DeepSense: Device-Free Human Activity Recognition via Autoencoder Long-Term Recurrent Convolutional Network

Zou, Han; Zhou, Yuxun; Yang, Jianfei; Jiang, Hao; Xie, Lihua; Spanos, Costas J.

doi:10.1109/icc.2018.8422895

Cited by 78 publications

(67 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There were semi-unsupervised approaches [ 36 , 37 , 38 ] for activity recognition. Stacked autoencoders were trained in an unsupervised way to reduce noises and extract features from sensor data, but a supervised classification scheme was involved for activity recognition [ 36 ].…”

Section: Related Workmentioning

confidence: 99%

“…The training process of a convolutional autoencoder consists of two steps of which the first stage is unsupervised while the second is supervised [ 37 ]. The unsupervised training of an autoencoder was carried out for an auxiliary purpose such as noise sanitization in raw CSI data and high-level representative feature extraction [ 38 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised End-to-End Deep Model for Newborn and Infant Activity Recognition

Jun

Choi

2020

Sensors

View full text Add to dashboard Cite

Human activity recognition (HAR) works have mostly focused on the activities of adults. However, HAR is typically beneficial to the safety and wellness of newborn or infants because they have difficulties in verbal communication. The activities of infants are different from those of adults in terms of its types and intensity. Hence, it is necessary to study the behavior of infants separately. We study newborn and infant activity recognition by analyzing accelerometer data from the sensors attached to body. We aim to classify four types of activities: sleeping, moving in agony, moving in normal condition, and movement by external force. For this work, we collected 11 h videos and corresponding sensor data from 10 infant subjects. For recognition, we propose an end-to-end deep model using autoencoder and k-means clustering, which is trained in an unsupervised way. From a set of performance tests, our model can achieve 0.96 in balanced accuracy and F-1 score of 0.95.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Unsupervised End-to-End Deep Model for Newborn and Infant Activity Recognition

Jun

Choi

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…By constructing a histogram of width k to traverse the input data, the variance information gain is estimated according to Equation (16) to find the optimal segmentation point. [31]…”

Section: Theft Detection Based On Lightgbm Classificationmentioning

confidence: 99%

Noise Reduction Power Stealing Detection Model Based on Self-Balanced Data Set

Liu

2020

Energies

View full text Add to dashboard Cite

In recent years, various types of power theft incidents have occurred frequently, and the training of the power-stealing detection model is susceptible to the influence of the imbalanced data set and the data noise, which leads to errors in power-stealing detection. Therefore, a power-stealing detection model is proposed, which is based on Improved Conditional Generation Adversarial Network (CWGAN), Stacked Convolution Noise Reduction Autoencoder (SCDAE) and Lightweight Gradient Boosting Decision Machine (LightGBM). The model performs Generation- Adversarial operations on the original unbalanced power consumption data to achieve the balance of electricity data, and avoids the interference of the imbalanced data set on classifier training. In addition, the convolution method is used to stack the noise reduction auto-encoder to achieve dimension reduction of power consumption data, extract data features and reduce the impact of random noise. Finally, LightGBM is used for power theft detection. The experiments show that CWGAN can effectively balance the distribution of power consumption data. Comparing the detection indicators of the power-stealing model with various advanced power-stealing models on the same data set, it is finally proved that the proposed model is superior to other models in the detection of power stealing.

show abstract

“…In [134], DeepSense , a CSI and deep learning based HAR method is presented. The autoencoder long-term recurrent convolutional network is used to classify the proposed activities (walk, stand, lie, run, and empty) and achieved a high accuracy rate of 97.4%.…”

Section: Channel State Information (Csi)mentioning

confidence: 99%

Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey

Al-qaness

Elaziz

Kim

et al. 2019

Sensors

View full text Add to dashboard Cite

Human motion detection and activity recognition are becoming vital for the applications in smart homes. Traditional Human Activity Recognition (HAR) mechanisms use special devices to track human motions, such as cameras (vision-based) and various types of sensors (sensor-based). These mechanisms are applied in different applications, such as home security, Human–Computer Interaction (HCI), gaming, and healthcare. However, traditional HAR methods require heavy installation, and can only work under strict conditions. Recently, wireless signals have been utilized to track human motion and HAR in indoor environments. The motion of an object in the test environment causes fluctuations and changes in the Wi-Fi signal reflections at the receiver, which result in variations in received signals. These fluctuations can be used to track object (i.e., a human) motion in indoor environments. This phenomenon can be improved and leveraged in the future to improve the internet of things (IoT) and smart home devices. The main Wi-Fi sensing methods can be broadly categorized as Received Signal Strength Indicator (RSSI), Wi-Fi radar (by using Software Defined Radio (SDR)) and Channel State Information (CSI). CSI and RSSI can be considered as device-free mechanisms because they do not require cumbersome installation, whereas the Wi-Fi radar mechanism requires special devices (i.e., Universal Software Radio Peripheral (USRP)). Recent studies demonstrate that CSI outperforms RSSI in sensing accuracy due to its stability and rich information. This paper presents a comprehensive survey of recent advances in the CSI-based sensing mechanism and illustrates the drawbacks, discusses challenges, and presents some suggestions for the future of device-free sensing technology.

show abstract

DeepSense: Device-Free Human Activity Recognition via Autoencoder Long-Term Recurrent Convolutional Network

Cited by 78 publications

References 18 publications

Unsupervised End-to-End Deep Model for Newborn and Infant Activity Recognition

Unsupervised End-to-End Deep Model for Newborn and Infant Activity Recognition

Noise Reduction Power Stealing Detection Model Based on Self-Balanced Data Set

Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey

Contact Info

Product

Resources

About