EQGraphNet:Advancing single-station earthquake magnitude estimation via deep graph networks with residual connections

Magnitude estimation is a critical task in seismology,and conventional methods usually require dense seismic station arrays to provide data with sufficient spatiotemporal distribution.In this context,we propose the Earthquake Graph Network(EQGraphNet)to enhance the performance of single-station magnitude estimation.The backbone of the proposed model consists of eleven convolutional neural network layers and ten RCGL modules,where a RCGL combines a Residual Connection and a Graph convolutional Layer capable of mitigating the over-smoothing problem and simultaneously extracting temporal features of seismic signals.Our work uses the STanford EArthquake Dataset for model training and performance testing.Compared with three existing deep learning models,EQGraphNet demonstrates improved accuracy for both local magnitude and duration magnitude scales.To evaluate the robustness,we add natural background noise to the model input and find that EQGraphNet achieves the best results,particularly for signals with lower signal-to-noise ratios.Additionally,by replacing various network components and comparing their estimation performances,we illustrate the contribution of each part of EQGraphNet,validating the rationality of our approach.We also demonstrate the generalization capability of our model across different earthquakes occurring environments,achieving mean errors of±0.1 units.Furthermore,by demonstrating the effectiveness of deeper architectures,this work encourages further exploration of deeper GNN models for both multi-station and single-station magnitude estimation.

Restoring force correction based on online discrete tangent stiffness estimation method for real-time hybrid simulation

In real-time hybrid simulation（RTHS）, it is difficult if not impossible to completely erase the error in restoring force due to actuator response delay using existing displacement-based compensation methods. This paper proposes a new force correction method based on online discrete tangent stiffness estimation（online DTSE） to provide accurate online estimation of the instantaneous stiffness of the physical substructure. Following the discrete curve parameter recognition theory, the online DTSE method estimates the instantaneous stiffness mainly through adaptively building a fuzzy segment with the latest measurements, constructing several strict bounding lines of the segment and calculating the slope of the strict bounding lines, which significantly improves the calculation efficiency and accuracy for the instantaneous stiffness estimation. The results of both computational simulation and real-time hybrid simulation show that：（1） the online DTSE method has high calculation efficiency, of which the relatively short computation time will not interrupt RTHS; and（2） the online DTSE method provides better estimation for the instantaneous stiffness, compared with other existing estimation methods. Due to the quick and accurate estimation of instantaneous stiffness, the online DTSE method therefore provides a promising technique to correct restoring forces in RTHS.

A Real-time Updated Model Predictive Control Strategy for Batch Processes Based on State Estimation

Nonlinear model predictive control(NMPC) is an appealing control technique for improving the performance of batch processes, but its implementation in industry is not always possible due to its heavy on-line computation. To facilitate the implementation of NMPC in batch processes, we propose a real-time updated model predictive control method based on state estimation. The method includes two strategies: a multiple model building strategy and a real-time model updated strategy. The multiple model building strategy is to produce a series of sim-plified models to reduce the on-line computational complexity of NMPC. The real-time model updated strategy is to update the simplified models to keep the accuracy of the models describing dynamic process behavior. The me-thod is validated with a typical batch reactor. Simulation studies show that the new method is efficient and robust with respect to model mismatch and changes in process parameters.

Real-Time Maqam Estimation Model in Max/MSP Configured for the Nāy

Automatic maqam estimation is considered significant toward improving multimedia live music performances and automatic accompaniment. This contribution proposed a real-time maqam estimation model developed in the visual programming language MAX/MSP and configured for the nāydukah. The model’s design stood on basic formulas of Arab music maqamat as explained in theory and applied in practice. The model consisted of different layers of competition;the first was for the identification of the instant tonic of the melodic figure, and the second was for the recognition of its identifying E (E, E half-flat and E flat). Those two competitions were used to estimate the maqam in real-time. Then, accumulated estimation results were used to estimate the maqam in longer durations;five-second and full duration. The model was evaluated using professionally performed nāy improvisations. Results reflected a success in estimating all the studied maqamat when the full improvisation was considered. In addition, results were very good for real-time and five-second estimation where average estimation confidence was 75.98% and 80.04%, respectively.

Analyzing the Impact of Scene Transitions on Indoor Camera Localization through Scene Change Detection in Real-Time

Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.

