scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Accurate activity recognition in a home setting

TL;DR: This paper presents an easy to install sensor network and an accurate but inexpensive annotation method and shows how the hidden Markov model and conditional random fields perform in recognizing activities.
Abstract: A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its annotation is described and made available to the community. Through a number of experiments we show how the hidden Markov model and conditional random fields perform in recognizing activities. We achieve a timeslice accuracy of 95.6% and a class accuracy of 79.4%.
Citations
More filters
Christopher M. Bishop1
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

10,141 citations

Journal ArticleDOI
TL;DR: In this paper, the authors provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition using on-body inertial sensors and describe the concept of an Activity Recognition Chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems.
Abstract: The last 20 years have seen ever-increasing research activity in the field of human activity recognition. With activity recognition having considerably matured, so has the number of challenges in designing, implementing, and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition. It specifically focuses on activity recognition using on-body inertial sensors. We first discuss the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. We then describe the concept of an Activity Recognition Chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems. We detail each component of the framework, provide references to related research, and introduce the best practice methods developed by the activity recognition research community. We conclude with the educational example problem of recognizing different hand gestures from inertial sensors attached to the upper and lower arm. We illustrate how each component of this framework can be implemented for this specific activity recognition problem and demonstrate how different implementations compare and how they impact overall recognition performance.

1,214 citations

01 Jan 2014
TL;DR: This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition using on-body inertial sensors and describes the concept of an Activity Recognition Chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems.
Abstract: The last 20 years have seen ever-increasing research activity in the field of human activity recognition. With activity recognition having considerably matured, so has the number of challenges in designing, implementing, and evaluating activity recognition systems. This tutorial aims to provide a comprehensive hands-on introduction for newcomers to the field of human activity recognition. It specifically focuses on activity recognition using on-body inertial sensors. We first discuss the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. We then describe the concept of an Activity Recognition Chain (ARC) as a general-purpose framework for designing and evaluating activity recognition systems. We detail each component of the framework, provide references to related research, and introduce the best practice methods developed by the activity recognition research community. We conclude with the educational example problem of recognizing different hand gestures from inertial sensors attached to the upper and lower arm. We illustrate how each component of this framework can be implemented for this specific activity recognition problem and demonstrate how different implementations compare and how they impact overall recognition performance.

1,078 citations


Cites background or methods from "Accurate activity recognition in a ..."

  • ...…rec [Huynh et al. 2008]3 Joint boosting daily routines 4 1 88% prec, 90% rec [Blanke and Schiele 2009]4 CRF/HMM daily home activities 7 1 96%/95% [van Kasteren et al. 2008]5 Decision tree selected daily activities 20 20 84% acc [Bao and Intille 2004]6 AdaBoost+HMM selected daily activities 8…...

    [...]

  • ...…temporal probabilistic models such as Hidden Markov Models (HMMs) [Rabiner 1989; Bulling et al. 2008; Fink 2008], Conditional Random Fields (CRFs) [Liao et al. 2005; van Kasteren et al. 2008; Blanke and Schiele 2010], or dynamic Bayesian networks [Patterson et al. 2005] have been used....

    [...]

  • ...2000] Reed switches EO-Use of objects and ambient infrastructure [van Kasteren et al. 2008] RFID EO-Radio-frequency identi.cation: Use of objects and ambient infrastructure [Philipose et al. 2004; Stikic et al.2008; Wang et al. 2007; Buettner et al. 2009] Proximity E-B motion detection, tracking,…...

    [...]

Proceedings ArticleDOI
15 Jun 2010
TL;DR: The networked sensor setup and the methodology for data acquisition, synchronization and curation, and the use of the dataset to develop new sensor network self-organization principles and machine learning techniques for activity recognition in opportunistic sensor configurations are described.
Abstract: We deployed 72 sensors of 10 modalities in 15 wireless and wired networked sensor systems in the environment, in objects, and on the body to create a sensor-rich environment for the machine recognition of human activities. We acquired data from 12 subjects performing morning activities, yielding over 25 hours of sensor data. We report the number of activity occurrences observed during post-processing, and estimate that over 13000 and 14000 object and environment interactions occurred. We describe the networked sensor setup and the methodology for data acquisition, synchronization and curation. We report on the challenges and outline lessons learned and best practice for similar large scale deployments of heterogeneous networked sensor systems. We evaluate data acquisition quality for on-body and object integrated wireless sensors; there is less than 2.5% packet loss after tuning. We outline our use of the dataset to develop new sensor network self-organization principles and machine learning techniques for activity recognition in opportunistic sensor configurations. Eventually this dataset will be made public.

659 citations


Cites background from "Accurate activity recognition in a ..."

  • ...A few of the more known datasets are: the PlaceLab dataset, focusing on ambient and object sensing [13]; Van Kasteren’s dataset [14] with particularly long recordings (month-long) but with fewer sensors, and the Darmstadt routine dataset used for unsupervised activity pattern discovery [15], that is a long recording from body activity collected by the Porcupine system [16]....

