Seismic waveform modeling is a powerful tool for determining earth structure models and unraveling earthquake rupture processes, but it is usually computationally expensive. We introduce a scheme to vastly accelerate these calculations with a recently developed machine learning paradigm called the neural operator. Once trained, these models can simulate a full wavefield at negligible cost. We use a U-shaped neural operator to learn a general solution operator to the 2D elastic wave equation from an ensemble of numerical simulations performed with random velocity models and source locations. We show that full waveform modeling with neural operators is nearly two orders of magnitude faster than conventional numerical methods, and more importantly, the trained model enables accurate simulation for velocity models, source locations, and mesh discretization distinctly different from the training dataset. The method also enables convenient full-waveform inversion with automatic differentiation.
Abstract Human ether‐a‐go‐go‐related gene (hERG) K+ channel blockage may cause severe cardiac side‐effects and has become a serious issue in safety evaluation of drug candidates. Therefore, improving the ability to avoid undesirable hERG activity in the early stage of drug discovery is of significant importance. The purpose of this study was to build predictive models of hERG activity by deep neural networks. For each combination of sampling methods and descriptors, deep neural networks with different architectures were implemented to build classification models. The optimal model M15 with three hidden layers, undersampling method, and 2D descriptors yielded the prediction accuracy of 0.78 and F1 score of 0.75 on the test set as well as accuracy of 0.77 and F1 score of 0.34 on the external validation set, outperforming the other 35 models including 9 random forest models. Particularly, the optimal model M15 achieved the highest F1 score and the second highest accuracy when compared with other five methods from four groups using different machine learning algorithms with the same external validation set. It can be believed that this model has powerful capability on prediction of hERG toxicity, which is of great benefit for developing novel drug candidates.
Because the negative pressure caused by oil pipeline leak wave propagation to the monitoring point of leak point of the upstream and downstream,may make the point pressure signal to produce a larger shocking,with the shock curve it will produce some noise.Contrary to this phenomenon,getting pressure signal collected by pipeline monitoring sites,combining wavelet transform and median filtering method,the denoising simulation experiments under in the MATLAB software surrounding are carried out,the conclusion are made that the method can remove the interference in negative pressure wave signal well.
In the waveform design, the distance measurement and resolution are a pair of irreconcilable contradictions. Linear Frequency Modulation (LFM) can alleviate this contradiction. LFM is widely used in radar and sonar, however, its Doppler tolerance is not ideal. Hyperbolic Frequency Modulation (HFM) signal has a particularly strong tolerance towards Doppler frequency shift. When the unidirectionally modulated HFM signal is in distance measurement, the Doppler delay of the matched filtering output cannot be eliminated, and there is a ranging error. After matched filtering of the positive and negative frequency modulation (HFM+LFM) echo signal based on the same frequency band, the Doppler-induced delay is the same but opposite in direction, and the delay is closely related to the frequency, bandwidth, and pulse width of the transmitted signal. By using the inverse time delay difference of the positive and negative frequency modulation, the ranging error in the ranging of unidirectionally modulated LFM signal can be eliminated. In this paper, a Joint Linear frequency modulation and Hyperbolic frequency modulation approach for Speed measurement (JLHS) is proposed, which employs the same frequency band of positive and negative frequency modulation signals for speed measurement and ranging. Extensive simulation results show that the proposed approach can better estimate the speed and distance of moving targets, and it has reference value for engineering application.
Considering the problem of poor tracking accuracy and particle degradation in the traditional particle filter algorithm,discussed a new improved particle filter algorithm with the Markov chain Monte Carlo(MCMC) and extended particle filter.The algorithm used extend Kalman filter to generate a proposal distribution,which could integrate latest observation information to get the posterior probability distribution that was more in line with the true state.Meanwhile,optimized the algorithm by MCMC sampling method,which made the particles more diverse.The simulation results show that the improved extend Kalman particle filter solves particle degradation effectively and improves tracking accuracy.
at the new time,youth self-organization's type and form presents diversified trend.Flat and network structure are more popular and fast developed in our society.This article take Chongqing for example,adopt questionnaire survey and case interview in order to know basic information of youth self-organization member,activity content and operational mode.This article analyzes various kinds of Influencing factors,which block the development of youth self-organization.And give some countermeasures and suggestions on the following three aspects:to promote youth ability on self organization,to strengthen guidance and management from Youth League,to provide guarantee from law and policy.Promoting development of youth self-organization in a healthy and Sustainable way is the final objective of this article.
The stage on the gate of Heilong Temple of an ancient town in Linxian's Qikou of Shanxi has three kinds of acoustic effects: difference between the inside and outside of the cave; no great effort is needed in singing on this stage; in Shaanxi can hear people who sing on this stage in Shanxi. Through on- the- spot investigation,using acoustic theory of voices' direction,reflection,and resonance and so on,we discuss and analyze the acoustic effects of the stage on the gate of Heilong Temple from three perspectives: sound origin,sound transmission and reception. In this paper,we think thatsound difference between the inside and outside of the caveis the manifestation of sound convergence,sound resonance and sound transmission of the cave in the temple; no more effort is needed in singing on this stageis a reflection of the temple's sound reverberation; and in Shaanxi can hear people who sing on this stage in Shanxiis the acoustic effect formed under the combining influences of the structure of the temple and its environment.
Let T=U|T|be the polar decomposition of a bounded linear operator T on a Hilbert space.The transformation T■=|T|~(1/2)U|T|~(1/2)is called the Aluthge transformation and■means the n-th Aluthge transformation.Similarly,the transformation■~(*)=|T~*|~(1/2)U|T~*|~(1/2)is called the *-Aluthge transformation and■_n~((*))means the n-th *-Aluthge transformation.In this paper,firstly,we show that ■~((*))=UV|■~((*))| is the polar decomposition of■~((*)),where |T|~(1/2)|T~*|~(1/2)=V||[T|~(1/2)|T~*|~(1/2)|is the polar decomposition.Secondly,we show that■~((*))=U|~((*))| if and only if T is binormal,i.e.,[|T|,|T~*|]=0, where[A,B]=AB-BA for any operator A and B.Lastly,we show that■~((*))is binormal for all non-negative integer n if and only if T is centered,and so on.
The main characters in D.H.Lawrence's novel Sons and Lovers can be regarded as symbols standing for different emotions.The characteristics of these symbols and the semiosis of the characters reveal both the surface structure of the novel and the cause of the tragedy in the novel.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)