Different skin pigments among various ethnic group people have an impact on spectrometric illumination on skin surface. To effectively capture photoplethysmographic (PPG) signals, a multi-wavelength opto-electronic patch sensor (OEPS) together with a schematic architecture of electronics were developed to overcome the drawback of present PPG sensor. To perform a better in vivo physiological measurement against skin pigments, optimal illuminations in OEPS, whose wavelength is compatible with a specific skin type, were optimized to capture a reliable physiological sign of heart rate (HR). A protocol was designed to investigate an impact of five skin types in compliance with Von Luschan’s chromatic scale. Thirty-three healthy male subjects between the ages of 18 and 41 were involved in the protocol implemented by means of the OEPS system. The results show that there is no significant difference (p: 0.09, F = 3.0) in five group tests with the skin types across various activities throughout a series of consistent measurements. The outcome of the present study demonstrates that the OEPS, with its multi-wavelength illumination characteristics, could open a path in multiple applications of different ethnic groups with cost-effective health monitoring.

Photoplethysmography (PPG) based pulse oximetry devices normally use red and infrared illuminations to obtain oxygen saturation (SpO ${}_2$ ) readings. In addition, the presence of motion artefacts severely restricts the utility of pulse oximetry physiological measurements. In the current study, a combination of green and orange illuminations from a multi-wavelength optoelectronic patch sensor (mOEPS) was investigated in order to improve robustness to subjects’ movements in the extraction of SpO ${}_2$ measurement. The experimental protocol with 31 healthy subjects was divided into two sub-protocols, and was designed to determine SpO ${}_2$ measurement. The datasets for the first sub-protocol were collected from 15 subjects at rest, with the subjects free to move their hands. The datasets for the second sub-protocol with 16 subjects were collected during cycling and walking exercises. The results showed good agreement with SpO ${}_2$ measurements (r = 0.98) in both sub-protocols. The outcomes promise a robust and cost-effective approach of physiological monitoring with the prospect of providing health monitoring that does not restrict user physical movements.

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG acquisition device (Max30101 photonic sensor) was utilized to (1) capture PPG signals and (2) wirelessly transmit data sets. In contrast to traditional feature engineering machine learning classification schemes, this study preprocessed raw data and applied a deep learning algorithm (LSTM-Attention) directly to extract deeper correlations between these raw datasets. The Long Short-Term Memory (LSTM) model underlying a gate mechanism and memory unit enables it to handle long sequence data more effectively, avoiding gradient disappearance and possessing the ability to solve long-term dependencies. To enhance the correlation between distant sampling points, an attention mechanism was introduced to capture more data change features than a separate LSTM model. A protocol with 15 healthy volunteers and 15 hypertension patients was implemented to obtain these datasets. The processed result demonstrates that the proposed model could present satisfactory performance (accuracy: 0.991; precision: 0.989; recall: 0.993; F1-score: 0.991). The model we proposed also demonstrated superior performance compared to related studies. The outcome indicates the proposed method could effectively diagnose and identify hypertension; thus, a paradigm to cost-effectively screen hypertension could rapidly be established using wearable smart devices.

Pneumatic diaphragm pump is an important part in intelligent spraying. When pneumatic diaphragm pump does not work normally, the entire intelligent spraying product line will be malfunctioned. To maintain and manage pneumatic diaphragm pump effectively, the grade analysis of the health status of pneumatic diaphragm pump is generally used according to its working state. Due to the effects of condition monitoring and random faults, some observable health predictions are often inaccurate. There are very few papers dealing with the health monitoring of pneumatic diaphragm pump and their estimation of residual life span. In this article, a method with vector autoregressive model and continuous-time hidden Markov model was proposed to analyze and evaluate the life span of pneumatic diaphragm pump based on the estimation error of the health condition and the cumulative deterioration of pneumatic diaphragm pump. It is modeled through a continuous-time Markov chain with three states, which includes unobservable healthy state 0, unobservable warning state 1, and observable fault state 2. The expectation–maximization algorithm is used to estimate the model parameters of the fitted hidden Markov. Through the posterior probability of pneumatic diaphragm pump in warning state 1, the derived conditional reliability function and mean residual life span formula can be calculated to evaluate the residual life span of pneumatic diaphragm pump. The results showed that the method can effectively predict the residual life span of pneumatic diaphragm pump, illustrate the effectiveness of the model, and improve the accuracy of the health status rating.

As the energy-saving control of central air conditioning has been widely applied in modern architecture, research of real-time optimal control based on historical data and identification of its optimal control strategies are of great importance for reducing energy wasting of buildings. However, due to the property of easily falling into local optimum, conventional k-means approach cannot achieve the goal of real-time optimal control, we therefore propose an innovative binary k-means clustering algorithm which is used to adjust the target value of temperature difference (TD) in the control system of chilled water and cooling water of central air conditioning system (CACS). Thanks to the clustering control, among the 304 test data, the coefficient of performance (COP) of 211 sets of data, which accounted for 69.41%, are higher than those of the traditional control method. In the simulation system, the COP of 191 sets of data, which accounted for 62.83%, are higher than those of traditional control methods, achieving better energy efficiency. To achieve the goal of identify potential energy-saving control strategies, the Apriori algorithm is proposed to correlate the key parameters and energy consumption efficiency of the CACS. The results show when the chilled water temperature difference (CWTD) > 2.0 °C and the cooling water temperature difference (COWTD) > 2.4 °C, some rules are discovered as follows: 1. The probability of a larger system COP will increase if the CWTD is set lower than the third quartile value or the COWTD is set lower than the first quartile value. 2. The probability of a larger system COP will also increase if the CTWD is set lower than the first quartile and the COWTD is set between the first and the third quartile. These underlying regularity is useful for technicians to adjust the control parameters of the equipment, to improve energy efficiency and to reduce energy consumption.