A NEW HYBRID WAVELET-KALMAN FILTER METHOD FOR THE ESTIMATION OF DYNAMIC SYSTEM

A new hybrid wavelet-Kalman filter method for the estimation of dynamic system is developed, Using this method, the real-time multiscale estimation of the dynamic system is implemented, and the observation equation established is for the object signal itself rather than its wavelet decomposition. The simulation results show that this method can be used to estimate the object's state of the stacked system, which is the foundation of multiscale data fusion; besides the performance of the new algorithm developed in the letter is almost optimal.

FPGA Implementation of Extended Kalman Filter for Parameters Estimation of Railway Wheelset

It is necessary to know the status of adhesion conditions between wheel and rail for efficient accelerating and decelerating of railroad vehicle.The proper estimation of adhesion conditions and their real-time implementation is considered a challenge for scholars.In this paper,the development of simulation model of extended Kalman filter(EKF)in MATLAB/Simulink is presented to estimate various railway wheelset parameters in different contact conditions of track.Due to concurrent in nature,the Xilinx®System-on-Chip Zynq Field Programmable Gate Array(FPGA)device is chosen to check the onboard estimation ofwheel-rail interaction parameters by using the National Instruments(NI)myRIO®development board.The NImyRIO®development board is flexible to deal with nonlinearities,uncertain changes,and fastchanging dynamics in real-time occurring in wheel-rail contact conditions during vehicle operation.The simulated dataset of the railway nonlinear wheelsetmodel is tested on FPGA-based EKF with different track conditions and with accelerating and decelerating operations of the vehicle.The proposed model-based estimation of railway wheelset parameters is synthesized on FPGA and its simulation is carried out for functional verification on FPGA.The obtained simulation results are aligned with the simulation results obtained through MATLAB.To the best of our knowledge,this is the first time study that presents the implementation of a model-based estimation of railway wheelset parameters on FPGA and its functional verification.The functional behavior of the FPGA-based estimator shows that these results are the addition of current knowledge in the field of the railway.

EFFECTS OF ORIGINAL PHASE AND TIME-DELAY ON THE HF CHANNEL PARAMETER ESTIMATION

It is proposed firstly that the original phase and the time-delay are the main factors which affect the measuring resolution of the multitone complex envelope method. The effects of these factors are analysed and checked by the computer simulation. Finally, three possible ways to eliminate these effects are given.

Optimal parameter estimation of open quantum systems

In quantum information technologies,quantum weak measurement is beneficial for protecting coherence of systems.In order to further improve the protection effect of quantum weak measurement on coherence,we propose an optimization scheme of quantum Fisher information(QFI)protection in an open quantum system by combing no-knowledge quantum feedback control with quantum weak measurement.On the basis of solving the dynamic equations of a stochastic two-level quantum system under feedback control,we compare the effects of different feedback Hamiltonians on QFI and find that via no-knowledge quantum feedback,the observation operatorσx(orσx andσz)can protect QFI for a long time.Namely,no-knowledge quantum feedback can improve the estimation precision of feedback coefficient as well as that of detection coefficient.

A Bayesian Approach to Seismic Hazard Estmation: Maximum Values of Magnitudes and Peak Ground Accelerations

A rather simple straightforward procedure of estimating maximum values of the considered parameter (earthquake magnitude in a given region or seismic peak ground acceleration at the considered site) and quantiles of its probabilistic distribution in a future time interval of a given length is presented. To assess the peak ground acceleration using this method, the input information is the earthquake catalog and the regressive relation where the peak seismic acceleration at a given point bears the magnitude and epicentral distance of the site considered (seismic attenuation law). The method is based on the Bayesian approach, in which the influence of uncertainties of magnitudes and seismic acceleration values can be taken into account. The main assumptions for the method are the Poissonian character of the seismic event flow, a frequency-magnitude law of Gutenberg-Richter’s type with a cutoff maximum value for the estimated parameter, and an earthquake catalog that has a rather large number of events. The method has been applied to seismic hazard estimation in California, the Balkans, and Japan.

Real-time prediction of earthquake potential damage:A case study for the January 8,2022 M_(S) 6.9 Menyuan earthquake in Qinghai,China

It is critical to determine whether a site has potential damage in real-time after an earthquake occurs,which is a challenge in earthquake disaster reduction.Here,we propose a real-time Earthquake Potential Damage predictor(EPDor)based on predicting peak ground velocities(PGVs)of sites.The EPDor is composed of three parts:(1)predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models;(2)predicting the PGVs at distant sites based on the empirical ground motion prediction equation;(3)generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in(1)and(2).We apply the EPDor to the 2022 M_(S) 6.9 Menyuan earthquake in Qinghai Province,China to predict its potential damage.Within the initial few seconds after the first station is triggered,the EPDor can determine directly whether there is potential damage for some sites to a certain degree.Hence,we infer that the EPDor has potential application for future earthquakes.Meanwhile,it also has potential in Chinese earthquake early warning system.

