Real-time Test Data Research Articles

Applying LSTM and GRU Methods to Recognize and Interpret Hand Gestures, Poses, and Face-Based Sign Language in Real Time

This research uses a real-time, human-computer interaction application to examine sign language recognition. This work develops a rule-based hand gesture approach for Indonesian sign language in order to interpret some words using a combination of hand movements, mimics, and poses. The main objective in this study is the recognition of sign language that is based on hand movements made in front of the body with one or two hands, movements which may involve switching between the left and right hand or may be combined with mimics and poses. To overcome this problem, a research framework is developed by coordinating hand gestures with poses and mimics to create features by using holistic MediaPipe. To train and test data in real time, the long short time memory (LSTM) and gated recurrent unit (GRU) approaches are used. The research findings presented in this paper show that hand gestures in real-time interactions are reliably recognized, and some words are interpreted with the high accuracy rates of 94% and 96% for the LSTM and GRU methods, respectively.

Predicting the Performance of PEM Fuel Cells by Determining Dehydration or Flooding in the Cell Using Machine Learning Models

Modern industries encourages the use of hydrogen as an energy carrier to decarbonize the electricity grid, Polymeric Electrolyte membrane fuel cell which uses hydrogen as a fuel to produce electricity, is an efficient and reliable ‘power to gas’ technology. However, a key issue obstructing the advancement of PEMFCs is the unpredictability of their performance and failure events caused by flooding and dehydration. The accurate prediction of these two events is required to avoid any catastrophic failure in the cell. A typical approach used to predict failure modes relies on modeling failure-induced performance losses and monitoring the voltage of a cell. Data-driven machine learning models must be developed to address these challenges. Herein, we present a machine learning model for the prediction of the failure modes of operating cells. The model predicted the relative humidity of a cell by considering the cell voltage and current density as the input parameters. Advanced regression techniques, such as support vector machine, decision tree regression, random forest regression and artificial neural network, were used to improve the predictions. Features related to the model were derived from cell polarization data. The model’s results were validated with real-time test data obtained from the cell. The statistical machine learning models accurately provided information on the flooding- and dehydration-induced failure events.

Utilizing Real-Time Test Data to Solve Attenuation Paradox in Computerized Adaptive Testing to Enhance Optimal Design

To solve the attenuation paradox in computerized adaptive testing (CAT), this study proposes an item selection method, the integer programming approach based on real-time test data (IPRD), to improve test efficiency. The IPRD method turns information regarding the ability distribution of the population from real-time test data into feasible test constraints to reversely assembled shadow tests for item selection to prevent the attenuation paradox by integer programming. A simulation study was conducted to thoroughly investigate IPRD performance. The results indicate that the IPRD method can efficiently improve CAT performance in terms of the precision of trait estimation and satisfaction of all required test constraints, especially for conditions with stringent exposure control.

Diagnostics using a physics-based engine model in aero gas turbine engine verification tests

In the present study, the application of a diagnostic method using a physics-based model is proposed during engine verification testing. A physics-based engine model is constructed, based on a 0-dimensional system analysis method, and then revised through performance adaptation with a basic engine model. Adaptation factors are used for the compressor, secondary air system, nozzle, exhaust gas temperature, and engine thrust. Gas path analysis is conducted using the physics-based engine model and the performance test data in real time. A health parameter that can quantitatively evaluate the performance difference of components was defined. Health parameters for the compressor capacity and efficiency, secondary air system, and nozzle are calculated from the gas path analysis. The multi-variable Newton–Raphson method is employed for the performance adaptation and gas path analysis in real time. A single-shaft gas turbine engine, which is constructed based on the core part of a turbofan engine currently under development, is utilized to test and evaluate the effectiveness of the proposed method. Three tests are performed for engine verification. The proposed diagnostic method is applied to the aero gas turbine engine verification test. In 33 test cases, the fault detection rates for the compressor's variable guide vane, secondary air system, and variable area nozzle are 100%, 91%, and 79%, respectively. As a result, it is confirmed that the proposed method can simultaneously detect abnormalities in the compressor's variable guide vane, secondary air system, and variable area nozzle. In addition, this study indicates that applying the physics-based engine model to the diagnostics logic can effectively detect failures with a small amount of data.

