Novel Fingertip Image-Based Heart Rate Detection Methods for a Smartphone

Abstract

Abstract:We hypothesize that our fingertip image-based heart rate detection methods using smartphone reliably detect the heart rhythm and rate of subjects. We propose fingertip curve line movement-based and fingertip image intensity-based detection methods, which both use the movement of successive fingertip images obtained from smartphone cameras. To investigate the performance of the proposed methods, heart rhythm and rate of the proposed methods are compared to those of the conventional method, which is based on average image pixel intensity. Using a smartphone, we collected 120 s pulsatile time series data from each recruited subject. The results show that the proposed fingertip curve line movement-based method detects heart rate with a maximum deviation of 0.0832 Hz and 0.124 Hz using time-and frequency-domain based estimation, respectively, compared to the conventional method. Moreover, another proposed fingertip image intensity-based method detects heart rate with a maximum deviation of 0.125 Hz and 0.03 Hz using time-and frequency-based estimation, respectively.

Validation of Smartphone Free Heart Rate Monitoring Application During Treadmill Exercise

“…14 Mitchell et al believed that smartphone app is a reliable and valid tool to assess pulse rate in healthy individuals. 17 Heart rate measurement using finger-tip showed comparable results and accurate concerning ECG 18,19 and contacted PPG based apps have higher feasibility and better accuracy. 13 In a previous study done by Spierer et al, they suggested that data recorded by heart rate monitor are valid if the correlation coefficients are ≥0.90 and SEEs ≤5 beats per minute (bpm).…”

“…Our findings showed that the heart rates measured using the free smartphone app at rest, during low to moderate exercise and recovery were accurate with r ≥0.95 and SEEs <1 bpm, though, Zaman et al reported that the smartphone app has r= 0.83 in their study. 19 The correlation values (r) in this study for the smartphone HR measured were highly correlated during resting stage (0-2 minute), stage 1 walk at 2.0 mph (3-5 minutes), stage 2 brisk walk at 3.5 mph (6-8 minutes), stage 3 slow jogging at 4.5 mph (9-11 minutes) and recovery stage (15-17 minutes) with (r) ≥0.95. However, the correlation values (r) for stage 4 which was running at 6 mph (12-14 minute) were inconsistent, suggesting that the HR monitoring using smartphone app at this stage was not accurately measured.…”

A sensor-centric survey on the development of smartphone measurement and sensing systems

“…[81], Poladia et al [82] and Kumar et al [83]. Other computer vision applications for smartphone include a system for continous surveillance of fruit flies [84], a food recognition tool assisted by image retrieval [85] and nutritional value estimation [86], a heart rate measurement system exploiting the time variation of acquired images of the user fingertip placed on the phone camera [87].…”

“…Despite the increasing interest in smartphone based sensing systems, there are also some gaps that from [190]. colorimetric alcohol concentration in saliva 0 -0.3% [38] colorimetric pH, protein and glucose in urine 5 -9, 0 -100 mg/dL, 0 -300 mg/dL [39] colorimetric blood hematocrit level 10 -65% [41] colorimetric streptomycin concentration in food 50 -267 nM [42] colorimetric BSA, catalase enzyme and carbohydrate 0 -1 mg/mL, 0 -1 mg/mL, 0 -140 µg/mL [43] colorimetric cloud coverage 4 -98% [48] colorimetric surface corrosion of iron N/A [50] irradiance measurement UVA solar irradiance 0 -10 mW/m 2 [60] irradiance measurement UVA aerosol optical depth 0.05 -0.20 [61] irradiance measurement UVB solar irradiance 1 -9 mW/m 2 [63] irradiance measurement atmospheric total ozone column 260 -320 DU [65] irradiance measurement SO 2 volcanic emission 0 -3. computer vision bacterial colony counter N/A [80] computer vision bacterial colony counter 0 -250 CFU [81] computer vision bacterial colony counter N/A [82] computer vision bacterial colony counter 0 -500 CFU [83] computer vision surveillance of fruit flies N/A [84] computer vision food recognition tool N/A [85] computer vision food recognition and nutritional value N/A [86] computer vision heart rate measurement N/A [87] mobile microscopy cell imaging (brightfield and fluorescent) N/A [88] mobile microscopy image analysis of green algae in freshwater N/A [89] sound recording and analysis chronic lung diseases average error 5.1%, detection rate 80 -90% [90] sound recording and analysis chronic lung diseases average error 8.01% [91] sound recording and analysis number of coughs detection rate 92% [92] sound recording and analysis respiratory rate estimation error < 1% [93] sound recording and analysis nasal symptoms N/A [94] sound recording and analysis snoring quantification correlation > 0.9 [95] sound recording and analysis hearing threshold in noisy environment N/A …”

A novel diversity method for smartphone camera-based heart rhythm signals in the presence of motion and noise artifacts

“…Previous studies showed that the smartphone PPG signal could be used for AF determination and discriminating AF from premature atrial contractions (PACs), premature ventricular contractions (PVCs) and normal heart rhythm [1, 5, 6, 11]. Moreover, the advent of highly sensitive image sensors in smartphone video cameras has enabled acquisition of fingertip movement caused by heart pumping [12].…”