Distributed Real-time State Estimation for Combined Heat and Power Systems

This paper proposes a distributed real-time state estimation(RTSE)method for the combined heat and power systems(CHPSs).First,a difference-based model for the heat system is established considering the dynamics of heat systems.This heat system model is further used along with the power system steady-state model for holistic CHPS state estimation.A cubature Kalman filter(CKF)-based RTSE is developed to deal with the system nonlinearity while integrating both the historical and present measurement information.Finally,a multi-timescale asynchronous distributed computation scheme is designed to enhance the scalability of the proposed method for largescale systems.This distributed implementation requires only a small amount of information exchange and thus protects the privacy of different energy systems.Simulations carried out on two CHPSs show that the proposed method can significantly improve the estimation efficiency of CHPS without loss of accuracy compared with other existing models and methods.

Real-Time Facial Pose Estimation and Tracking by Coarse-to-Fine Iterative Optimization

We present a novel and efficient method for real-time multiple facial poses estimation and tracking in a single frame or video.First,we combine two standard convolutional neural network models for face detection and mean shape learning to generate initial estimations of alignment and pose.Then,we design a bi-objective optimization strategy to iteratively refine the obtained estimations.This strategy achieves faster speed and more accurate outputs.Finally,we further apply algebraic filtering processing,including Gaussian filter for background removal and extended Kalman filter for target prediction,to maintain real-time tracking superiority.Only general RGB photos or videos are required,which are captured by a commodity monocular camera without any priori or label.We demonstrate the advantages of our approach by comparing it with the most recent work in terms of performance and accuracy.

A new real-time algorithm for off-road terrain estimation using laser data

Gaussian mixture algorithm （GMA） is an effective approach for off-road terrain estimation, but still suffers from some difficulties in practical applications, such as complex calculation and object abstraction. In this paper, GMA is modified to improve its real-time performance and to provide it with a potential ability of obstacle detection. First, a selection window is designed based on the dominant-ellipse-principle to limit the probability distribution area of each measurement point, therefore avoiding the calculation on the cells outside the dominant ellipse. Second, a clustering approach is proposed in order to distinguish objects efficiently and decrease the operation area of one laser scan. Third, a virtual point vector is introduced to further reduce the computational load of the mean square error matrix. The modified GMA is experimented on a tracked mobile robot, and its improved performance is shown in comparison to the original GMA.

A square root information filter for multi-GNSS real-time precise clock estimation

Real-time satellite orbit and clock estimations are the prerequisite for Global Navigation Satellite System(GNSS)real-time precise positioning services.To meet the high-rate update requirement of satellite clock corrections,the computational efficiency is a key factor and a challenge due to the rapid development of multi-GNSS constellations.The Square Root Information Filter(SRIF)is widely used in real-time GNSS data processing thanks to its high numerical stability and computational efficiency.In real-time clock estimation,the outlier detection and elimination are critical to guarantee the precision and stability of the product but could be time-consuming.In this study,we developed a new quality control procedure including the three standard steps:i.e.,detection,identification,and adaption,for real-time data processing of huge GNSS networks.Effort is made to improve the computational efficiency by optimizing the algorithm to provide only the essential information required in the processing,so that it can be applied in real-time and high-rate estimation of satellite clocks.The processing procedure is implemented in the PANDA(Positioning and Navigation Data Analyst)software package and evaluated in the operational generation of real-time GNSS orbit and clock products.We demonstrated that the new algorithm can efficiently eliminate outliers,and a clock precision of 0.06 ns,0.24 ns,0.06 ns,and 0.11 ns can be achieved for the GPS,GLONASS,Galileo,and BDS-2 IGSO/MEO satellites,respectively.The computation time per epoch is about 2 to 3 s depending on the number of existing outliers.Overall,the algorithm can satisfy the IGS real-time clock estimation in terms of both the computational efficiency and product quality.

