A Segmentation Scheme for Knowledge Discovery in Human Activity Spotting

Uslu, Gamze; Baydere, Şebnem

doi:10.1109/tcyb.2021.3137753

Cited by 5 publications

(4 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this classifier, only the source user labels are available, while the target user labels are unavailable. Although the target domain label is unknown, it is common to assume that the association between samples and classes is known [34] [35] [36]. For example, we may know a particular sample is associated with class A, but we have no knowledge of what class A is (i.e.…”

Section: Fine-grained Temporal Relation Feature Extractionmentioning

confidence: 99%

Cross-session Specific Emitter Identification using Adversarial Domain Adaptation with Wasserstein distance

Wang

Dong

et al. 2022

2022 26th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Human Activity Recognition (HAR) is a cornerstone of ubiquitous computing, with promising applications in diverse fields such as health monitoring and ambient assisted living. Despite significant advancements, sensor-based HAR methods often operate under the assumption that training and testing data have identical distributions. However, in many real-world scenarios, particularly in sensor-based HAR, this assumption is invalidated by out-of-distribution (o.o.d.) challenges, including differences from heterogeneous sensors, change over time, and individual behavioural variability. This paper centres on the latter, exploring the cross-user HAR problem where behavioural variability across individuals results in differing data distributions. To address this challenge, we introduce the Deep Temporal State Domain Adaptation (DTSDA) model, an innovative approach tailored for time series domain adaptation in crossuser HAR. Contrary to the common assumption of sample independence in existing domain adaptation approaches, DTSDA recognizes and harnesses the inherent temporal relations in the data. Therefore, we introduce 'Temporal State', a concept that defined the different sub-activities within an activity, consistent across different users. We ensure these sub-activities follow a logical time sequence through 'Temporal Consistency' property and propose the 'Pseudo Temporal State Labeling' method to identify the user-invariant temporal relations. Moreover, the design principle of DTSDA integrates adversarial learning for better domain adaptation. Comprehensive evaluations on three HAR datasets demonstrate DTSDA's superior performance in cross-user HAR applications by briding individual behavioral variability using temporal relations across sub-activities.

show abstract

Section: Fine-grained Temporal Relation Feature Extractionmentioning

confidence: 99%

Cross-session Specific Emitter Identification using Adversarial Domain Adaptation with Wasserstein distance

Wang

Dong

et al. 2022

2022 26th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

show abstract

“…As described in the Methodology section we used classification ability to represent knowledge discovery by use of AUROC [34]. There are many opinions on which measures or scores to use when measuring discovered knowledge [29,30,[53][54][55][56][57]. The study mainly used the intrinsic AUROC implementations for each classification method, which could lead to AUROC implementation bias.…”

Section: Knowledge Representationmentioning

confidence: 99%

Case Study - Feature Engineering Inspired by Domain Experts on Real World Medical Data

2022

View full text Add to dashboard Cite

“…Most scholars first performed a segmentation task on the entire timeseries data into the optimal size for classifying target activities [ 5 ] and then classified each segment. However, this approach has limitations in performance because human activities are not standardized for each person [ 6 ]. In detail, the fixed-size window (FSW) method, shown on the left of Figure 1 , cannot cover properly when the target activity execution time is larger than the window size.…”

Section: Introductionmentioning

confidence: 99%

“…A too-small window size could not include the entire activity, and a too-large window size could be a reason for classification error. In [ 6 ], the window size of SW significantly influenced the recognition performance. In addition, the authors mentioned that the optimal window size is hard to predefine because of the inconstancy of the type and duration of human activity.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning-Based Semantic Segmentation Model Using MCNN and Attention Layer for Human Activity Recognition

Lee

Kim

2023

Sensors

View full text Add to dashboard Cite

With the development of wearable devices such as smartwatches, several studies have been conducted on the recognition of various human activities. Various types of data are used, e.g., acceleration data collected using an inertial measurement unit sensor. Most scholars segmented the entire timeseries data with a fixed window size before performing recognition. However, this approach has limitations in performance because the execution time of the human activity is usually unknown. Therefore, there have been many attempts to solve this problem through the method of activity recognition by sliding the classification window along the time axis. In this study, we propose a method for classifying all frames rather than a window-based recognition method. For implementation, features extracted using multiple convolutional neural networks with different kernel sizes were fused and used. In addition, similar to the convolutional block attention module, an attention layer to each channel and spatial level is applied to improve the model recognition performance. To verify the performance of the proposed model and prove the effectiveness of the proposed method on human activity recognition, evaluation experiments were performed. For comparison, models using various basic deep learning modules and models, in which all frames were classified for recognizing a specific wave in electrocardiography data were applied. As a result, the proposed model reported the best F1-score (over 0.9) for all kinds of target activities compared to other deep learning-based recognition models. Further, for the improvement verification of the proposed CEF method, the proposed method was compared with three types of SW method. As a result, the proposed method reported the 0.154 higher F1-score than SW. In the case of the designed model, the F1-score was higher as much as 0.184.

show abstract

A Segmentation Scheme for Knowledge Discovery in Human Activity Spotting

Cited by 5 publications

References 67 publications

Cross-session Specific Emitter Identification using Adversarial Domain Adaptation with Wasserstein distance

Cross-session Specific Emitter Identification using Adversarial Domain Adaptation with Wasserstein distance

Case Study - Feature Engineering Inspired by Domain Experts on Real World Medical Data

A Deep Learning-Based Semantic Segmentation Model Using MCNN and Attention Layer for Human Activity Recognition

Contact Info

Product

Resources

About