    [...]

Proceedings ArticleDOI
03 Nov 2010
TL;DR: How to use cheap and simple sensing technology to automatically sense occupancy and sleep patterns in a home, and how to use these patterns to save energy by automatically turning off the home's HVAC system, called the smart thermostat.
Abstract: Heating, ventilation and cooling (HVAC) is the largest source of residential energy consumption. In this paper, we demonstrate how to use cheap and simple sensing technology to automatically sense occupancy and sleep patterns in a home, and how to use these patterns to save energy by automatically turning off the home's HVAC system. We call this approach the smart thermostat. We evaluate this approach by deploying sensors in 8 homes and comparing the expected energy usage of our algorithm against existing approaches. We demonstrate that our approach will achieve a 28% energy saving on average, at a cost of approximately $25 in sensors. In comparison, a commercially-available baseline approach that uses similar sensors saves only 6.8% energy on average, and actually increases energy consumption in 4 of the 8 households.

632 citations


Cites background or methods from "Accurate activity recognition in a ..."

  • ...To illustrate the concept of a deep setback, Figure 8 shows the distributions of leave and return times for the publicly available Kasteren [25] and Tulum [31] home monitoring datasets, excluding weekends....

    [...]

  • ...We call these the Kasteren [25] and Tulum [31] datasets, respectively....

    [...]

  • ...Therefore, the smart thermostat does not require cameras or wearable tags that may be considered intrusive to the user [22, 23] or more sophisticated sensing systems used for fine-grained tracking and activity recognition [24, 25, 26]....

    [...]

  • ...Ground truth in home monitoring experiments is very difficult to collect, and previous studies have used a wide variety of approaches ranging from self reports to video camera recordings to having a proctor physically on site to monitor home activities [32, 25, 33]....

    [...]

References
More filters
Book
Christopher M. Bishop1
17 Aug 2006
TL;DR: Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

22,840 citations


"Accurate activity recognition in a ..." refers background or methods in this paper

  • ...In this work, we adopt the notation [17, 4 ] which allows different forms of CRFs to be expressed using a common formula....

    [...]

  • ...Unlike a probability, potentials are not restricted to a value between 0 and 1 [ 4 ]....

    [...]

Journal ArticleDOI
Lawrence R. Rabiner1
01 Feb 1989
TL;DR: In this paper, the authors provide an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and give practical details on methods of implementation of the theory along with a description of selected applications of HMMs to distinct problems in speech recognition.
Abstract: This tutorial provides an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and gives practical details on methods of implementation of the theory along with a description of selected applications of the theory to distinct problems in speech recognition. Results from a number of original sources are combined to provide a single source of acquiring the background required to pursue further this area of research. The author first reviews the theory of discrete Markov chains and shows how the concept of hidden states, where the observation is a probabilistic function of the state, can be used effectively. The theory is illustrated with two simple examples, namely coin-tossing, and the classic balls-in-urns system. Three fundamental problems of HMMs are noted and several practical techniques for solving these problems are given. The various types of HMMs that have been studied, including ergodic as well as left-right models, are described. >

21,819 citations

Christopher M. Bishop1
01 Jan 2006
TL;DR: Probability distributions of linear models for regression and classification are given in this article, along with a discussion of combining models and combining models in the context of machine learning and classification.
Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

10,141 citations

Book
01 Aug 2006
TL;DR: Looking for competent reading resources?
Abstract: Looking for competent reading resources? We have pattern recognition and machine learning information science and statistics to read, not only read, but also download them or even check out online. Locate this fantastic book writtern by by now, simply here, yeah just here. Obtain the reports in the kinds of txt, zip, kindle, word, ppt, pdf, as well as rar. Once again, never ever miss to review online and download this book in our site right here. Click the link.

8,923 citations


"Accurate activity recognition in a ..." refers background or methods in this paper

  • ...In this work, we adopt the notation [17, 4] which allows different forms of CRFs to be expressed using a common formula....

    [...]

  • ...Unlike a probability, potentials are not restricted to a value between 0 and 1 [4]....

    [...]

Proceedings ArticleDOI
27 Sep 1999
TL;DR: Some of the research challenges in understanding context and in developing context-aware applications are discussed, which are increasingly important in the fields of handheld and ubiquitous computing, where the user?s context is changing rapidly.
Abstract: When humans talk with humans, they are able to use implicit situational information, or context, to increase the conversational bandwidth. Unfortunately, this ability to convey ideas does not transfer well to humans interacting with computers. In traditional interactive computing, users have an impoverished mechanism for providing input to computers. By improving the computer’s access to context, we increase the richness of communication in human-computer interaction and make it possible to produce more useful computational services. The use of context is increasingly important in the fields of handheld and ubiquitous computing, where the user?s context is changing rapidly. In this panel, we want to discuss some of the research challenges in understanding context and in developing context-aware applications.

4,842 citations


"Accurate activity recognition in a ..." refers background in this paper

  • ...INTRODUCTION Activities are a very important piece of information for ubiquitous applications [3]....

    [...]