A Hemodynamic Pulse Wave Simulator Designed for Calibration of Local Pulse Wave Velocities Measurement for Cuffless Techniques.

OBJECTIVE: Devices for cuffless blood pressure (BP) measurement have become increasingly widespread in recent years. Non-invasive continuous BP monitor (BPM) devices can diagnose potential hypertensive patients at an early stage; however, these cuffless BPMs require more reliable pulse wave simulation equipment and verification methods. Therefore, we propose a device to simulate human pulse wave signals that can test the accuracy of cuffless BPM devices using pulse wave velocity (PWV). METHODS: We design and develop a simulator capable of simulating human pulse waves comprising an electromechanical system to simulate the circulatory system and an arm model-embedded arterial phantom. These parts form a pulse wave simulator with hemodynamic characteristics. We use a cuffless device for measuring local PWV as the device under test to measure the PWV of the pulse wave simulator. We then use a hemodynamic model to fit the cuffless BPM and pulse wave simulator results; this model can rapidly calibrate the cuffless BPM's hemodynamic measurement performance. RESULTS: We first used multiple linear regression (MLR) to generate a cuffless BPM calibration model and then investigated differences between the measured PWV with and without MLR model calibration. The mean absolute error of the studied cuffless BPM without the MLR model is 0.77 m/s, which improves to 0.06 m/s when using the model for calibration. The measurement error of the cuffless BPM at BPs of 100-180 mmHg is 1.7-5.99 mmHg before calibration, which decreases to 0.14-0.48 mmHg after calibration. CONCLUSION: This study proposes a design of a pulse wave simulator based on hemodynamic characteristics and provides a standard performance verification method for cuffless BPMs that requires only MLR modeling on the cuffless BPM and pulse wave simulator. The pulse wave simulator proposed in this study can be used to quantitively assess the performance of cuffless BPMs. The proposed pulse wave simulator is suitable for mass production for the verification of cuffless BPMs. As cuffless BPMs become increasingly widespread, this study can provide performance testing standards for cuffless devices.

A novel smart photoelectric lock system: Speech transmitted by laser and speech to text.

We propose a circuit that modulates a speech signal to a laser, using which the speech signal can be transmitted using the laser. Also, it shows the use of a platform based on embedded ARM (Advanced RISC Machine), running a small deep learning model based on TDNN (Time delay neural network) and LSTM (Long short-term memory), and converting speech to text, and use the text cipher for unlocking. This research implements a smart lock system that can set a pre-record speech cipher and verify the similarity through a laser transmission speech cipher to unlock it. In our experiment result, the English speech of laser transmission can reach a WER (Word error rate) of 14.06% through the deep learning model to recognize the content of the speech cipher. We also design a similarity comparison algorithm based on LCS (Longest common subsequence) to compare the character set of the laser transmission speech compare and the prerecord speech cipher to calculate the similarity rate. Through the similarity comparison algorithm, when the WER is 27.27%, the male speech samples used in this study still have a 95% unlocking success rate, while the female speech samples have a 100% unlocking success rate. Compared with only using automatic speech recognition (ASR) to unlock, the method we propose is to compare the similarity of the content of speech cipher. The method significantly improves the unlocking fault tolerance of using lasers to transmit audio. Therefore, by using the laser to transmit the speech cipher, the usability of the photoelectric smart lock system has been significantly improved. At the same time, the characteristics of the laser are not easy to eavesdrop on the cipher, which can also improve security.

Multi-Sensor Fault Diagnosis of Underwater Thruster Propeller Based on Deep Learning.

With the rapid development of unmanned surfaces and underwater vehicles, fault diagnoses for underwater thrusters are important to prevent sudden damage, which can cause huge losses. The propeller causes the most common type of thruster damage. Thus, it is important to monitor the propeller's health reliably. This study proposes a fault diagnosis method for underwater thruster propellers. A deep convolutional neural network was proposed to monitor propeller conditions. A Hall element and hydrophone were used to obtain the current signal from the thruster and the sound signal in water, respectively. These raw data were fast Fourier transformed from the time domain to the frequency domain and used as the input to the neural network. The output of the neural network indicated the propeller's health conditions. This study demonstrated the results of a single signal and the fusion of multiple signals in a neural network. The results showed that the multi-signal input had a higher accuracy than the one-signal input. With multi-signal inputs, training two types of signals with a separated neural network and then merging them at the end yielded the best results (99.88%), as compared to training two types of signals with a single neural network.

A Novel Dentary Bone Conduction Device Equipped with Laser Communication in DSP.

In this study, we designed a dentary bone conduction system that transmits and receives audio by laser. The main objective of this research was to propose a complete hardware design method, including a laser audio transmitter and receiver and digital signal processor (DSP) based digital signal processing system. We also present a digital filter algorithm that can run on a DSP in real time. This experiment used the CMU ARCTIC databases' human-voice reading audio as the standard audio. We used a piezoelectric sensor to measure the vibration signal of the bone conduction transducer (BCT) and separately calculated the signal-to-noise ratio (SNR) of the digitally filtered audio output and the unfiltered audio output using DSP. The SNR of the former was twice that of the latter, and the BCT output quality significantly improved. From the results, we can conclude that the dentary bone conduction system integrated with a DSP digital filter enhances sound quality.

