High Real-time Performance Research Articles

Quantitative analysis of heart rate variability parameter and mental stress index.

BackgroundCardiovascular disease not only occurs in the elderly but also tends to become a common social health problem. Considering the fast pace of modern life, quantified heart rate variability (HRV) indicators combined with the convenience of wearable devices are of great significance for intelligent telemedicine. To quantify the changes in human mental state, this article proposes an improved differential threshold algorithm for R-wave detection and recognition of electrocardiogram (ECG) signals.MethodsHRV is a specific quantitative indicator of autonomic nerve regulation of the heart. The recognition rate is increased by improving the starting position of R wave and the time-window function of the traditional differential threshold method. The experimental platform is a wearable sign monitoring system constructed based on body area networks (BAN) technology. Analytic hierarchy process (AHP) is used to construct the mental stress assessment model, the weight judgment matrix is constructed according to the influence degree of HRV analysis parameters on mental stress, and the consistency check is carried out to obtain the weight value of the corresponding HRV analysis parameters.ResultsExperimental results show that the recognition rate of R wave of real-time 5 min ECG data collected by this algorithm is >99%. The comprehensive index of HRV based on weight matrix can greatly reduce the deviation caused by the measurement error of each parameter. Compared with traditional characteristic wave recognition algorithms, the proposed algorithm simplifies the process, has high real-time performance, and is suitable for wearable analysis devices with low-configuration requirements.ConclusionOur algorithm can describe the mental stress of the body quantitatively and meet the requirements of application demonstration.

Comparison of different algorithms based on TKEO for EMG change point detection

Objective. A significant challenge in surface electromyography (EMG) is the accurate identification of onset and offset of muscle activation while maintaining high real-time performance. Teager–Kaiser energy operator (TKEO) is widely used in muscle activity monitoring systems because of its computational simplicity and strong real-time performance. However, in contrast to TKEO ontology, few studies have examined how well the energy operator variants from multiple fields perform in conditioning EMG signals. This paper aims to investigate the role of the energy operator and its variants in EMG change point detection by a threshold detector. Approach. To compare the stability and accuracy of TKEO and its variants for EMG change point detection, the EMG data of extensor carpi radialis longus and flexor carpi radialis were acquired from twenty participants operating a controller under normal and disturbed conditions, and EMG change point detection was performed by four energy operators and their rectified versions. Main results. Based on the ‘standard’ change points collected by the controller, the detection results were evaluated by three evaluation indexes: detection rate, F1 Score, and accuracy. The experimental results show that the multiresolution energy operator and the TKEO with rectified (abs-TKEO) are more suitable for EMG change point detection. Significance. This paper compared the effect of the energy operator and its variants on a threshold-based EMG change point detector. The experimental results in this paper can provide a reference for the selection of EMG signal conditioning methods to improve the detection performance of the EMG change point detector.

Influence of the Athlete’s Training Physical State Test Based on the Principle of Artificial Intelligence Sensor

Artificial intelligence is the study of the laws of human intelligent activities, the construction of artificial systems with certain intelligence, and the study of how to make computers perform tasks that required human intelligence in the past. Basic Theories, Methods, and Techniques. With the maturity of the highly integrated hardware technology, the rapid development of sensor technology provides a material basis for the study of sports states based on smart terminals, and the mature model method theory provides a theoretical research basis for the research. The working principle of the sensor is to convert the specific measured signal into a certain “available signal” according to a certain rule through the sensitive element and the conversion element and output it to meet the requirements of information transmission, processing, recording, display, and control. In order to deeply study the application of artificial intelligence sensor theory in athlete training physical condition testing, this article uses theoretical analysis method, formula image combination method, and real person survey method, collects samples, analyzes artificial intelligence sensor, and streamlines the algorithm. In studying the accuracy of smart sensors on athlete training tests, a total of 9 athletes, 4 females, and 5 males are selected. Each experimenter performed three actions of running, jumping, and squatting 10 times, with an interval of more than 20 s. The results showed that the recognition accuracy of running in this paper was 98.51%, and the recognition accuracy of jumping and squatting was 92.59% and 93.33%; we have achieved more than 92% recognition rate for the three kinds of actions. On further study of the real-time performance of the sensor, the average response time of the algorithm is the average value obtained from 80 experimental records in this paper. The average response time of the algorithm proposed in this paper is within 1.5 s. Since the falling process occurs within 2.1 s, the recognition algorithm proposed in this paper has high real-time performance. It is basically realized that starting from the theory of artificial intelligence sensors, a high-precision sensor that can be applied to athlete training is designed.