Gender Voice Recognition Using Machine Learning Algorithms

Abstract: Gender identification is one of the major problems in the area of signal processing. The system deals with finding the gender of a person using oral features. One of the most persnickety problems faced is feature selection from wide range of features, which is distinguishing factor in classifying the gender of aperson. The ideal of this design is to design a system that determines the speaker gender using the pitch of the speaker's voice. relating the gender from the plots of voice data set i.e., pitch, median, frequency etc. can be possible by using machine learning. In this design, we're trying to classify gender into male or female based on the data set containing varied attributes related to voice like pitch, frequency etc. The data set have features with explanation data points recorded samples of male and female voices. The data set can be trained with different machine learning algorithms. The proposed system can determine the gender of the speaker with real time test data a new result to discover the gender of the speaker using Fast Fourier Transform with Logistic Regression

Development of an autonomous fog computing platform using control-theoretic approach for robot-vision applications

This paper presents the dynamic modelling and linear matrix inequality (LMI) based controller design of a distributed fog computing framework for real-time robot vision applications. A mobile robot vision system acquires the images from an application environment such as a warehouse, where articles are stacked in numerous racks. We characterise the mobile robot vision data (MRVD) using frames per second (FPS) and the image resolution. From the MRVD, object detection is performed by an open-source deep learning (DL) platform for detecting and localising various objects. However, with higher FPS together with high-resolution images, the processing time by the DL algorithm increases significantly. This necessitates the deployment of a distributed computing platform with several computing nodes. In this work, we deploy a distributed fog computing environment (DFCE) for the real-time object detection in an application environment.The processing time required to handle the MRVD is called the service time. However, for efficient auto-scaling performance, the mathematical model of the DFCE, taking into consideration the characteristics of the MRVD is necessary. In this context, we envisage the application of control theory to build the dynamic model of the DFCE. A Linear Parameter Varying (LPV) model is proposed for the DFCE with the service time as the output, the number of fog nodes as the input, and the characteristics of MRVD as the time-varying parameters. At first, an LPV model for the DFCE is derived using system identification, and the model is validated using the real-time test data. The LPV model is converted to a Polytopic LPV (PLPV) model for LMI based controller design. Finally, we develop and validate a Linear Matrix Inequality (LMI) based LPV controller to meet the service time constraints for a given application environment.For localisation and trajectory tracking with obstacle avoidance in the application environment, the mobile robot implements an Extended Kalman Filter (EKF) based simultaneous localisation and mapping (SLAM) and a bug-based path planning algorithm respectively. Finally, we present, detailed controller validation results illustrating the mobile robot navigation together with the auto-scaling control for the fog computing platform to modulate the service time.

Research on rotor system fault diagnosis method based on vibration signal feature vector transfer learning

Aiming at the common fault diagnosis problems of rotors in industrial applications. A rotor system fault diagnosis method based on vibration signal feature vector transfer learning is proposed. First, Statistical methods and wavelet packet decomposition are used for vibration signal feature extraction. Then, the ReliefF algorithm is used to evaluate the fault features and screen out the sensitive fault features set. Next, the training data and real time test data are mapped to the kernel Hilbert space using the transfer component analysis method. Finally, the weighted k-nearest neighbor method is used as the fault feature classifier for fault pattern recognition. Model training and validation using typical failure datasets of different equipment and different operating conditions. Compared with other related methods, the results indicate that the proposed method has better generalization and diagnostic accuracy. This research will promote the engineering application of intelligent fault diagnosis of rotor system.