Determining the time and space domains forestimating b value in seismic zoning

To take the seismic zone that includes the great shock with M S8.5 as the statistical unit of estimating b value can often lead to more large variance, because the seismogenic zone of the great shock with M S8.5 are larger than that delineated in general seismic zone. Two-level statistical units are considered in this paper. The seismic province is the first level unit that is suitable for group of earthquakes including the great shock of M S8.5. A seismic province can be divided into several seismic zones. They can be taken as the second level unit for group of quakes in which the super magnitude of the greatest shock do not exceed 8. Because of the nonstationarity in time of seismic activity, the unbalancedness of data and differential of seismic temporal series feature in different areas need to be considered when we select the time period for estimating b value. According to local conditions, the time period is selected at one′s discretion in order to reflect seismicity level of this statistical unit in future 100 years.

Physical background on estimating bvalue

The G R relation lg N=a-bM( 1954)is an empirical formula used widely in the seismicity research. But the linearity of b curves has great difference in different time and space domains. An interested question in this paper is that in how large a space time strength domain the b value has certain physical connotation. This study told us that we can get optimal statistical results of b value in those space time domains which can develop correspondent strong shocks with magnitude interval( M S≥8.5, 8.0≤ M S<8.5, 7.0≤ M S<8.0). Thus, the possible seismogenic areas in which strong shocks with different magnitude intervals develop can be inferred in different regions of the mainland of China. Finally, some new problems are proposed, such as the delimitation of seismic province, the seismicity parameter determination in seismic hazard analysis and in earthquake predictions by using b value.

A Real-Time Multi-Stage Architecture for Pose Estimation of Zebrafish Head with Convolutional Neural Networks

In order to conduct optical neurophysiology experiments on a freely swimming zebrafish,it is essential to quantify the zebrafish head to determine exact lighting positions.To efficiently quantify a zebrafish head's behaviors with limited resources,we propose a real-time multi-stage architecture based on convolutional neural networks for pose estimation of the zebrafish head on CPUs.Each stage is implemented with a small neural network.Specifically,a light-weight object detector named Micro-YOLO is used to detect a coarse region of the zebrafish head in the first stage.In the second stage,a tiny bounding box refinement network is devised to produce a high-quality bounding box around the zebrafish head.Finally,a small pose estimation network named tiny-hourglass is designed to detect keypoints in the zebrafish head.The experimental results show that using Micro-YOLO combined with RegressNet to predict the zebrafish head region is not only more accurate but also much faster than Faster R-CNN which is the representative of two-stage detectors.Compared with DeepLabCut,a state-of-the-art method to estimate poses for user-defined body parts,our multi-stage architecture can achieve a higher accuracy,and runs 19x faster than it on CPUs.

Real-time urban traffic information estimation with a limited number of surveillance cameras

Constant traffic congestion consumes enormous amounts of energy and causes vastly increased journey times. Therefore, real-time traffic information is of great importance to the public because such information is invaluable to more efficient traffic control and travel planning. To obtain such information in metropolises like Shanghai, however, is very challenging due to the extraordinarily large scale and com- plexity of the underlying road network. In this paper, we pro- pose a novel traffic estimation scheme utilizing surveillance cameras pervasively deployed in cities. With only a limited number of roads with cameras, we adopt a measurement- based traffic matrix （TM） estimation method to infer the traf- fic conditions on those roads with no cameras. Extensively trace-driven simulations as well as field study results show that our scheme can achieve high accuracy with a very limited number of measurements. The accuracy of our measurement- based algorithm outperforms the traditional speed-based and model-based approaches by up to 50%.

基于地震P波初至2 s功率信息的高速铁路地震预警系统快速震级估算方法

震级估算是高速铁路地震预警系统的关键技术参数,更加快速、准确的震级估算模型能够更好地保障人民的生命财产安全。利用日本K-net强震动数据,建立基于地震P波到达后携带功率信息的地震动衰减模型并用于震级估算,并将本文算法与传统算法对比。结果表明,在1~5 s的时间窗下,模型的震级估算误差均明显小于传统的方法,且小震高估现象也明显改善;随着时窗长度的增加,模型的震级估算误差及标准差也逐渐降低,实现率也逐步提升,在1 s的时窗长度下,模型的单台震级估算实现率满足规范要求;对7级以下地震,模型的震级估算实现率可在地震P波到达1 s后满足规范要求;对7级以上地震,模型的震级估算实现率可以在地震P波到达2 s后满足规范要求。