Using Topic Modelling Algorithms for Hierarchical Activity Discovery

Rogers, Eoin; Kelleher, John D.; Ross, Robert

doi:10.1007/978-3-319-40114-0_5

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to try to determine if our proposed metric is useful, we used an activity discovery system that was presented previously by the same authors [6]. We refer the interested reader to the cited paper for a detailed explanation of how this system works, but in summary we split the dataset D up into L − w + 1 subsets using a sliding window of length w and run each window through a topic modelling algorithm as if it was a single document.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner

Rogers¹,

Ross²,

Kelleher³

2018

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

Abstract. Activity discovery is a challenging machine learning problem where we seek to uncover new or altered behavioural patterns in sensor data. In this paper we motivate and introduce a novel approach to evaluating activity discovery systems. Pre-annotated ground truths, often used to evaluate the performance of such systems on existing datasets, may exist at different levels of abstraction to the output of the output produced by the system. We propose a method for detecting and dealing with this situation, allowing for useful ground truth comparisons. This work has applications for activity discovery, and also for related fields. For example, it could be used to evaluate systems intended for anomaly detection, intrusion detection, automated music transcription and potentially other applications.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner

Rogers¹,

Ross²,

Kelleher³

2018

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Topic models have been applied to discover activity patterns from unseen sensor data in an unsupervised fashion [13]. The discovered activity patterns correspond to high-level activities that are composed by a set of low-level activity patterns [13], [14] or a set of sensor events [15], [16], [17]. The low-level activities, considered as words, are concrete and short-term activities such as body movement, location, object usage.…”

Section: Related Workmentioning

confidence: 99%

Discovery and Recognition of Emerging Human Activities Using a Hierarchical Mixture of Directional Statistical Models

Fang

Dobson

2020

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Human activity recognition plays a significant role in enabling pervasive applications as it abstracts low-level noisy sensor data into high-level human activities, which applications can respond to. With more and more activity-aware applications deployed in real-world environments, a research challenge emerges-discovering and learning new activities that have not been pre-defined or observed in the training phase. This paper tackles this challenge by proposing a hierarchical mixture of directional statistical models. The model supports incrementally, continuously updating the activity model over time with the reduced annotation effort and without the need for storing historical sensor data. We have validated this solution on four publicly available, third-party smart home datasets, and have demonstrated up to 91.5% accuracies of detecting and recognising new activities.

show abstract

“…Taghia et al did similar research on Bayesian learning on vMF mixture models via variational inference [18]. The infinite mixture extension of the vMFs mixture model is first studied by Bangert et al [19] to cluster treatment beam in external radiation therapy; while later Roge et al propose an alternative Collapsed Gibbs sampler to infer the same infinite mixture model [20]. Qin et al [21] developed a reverse jump Markov Chain Monte Carlo algorithm to learn trans-dimensional model of von Mises Fisher models.…”

Section: B Unsupervised Learningmentioning

confidence: 99%

Sensor-Based Human Activity Mining Using Dirichlet Process Mixtures of Directional Statistical Models

Fang

Dobson

2019

2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

We have witnessed an increasing number of activityaware applications being deployed in real-world environments, including smart home and mobile healthcare. The key enabler to these applications is sensor-based human activity recognition; that is, recognising and analysing human daily activities from wearable and ambient sensors. With the power of machine learning we can recognise complex correlations between various types of sensor data and the activities being observed. However the challenges still remain: (1) they often rely on a large amount of labelled training data to build the model, and (2) they cannot dynamically adapt the model with emerging or changing activity patterns over time. To directly address these challenges, we propose a Bayesian nonparametric model, i.e. Dirichlet process mixture of conditionally independent von Mises Fisher models, to enable both unsupervised and semi-supervised dynamic learning of human activities. The Bayesian nonparametric model can dynamically adapt itself to the evolving activity patterns without human intervention and the learning results can be used to alleviate the annotation effort. We evaluate our approach against real-world, third-party smart home datasets, and demonstrate significant improvements over the state-of-the-art techniques in both unsupervised and supervised settings.

show abstract

Using Topic Modelling Algorithms for Hierarchical Activity Discovery

Cited by 6 publications

References 10 publications

Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner

Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner

Discovery and Recognition of Emerging Human Activities Using a Hierarchical Mixture of Directional Statistical Models

Sensor-Based Human Activity Mining Using Dirichlet Process Mixtures of Directional Statistical Models

Contact Info

Product

Resources

About