Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data

Konak, Orhan; Wegner, Pit; Albert, Justin Amadeus; Arnrich, Bert

doi:10.5220/0010838800003116

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike semi-supervised learning [14,15], new activity classes in unlabeled data are completely disjointed with labeled data. Similar to unsupervised clustering [17][18][19][20][21], the NCD aims to classify new activities by clustering unlabeled data into several new classes. However, the NCD differs in its setting to leverage transferred knowledge from labeled data to explore unlabeled datasets.…”

Section: Novel Class Discoverymentioning

confidence: 99%

“…It aims to partition a set of unlabeled data into different activity classes without available labeled data. In works [17,18], statistical properties of raw sensor data, including average and standard deviations, are considered as features and then these features are clustered by the k-means algorithm [30]. However, high sensitivity to sensor noise [31] are attributed to these methods.…”

Section: Unsupervised Clusteringmentioning

confidence: 99%

“…Class incremental learning [16] continuously recognizes new activity classes along with some tasks, whereas the learning of new classes at each task still requires annotation information. The NCD problem is similar to unsupervised clustering [17][18][19][20][21] that partitions unannotated data into several clusters that are different activity class groups. However, this problem can leverage knowledge of old classes to improve the discovery of the new ones.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

More Reliable Neighborhood Contrastive Learning for Novel Class Discovery in Sensor-Based Human Activity Recognition

Zhang,

Zhu,

Nie

et al. 2023

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) systems have made significant progress in recognizing and classifying human activities using sensor data from a variety of sensors. Nevertheless, they have struggled to automatically discover novel activity classes within massive amounts of unlabeled sensor data without external supervision. This restricts their ability to classify new activities of unlabeled sensor data in real-world deployments where fully supervised settings are not applicable. To address this limitation, this paper presents the Novel Class Discovery (NCD) problem, which aims to classify new class activities of unlabeled sensor data by fully utilizing existing activities of labeled data. To address this problem, we propose a new end-to-end framework called More Reliable Neighborhood Contrastive Learning (MRNCL), which is a variant of the Neighborhood Contrastive Learning (NCL) framework commonly used in visual domain. Compared to NCL, our proposed MRNCL framework is more lightweight and introduces an effective similarity measure that can find more reliable k-nearest neighbors of an unlabeled query sample in the embedding space. These neighbors contribute to contrastive learning to facilitate the model. Extensive experiments on three public sensor datasets demonstrate that the proposed model outperforms existing methods in the NCD task in sensor-based HAR, as indicated by the fact that our model performs better in clustering performance of new activity class instances.

show abstract