Fault Diagnosis and Fault Frequency Determination of Permanent Magnet Synchronous Motor Based on Deep Learning.

The early diagnosis of a motor is important. Many researchers have used deep learning to diagnose motor applications. This paper proposes a one-dimensional convolutional neural network for the diagnosis of permanent magnet synchronous motors. The one-dimensional convolutional neural network model is weakly supervised and consists of multiple convolutional feature-extraction modules. Through the analysis of the torque and current signals of the motors, the motors can be diagnosed under a wide range of speeds, variable loads, and eccentricity effects. The advantage of the proposed method is that the feature-extraction modules can extract multiscale features from complex conditions. The number of training parameters was reduced so as to solve the overfitting problem. Furthermore, the class feature map was proposed to automatically determine the frequency component that contributes to the classification using the weak learning method. The experimental results reveal that the proposed model can effectively diagnose three different motor states-healthy state, demagnetization fault state, and bearing fault state. In addition, the model can detect eccentric effects. By combining the current and torque features, the classification accuracy of the proposed model is up to 98.85%, which is higher than that of classical machine-learning methods such as the k-nearest neighbor and support vector machine.

Early prediction of coronavirus disease epidemic severity in the contiguous United States based on deep learning.

In November 2019, the coronavirus disease outbreak began, caused by the novel severe acute respiratory syndrome coronavirus 2. In just over two months, the unprecedented rapid spread resulted in more than 10,000 confirmed cases worldwide. This study predicted the infectious spread of coronavirus disease in the contiguous United States using a convolutional autoencoder with long short-term memory and compared its predictive performance with that of the convolutional autoencoder without long short-term memory. The epidemic data were obtained from the World Health Organization and the US Centers for Disease Control and Prevention from January 1st to April 6th, 2020. We used data from the first 366,607 confirmed cases in the United States. In this study, the data from the Centers for Disease Control and Prevention were gridded by latitude and longitude and the grids were categorized into six epidemic levels based on the number of confirmed cases. The input of the convolutional autoencoder with long short-term memory was the distribution of confirmed cases 14 days before, whereas the output was the distribution of confirmed cases 7 days after the date of testing. The mean square error in this model was 1.664, the peak signal-to-noise ratio was 55.699, and the structural similarity index was 0.99, which were better than those of the corresponding results of the convolutional autoencoder. These results showed that the convolutional autoencoder with long short-term memory effectively and reliably predicted the spread of infectious disease in the contiguous United States.

Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning.

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird's eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

Estimation of the Number of Passengers in a Bus Using Deep Learning.

For the development of intelligent transportation systems, if real-time information on the number of people on buses can be obtained, it will not only help transport operators to schedule buses but also improve the convenience for passengers to schedule their travel times accordingly. This study proposes a method for estimating the number of passengers on a bus. The method is based on deep learning to estimate passenger occupancy in different scenarios. Two deep learning methods are used to accomplish this: the first is a convolutional autoencoder, mainly used to extract features from crowds of passengers and to determine the number of people in a crowd; the second is the you only look once version 3 architecture, mainly for detecting the area in which head features are clearer on a bus. The results obtained by the two methods are summed to calculate the current passenger occupancy rate of the bus. To demonstrate the algorithmic performance, experiments for estimating the number of passengers at different bus times and bus stops were performed. The results indicate that the proposed system performs better than some existing methods.

Mortality Prediction of Septic Patients in the Emergency Department Based on Machine Learning.

In emergency departments, the most common cause of death associated with suspected infected patients is sepsis. In this study, deep learning algorithms were used to predict the mortality of suspected infected patients in a hospital emergency department. During January 2007 and December 2013, 42,220 patients considered in this study were admitted to the emergency department due to suspected infection. In the present study, a deep learning structure for mortality prediction of septic patients was developed and compared with several machine learning methods as well as two sepsis screening tools: the systemic inflammatory response syndrome (SIRS) and quick sepsis-related organ failure assessment (qSOFA). The mortality predictions were explored for septic patients who died within 72 h and 28 days. Results demonstrated that the accuracy rate of deep learning methods, especially Convolutional Neural Network plus SoftMax (87.01% in 72 h and 81.59% in 28 d), exceeds that of the other machine learning methods, SIRS, and qSOFA. We expect that deep learning can effectively assist medical staff in early identification of critical patients.

Gain-phase margin analysis of dynamic fuzzy control systems.

In this paper, we apply some effective methods, including the gain-phase margin tester, describing function and parameter plane, to predict the limit cycles of dynamic fuzzy control systems with adjustable parameters. Both continuous-time and sampled-data fuzzy control systems are considered. In general, fuzzy control systems are nonlinear. By use of the classical method of describing functions, the dynamic fuzzy controller may be linearized first. According to the stability equations and parameter plane methods, the stability of the equivalent linearized system with adjustable parameters is then analyzed. In addition, a simple approach is also proposed to determine the gain margin and phase margin which limit cycles can occur for robustness. Two examples of continuous-time fuzzy control systems with and without nonlinearity are presented to demonstrate the design procedure. Finally, this approach is also extended to a sampled-data fuzzy control system.