The classifier of support vector machine (SVM) learning for assessing the quality of arteriovenous fistulae (AVFs) in hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor device is presented in this work. In clinical practice, there are two important indices for assessing the quality of AVF: the blood flow volume (BFV) and the degree of stenosis (DOS). In hospitals, the BFV and DOS of AVFs are nowadays assessed using an ultrasound Doppler machine, which is bulky, expensive, hard to use, and time consuming. In this study, a newly-developed PPG sensor device was utilized to provide patients and doctors with an inexpensive and small-sized solution for ubiquitous AVF assessment. The readout in this sensor was custom-designed to increase the signal-to-noise ratio (SNR) and reduce the environment interference via maximizing successfully the full dynamic range of measured PPG entering an analog–digital converter (ADC) and effective filtering techniques. With quality PPG measurements obtained, machine learning classifiers including SVM were adopted to assess AVF quality, where the input features are determined based on optical Beer–Lambert’s law and hemodynamic model, to ensure all the necessary features are considered. Finally, the clinical experiment results showed that the proposed PPG sensor device successfully achieved an accuracy of 87.84% based on SVM analysis in assessing DOS at AVF, while an accuracy of 88.61% was achieved for assessing BFV at AVF.

Blood pressure (BP) is predicted by this effort based on photoplethysmography (PPG) data to provide effective pre-warning of possible preeclampsia of pregnant women. Towards frequent BP measurement, a PPG sensor device is utilized in this study as a solution to offer continuous, cuffless blood pressure monitoring frequently for pregnant women. PPG data were collected using a flexible sensor patch from the wrist arteries of 194 subjects, which included 154 normal individuals and 40 pregnant women. Deep-learning models in 3 stages were built and trained to predict BP. The first stage involves developing a baseline deep-learning BP model using a dataset from common subjects. In the 2 ^nd stage, this model was fine-tuned with data from pregnant women, using a 1-Dimensional Convolutional Neural Network (1D-CNN) with Convolutional Block Attention Module (CBAMs), followed by bi-directional Gated Recurrent Units (GRUs) layers and attention layers. The fine-tuned model results in a mean error (ME) of -1.40 ± 7.15 (standard deviation, SD) for systolic blood pressure (SBP) and -0.44 (ME) ± 5.06 (SD) for diastolic blood pressure (DBP). At the final stage is the personalization for individual pregnant women using transfer learning again, enhancing further the model accuracy to -0.17 (ME) ± 1.45 (SD) for SBP and 0.27 (ME) ± 0.64 (SD) for DBP showing a promising solution for continuous, non-invasive BP monitoring in precision by the proposed 3-stage of modeling, fine-tuning and personalization.

A portable, wireless photoplethysomography (PPG) sensor for assessing arteriovenous fistula (AVF) by using class-weighted support vector machines (SVM) was presented in this study. Nowadays, in hospital, AVF are assessed by ultrasound Doppler machines, which are bulky, expensive, complicated-to-operate, and time-consuming. In this study, new PPG sensors were proposed and developed successfully to provide portable and inexpensive solutions for AVF assessments. To develop the sensor, at first, by combining the dimensionless number analysis and the optical Beer Lambert’s law, five input features were derived for the SVM classifier. In the next step, to increase the signal-noise ratio (SNR) of PPG signals, the front-end readout circuitries were designed to fully use the dynamic range of analog-digital converter (ADC) by controlling the circuitries gain and the light intensity of light emitted diode (LED). Digital signal processing algorithms were proposed next to check and fix signal anomalies. Finally, the class-weighted SVM classifiers employed five different kernel functions to assess AVF quality. The assessment results were provided to doctors for diagonosis and detemining ensuing proper treatments. The experimental results showed that the proposed PPG sensors successfully achieved an accuracy of 89.11% in assessing health of AVF and with a type II error of only 9.59%.

A new cuff-less blood pressure (BP) sensor is designed and optimized in this paper. This BP sensor is in a shape of a circular disc of polymer enclosing an electrode. As the sensor is attached to the wrist artery, the dynamic bending of the sensor due to small artery pulsation induces variation in the electrode strain, and then, its resistance varies. With adequate amplification to sense resistance variation, the pulsation signals can be successfully obtained. With the measured pulsation representing well the blood volume pulsation (BVP), BP can be estimated next via the pulse wave velocity (PWV) theory. Effort is dedicated by this paper to optimize the sizes and geometry of the proposed sensor to maximize the electrode curvature change for largest measured signal-to-noise ratio (SNR) possible, which maximizes the accuracy of BP estimation. To this end, the optimization via the finite element modeling and the Taguchi method is carried out. In results, the optimal sizes in height/radius, fillet, hardness, and the electrode position of the polymer disc are successfully derived, which are in the height of 2 mm, the radius of 6mm, the distance between the planar electrode and the bottom surface of sensor being 1 mm, the hardness of the encapsulating polymer being 25 in shore A hardness, and the fillets at the bottom of the polymer disc being 1 mm in radii. BP is measured for 59 subjects. The resulted errors are 3.60 ± 5.40 mmHg (mean difference ± standard deviation) and 1.15 ± 1.63 mmHg for SBP and DBP, respectively. The correlations are 0.8787 and 0.9648, demonstrating well the favorable performance of the developed sensor.

The classifier of support vector machine (SVM) learning for assessing quality of arteriovenous fistula (AVF) at hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor are presented in this work. Based on current medical standard, there are two important indices for assessing AVF quality, the blood flow volume (BFV) and the degree of stenosis (DOS). In current clinical practice, BFV and DOS of AVFs are assessed by using an ultrasound Doppler machine, which is bulky, expensive, hard-to-use and time-consuming. Therefore, a new PPG sensor module is designed to provide patients and doctors an inexpensive and small-sized solution to assess AVF quality. The readout of the sensor is successfully optimized to increase the signal to noise ratio (SNR) and reduce the environment interference, the readout circuitries are designed to fit the full dynamic range of analog-digital converter (ADC) and to filter out the noise. To assess quality of AVF, three different machine learning classifiers are developed, where the input features are selected based on optical Beer Lambert’s law and hemodynamic model. Finally, the clinical experiment results show that the proposed PPG sensor successfully achieves an accuracy of 87.838% in assessing AVF quality based on satisfactory DOS and BFV measured.

Magnetic gel abrasive finishing is a high-precision polishing method that uses magnetic forces to attract and restrain a gel abrasive, composed of aqueous slime gel, steel grits, and silicon carbon (SiC), for polishing workpieces. However, the magnetic adsorption performance of the gel abrasive will drop quickly when polishing non-ferromagnetic material such as stainless-steel or brass. Moreover, centrifugal force will push out the gel abrasive from the machining surface reducing the stability of polishing. Therefore, this paper developed a rotating cylinder-based magnetic finishing setup to allow the gel abrasive and workpieces to tumble and rotate together during the polishing process. To make the gel abrasive produce irregular and complicated movement paths for improving the polishing performance, this study first analyzed and compared the average surface roughness and removed material weight of workpieces using three kinds of motor operating modes; a unidirectional trapezoidal wave mode, a bidirectional sine wave mode, and a bidirectional trapezoidal wave mode. After identifying the best motor operating mode, the study further compared the polishing characteristics using several SiC particle and steel grit sizes. The experimental results showed that the rotating cylinder driven using a bidirectional trapezoidal wave could obtain better results for average surface roughness and removed material weight than the other two operating modes, while use of the larger steel grit size also obtained improved results. However, different silicon carbide particle sizes did not have a significant impact on the polishing characteristics.