Real-time Acquisition and Analysis Test Data of Commercial Vehicle Handling Stability Based on LABVIEW Virtual Instrument

Aiming at the problems of complex time-consuming and heavy data processing workload in the field test of commercial vehicle handling stability, a vehicle handling stability test solution based on virtual instrument technology is proposed. This solution is based on the existing test equipment and conditions, using LABVIEW virtual instrument, integrated application of GPS, AHRS and steering force angle tester to form a set of road test system solutions that can realize vehicle handling and stability. The system can meet the requirements of the national standard Controllability and Stability Test Procedure for Automobile (GB / T 6323-2014) to realize the vehicle handling stability test, and the system test is verified by the real vehicle test data, which provides a more efficient and convenient test method for the study of vehicle handling stability test.

A real-time COVID-19 surveillance dashboard to support epidemic response in Connecticut: lessons from an academic-health department partnership.

In response to the coronavirus disease-19 (COVID-19) pandemic, numerous institutions published COVID-19 dashboards for reporting epidemiological statistics at the county, state, or national level. However, statistics for smaller cities were often not reported, requiring these areas to develop their own data processing pipelines. For under-resourced departments of health, the development of these pipelines was challenging, leading them to rely on nonspecific and often delayed infection statistics during the pandemic. To avoid this issue, the Stamford, Connecticut Department of Health (SDH) contracted with the Columbia Mailman School of Public Health to develop an online dashboard that displays real-time case, death, test, vaccination, hospitalization, and forecast data for their city, allowing SDH to monitor trends for specific demographic and geographic groups. Insights from the dashboard allowed SDH to initiate timely and targeted testing/vaccination campaigns. The dashboard is widely used and highlights the benefit of public-academic partnerships in public health, especially during the COVID-19 pandemic.

A Design of Test Equipment on Gun Control Systems and Autoloaders

In response to a series of problems in the actual use of a certain type of tank fire control system and autoloader, such as many sudden failures, difficulties in diagnosing and locating failures, and complex maintenance and guarantee, a testing equipment is designed for the gun control box and autoloader, which is used to monitor the status of the gun control box and autoloader, and store the test data in real time. By comparing the test data and analysing the abnormal problems that occur in the work of the gun control box and the autoloader, it realises the monitoring of the working condition of the tank gun control box and the autoloader components, providing effective data support for the next step of repair.

A new automatic, very efficient method for the analysis of flight flutter testing data

This article presents a new data processing method, based on higher order dynamic mode decomposition, to analyze actual flight test experimental data. The new methodology (i) is fast and efficient, (ii) is automatic, (iii) provides a clean spectrum in terms of the frequencies and damping rates of the flutter modes, and (iv) reconstructs the spatial distribution of the modes over the aircraft surface. The method gives useful and interesting information for predicting flutter and is suitable to analyze flight test data in real time.

Model for Mitigation of Workplace Transmission of COVID-19 Through Population-Based Testing and Surveillance.

The coronavirus disease-2019 (COVID-19) pandemic is having a widespread impact on societies across the globe. As part of the effort to control transmission in the United States, many businesses either closed or instituted nonpharmaceutical control measures and allowed only essential workers on-site. During summer and fall of 2020, employers began formulating “return to work” strategies designed to mitigate the risk of transmission among employees. On a population level, several countries implemented national testing and surveillance strategies that proved effective in mitigating citizen-to-citizen transmission and contributed to suppressing COVID-19. A crucial component of many such strategies is population-based testing to identify and engage individuals with asymptomatic or presymptomatic infection, which also is relevant to return-to-work strategies. The authors describe an approach that multisite employers might use to help mitigate transmission of COVID-19 in the workplace. This approach leverages a bioinformatics platform informed by real-time PCR test data at the county and subcounty (eg, Public Use Microdata Area) level, allowing for population-based testing to be selectively targeted for employees in geographies with elevated SARS-CoV-2 positivity. A “Command Center” application integrates data from multiple sources (eg, local infection trends, employee symptom diaries, Bluetooth thermometers) in real time, which can be used to inform decisions regarding surveillance and employee self-isolation or quarantine; a mobile phone-based application provides for rapid, secure communication with employees. This overview is based on peer-reviewed literature and the early experience of a large employer with implementing bioinformatics tools to mitigate the impact of the pandemic on the workplace.