A Lightweight Semantic Segmentation Model of Wucai Seedlings Based on Attention Mechanism

Accurate wucai seedling segmentation is of great significance for growth detection, seedling location, and phenotype detection. To segment wucai seedlings accurately in a natural environment, this paper presents a lightweight segmentation model of wucai seedlings, where U-Net is used as the backbone network. Specifically, to improve the feature extraction ability of the model for wucai seedlings of different sizes, a multi-branch convolution block based on inception structure is proposed and used to design the encoder. In addition, the expectation “maximizationexpectation” maximization attention module is added to enhance the attention of the model to the segmentation object. In addition, because of the problem that a large number of parameters easily increase the difficulty of network training and computational cost, the depth-wise separable convolution is applied to replace the original convolution in the decoding stage to lighten the model. The experimental results show that the precision, recall, MIOU, and F1-score of the proposed model on the self-built wucai seedling dataset are 0.992, 0.973, 0.961, and 0.982, respectively, and the average recognition time of single frame image is 0.0066 s. Compared with several state-of-the-art models, the proposed model achieves better segmentation performance and has the characteristics of smaller-parameter scale and higher real-time performance. Therefore, the proposed model can achieve good segmentation effect for wucai seedlings in natural environment, which can provide important basis for target spraying, growth recognition, and other applications.

IRePf: An Instruction Reorganization Virtual Platform for Kernel Stack Overflow Detection

Stack overflow vulnerabilities are among the most common security issues. However, the existing stack overflow detection solutions only protect the return address and ignore the imbalance between function calls and returns in the system, which will lead to a higher false-positive rate. In this paper, we propose an instruction reorganization virtual platform technique for kernel stack overflow detection, named IRePf. It can dynamically monitor the kernel stack when the system is running through dynamic reorganization instructions, thread creation and termination, call instructions, and RET instructions. IRePf uses backup stack creation and destruction technology to back up the return address and the address of the return address at the same time. IRePf determines whether the stack overflow occurs in the system when the function call and return are unbalanced to realize the kernel stack overflow detection. The experimental results show that IRePf can effectively detect stack overflow attacks, has low system resource occupancy and high real-time performance, and effectively improves the ability and security of defense stack attacks.

A_CenterNet: Object as a Point by Attention

In this paper, in view of the insufficiency of the CenterNet detector’s inability to achieve high real-time performance with high accuracy when performing object detection, we designed a new detector called A_CenterNet. In the detector, we use our newly designed lightweight Hourglass-256 model, and we also use the feature map fusion method we designed, as well as our improved attention mechanism. Through the experimental results on multiple datasets, it can be known that the A_CenterNet proposed in this paper has a competitive advantage compared with some existing classic detectors. A_CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 44.6 AP at 36 FPS. Compared with CenterNet, A_CenterNet greatly improves the detection speed without loss of detection accuracy.

