Sensing Technology for Human Activity Recognition: A Comprehensive Survey

Fu, Biying; Damer, Naser; Kirchbuchner, Florian; Kuijper, Arjan

doi:10.1109/access.2020.2991891

Cited by 104 publications

(61 citation statements)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future work, we can investigate a tailored motion representation or apply further sensors to distinguish the intended behavior more precisely [13], [38]. Additionally, a data set of representative HA users can be evaluated to determine the DRR performance of these elderly wearers.…”

Section: Discussionmentioning

confidence: 99%

“…Thereby, the random forest (RF) and multi-layer perceptron (MLP) network showed the best performance in both scenarios on our data set of seven people featuring ACC and additional audio data [3]. In particular, the acoustic features are very rich for detecting sound events or characteristic acoustic scenes like certain environments [10], activities of daily living [11], conversations [12], or transportation modalities [13]. This effectively complements the analysis of ACC patterns to differentiate, for example, seated activities like office work vs. having a conversation [14].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

2021

View full text Add to dashboard Cite

This work focuses on sequence learning to improve the daily routine recognition in hearing aids (HA), where the goal is to personalize the device configuration for each user. We apply the sequence methods on two large real-world data sets. One publicly available set contains the acceleration (ACC) data of one person, Huynh, over seven working days, whereas our set includes the real life of seven subjects over 104 days with ACC and audio data of a HA. For both sets, we design statistical features to represent the recurring routine behavior well. In our comprehensive simulations, we analyze several sequence classifiers learning the temporal relationships of high-level activities. The multi-layer perceptron (MLP) and random forest (RF) as an observation model for the hidden Markov model (HMM) show the best F-measure performance of 85.3% and 91.6% on our set and the Huynh set, respectively. In particular, the MLP-HMM combination strongly improves on both sets compared to the non-sequence classifier MLP by 6.7% and 10.2%. Within the segment error analysis, we show that the sequence classifiers improve the temporal prediction stability by a reduction of insertion errors. Thus, the improved sequence classification helps the user to better address his condition due to preferred HA settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

2021

View full text Add to dashboard Cite

show abstract

“…In this study, the frequency time of various body parts was used while performing certain tasks in order to recognize 9 different movements such as pushing, pulling, dragging, kicking with an accuracy over 90%. Wi-Fi-based activity recognition aims to use the existing wireless transceiver infrastructure in the environment to measure the Wi-Fi signal changes caused by the activity [18]. Using time series data from passive RFID tags to recognize different movements in real time, a device-free technique is proposed in the study; RSSI and Phase values of deep learning based RFID tags are used [61].…”

Section: Gesture Detectionmentioning

confidence: 99%

Novel tent pooling based human activity recognition approach

Tuncer

Ertam

2020

Multimed Tools Appl

View full text Add to dashboard Cite

Nowadays, mobile devices have been widely used worldwide and they have variable sensors. By using these sensors, many applications for instance navigation, healthcare, and human activity recognition (HAR) have been developed. The primary objective of this paper is to present a multi lightweight HAR method with high prediction performance. To implement this objective, novel pooling methodology is presented and it is called as tent pooling since pooling is processed using the variable size of blocks. 2 × 2, 3 × 3, 4 × 4, 5 × 5, 6 × 6, 7 × 7 and 8 × 8 sized non-overlapping blocks are used for pooling and maximum, minimum and average pooling methods. These pooling methods have been utilized as a feature generation model. The generated features are forwarded to the ReliefF feature selection method. ReliefF is a weight-based feature selector and uses Manhattan distance based fitness function. By using relief, the weights of the features are calculated and the negative weighted features are eliminated. This operation is named positive weighted feature selection. The selected positive weighted features are classified using a cubic support vector machine (SVM). To test the proposed method, a publicly and freely published HAR dataset is used. There are 6 activities in the used dataset. Also, the results of the proposed method were compared to other state of art methods. The best accuracy rate of the proposed tent pooling based HAR method was calculated as 99.81% using the average pooling. This results clearly prove that the success of the proposed tent pooling based method. The proposed method is also simple and effective. It has the highest success rates among the selected state-art-of HAR methods.

show abstract

“…Tracking 3D human motion has made significant progress recently due to advanced object tracking sensor availability, and has become a useful technique in various applications, such as human–computer interaction (HCI), activity recognition, virtual reality, fitness training, healthcare, and rehabilitation [ 4 ]. Significant milestones have been achieved for tracking human pose using depth, inertial, vision, light detection and ranging (lidar) sensor systems, and more recently, heterogeneous multi-sensor systems [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

An Open-Source Platform for Human Pose Estimation and Tracking Using a Heterogeneous Multi-Sensor System

Patil

Balasubramanyam

Ryu

et al. 2021

Sensors

View full text Add to dashboard Cite

Human pose estimation and tracking in real-time from multi-sensor systems is essential for many applications. Combining multiple heterogeneous sensors increases opportunities to improve human motion tracking. Using only a single sensor type, e.g., inertial sensors, human pose estimation accuracy is affected by sensor drift over longer periods. This paper proposes a human motion tracking system using lidar and inertial sensors to estimate 3D human pose in real-time. Human motion tracking includes human detection and estimation of height, skeletal parameters, position, and orientation by fusing lidar and inertial sensor data. Finally, the estimated data are reconstructed on a virtual 3D avatar. The proposed human pose tracking system was developed using open-source platform APIs. Experimental results verified the proposed human position tracking accuracy in real-time and were in good agreement with current multi-sensor systems.

show abstract

Sensing Technology for Human Activity Recognition: A Comprehensive Survey

Cited by 104 publications

References 154 publications

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

Improving Daily Routine Recognition in Hearing Aids Using Sequence Learning

Novel tent pooling based human activity recognition approach

An Open-Source Platform for Human Pose Estimation and Tracking Using a Heterogeneous Multi-Sensor System

Contact Info

Product

Resources

About