Recent Advances in Pedestrian Navigation Activity Recognition: A Review

Wang, Qu; Luo, Haiyong; Wang, Jianquan; Sun, Lei; Ma, Zhangchao; Zhang, Chaoyi; Fu, Meixia; Zhao, Fang

doi:10.1109/jsen.2022.3153610

Cited by 30 publications

(13 citation statements)

References 170 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features are mainly classified into time-domain and frequency-domain. The common time-domain features are periodicity, zero crossing rate, short-time energy, loudness, and sharpness [8]. Spectral flatness, frequency component, high-low frequency rate, Melfrequency cepstral coefficient (MFCC) and Log Mel Filter-bank are the most used frequency-domain features.…”

Section: Voice Activity Recognitionmentioning

confidence: 99%

A Smartphone-based Zero-Effort Method for Mitigating Epidemic Propagation

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

A large number of epidemics, including COVID-19 and SARS, spread through droplets, quickly swept the world and claimed the precious lives of large numbers of people. Building a low-cost and real-time epidemic early warning system to identify individuals who have been in contact with infected individuals and determine whether they need to be quarantined is an effective means to mitigate the spread of the epidemic. In this paper, we propose a smartphone-based zero-effort epidemic warning method for mitigating epidemic propagation. Firstly, we recognize epidemic-related voice activity relevant to epidemics spread by hierarchical attention mechanism and temporal convolutional network. The hierarchical attention mechanism is used to find local important information through global scanning, then enhances useful information and suppresses useless information. Subsequently, we estimate the social distance between users through sensors built-in smartphone. Furthermore, we combine Wi-Fi network logs and social distance to comprehensively judge whether there is spatiotemporal contact between users and determine the duration of contact. Finally, we estimate infection risk based on epidemic-related vocal activity, social distance, and contact time. We conduct a large number of well-designed experiments in typical scenarios to fully verify the proposed method. The proposed method does not rely on any additional infrastructure and historical training data, which is conducive to integration with epidemic prevention and control systems and large-scale applications.

show abstract

Section: Voice Activity Recognitionmentioning

confidence: 99%

A Smartphone-based Zero-Effort Method for Mitigating Epidemic Propagation

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These features are mainly classified into time domain and frequency domain. The common time-domain features are periodicity, zero-crossing rate, short-time energy, loudness, and sharpness [ 7 ]. Spectral flatness, frequency component, high/low-frequency rate, Mel-frequency cepstral coefficient (MFCC), and Log Mel Filter-bank are the most used frequency-domain features.…”

Section: Related Workmentioning

confidence: 99%

A smartphone-based zero-effort method for mitigating epidemic propagation

Wang

et al. 2023

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

A large number of epidemics, including COVID-19 and SARS, quickly swept the world and claimed the precious lives of large numbers of people. Due to the concealment and rapid spread of the virus, it is difficult to track down individuals with mild or asymptomatic symptoms with limited human resources. Building a low-cost and real-time epidemic early warning system to identify individuals who have been in contact with infected individuals and determine whether they need to be quarantined is an effective means to mitigate the spread of the epidemic. In this paper, we propose a smartphone-based zero-effort epidemic warning method for mitigating epidemic propagation. Firstly, we recognize epidemic-related voice activity relevant to epidemics spread by hierarchical attention mechanism and temporal convolutional network. Subsequently, we estimate the social distance between users through sensors built-in smartphone. Furthermore, we combine Wi-Fi network logs and social distance to comprehensively judge whether there is spatiotemporal contact between users and determine the duration of contact. Finally, we estimate infection risk based on epidemic-related vocal activity, social distance, and contact time. We conduct a large number of well-designed experiments in typical scenarios to fully verify the proposed method. The proposed method does not rely on any additional infrastructure and historical training data, which is conducive to integration with epidemic prevention and control systems and large-scale applications.

show abstract

“…Some researchers have discussed methods for detecting the orientation and movement direction of a smartphone user using sensors, such as Global Positioning System(GPS) and accelerometers, which are commonly used in indoor and outdoor navigation applications [13].…”

Section: ) Extracting Data From Smartphonementioning

confidence: 99%

Analyzing the Features of Passenger Drop-Off Behavior at Airport Curbsides: A Case Study From Guangxi Province, China

Jianfeng,

Qian,

Qianqian

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Vehicles often face congestion at airport curbsides because private vehicles, taxis, and ridehailing vehicles compete for limited space while dropping off passengers. This competition may lead to blockages and long dwell times, thus worsening the congestion. To solve this issue, management strategies such as first-in-first-out queuing or fines for excessive dwell times have been suggested. However, there is a lack of reliable video data and analysis of drop-off behavior at airport curbsides. In this study, we empirically analyzed the key characteristics of passenger drop-off behavior at the Airport T2 terminal in Guangxi Province, China, which handles approximately 18 million passengers per year. First, we extracted the relevant features of both passengers and vehicles by deep learning algorithm, such as the direction of passenger movement, vehicle type, vehicle location, trunk state, and passenger drop-off time. Subsequently, we constructed new features, such as driver behavior and passenger behavioral complexity, based on the original features. We used least-squares regression and logistic regression to analyze the data. Our analysis reveals that the drop-off time of passengers primarily depends on the complexity of their behavior during the dropoff process. Additionally, we observed that specific features, such as driver behavior and vehicle type, could be employed to estimate passenger drop-off behavior. These findings have practical implications in providing valuable insights into the design and management of airport curbside areas and future strategies for connected vehicles.

show abstract

Recent Advances in Pedestrian Navigation Activity Recognition: A Review

Cited by 30 publications

References 170 publications

A Smartphone-based Zero-Effort Method for Mitigating Epidemic Propagation

A Smartphone-based Zero-Effort Method for Mitigating Epidemic Propagation

A smartphone-based zero-effort method for mitigating epidemic propagation

Analyzing the Features of Passenger Drop-Off Behavior at Airport Curbsides: A Case Study From Guangxi Province, China

Contact Info

Product

Resources

About