scholarly journals Sensor-Based Human Activity Recognition Using Adaptive Class Hierarchy

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7743
Author(s):  
Kazuma Kondo ◽  
Tatsuhito Hasegawa
Keyword(s):  
Prior Knowledge ◽  
Activity Recognition ◽  
Human Activity ◽  
Recognition Performance ◽  
Human Activity Recognition ◽  
Training Data ◽  
Class Hierarchy ◽  
Recognition Model ◽  
Hierarchical Relationship ◽  
Class Hierarchies

In sensor-based human activity recognition, many methods based on convolutional neural networks (CNNs) have been proposed. In the typical CNN-based activity recognition model, each class is treated independently of others. However, actual activity classes often have hierarchical relationships. It is important to consider an activity recognition model that uses the hierarchical relationship among classes to improve recognition performance. In image recognition, branch CNNs (B-CNNs) have been proposed for classification using class hierarchies. B-CNNs can easily perform classification using hand-crafted class hierarchies, but it is difficult to manually design an appropriate class hierarchy when the number of classes is large or there is little prior knowledge. Therefore, in our study, we propose a class hierarchy-adaptive B-CNN, which adds a method to the B-CNN for automatically constructing class hierarchies. Our method constructs the class hierarchy from training data automatically to effectively train the B-CNN without prior knowledge. We evaluated our method on several benchmark datasets for activity recognition. As a result, our method outperformed standard CNN models without considering the hierarchical relationship among classes. In addition, we confirmed that our method has performance comparable to a B-CNN model with a class hierarchy based on human prior knowledge.

scholarly journals Contrastive Predictive Coding for Human Activity Recognition

2021 ◽  
Vol 5 (2) ◽  
pp. 1-26
Author(s):  
Harish Haresamudram ◽  
Irfan Essa ◽  
Thomas Plötz
Keyword(s):  
Ubiquitous Computing ◽  
Activity Recognition ◽  
Human Activity ◽  
Recognition Performance ◽  
Temporal Structure ◽  
Predictive Coding ◽  
Real Life ◽  
Human Activity Recognition ◽  
Training Data ◽  
Sensor Data

Feature extraction is crucial for human activity recognition (HAR) using body-worn movement sensors. Recently, learned representations have been used successfully, offering promising alternatives to manually engineered features. Our work focuses on effective use of small amounts of labeled data and the opportunistic exploitation of unlabeled data that are straightforward to collect in mobile and ubiquitous computing scenarios. We hypothesize and demonstrate that explicitly considering the temporality of sensor data at representation level plays an important role for effective HAR in challenging scenarios. We introduce the Contrastive Predictive Coding (CPC) framework to human activity recognition, which captures the temporal structure of sensor data streams. Through a range of experimental evaluations on real-life recognition tasks, we demonstrate its effectiveness for improved HAR. CPC-based pre-training is self-supervised, and the resulting learned representations can be integrated into standard activity chains. It leads to significantly improved recognition performance when only small amounts of labeled training data are available, thereby demonstrating the practical value of our approach. Through a series of experiments, we also develop guidelines to help practitioners adapt and modify the framework towards other mobile and ubiquitous computing scenarios.

scholarly journals Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 692
Author(s):  
Jingcheng Chen ◽  
Yining Sun ◽  
Shaoming Sun
Keyword(s):  
Feature Selection ◽  
Activity Recognition ◽  
Human Activity ◽  
Joint Angle ◽  
Recognition Performance ◽  
Wearable Sensors ◽  
Estimation Algorithm ◽  
Recognition System ◽  
Human Activity Recognition ◽  
Time Frequency

Human activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be applied in real-time use with limited resources, the activity recognition system must be compact and reliable. This requirement can be achieved by feature selection (FS). By eliminating irrelevant and redundant features, the system burden is reduced with good classification performance (CP). This manuscript proposes a two-stage genetic algorithm-based feature selection algorithm with a fixed activation number (GFSFAN), which is implemented on the datasets with a variety of time, frequency and time-frequency domain features extracted from the collected raw time series of nine activities of daily living (ADL). Six classifiers are used to evaluate the effects of selected feature subsets from different FS algorithms on HAR performance. The results indicate that GFSFAN can achieve good CP with a small size. A sensor-to-segment coordinate calibration algorithm and lower-limb joint angle estimation algorithm are introduced. Experiments on the effect of the calibration and the introduction of joint angle on HAR shows that both of them can improve the CP.

MMHAR-EnsemNet: A Multi-modal Human Activity Recognition Model

2020 ◽  
pp. 1-1
Author(s):  
Avigyan Das ◽  
Pritam Sil ◽  
Pawan Kumar Singh ◽  
Vikrant Bhateja ◽  
Ram Sarkar
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Recognition Model

scholarly journals Context-Aware Human Activity and Smartphone Position-Mining with Motion Sensors

2019 ◽  
Vol 11 (21) ◽  
pp. 2531 ◽  
Author(s):  
Zhiqiang Gao ◽  
Dawei Liu ◽  
Kaizhu Huang ◽  
Yi Huang
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Learning Strategy ◽  
Recognition Performance ◽  
Body Position ◽  
Human Activity Recognition ◽  
Motion Sensors ◽  
Context Aware ◽  
User Identification ◽  
Additional Information

