Hybrid D1DCnet Using Forehead iPPG for Continuous and Noncontact Blood Pressure Measurement

Li, Yunjie; Wei, Min; Chen, Qiliang; Xing, Zhu; Li, Hui; Wang, Hongbo

doi:10.1109/jsen.2022.3230210

Cited by 15 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, it generated CWT images of blood pressure, and the blood pressure time series was derived by inverting the CWT. Furthermore, when compared to the approach that directly employs iPPG signals as input for a blood pressure model without the necessity of feature extraction, Li et al's study [ 26 ] showcased the efficacy of deep learning methods in estimating blood pressure from iPPG waveforms, along with the inclusion of personal information such as height, weight, gender, and BMI. In contrast, Cheng et al [ 27 ] introduced a multi-stage deep learning model for blood pressure prediction based on iPPG signals.…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, a documented approach involves the direct utilization of iPPG signals as input for a blood pressure model, eliminating the need for feature extraction. Li et al's study [ 26 ] demonstrated the effectiveness of deep learning methods in estimating blood pressure from iPPG waveforms. However, to enhance the model's predictive performance, the inclusion of personal information such as height, weight, gender, and BMI is necessary.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter

Trirongjitmoah,

Promking,

Kaewdang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter

Trirongjitmoah,

Promking,

Kaewdang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Several models with different structures were evaluated for accuracy in terms of SBP and DBP. According to the experimental results in [ 9 , 26 , 27 , 28 ], the comparative results indicate significant variations in performance across models, as reflected by the MAE and STD metrics. For systolic pressure predictions, the CNN-LSTM model demonstrated the lowest MAE (4.25 mmHg) and STD (5.91 mmHg).…”

Section: Discussionmentioning

confidence: 99%

“…Rong and Li [ 8 ] provided a machine learning method that supports vector regression (SVR) to detect BP using iPPG signals. Also, Li et al [ 9 ] introduced an attention-based LSTM machine learning technology that uses iPPG signals. However, some of the published papers mentioned above did not discuss the measurement of distance and time or more complete evaluation metrics, e.g., mean absolute percentage error (MAPE), root mean square error (RSME), promotion of improved accuracy, etc.…”

Section: Introductionmentioning

confidence: 99%

Application of Independent Component Analysis and Nelder–Mead Particle Swarm Optimization Algorithm in Non-Contact Blood Pressure Estimation

Su,

Lin,

Zhuang

et al. 2024

Sensors

View full text Add to dashboard Cite

In recent years, hypertension has become one of the leading causes of illness and death worldwide. Changes in lifestyle among the population have led to an increasing prevalence of hypertension. This study proposes a non-contact blood pressure estimation method that allows patients to conveniently monitor their blood pressure values. By utilizing a webcam to track facial features and the region of interest (ROI) for obtaining forehead images, independent component analysis (ICA) is employed to eliminate artifact signals. Subsequently, physiological parameters are calculated using the principle of optical wave reflection. The Nelder–Mead (NM) simplex method is combined with the particle swarm optimization (PSO) algorithm to optimize the empirical parameters, thus enhancing computational efficiency and accurately determining the optimal solution for blood pressure estimation. The influences of light intensity and camera distance on the experimental results are also discussed. Furthermore, the measurement time is only 10 s. The superior accuracy and efficiency of the proposed methodology are demonstrated by comparing them with those in other published literature.

show abstract

“…Recognizing the challenges associated with the extraction of IPPG signals due to factors such as subject head movements and variations in ambient light, some researchers have adopted dedicated IPPG acquisition devices. Yunjie Li et al [ 9 ], for example, utilized a self-developed IPPG signal acquisition device to extract signals from the forehead region. They collected blood pressure and IPPG data from 403 subjects aged 17 to 21 years.…”

Section: Introductionmentioning

confidence: 99%

Fair non-contact blood pressure estimation using imaging photoplethysmography

Fang,

Xiong,

2024

Biomed. Opt. Express

View full text Add to dashboard Cite

Hypertension is typically manifested as a latent symptom that requires detection through specialized equipment. This poses an inconvenience for individuals who need to undergo long-term blood pressure monitoring in their daily lives. Therefore, there is a need for a portable, non-contact method for estimating blood pressure. However, current non-contact blood pressure estimation methods often rely on relatively narrow datasets, lacking a broad range of blood pressure distributions. Additionally, their applicability is confined to controlled experimental environments. This study proposes a non-contact blood pressure estimation method suitable for various life scenarios, encompassing multiple age groups, diverse ethnicities, and individuals with different skin tones. The aim is to enhance the practicality and accuracy of existing non-contact blood pressure estimation methods. The research extracts the imaging photoplethysmogram (IPPG) signal from facial videos and processes the signal through four layers of filtering operations to obtain an IPPG signal reflecting pulse wave variations. A CNN+BiLSTM+GRU network structure is constructed to improve the accuracy of current non-contact blood pressure estimation methods. In comparison to existing approaches, the mean absolute error (MAE) for systolic blood pressure (SBP) and diastolic blood pressure (DBP) is reduced by 13.6% and 16.4%, respectively.

show abstract

Hybrid D1DCnet Using Forehead iPPG for Continuous and Noncontact Blood Pressure Measurement

Cited by 15 publications

References 42 publications

Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter

Assessing heart rate and blood pressure estimation from image photoplethysmography using a digital blood pressure meter

Application of Independent Component Analysis and Nelder–Mead Particle Swarm Optimization Algorithm in Non-Contact Blood Pressure Estimation

Fair non-contact blood pressure estimation using imaging photoplethysmography

Contact Info

Product

Resources

About