Diagnostics Using First-Principles Based Digital Twin and Application for Gas Turbine Verification Test

In the present study, a diagnostic method using a first-principles based digital twin is proposed for application during engine verification test. The first-principles model is applied to generate the digital twin model using a small number of measurement data. A method is developed to identify abnormalities of components in a short time and to classify faults through detailed inspection. The digital twin model is generated through performance adaptation with a basic first-principles model. Performance adaptation factors are used for compressor, secondary air system, nozzle, exhaust gas temperature, and engine thrust. Gas path analysis is conducted using the digital twin and the performance test data in real time. Health parameters for compressor capacity and efficiency, secondary air system, and nozzle are calculated from the gas path analysis. Multi-variable Newton-Raphson method is employed for the performance adaptation and the gas path analysis in real time. A single-shaft gas turbine engine is utilized to test and evaluate the effectiveness of the proposed method. Three tests are performed for engine verification. The diagnostic method is applied to the engine test. As a result, it is confirmed that the proposed method can simultaneously detect abnormalities in HPC VGV, secondary air system, and variable area nozzle.

Design of Wireless Sensor Body Measurement Information Acquisition System for College Students’ Physical Health Management

With the improvement of the quality of national life, the physical health problem is gradually placed in the same important position as the basic problems such as education, people’s livelihood, and safety. Improving the physical quality of college students and promoting the healthy growth of students are major events in the future of the country and the nation. Therefore, each school will conduct a physical test every year. The use of wireless sensors for data acquisition has played an important role in various fields. Therefore, for the physical health management of college students, this paper proposes to design a sensor system to collect physical measurement data. The measured data is collected through the sensor, such as the XGZP6847 gas pressure sensor to collect students’ vital capacity. Then, the sensor node and the coordinator are connected to the PC through the serial port, respectively, and the CC2530 chip transmits the data to the coordinator through the ZigBee module, establishes communication with the PC through the 2.4G wireless communication module, adopts the strategy of the thread pool to save resources, improves the response speed, and obtains students’ body test data in real time. Taking the data acquisition and transmission of vital capacity and body weight subjects as an example, the system realizes the accurate transmission of the collected test data from the sensor to the terminal, greatly improves the accuracy and real‐time body test data acquisition, and reduces the probability of errors in the recording process, and the collected data can be used directly or for secondary development, and it promotes the establishment of college students’ physical health management system.

A Novel ESPRIT Algorithm for Analysis of Low Frequency Oscillations in Power System

With rapidly increasing load and randomly varying load scenario in a densely connected power system may lead to low-frequency oscillations which can further make a power system unstable. To keep the power system in stable operating limits identifying such dominant low-frequency oscillations is essential. Numerous signal processing techniques are used to detect low-frequency oscillations in a power system. Different techniques have their advantages and disadvantages. Estimation of signal parameters via rotational invariance technique (ESPRIT) is a signal processing technique by which low-frequency oscillations can be identified even under noisy conditions . In this paper, a novel ESPRIT algorithm for identifying low-frequency oscillations is proposed. This methodology is based on the ESPRIT algorithm, whose key concept is that real modes existing in oscillations emerge consistently regardless of the algorithm's order. The performance of this algorithm is verified through a set of synthetic signals generated in MATLAB with different noise levels and varying PMU rates and compared with traditional Prony algorithm. The performance of the proposed algorithm is also verified on real-time test data obtained from the Western Electricity Coordinating Council (WECC). This technique performs fairly well in finding low-frequency oscillation characteristics in the power grid.