Fault Diagnosis of Automobile Engine Based on Improved BP Neutral Network

With the continuous enrichment of automobile functions and the complexity of automobile structure, the difficulty of automobile fault diagnosis is constantly increasing. The study of fault diagnosis methods with high real-time performance, accuracy, and predictability is of great significance to improve automobile safety performance and ensure driving safety. Since the convergence speed of the traditional BP neural network algorithm is slow and the accuracy is insufficient in the process of automobile engine fault diagnosis, this paper improves convergence speed of the algorithm by introducing the momentum term, and the weights and thresholds of the neural network are optimized by using GA selection, crossover, and genetic characteristics, to propose a genetic algorithm (GA) optimization BP neural network fault diagnosis method. The average absolute error of the traditional BP neural network algorithm is 0.5976, while the average absolute error of the improved BP neural network algorithm in this paper is 0.1027. The comparative simulation results show that the proposed improved algorithm is better than the traditional BP neural network algorithm in diagnosis precision, accuracy, and other key indicators.

Estimation of water attenuation coefficient by imaging modeling of the backscattered light with the pulsed laser range-gated imaging system

Compared to conventional floodlighted imaging systems, a pulsed laser range-gated imaging system can get a real-time high performance underwater image when the distance of target is known. Otherwise, optical properties of the water, mainly the attenuation coefficient of the water, should be obtained to automatically set the parameters of the imaging system. Typically, special instrument is required to measure the attenuation coefficient of the water. In this work, a water attenuation coefficient estimation method is proposed merely with the pulsed laser range-gated imaging system. The imaging model of the backscattered light of the pulsed laser range-gated imaging system is built through the light propagation theory. As a result, the water attenuation coefficient is calculated by nonlinear estimation method. Experiments under different water conditions are designed and carried out to verify the proposed method. Results show that the relative errors between the estimation and the reference are about 1% for the water in the water tank and seawater pool, and about 4% for the towing boat tank, respectively.

A Digital Twin-Based Operation Status Monitoring System for Port Cranes.

To address the problems of the lack of an online data simulation test environment, the poor openness of data collection, and the low degree of data visualization in the online control process of port cranes, an operation state monitoring system framework for port cranes based on digital twins is proposed. In this framework, the digital twin port crane is used as the core, and the multi-sensor data acquisition method, OPC UA information model, and plug-in programming method are combined to realize multi-source heterogeneous virtual and real data fusion. The digital twin crane monitoring system based on this framework can fulfil the following functions: crane historical operation process reproduction, control program simulation testing, synchronous mapping simulation, and remote control. In order to verify the proposed method, a digital twin-based physical platform for monitoring a rail-mounted gantry crane (RMGC) was built, in which a virtual test of anti-swing control and a digital twin monitoring experiment were carried out. The results show that the virtual RMGC can test the control algorithm and map the movement process of the physical RMGC, and the crane operation monitoring system has high real-time performance and good visualization effect. In addition, the remote control of the software platform is accurate and effective.

A Configurable and Real-Time Multi-Frequency 3D Image Signal Processor for Indirect Time-of-Flight Sensors

3D time-of-flight (ToF) cameras have recently attracted widespread attention because of their potential in wide applications. However, the lack of versatile 3D image signal processor (ISP) is still an obstacle that hinders their popularity. The main challenges lie in the management of high-throughput raw data and the complexity of 3D image processing in hardware. To address these challenges, this paper presents a top-down 3D ISP with high real-time performance and high energy efficiency for indirect ToF (IToF) imaging. First, we propose configurable cache strategies to improve the efficiency of non-streaming memory accesses and support different IToF sensors. Then, to resolve the phase ambiguity problem commonly existing in IToF sensors, we develop a hardware-optimized cascaded multi-frequency fusion method, which not only supports up to six modulation frequencies but also facilitates the pixel-wise detection of multipath interference. Moreover, we propose a scalable calculation engine for depth calculation and calibration, 3D image enhancement, and post-processing. The pipeline is prototyped on a Xilinx ZCU102 FPGA board. Results show that the 3D ISP has negligible precision loss and low latency, achieving <inline-formula> <tex-math notation="LaTeX">$53.35\times $ </tex-math></inline-formula> energy efficiency improvement compared with the implementation on Intel CPU and <inline-formula> <tex-math notation="LaTeX">$55.45\times $ </tex-math></inline-formula> improvement over the ARM CPU implementation. When running at 75 MHz, the 3D ISP can support <inline-formula> <tex-math notation="LaTeX">$1280\times 960$ </tex-math></inline-formula> depth, intensity, and point cloud output at a frame rate of 30 f/s.

