Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features

Piyathilaka, Lasitha; Kodagoda, Sarath

doi:10.1109/iciea.2013.6566433

Cited by 116 publications

(66 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since these sensors typically consume several orders of magnitude more power than accelerometers, we do not consider these here. Note also that although outside the scope of this study, there is recent research in the area of Activities of Daily Living (ADL) recognition using other types of sensor, such as Red/Green/Blue-Depth (RGB-D) sensors [6] or other environmental sensors [7], or the fusion thereof [8].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study of Activity Recognition Using Accelerometers

et al. 2018

View full text Add to dashboard Cite

This paper serves as a survey and empirical evaluation of the state-of-the-art in activity recognition methods using accelerometers. The paper is particularly focused on long-term activity recognition in real-world settings. In these environments, data collection is not a trivial matter; thus, there are performance trade-offs between prediction accuracy, which is not the sole system objective, and keeping the maintenance overhead at minimum levels. We examine research that has focused on the selection of activities, the features that are extracted from the accelerometer data, the segmentation of the time-series data, the locations of accelerometers, the selection and configuration trade-offs, the test/retest reliability, and the generalisation performance. Furthermore, we study these questions from an experimental platform and show, somewhat surprisingly, that many disparate experimental configurations yield comparable predictive performance on testing data. Our understanding of these results is that the experimental setup directly and indirectly defines a pathway for context to be delivered to the classifier, and that, in some settings, certain configurations are more optimal than alternatives. We conclude by identifying how the main results of this work can be used in practice, specifically in experimental configurations in challenging experimental conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study of Activity Recognition Using Accelerometers

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Furthermore, variants that assume an infinite number of Gaussian components have been proposed [42]. GMMs have been used for example to classify multiple-limb motion using myoelectric (EMG) signals [43] or recognizing human motion from RGB-D camera data [25].…”

Section: Unsupervised Ar: Clusteringmentioning

confidence: 99%

“…There are several works proposing recognizing human activities from images or video. A popular approach is using depth-enhanced (RGB-D) video data to construct a skeleton representation of the human body and estimate activities based on the calculated poses of the participant [23][24][25]. While this is a valid approach in general, we do not use the video data in our recognition system, not only because no depth data are provided in the datasets, but because it would add significant complexity to our otherwise deliberately simple approach to recognizing steps in a process.…”

Section: Ar Via Image Processingmentioning

confidence: 99%

Detecting Transitions in Manual Tasks from Wearables: An Unsupervised Labeling Approach

2018

View full text Add to dashboard Cite

Authoring protocols for manual tasks such as following recipes, manufacturing processes or laboratory experiments requires significant effort. This paper presents a system that estimates individual procedure transitions from the user's physical movement and gestures recorded with inertial motion sensors. Combined with egocentric or external video recordings, this facilitates efficient review and annotation of video databases. We investigate different clustering algorithms on wearable inertial sensor data recorded on par with video data, to automatically create transition marks between task steps. The goal is to match these marks to the transitions given in a description of the workflow, thus creating navigation cues to browse video repositories of manual work. To evaluate the performance of unsupervised algorithms, the automatically-generated marks are compared to human expert-created labels on two publicly-available datasets. Additionally, we tested the approach on a novel dataset in a manufacturing lab environment, describing an existing sequential manufacturing process. The results from selected clustering methods are also compared to some supervised methods.

show abstract

“…Apart from malware detection, HMMs are also used for speech recognition [27], gene prediction, human activity recognition [26], etc. In the following sections we give a brief overview of HMM and how it is used for malware detection.…”

Section: Hmm Based Detectionmentioning

confidence: 99%

Clustering versus SVM for malware detection

Narra

Troia

Visaggio

et al. 2015

J Comput Virol Hack Tech

View full text Add to dashboard Cite

Clustering versus SVM for Malware Detection by Usha NarraPrevious work has shown that we can effectively cluster certain classes of malware into their respective families. In this research, we extend this previous work to the problem of developing an automated malware detection system. We first compute clusters for a collection of malware families. Then we analyze the effectiveness of classifying new samples based on these existing clusters. We compare results obtained using -means and Expectation Maximization (EM) clustering to those obtained using Support Vector Machines (SVM). Using clustering, we are able to detect some malware families with an accuracy comparable to that of SVMs. One advantage of the clustering approach is that there is no need to retrain for new malware families.

show abstract

Gaussian mixture based HMM for human daily activity recognition using 3D skeleton features

Cited by 116 publications

References 13 publications

A Comprehensive Study of Activity Recognition Using Accelerometers

A Comprehensive Study of Activity Recognition Using Accelerometers

Detecting Transitions in Manual Tasks from Wearables: An Unsupervised Labeling Approach

Clustering versus SVM for malware detection

Contact Info

Product

Resources

About