Controlled-source electromagnetic method (CSEM) signals are inevitably contaminated by man-made noises. For this reason, a new CSEM data processing method was proposed. First, the 50 Hz powerline interference was remo...
详细信息
Controlled-source electromagnetic method (CSEM) signals are inevitably contaminated by man-made noises. For this reason, a new CSEM data processing method was proposed. First, the 50 Hz powerline interference was removed by FFT method, followed by the CEEMD method to remove baseline drift, and finally the correlation analysis method was used to select the high-quality signal. The method was applied to the processing of measured data in Huidong, Sichuan. As a conclusion, the presented method can effectively remove the strong cultural noise from raw CSEM data and preserve the useful signal completely; the apparent resistivity curves acquired by using the filtered data are improved significantly upon the previous.
Traditional machine learning algorithms cannot adequately train the parameters of networks using massive data. A deep convolutional neural network based on multi-parameter optimization by the TensorFlow deep learning ...
详细信息
The traditional single-channel speech enhancement algorithm has many unreasonable assumptions, which limit the performance of the algorithm. The speech enhancement based on deep neural network can effectively eliminat...
The traditional single-channel speech enhancement algorithm has many unreasonable assumptions, which limit the performance of the algorithm. The speech enhancement based on deep neural network can effectively eliminate the problems such as 'music noise' in the traditional methods, thus achieving better results than the traditional single-channel speech enhancement. However, the DNN-based speech enhancement model does not perform well at low SNR. In order to improve the robustness of the model, we used voice activity detection (VAD) to process the training data to obtain a new VAD-DNN speech enhancement model. We added 100 kinds of noise in the training set to improve the ability of the model to deal with the unseen noise. At the same time, in order to prevent the occurrence of overfitting problem, we introduced dropout technology to process the network, and improved the generalization ability of the model by using noise awareness training (NAT). Through experiments, we found that the speech enhancement model based on VAD-DNN improved PESQ index by 0.02 and STOI index by 0.01 on average under the condition of low SNR.
As an emerging method for monitoring and prediction of seismic underground fluid, the reliability and stability of in-situ online monitoring devices for soil radon are crucial performance indicators that are directly ...
详细信息
The application of bigdata has penetrated into many fields of society, and the education industry is no exception. In this paper, we try to collect and analyze the data related to teaching activities, use data mining...
The application of bigdata has penetrated into many fields of society, and the education industry is no exception. In this paper, we try to collect and analyze the data related to teaching activities, use data mining technology to construct a mathematical model of the corresponding large teaching data, explore the relationship between representation and substance, provide useful information support for teaching activities, promote and help improve the quality of teaching, and verify the proposed mathematical model through experimental analysis. Better analysis results.
At present, the laboratory management system of most universities lacks functions and expansibility, so it cannot be adapted to laboratories with high degree of customization. Based on the analysis of the past experie...
At present, the laboratory management system of most universities lacks functions and expansibility, so it cannot be adapted to laboratories with high degree of customization. Based on the analysis of the past experience of the laboratory management system in colleges and universities, this paper explores the construction of a comprehensive system suitable for the appointment management of laboratory equipment in colleges and universities. The system adopts Java Web related technology, Web database interaction technology and B/S architecture to form a modular structure with complete functions and flexible management. The construction of the system has realized the standardization, process and integration management of university laboratories, and promoted the effective utilization of university laboratory equipment in colleges and universities.
This paper introduces a whole project of augmented reality interaction mode based on netty communication method, determines the main technical difficulties in the implementation process, and finds the solution by mean...
This paper introduces a whole project of augmented reality interaction mode based on netty communication method, determines the main technical difficulties in the implementation process, and finds the solution by means of system architecture design and communication protocol development. In this paper, the netty framework is adopted to deal with network IO and business logic, and the communication between each terminal device, virtual environment and server is established through long connection, This paper adopts the netty framework to deal with network IO and business logic, establishes communication between each terminal device and virtual environment and server through long connection, so as to realize fast and natural real-time interaction between various interactive devices and other augmented reality devices and virtual environments under multiple users. It can also solve the problem of high concurrency of real-time communication between various devices and the virtual environment in augmented reality.
Neutron logging is a method of measuring uranium fission neutrons by bombarding uranium in ore beds with neutrons emitted by neutron sources or neutron generators. The pulsed neutron logging technology of uranium ore ...
Neutron logging is a method of measuring uranium fission neutrons by bombarding uranium in ore beds with neutrons emitted by neutron sources or neutron generators. The pulsed neutron logging technology of uranium ore has been popularized and applied in the United States, Russia, Australia and other countries. The key technology is almost monopolized by these countries, but the technology is prohibited in China. In the field of uranium logging, natural gamma logging has always been used in China for uranium quantification, which is characterized by large error, low efficiency, high cost and technical and economic bottlenecks. Due to the fact that the research and application of pulsed neutron log in the field of petroleum exploration and production is relatively mature in China, it is urgent to develop relevant logging instruments and uranium quantitative interpretation methods as independent intellectual property rights. This will lead to a change in the backward appearance of uranium logging. This paper analyzes the research status and development trend of neutron logging in uranium at home and abroad.
暂无评论