Today’s smartphones are equipped with embedded sensors, such as accelerometers and gyroscopes, which have enabled a variety of measurements and recognition tasks. In this paper, we jointly investigate two types of recognition problems in a joint manner, e.g., human activity recognition and smartphone on-body position recognition, in order to enable more robust context-aware applications. So far, these two problems have been studied separately without considering the interactions between each other. In this study, by first applying a novel data preprocessing technique, we propose a joint recognition framework based on the multi-task learning strategy, which can reduce computational demand, better exploit complementary information between the two recognition tasks, and lead to higher recognition performance. We also extend the joint recognition framework so that additional information, such as user identification with biometric motion analysis, can be offered. We evaluate our work systematically and comprehensively on two datasets with real-world settings. Our joint recognition model achieves the promising performance of 0.9174 in terms of F 1 -score for user identification on the benchmark RealWorld Human Activity Recognition (HAR) dataset. On the other hand, in comparison with the conventional approach, the proposed joint model is shown to be able to improve human activity recognition and position recognition by 5.1 % and 9.6 % respectively.

scholarly journals Comparing Person-Specific and Independent Models on Subject-Dependent and Independent Human Activity Recognition Performance

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3647
Author(s):  
Sebastian Scheurer ◽  
Salvatore Tedesco ◽  
Brendan O’Flynn ◽  
Kenneth N. Brown
Keyword(s):  
Machine Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Recognition Performance ◽  
Human Activity Recognition ◽  
Machine Learning Algorithms ◽  
Specific Target ◽  
Single Person ◽  
Target User ◽  
The Subject

The distinction between subject-dependent and subject-independent performance is ubiquitous in the human activity recognition (HAR) literature. We assess whether HAR models really do achieve better subject-dependent performance than subject-independent performance, whether a model trained with data from many users achieves better subject-independent performance than one trained with data from a single person, and whether one trained with data from a single specific target user performs better for that user than one trained with data from many. To those ends, we compare four popular machine learning algorithms’ subject-dependent and subject-independent performances across eight datasets using three different personalisation–generalisation approaches, which we term person-independent models (PIMs), person-specific models (PSMs), and ensembles of PSMs (EPSMs). We further consider three different ways to construct such an ensemble: unweighted, κ -weighted, and baseline-feature-weighted. Our analysis shows that PSMs outperform PIMs by 43.5% in terms of their subject-dependent performances, whereas PIMs outperform PSMs by 55.9% and κ -weighted EPSMs—the best-performing EPSM type—by 16.4% in terms of the subject-independent performance.

Can You See It?

2021 ◽  
Vol 25 (2) ◽  
pp. 38-42
Author(s):  
Hyeokhyen Kwon ◽  
Catherine Tong ◽  
Harish Haresamudram ◽  
Yan Gao ◽  
Gregory D. Abowd ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Inertial Sensors ◽  
Human Subjects ◽  
Wearable Devices ◽  
Human Activity Recognition ◽  
Training Data ◽  
Considerable Time ◽  
Administrative Work ◽  
Everyday Activities

Today's smartphones and wearable devices come equipped with an array of inertial sensors, along with IMU-based Human Activity Recognition models to monitor everyday activities. However, such models rely on large amounts of annotated training data, which require considerable time and effort for collection. One has to recruit human subjects, define clear protocols for the subjects to follow, and manually annotate the collected data, along with the administrative work that goes into organizing such a recording.

scholarly journals SVSL: A Human Activity Recognition Method Using Soft-Voting and Self-Learning

Algorithms ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 245
Author(s):  
Aiiad Albeshri
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Prediction Accuracy ◽  
Elderly Care ◽  
Human Activity Recognition ◽  
Training Data ◽  
Smart Surveillance ◽  
Smartphone Sensors ◽  
Self Learning ◽  
User Activities

Many smart city and society applications such as smart health (elderly care, medical applications), smart surveillance, sports, and robotics require the recognition of user activities, an important class of problems known as human activity recognition (HAR). Several issues have hindered progress in HAR research, particularly due to the emergence of fog and edge computing, which brings many new opportunities (a low latency, dynamic and real-time decision making, etc.) but comes with its challenges. This paper focuses on addressing two important research gaps in HAR research: (i) improving the HAR prediction accuracy and (ii) managing the frequent changes in the environment and data related to user activities. To address this, we propose an HAR method based on Soft-Voting and Self-Learning (SVSL). SVSL uses two strategies. First, to enhance accuracy, it combines the capabilities of Deep Learning (DL), Generalized Linear Model (GLM), Random Forest (RF), and AdaBoost classifiers using soft-voting. Second, to classify the most challenging data instances, the SVSL method is equipped with a self-training mechanism that generates training data and retrains itself. We investigate the performance of our proposed SVSL method using two publicly available datasets on six human activities related to lying, sitting, and walking positions. The first dataset consists of 562 features and the second dataset consists of five features. The data are collected using the accelerometer and gyroscope smartphone sensors. The results show that the proposed method provides 6.26%, 1.75%, 1.51%, and 4.40% better prediction accuracy (average over the two datasets) compared to GLM, DL, RF, and AdaBoost, respectively. We also analyze and compare the class-wise performance of the SVSL methods with that of DL, GLM, RF, and AdaBoost.

Sign in / Sign up

Export Citation Format

Share Document