Application prospect of time-sensitive network in airborne communication network

TSN (Time Sensitive Network) is a real-time Network communication technology being promoted by the international industry. It has the characteristics of more flexibility and high real-time performance. This paper firstly introduces the background of airborne network and real-time network. Then, TSN and the mainstream airborne communication network technology are compared and analyzed from the aspects of synchronization mechanism, scheduling strategy, redundancy and reliability mechanism. Finally, the prospect of TSN in the field of civil aviation is analyzed in general, which makes the application route of TSN in the airborne communication network more clear.

MULTI-SCALE DIRECTED ACYCLIC GRAPH-CNN FOR AUTOMATED CLASSIFICATION OF DIABETIC RETINOPATHY FROM OCT IMAGES

Diabetic Retinopathy (DR) is the principal cause of vision loss that interrupts the regular interaction of vascular, neural, and retinal constituents leading to impaired neuronal function and retinal abnormalities. Diagnosis of DR from Optical Coherence Tomography (OCT) image is difficult and time-consuming because several small features must be identified and graded, which results in a strenuous diagnosis when integrated with the complexity of the grading system. This study focuses on classifying DR from normal Spectral Domain-OCT (SD-OCT) images using the Directed Acyclic Graph (DAG) network without any pre-processing techniques. The proposed DAG-CNN model comprises 16 convolutional blocks, which learns multi-scale features automatically from multiple layers in the convolutional network and combines them effectively for the DR and normal prediction. The proposed model is tested on the public OCTID_DR and private LFH_DR SD-OCT databases containing DR and healthy OCT images. The model achieved an accuracy, precision, recall, F1-score, and AUC on OCTID_DR database of 0.9841, 0.9727, 0.9818, 0.9772, and 0.9836, respectively; and on LFH_DR database the respective values are 0.9988, 1, 0.9976, 0.9988, and 0.9988 with only 0.1569 Million of learnable parameters. This method significantly reduces the number of learnable parameters and the model’s computational complexity in terms of memory required and FLoating point OPerations (FLOPs). Guided Gradient-weighted Class Activation Mapping (Grad-CAM) is performed to highlight the regions of SD-OCT images that contribute to the decision of the classifier. Our model significantly surpasses the accuracy of the existing models with lower resource consumption and higher real-time performance.

Motion Estimation and Hand Gesture Recognition-Based Human-UAV Interaction Approach in Real Time.

As an alternative to traditional remote controller, research on vision-based hand gesture recognition is being actively conducted in the field of interaction between human and unmanned aerial vehicle (UAV). However, vision-based gesture system has a challenging problem in recognizing the motion of dynamic gesture because it is difficult to estimate the pose of multi-dimensional hand gestures in 2D images. This leads to complex algorithms, including tracking in addition to detection, to recognize dynamic gestures, but they are not suitable for human–UAV interaction (HUI) systems that require safe design with high real-time performance. Therefore, in this paper, we propose a hybrid hand gesture system that combines an inertial measurement unit (IMU)-based motion capture system and a vision-based gesture system to increase real-time performance. First, IMU-based commands and vision-based commands are divided according to whether drone operation commands are continuously input. Second, IMU-based control commands are intuitively mapped to allow the UAV to move in the same direction by utilizing estimated orientation sensed by a thumb-mounted micro-IMU, and vision-based control commands are mapped with hand’s appearance through real-time object detection. The proposed system is verified in a simulation environment through efficiency evaluation with dynamic gestures of the existing vision-based system in addition to usability comparison with traditional joystick controller conducted for applicants with no experience in manipulation. As a result, it proves that it is a safer and more intuitive HUI design with a 0.089 ms processing speed and average lap time that takes about 19 s less than the joystick controller. In other words, it shows that it is viable as an alternative to existing HUI.

