Through the wall human heart beat detection using single channel CW radar

Frontiers in Physiology, Journal Year: 2024, Volume and Issue: 15

Published: Jan. 24, 2024

Single-channel continuous wave (CW) radar is widely used and has gained popularity due to its simple architecture despite inability measure the range angular location of target. Its arises in industry simplicity required components, low demands on sampling rate, their costs. Through-the-wall life signs detection using microwave Doppler Radar an active area research investigation. Most work literature focused utilizing multi-channel frequency modulated (FMCW), CW, ultra-wideband (UWB) for capability direction arrival (DOA) estimation. In this paper, through-the-wall single-subject two-subject concurrent heart rate single-channel 24-GHz CW leveraged with maximal overlap discrete wavelet transform (MODWT) proposed. Experimental results demonstrated that repetitive measurement seven different subjects at a distance 20 cm up 100 through two barriers (wood brick wall) showed average accuracy extraction 95.27% varied distances (20–100 cm) comparison Biopac ECG acquisition signal. Additionally, MODWT method can also isolate independent heartbeat waveforms from subjects’ measurements wall. This involved four trials eight subjects, achieving 97.04% fixed 40 without estimating subjects. Notably, it superseded performance direct FFT single subject after measurements. The proposed simpler several potential applications, including post-disaster search rescue scenarios finding trapped, injured people under debris, emergency evacuation, security, surveillance, patient vital monitoring.

Language: Английский

---

Unsupervised domain adaptation with and without access to source data for estimating occupancy and recognizing activities in smart buildings

Building and Environment, Journal Year: 2023, Volume and Issue: 243, P. 110651 - 110651

Published: July 22, 2023

Language: Английский

---

Multimodal feature fusion and ensemble learning for non-intrusive occupancy monitoring using smart meters

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112635 - 112635

Published: Jan. 1, 2025

Language: Английский

---

Building occupancy estimation using single channel CW radar and deep learning

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 1, 2025

Counting the number of people in a room is crucial for optimizing smart buildings, enhancing energy efficiency, and ensuring security while preserving privacy. This study introduces novel radar-based occupancy estimation method leveraging 24-GHz Continuous Wave (CW) radar system integrated with time-frequency mapping techniques using Wavelet Transform (CWT) power spectrum analysis. Unlike previous studies that rely on WiFi or PIR-based sensors, this approach provides robust alternative without privacy concerns. The scalograms generated from echoes were used to train deep-learning models, including DarkNet19, MobileNetV2, ResNet18. Experiments conducted sedentary occupants over 4 hours 40 minutes resulted 1680 image samples. proposed achieved high accuracy, DarkNet19 performing best, reaching 92.7% CWT images 92.3% images. Additionally, experiments walking environment another continuous 1 hour data 86.5% demonstrating method's effectiveness beyond static scenarios. These results confirm CW deep learning can enable non-intrusive, privacy-preserving building applications.

Language: Английский

---

High-accuracy occupancy counting at crowded entrances for smart buildings

Energy and Buildings, Journal Year: 2024, Volume and Issue: 319, P. 114509 - 114509

Published: Sept. 1, 2024

Language: Английский

---

Non-Contact Soil Moisture Estimation Using Continuous Wave Radar and Deep Learning

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(17), P. 28419 - 28426

Published: July 24, 2024

Language: Английский

---

Characterization Technique for a Doppler Radar Occupancy Sensor

Electronics, Journal Year: 2023, Volume and Issue: 12(24), P. 4888 - 4888

Published: Dec. 5, 2023

Occupancy sensors are electronic devices used to detect the presence of people in monitored areas, and output these can be optimize lighting control, heating ventilation real-estate utilization. Testing methods already exist for certain types occupancy (e.g., passive infrared) evaluate their relative performance, allowing manufacturers report coverage patterns different motion. However, existing published techniques mostly tailored passive-infrared therefore limited evaluation large motions, such as walking hand movement. Here we define a characterization technique Doppler radar sensor based on detecting small motion representing human breathing, using well-defined readily reproducible target. The presented specifically provides robust testing method single-channel continuous wave Doppler-radar sensor, which has variation sensitivity within each wavelength range. By comparison with test data taken from subject, demonstrate that mobile target alternative better accounts impact placement. This enables generation breathing radar-based sensors.

Language: Английский

---

Classifying Occupancy Levels in Smart Building by Experimental Evaluation of KNN and its Variants

2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 6

Published: May 20, 2024

Language: Английский

---

Multi-Source Domain Adaptation Using Ambient Sensor Data

Applied Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(1)

Published: Nov. 19, 2024

Smart buildings have gained increasing interest recently by providing several advanced solutions, especially AI-based solutions. Activity recognition and occupancy estimation are among the outcomes of smart that can help provide advantages such as energy management security Previously, domain adaptation (DA) has been widely considered researchers to transfer knowledge from source domains, where we abundant labeled data, a target data is scarce. It tedious time-consuming task label with building applications which why unsupervised DA do in unlabeled domain. Semi-supervised (SSDA) also small amount Most (UDA) SSDA methods one target. However, it possible exploit multiple domains instead single enhance performance Multi-source (MSDA) more difficult than single-source but efficient. In this research, adapt MDSA evaluate them using sensorial datasets.

Language: Английский

---

A Cost-Effective System for Indoor Three-Dimensional Occupant Positioning and Trajectory Reconstruction

Buildings, Journal Year: 2023, Volume and Issue: 13(11), P. 2832 - 2832

Published: Nov. 11, 2023

Accurate indoor occupancy information extraction plays a crucial role in building energy conservation. Vision-based methods are popularly used for because of their high accuracy. However, previous vision-based either only provide 2D or require expensive equipment. In this paper, we propose cost-effective system that estimates occupant positions and trajectories 3D using single RGB camera. The proposed provides an inverse proportional model to estimate the distance between human head camera according pixel-heights heads, eliminating dependence on depth sensors. position coordinates heads calculated based above model. also associates with tracking results by assigning corresponding IDs from module, obtaining trajectory each person. Experimental demonstrate successfully calculates accurate occupants one surveillance conclusion, is low-cost high-accuracy has potential reducing consumption.

Language: Английский

---