hidden Markov models (HMMs), the state space is only partially observable [7]. It is formed by two dependent stochastic processes (Fig.…”

Section: Markov Decision Process and Hidden Markov Modelsmentioning

confidence: 99%

“…The second stochastic process generates observable emissions, conditional on the hidden process. Methodology has been developed to decode the hidden states from the observed data and has applications in a multitude of areas [7]. …”

Section: Markov Decision Process and Hidden Markov Modelsmentioning

confidence: 99%

Markov Models and Cost Effectiveness Analysis: Applications in Medical Research

Komorowski

Raffa

2016

Secondary Analysis of Electronic Health Records

View full text Add to dashboard Cite

Learning ObjectivesUnderstand how Markov models can be used to analyze medical decisions and perform cost-effectiveness analysis.This case study introduces concepts that should improve understanding of the following:1. Markov models and their use in medical research. 2. Basics of health economics. 3. Replicating the results of a large prospective randomized controlled trial using a Markov Chain and Monte Carlo simulations, and 4. Relating quality-adjusted life years (QALYs) and cost of interventions to each state of a Markov Chain, in order to conduct a simple cost-effectiveness analysis. IntroductionMarkov models were initially theroreticized at the beginning of the 20th century by Russian mathematician Andrey Markov [1]. They are stochastic processes that undergo transitions from one state to another. Over the years, they have found countless applications, especially for modeling processes and informing decision making, in the fields of physics, queuing theory, finance, social sciences, statistics and of course medicine. Markov models are useful to model environments and problems involving sequential, stochastic decisions over time. Representing such environments with decision trees would be confusing or intractable, if at all possible, and would require major simplifying assumptions [2]. Markov models can be examined by an array of tools including linear algebra (brute force), cohort simulations, Monte Carlo simulations and, for Markov Decision Processes, dynamic programming and reinforcement learning [3,4].

show abstract

Hidden Markov Models for Time Series

Cited by 336 publications

References 0 publications

Using Sensors to Study Home Activities

Using Sensors to Study Home Activities

A Measurement Model of Gestures in an Embodied Learning Environment: Accounting for Temporal Dependencies

Markov Models and Cost Effectiveness Analysis: Applications in Medical Research

Contact Info

Product

Resources

About