Research and verification on aero-propulsion system acceleration control under supersonic state

Under supersonic acceleration flight, the traditional passive control method brings about acceleration performance deterioration, due to the bad matching between inlet and engine. Accordingly, a real-time optimization control method of the integrated propulsion system is proposed. In the article, the effect of a supersonic inlet on propulsion system performance is analyzed, and an onboard model of the integrated propulsion system is built to calculate the installed parameters. An improved trust region algorithm is adopted to optimize the inlet ramp angle in real time. Besides, digital simulation and hardware-in-the-loop simulation are carried out. The digital simulation result shows that compared with conventional inlet passive control, the acceleration time of the propulsion system is reduced by 8.59%. The result of the hardware-in-the-loop simulation indicates that the proposed method has high real-time performance simultaneously, which proves the engineering application value.

Methodological Study on the Influence of Truck Driving State on the Accuracy of Weigh-in-Motion System

The weigh-in-motion (WIM) system weighs the entire vehicle by identifying the dynamic forces of each axle of the vehicle on the road. The load of each axle is very important to detect the total weight of the vehicle. Different drivers have different driving behaviors, and when large trucks pass through the weighing detection area, the driving state of the trucks may affect the weighing accuracy of the system. This paper proposes YOLOv3 network model as the basis for this algorithm, which uses the feature pyramid network (FPN) idea to achieve multi-scale prediction and the deep residual network (ResNet) idea to extract image features, so as to achieve a balance between detection speed and detection accuracy. In the paper, spatial pyramid pooling (SPP) network and cross stage partial (CSP) network are added to the original network model to improve the learning ability of the convolutional neural network and make the original network more lightweight. Then the detection-based target tracking method with Kalman filtering + RTS (rauch–tung–striebel) smoothing is used to extract the truck driving status information (vehicle trajectory and speed). Finally, the effective size of the vehicle in different driving states on the weighing accuracy is statistically analyzed. The experimental results show that the method has high accuracy and real-time performance in truck driving state extraction, can be used to analyze the influence of weighing accuracy, and provides theoretical support for personalized accuracy correction of WIM system. At the same time, it is beneficial for WIM system to assist the existing traffic system more accurately and provide a highway health management and effective decision making by providing reliable monitoring data.

A New Generation of Hardware-in-the-loop Simulation Technology Combined with High-performance Computers and Digital Twins

Liquid rocket engines are complex equipment with long maintenance cycles and high fault diagnosis costs. Therefore, hardware-in-the-loop simulation combining software and hardware has become the best choice. A hardware-in-the-loop simulation platform framework is proposed based on a V-type development model and related digital twin technology, and the main content of the framework is introduced. Based on the development process of the platform, a certain type of liquid rocket engine is taken as the object to verify the results. The results show that the platform can well simulate the engine changes under different faults, and has versatility and high real-time performance.

A Deep Learning Framework for Video-Based Vehicle Counting

Traffic surveillance can be used to monitor and collect the traffic condition data of road networks, which plays an important role in a wide range of applications in intelligent transportation systems (ITSs). Accurately and rapidly detecting and counting vehicles in traffic videos is one of the main problems of traffic surveillance. Traditional video-based vehicle detection methods, such as background subtraction, frame difference, and optical flow have some limitations in accuracy or efficiency. In this paper, deep learning is applied for vehicle counting in traffic videos. First, to solve the problem of the lack of annotated data, a method for vehicle detection based on transfer learning is proposed. Then, based on vehicle detection, a vehicle counting method based on fusing the virtual detection area and vehicle tracking is proposed. Finally, due to possible situations of missing detection and false detection, a missing alarm suppression module and a false alarm suppression module are designed to improve the accuracy of vehicle counting. The results show that the proposed deep learning vehicle counting framework can achieve lane-level vehicle counting without enough annotated data, and the accuracy of vehicle counting can reach up to 99%. In terms of computational efficiency, this method has high real-time performance and can be used for real-time vehicle counting.