Machine learning algorithms for failure prediction and yield improvement during electric resistance welded tube manufacturing

ABSTRACTAn electric-resistance-welded (ERW) tube is one of the leading contributor products for automotive manufacturers. Such tubes tend to fail due to weak weld quality that may be the result of several parameters, such as inappropriate selection of weld power, positions of forming rolls and fin pass rolls, mill operating speed and many more. This paper presents an application of classifier algorithm to predict weak welded tube during real production process. Real-time data with 86 independent variables are trained using logistic regression as classifier. A logistic regression model is validated on real-time test data with capability of predicting failure 82.55% of the time (often termed as sensitivity). Operating ranges for mill parameters are estimated with the help of model results. Significant yield improvement has been observed after deployment of model recommended operating ranges as recipe in manufacturing unit. Working of newly developed human machine interface (HMI) has been explained. This exercise has been performed for three different product segments being manufactured in Tubes Division, Tata Steel Limited. This work demonstrates an application of artificial intelligence in manufacturing plant for quality improvement.

Flow Channel Influence of a Collision-Based Piezoelectric Jetting Dispenser on Jet Performance.

To improve the jet performance of a bi-piezoelectric jet dispenser, mathematical and simulation models were established according to the operating principle. In order to improve the accuracy and reliability of the simulation calculation, a viscosity model of the fluid was fitted to a fifth-order function with shear rate based on rheological test data, and the needle displacement model was fitted to a nine-order function with time based on real-time displacement test data. The results show that jet performance is related to the diameter of the nozzle outlet and the cone angle of the nozzle, and the impacts of the flow channel structure were confirmed. The approach of numerical simulation is confirmed by the testing results of droplet volume. It will provide a reliable simulation platform for mechanical collision-based jet dispensing and a theoretical basis for micro jet valve design and improvement.

Design and Development of a Smart Exercise Bike for Motor Rehabilitation in Individuals with Parkinson's Disease.

Recent studies in rehabilitation of Parkinson's disease (PD) have shown that cycling on a tandem bike at a high pedaling rate can reduce the symptoms of the disease. In this research, a smart motorized bicycle has been designed and built for assisting Parkinson's patients with exercise to improve motor function. The exercise bike can accurately control the rider's experience at an accelerated pedaling rate while capturing real-time test data. Here, the design and development of the electronics and hardware as well as the software and control algorithms are presented. Two control algorithms have been developed for the bike; one that implements an inertia load (static mode) and one that implements a speed reference (dynamic mode). In static mode the bike operates as a regular exercise bike with programmable resistance (load) that captures and records the required signals such as heart rate, cadence and power. In dynamic mode the bike operates at a user-selected speed (cadence) with programmable variability in speed that has been shown to be essential to achieving the desired motor performance benefits for PD patients. In addition, the flexible and extensible design of the bike permits readily changing the control algorithm and incorporating additional I/O as needed to provide a wide range of riding experiences. Furthermore, the network-enabled controller provides remote access to bike data during a riding session.

Recursive and noise-exclusive fuzzy switching median filter for impulse noise reduction

A new model for impulse noise reduction with a recursive and noise-exclusive fuzzy switching median filter is proposed. The filter uses a S-type membership function for fuzzifying the noisy input variable and then estimates a correction label for it that aims at canceling the noisy effect. The fuzzification process provides better smoothing and generalization that improve the performance of the filter. The recursive and noise-exclusive operations further enhance the noise reduction capability of the filter. The recursive operation replaces the current pixel with the filtered pixel(s) and the noise-exclusive filtering uses only noise-free pixel(s) of the working window. The net effect of the filtering process thus preserves the sharp edges and fine details of the image in a more effective manner. The superiority of the proposed model to others in removing high density noise is established both quantitatively and qualitatively with various benchmarks and real-time test data sets. With the incorporation of the functionalities like fuzzy reasoning and noise-exclusive operations in the filtering process, the model becomes more efficient and fast. The applicability of the model thus opens ample scopes for hardware implementation in many electronics products that deal with images and videos.

Research on Network Virtual Instrument

According to research on the technologies of virtual instrument and network, a netwok virtual instrument test structure based on mixed C/S/B mode is presented in this paper. In order to solve the problem of real-time of network test, ActiveX client control and instrument testing application server is developed based on ActiveX plug-in technology. Users can login the virtual instrument test platform through the browser, submit request commands and test parameters to the Web server, control the remote equipments, and observe the real-time test data and analysis results.