Activity Recognition and Localization based on UWB Indoor Positioning System and Machine Learning

Cheng, Long; Zhao, Anguo; Wang, Kexin; Li, Hengguang; Wang, Yifan; Chang, Ruofei

doi:10.1109/iemcon51383.2020.9284937

Cited by 15 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the CNN-based multi-channel time-series architecture is taskdependent and is characterised by a higher discrimination accuracy for classifying human activities. Previous research has shown the use of UWB sensors to recognize human activities [26], [27]. Singh et al [28] proposed a framework for HAR using point clouds generated by mmWave radar.…”

Section: Introductionmentioning

confidence: 99%

Ultra-Wideband Radar-Based Activity Recognition Using Deep Learning

Noori¹,

Uddin

Tørresen

2021

IEEE Access

View full text Add to dashboard Cite

With recent advances in the field of sensing, it has become possible to build better assistive technologies. This enables the strengthening of eldercare with regard to daily routines and the provision of personalised care to users. For instance, it is possible to detect a person's behaviour based on wearable or ambient sensors; however, it is difficult for users to wear devices 24/7, as they would have to be recharged regularly because of their energy consumption. Similarly, although cameras have been widely used as ambient sensors, they carry the risk of breaching users' privacy. This paper presents a novel sensing approach based on deep learning for human activity recognition using a non-wearable ultra-wideband (UWB) radar sensor. UWB sensors protect privacy better than RGB cameras because they do not collect visual data. In this study, UWB sensors were mounted on a mobile robot to monitor and observe subjects from a specific distance (namely, 1.5-2.0 m). Initially, data were collected in a lab environment for five different human activities. Subsequently, the data were used to train a model using the state-of-the-art deep learning approach, namely long short-term memory (LSTM). Conventional training approaches were also tested to validate the superiority of LSTM. As a UWB sensor collects many data points in a single frame, enhanced discriminant analysis was used to reduce the dimensions of the features through application of principal component analysis to the raw dataset, followed by linear discriminant analysis. The enhanced discriminant features were fed into the LSTMs. Finally, the trained model was tested using new inputs. The proposed LSTM-based activity recognition approach performed better than conventional approaches, with an accuracy of 99.6%. We applied 5-fold cross-validation to test our approach. We also validated our approach on publically available dataset. The proposed method can be applied in many prominent fields, including human-robot interaction for various practical applications, such as mobile robots for eldercare.

show abstract

Section: Introductionmentioning

confidence: 99%

Ultra-Wideband Radar-Based Activity Recognition Using Deep Learning

Noori¹,

Uddin

Tørresen

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Cheng et al. [36] represented an ML‐based UWB indoor positioning environment to perceive and track down individual activities. Six UWB anchors and four UWB tags were engaged to capture the activity of ten human targets.…”

Section: Related Workmentioning

confidence: 99%

“…Generally, the UWB technology can offer three types of indoor localization frameworks by estimating the length between the target, attached with tag (transmitter) and anchors (receivers) [35]. Such distance assessment is dependent on given signal characteristics, for example, time of arrival (TOA), angle of arrival (AOA), and time difference of arrival (TDOA) [34,36]. TOA needs clock synchronization without delay in all transmitters.…”

Section: Introductionmentioning

confidence: 99%

Smart factory floor safety monitoring using UWB sensor

Islam

Lee

Kim

2022

IET Science Measure & Tech

View full text Add to dashboard Cite

Chemical asphyxiation at petrochemical factories can provoke the unconsciousness or death of factory workers through suffocation. Some chemicals vaporize and mix with air without showing any warning properties that raise the risk of oxygen deficiency. In light of this, Industry 5.0 focuses more on human‐centricity than technology‐driven implementations to ensure secured and work‐friendly environments in industries. Recently, research on factory safety management dependent on the Internet of things (IoT) sensors have been executed unwaveringly. In this work, the ultra‐wideband (UWB) sensor is adopted to recognize the motion and breathing pattern of workers in smart factory scenarios. After capturing the data from the UWB sensor in real‐time, the proposed dataset is further inspected by the deep learning (DL) and traditional machine learning (ML) approaches. Twofold detection schemes are considered where the movement and vital patterns are distinguished first by the stacked ensemble (SE) and the long short‐term memory (LSTM) frameworks. The Bayesian optimized ensemble learning (EL) and bidirectional (Bi‐LSTM) models are further occupied to analyze abnormalities in the breathing rate of a worker in the smart shop floors. The investigated outcome shows that the DL frameworks (LSTM and Bi‐LSTM) outperformed the others by acquiring 99.90% and 99.94% accuracy in 147 s and 293 s, respectively. The devised perception indicates prominent attainment to the smart factory shop floor, Internet of medical things (IoMT), the smart city paradigm, and e‐health appliances.

show abstract

“…where g(•) is the convolution layer, pooling layer, or full connection layer operation, W (l) and x (l) are the weights and the outputs of the l-th layer, respectively. The weights and inputs of hidden layers can be represented asW L = (W (1) , W (2) , • • • , W (L) ) and x L = (x (1) , x (2) , • • • , x (L) ), respectively. Therefore, the input and output relationship of CNN can be written as follows [25]:…”

Section: Convolutional Neural Network For Classification Problemsmentioning

confidence: 99%

“…Outdoor localization technology based on a global navigation satellite system has become viable. However in indoor and underground scenes without satellite signals, accurate localization has become a problem to be solved [1][2][3]. Ultra-wideband (UWB) has the advantages of high localization accuracy, high communication rate , strong multi-path resolution, and low power consumption.…”

Section: Introductionmentioning

confidence: 99%

The LOS/NLOS Classification Method Based on Deep Learning for the UWB Localization System in Coal Mines

Zhao

Wang

2022

Applied Sciences

View full text Add to dashboard Cite

A localization system is one of the basic requirements for coal mines. Ultra-wideband (UWB), as a technology with broad application prospects, is considered to have great potential in the absence of satellite signals, especially in the underground mine environment, as it can provide rescue assistance. However, state-of-the-art UWB position systems in coal mines cannot efficiently differ the line-of-sight from all communication links, which results in deterioration of the localization accuracy. In this paper, we propose a LOS/NLOS classification method based on a deep learning algorithm. Specifically, we utilize the Generative Adversarial Networks (GAN) to generate diagnostic data for frame transmission under non-line-of-sight (NLOS) condition. Then, a Convolutional Neural Network (CNN) is adopted to identify the NLOS communication. Finally, the trilateral centroid positioning algorithm (TCPA) based on ranging data is used to verify the effect of our method for a localization system in coal mines. Field experiments show that our method can accurately differ the LOS/NLOS with the accuracy of 91.19%. The TCPA algorithm with our method can obtain 3.11% improvement compared with the scenario without using our method.

show abstract

Activity Recognition and Localization based on UWB Indoor Positioning System and Machine Learning

Cited by 15 publications

References 20 publications

Ultra-Wideband Radar-Based Activity Recognition Using Deep Learning

Ultra-Wideband Radar-Based Activity Recognition Using Deep Learning

Smart factory floor safety monitoring using UWB sensor

The LOS/NLOS Classification Method Based on Deep Learning for the UWB Localization System in Coal Mines

Contact Info

Product

Resources

About