A Design of FPGA-Based Neural Network PID Controller for Motion Control System.

In the actual industrial production process, the method of adaptively tuning proportional–integral–derivative (PID) parameters online by neural network can adapt to different characteristics of different controlled objects better than the controller with PID. However, the commonly used microcontroller unit (MCU) cannot meet the application scenarios of real time and high reliability. Therefore, in this paper, a closed-loop motion control system based on BP neural network (BPNN) PID controller by using a Xilinx field programmable gate array (FPGA) solution is proposed. In the design of the controller, it is divided into several sub-modules according to the modular design idea. The forward propagation module is used to complete the forward propagation operation from the input layer to the output layer. The PID module implements the mapping of PID arithmetic to register transfer level (RTL) and is responsible for completing the output of control amount. The main state machine module generates enable signals that control the sequential execution of each sub-module. The error backpropagation and weight update module completes the update of the weights of each layer of the network. The peripheral modules of the control system are divided into two main parts. The speed measurement module completes the acquisition of the output pulse signal of the encoder and the measurement of the motor speed. The pulse width modulation (PWM) signal generation module generates PWM waves with different duty cycles to control the rotation speed of the motor. A co-simulation of Modelsim and Simulink is used to simulate and verify the system, and a test analysis is also performed on the development platform. The results show that the proposed system can realize the self-tuning of PID control parameters, and also has the characteristics of reliable performance, high real-time performance, and strong anti-interference. Compared with MCU, the convergence speed is far more than three orders of magnitude, which proves its superiority.

Small Object Detection Method Based on Adaptive Spatial Parallel Convolution and Fast Multi-Scale Fusion

As one type of object detection, small object detection has been widely used in daily-life-related applications with many real-time requirements, such as autopilot and navigation. Although deep-learning-based object detection methods have achieved great success in recent years, they are not effective in small object detection and most of them cannot achieve real-time processing. Therefore, this paper proposes a single-stage small object detection network (SODNet) that integrates the specialized feature extraction and information fusion techniques. An adaptively spatial parallel convolution module (ASPConv) is proposed to alleviate the lack of spatial information for target objects and adaptively obtain the corresponding spatial information through multi-scale receptive fields, thereby improving the feature extraction ability. Additionally, a split-fusion sub-module (SF) is proposed to effectively reduce the time complexity of ASPConv. A fast multi-scale fusion module (FMF) is proposed to alleviate the insufficient fusion of both semantic and spatial information. FMF uses two fast upsampling operators to first unify the resolution of the multi-scale feature maps extracted by the network and then fuse them, thereby effectively improving the small object detection ability. Comparative experimental results prove that the proposed method considerably improves the accuracy of small object detection on multiple benchmark datasets and achieves a high real-time performance.

Mechanism of berberine hydrochloride interfering with biofilm formation of Hafnia alvei.

The mechanism of berberine hydrochloride (BBH) inhibiting the biofilm formation of Hafnia alvei was investigated in this study. The antibiofilm potential of BBH was evaluated by confocal laser scanning microscopy (CLSM) and scanning electron microscopy (SEM) as well as crystal violet staining. The quorum-sensing (QS) inhibition was revealed by determination of QS-related genes expression and related signal molecules production using real-time quantitative PCR (RT-qPCR) and high performance liquid chromatography (HPLC). The binding of BBH to receptor proteins was simulated by molecular docking and molecular dynamics simulations. It was found that BBH at sub-minimum inhibitory concentrations (sub-MICs) significantly reduced the biofilm formation of H. alvei in a dose dependent manner. BBH inhibited the bacterial swimming motility, decreased the transcription of halI and halR genes, and reduced the production of signal molecule C14-HSL. It bound to HalR protein mainly through Van der Waals force and electrostatic interaction force. Based on these results, it was concluded that BBH inhibits the biofilm formation of H. alvei and the mechanism is related to its interference with QS through down-regulating the expression of halI and halR genes.