Human Activity Recognition Machine With an Anchor-Based Loss Function

Jin, Lei; Wang, Xiaojuan; Jiaming, Chu,; He, Mingshu

doi:10.1109/jsen.2021.3130761

Cited by 12 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our benchmark regroups head-to-head 17 articles (21)(22)(23)(24)(25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35) by sharing their approach concerning the human activity recognition task evaluated on the UniMiB-SHAR dataset. Deep learning was the method of choice in almost every case (21-26, 28-32, 34, 35) to try to achieve state-of-the-art results.…”

Section: Related Work From Benchmarkmentioning

confidence: 99%

“…This means that the results and metrics reported by one study cannot always be rigorously compared with all the others, as they must use the same evaluation methods. The evaluation methods featured in these articles are as follows: the evaluation of a validation set (21)(22)(23)(24)(25)(26), the evaluation of a test set (27, 28), cross-validation (29)(30)(31)(32), and leave-one-subject-out (32,34,35).…”

Section: Related Work From Benchmarkmentioning

confidence: 99%

See 1 more Smart Citation

The use of deep learning for smartphone-based human activity recognition

Stampfler

Elgendi²,

Fletcher³

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

The emerging field of digital phenotyping leverages the numerous sensors embedded in a smartphone to better understand its user's current psychological state and behavior, enabling improved health support systems for patients. As part of this work, a common task is to use the smartphone accelerometer to automatically recognize or classify the behavior of the user, known as human activity recognition (HAR). In this article, we present a deep learning method using the Resnet architecture to implement HAR using the popular UniMiB-SHAR public dataset, containing 11,771 measurement segments from 30 users ranging in age between 18 and 60 years. We present a unified deep learning approach based on a Resnet architecture that consistently exceeds the state-of-the-art accuracy and F1-score across all classification tasks and evaluation methods mentioned in the literature. The most notable increase we disclose regards the leave-one-subject-out evaluation, known as the most rigorous evaluation method, where we push the state-of-the-art accuracy from 78.24 to 80.09% and the F1-score from 78.40 to 79.36%. For such results, we resorted to deep learning techniques, such as hyper-parameter tuning, label smoothing, and dropout, which helped regularize the Resnet training and reduced overfitting. We discuss how our approach could easily be adapted to perform HAR in real-time and discuss future research directions.

show abstract

Section: Related Work From Benchmarkmentioning

confidence: 99%

Section: Related Work From Benchmarkmentioning

confidence: 99%

The use of deep learning for smartphone-based human activity recognition

Stampfler

Elgendi²,

Fletcher³

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Ref. [ 39 ] introduced using the distance-based loss function in MLP, CNN, LSTM and hybrid model, and found that CNN-D shows the best performance among these methods. Compared with CNN-D, the accuracy and F1-score increases by 1.21% and 0.89%.…”

Section: Performance Evaluationmentioning

confidence: 99%

A Novel Segmentation Scheme with Multi-Probability Threshold for Human Activity Recognition Using Wearable Sensors

Zhou

Wang

Huan

et al. 2022

Sensors

View full text Add to dashboard Cite

In recent years, much research has been conducted on time series based human activity recognition (HAR) using wearable sensors. Most existing work for HAR is based on the manual labeling. However, the complete time serial signals not only contain different types of activities, but also include many transition and atypical ones. Thus, effectively filtering out these activities has become a significant problem. In this paper, a novel machine learning based segmentation scheme with a multi-probability threshold is proposed for HAR. Threshold segmentation (TS) and slope-area (SA) approaches are employed according to the characteristics of small fluctuation of static activity signals and typical peaks and troughs of periodic-like ones. In addition, a multi-label weighted probability (MLWP) model is proposed to estimate the probability of each activity. The HAR error can be significantly decreased, as the proposed model can solve the problem that the fixed window usually contains multiple kinds of activities, while the unknown activities can be accurately rejected to reduce their impacts. Compared with other existing schemes, computer simulation reveals that the proposed model maintains high performance using the UCI and PAMAP2 datasets. The average HAR accuracies are able to reach 97.71% and 95.93%, respectively.

show abstract

“…For fair comparison experiments, we implemented these two models without incremental learning and replaced the feature extractor for video with multi-channel signals. [27] designed a new framework for the open-set HAR with class anchor clustering (CAC) loss [28] instead of the softmax-based cross-entropy loss. CAC loss is a distance-based loss that combines an anchor loss and a tuplet loss.…”

Section: Related Work a Open-set Recognition For Harmentioning

confidence: 99%

“…Especially for open-set HAR, the existing open-set algorithms have been faced with the problem that features or probabilities of the unknown activities have little discernability, which is caused by the inter-activity similarity and the intra-activity diversity [18]- [20]. More precisely, some human activities are made up of the atomic behavioral characteristics of other activities.…”

Section: Introductionmentioning

confidence: 99%

Sensor-Based Open-Set Human Activity Recognition Using Representation Learning With Mixup Triplets

Lee

Kim

2022

IEEE Access

View full text Add to dashboard Cite

The main objective of sensor-based human activity recognition (HAR) is to classify predefined human physical activities with multi-channel signals acquired from wearable sensors. In a realworld scenario, signal data is changing over time and undefined activities may occur. Thus, an openset classifier for HAR is required to detect it as an unknown class rather than to assign it to the one of the known classes. However, open-set HAR is a challenging task because of the small variability of inter-activities and the large variability of intra-activities. To tackle this problem, we propose mixup triplet learning for Mahalanobis distance (MTMD) for open-set recognition. In MTMD, we introduce a new representation learning with stochastically linearly interpolated triplets (mixup triplets) that makes discriminative features of the known from the unknown. In the trained embedding space with the proposed representation learning, thresholds based on Mahalanobis distances from the centers of each known activity are defined for the proposed open-set action recognition. To demonstrate the effectiveness of MTMD, we conducted experiments on sensor-based HAR benchmark datasets. The experimental results show that the proposed MTMD outperforms the existing methods for various open-set experimental settings in terms of numerical results of F1, recall, precision, and accuracy.

show abstract

Human Activity Recognition Machine With an Anchor-Based Loss Function

Cited by 12 publications

References 46 publications

The use of deep learning for smartphone-based human activity recognition

The use of deep learning for smartphone-based human activity recognition

A Novel Segmentation Scheme with Multi-Probability Threshold for Human Activity Recognition Using Wearable Sensors

Sensor-Based Open-Set Human Activity Recognition Using Representation Learning With Mixup Triplets

Contact Info

Product

Resources

About