Using RF Transmissions From IoT Devices for Occupancy Detection and Activity Recognition

Li, Wenda; Vishwakarma, Shelly; Chun, Tang; Woodbridge, K.; Piechocki, Robert J.; Chetty, Kevin

doi:10.1109/jsen.2021.3134895

Cited by 11 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to active radar systems, passive radar receivers have been used for occupancy detection and activity recognition by harvesting RF signals in the environment. Examples include a Passive Wi-Fi Radar (PWR) technique for occupancy detection and people counting in 21,22 and a Passive IoT Radar (PIoTR) system that uses RF transmissions from IoT devices for human monitoring in 23 .…”

Section: Literature Reviewmentioning

confidence: 99%

“…While the progress in works cited above is notable, these works have some limitations, such as short experimental duration (up to 60 s for [16][17][18][19][20] ), the inferior sensitivity of passive radar systems for detecting stationary persons 21,22,23 , and detection of stationary persons only at 2-3 m from the sensor 16,17 . The True Presence Occupancy Detection Sensor (TruePODS™) presented in this paper is a Doppler radar-sensor that detects physiological motion to indicate whether a space is occupied or vacant 24 .…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Unobtrusive occupancy and vital signs sensing for human building interactive systems

Song

Droitcour

Islam

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Cognitive buildings use data on how occupants respond to the built environment to proactively make occupant-centric adjustments to lighting, temperature, ventilation, and other environmental parameters. However, sensors that unobtrusively and ubiquitously measure occupant responses are lacking. Here we show that Doppler-radar based sensors, which can sense small physiological motions, provide accurate occupancy detection and estimation of vital signs in challenging, realistic circumstances. Occupancy was differentiated from an empty room over 93% of the time in a 3.4 m × 8.5 m conference room with a single sensor in both wall and ceiling-mounted configurations. Occupancy was successfully detected while an occupant was under the table, visibly blocked from the sensor, a scenario where infrared, ultrasound, and video-based occupancy sensors would fail. Heart and respiratory rates were detected in all seats in the conference room with a single ceiling-mounted sensor. The occupancy sensor can be used to control HVAC and lighting with a short, 1–2 min delay and to provide information for space utilization optimization. Heart and respiratory rate sensing could provide additional feedback to future human-building interactive systems that use vital signs to determine how occupant comfort and wellness is changing with time.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Unobtrusive occupancy and vital signs sensing for human building interactive systems

Song

Droitcour

Islam

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The change in signal quality is harmful to communication, but it may enhance the RF signal characteristic curve and introduce information bursts for activity recognition as a positive side effect. Therefore, the time-varying RF signal is affected by physical movement and thus can be used for monitoring purposes [7]. RF-based HAR uses RF signals to detect human activities, making it a non-invasive approach that does not require any physical contact with the human body.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning

Nie,

Zou,

Cui

et al. 2024

Electronics

View full text Add to dashboard Cite

This paper introduces a novel approach for enhancing human activity recognition through the integration of LoRa wireless RF signal preprocessing and deep learning. We tackle the challenge of extracting features from intricate LoRa signals by scrutinizing the unique propagation process of linearly modulated LoRa signals—a critical aspect for effective feature extraction. Our preprocessing technique involves converting intricate data into real numbers, utilizing Short-Time Fourier Transform (STFT) to generate spectrograms, and incorporating differential signal processing (DSP) techniques to augment activity recognition accuracy. Additionally, we employ frequency-to-image conversion for the purpose of intuitive interpretation. In comprehensive experiments covering activity classification, identity recognition, room identification, and presence detection, our carefully selected deep learning models exhibit outstanding accuracy. Notably, ConvNext attains 96.7% accuracy in activity classification, 97.9% in identity recognition, and 97.3% in room identification. The Vision TF model excels with 98.5% accuracy in presence detection. Through leveraging LoRa signal characteristics and sophisticated preprocessing techniques, our transformative approach significantly enhances feature extraction, ensuring heightened accuracy and reliability in human activity recognition.

show abstract

“…Multiform of such algorithms have been assessed for this purpose. Li et al [25] have developed a framework for occupancy sensing on IoT devices using radio-frequency based transmission for human monitoring. The model estimates the motion generated by human activity while it yields to doppler spectrogram for better sensing.…”

Section: Introductionmentioning

confidence: 99%

Novel Framework for Multi-Scale Occupancy Sensing for distributed monitoring in Internet-of-Things

Mane,

Rao

2023

Preprint

View full text Add to dashboard Cite

Occupancy sensing is one of the integral parts of modern evolving security surveillance and monitoring system used over different types of infrastructure. With an aid of multiple form of occupancy sensors, the prime idea of occupancy sensing is to identify the presence or absence of occupants in specifically monitored area followed by transmitting back the sensing information either for storage or for prompting a set of commands from the connected control units. Review of existing schemes exhibits the presence of adoption of multiple methodologies over different variants of use-cases; however, they are quite case specific, uses expensive deployment process, and performs highly sophisticated operation. At present, there are no studies specifically reported of using multi-scale occupancy sensing suitable for large and distributed environment of Internet-of-Things (IoT). Therefore, the proposed study introduces a mechanism of novel multi-scale occupancy sensing considering a use case of smart university campus, although, it can be implemented over any form of different infrastructures too connected over IoT environment. The proposed scheme is implemented considering different types of cost-effective sensors, handheld devices and access points in order to identify the state of occupancy in large number of rooms present in the campus. The sensed data from distributed connected campus are aggregated over cloud server where they are subjected to suitable preprocessing to increase the data quality suitable for reliable prediction. Multiple set of potential learning-based schemes are integrated with proposed model to explore best fit model. This assessment scenario is not found reported in existing scheme to perform classification of states of occupancy. The study outcome shows Convolution Neural Network and Long Short-Term Memory to accomplish higher accuracy compared to other learning approach.

show abstract

Using RF Transmissions From IoT Devices for Occupancy Detection and Activity Recognition

Cited by 11 publications

References 35 publications

Unobtrusive occupancy and vital signs sensing for human building interactive systems

Unobtrusive occupancy and vital signs sensing for human building interactive systems

Enhancing Human Activity Recognition with LoRa Wireless RF Signal Preprocessing and Deep Learning

Novel Framework for Multi-Scale Occupancy Sensing for distributed monitoring in Internet-of-Things

Contact Info

Product

Resources

About