Micro-seismic monitoring is one of the most critical technologies that guide hydraulic fracturing in hot dry rock resource development. Micro-seismic monitoring requires high precision detection of micro-seismic event...Micro-seismic monitoring is one of the most critical technologies that guide hydraulic fracturing in hot dry rock resource development. Micro-seismic monitoring requires high precision detection of micro-seismic events with a low signal-to-noise ratio. Because of this requirement, we propose a recurrent neural network model named gated recurrent unit and support vector machine(GRU;VM). The proposed model ensures high accuracy while reducing the parameter number and hardware requirement in the training process. Since micro-seismic events in hot dry rock produce large wave amplitudes and strong vibrations, it is difficult to reverse the onset of each individual event. In this study, we utilize a support vector machine(SVM) as a classifier to improve the micro-seismic event detection accuracy. To validate the methodology, we compare the simulation results of the short-term-average to the long-term-average(STA/LTA) method with GRU;VM method by using hot dry rock micro-seismic event data in Qinghai Province, China. Our proposed method has an accuracy of about 95% for identifying micro-seismic events with low signal-to-noise ratios. By ignoring smaller micro-seismic events, the detection procedure can be processed more efficiently, which is able to provide a real-time observation on the types of hydraulic fracturing in the reservoirs.展开更多
A program of adaptive quadrature demodulation is proposed to supply the gaps in the traditional analog detection technology of a silicon micro-machined gyroscope (SMG). This program is suitable for digital phase locke...A program of adaptive quadrature demodulation is proposed to supply the gaps in the traditional analog detection technology of a silicon micro-machined gyroscope (SMG). This program is suitable for digital phase locked loop (DPLL) drive technology that proposed in other papers. In addition the program adopts an adaptive filtering algorithm, which selects the in-phase and quadrature components that are outputs of the DPLL of the SMG's drive mode as reference signals to update the amplitude of the in-phase and quadrature components of the input signal by iteratively. An objective of the program is to minimize the mean square error of the accurate amplitudes and the estimated amplitudes of SMG's detection mode. The simulation and test results prove the feasibility of the program that lays the foundation for the further improvement of the SMG's system performance and the implementation of the SMG system's self-calibration and self-demarcation in future.展开更多
Conductive cementitious composites are innovated materials that have improved electrical conductivity compared to general types of cement,and are expected to be used in a variety of future infrastructures with unique ...Conductive cementitious composites are innovated materials that have improved electrical conductivity compared to general types of cement,and are expected to be used in a variety of future infrastructures with unique functionalities such as self-heating,electromagnetic shielding,and piezoelectricity.In the present study,machine learning methods that have been recently applied in various fields were proposed for the prediction of piezoelectric characteristics of carbon nanotubes(CNTs)-incorporated cement composites.Data on the resistivity change of CNTs/cement composites according to various water/binder ratios,loading types,and CNT content were considered as training values.These data were applied to numerous machine learning techniques including linear regression,decision tree,support vector machine,deep belief network,Gaussian process regression,genetic algorithm,bagging ensemble,random forest ensemble,boosting ensemble,long short-term memory,and gated recurrent units to estimate the time-independent and-dependent electrical properties of conductive cementitious composites.By comparing and analyzing the computed results of the proposed methods,an optimal algorithm suitable for application to CNTs-embedded cementitious composites was derived.展开更多
在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和...在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.展开更多
In recent years,machine learning(ML)and deep learning(DL)have significantly advanced intrusion detection systems,effectively addressing potential malicious attacks across networks.This paper introduces a robust method...In recent years,machine learning(ML)and deep learning(DL)have significantly advanced intrusion detection systems,effectively addressing potential malicious attacks across networks.This paper introduces a robust method for detecting and categorizing attacks within the Internet of Things(IoT)environment,leveraging the NSL-KDD dataset.To achieve high accuracy,the authors used the feature extraction technique in combination with an autoencoder,integrated with a gated recurrent unit(GRU).Therefore,the accurate features are selected by using the cuckoo search algorithm integrated particle swarm optimization(PSO),and PSO has been employed for training the features.The final classification of features has been carried out by using the proposed RF-GNB random forest with the Gaussian Naïve Bayes classifier.The proposed model has been evaluated and its performance is verified with some of the standard metrics such as precision,accuracy rate,recall F1-score,etc.,and has been compared with different existing models.The generated results that detected approximately 99.87%of intrusions within the IoT environments,demonstrated the high performance of the proposed method.These results affirmed the efficacy of the proposed method in increasing the accuracy of intrusion detection within IoT network systems.展开更多
基金supported by National Key R&D Program of China(Grant No.2018YFB1501803,2019YFC1804805-4)China Geological Survey Project(Grant No.DD2019135)。
文摘Micro-seismic monitoring is one of the most critical technologies that guide hydraulic fracturing in hot dry rock resource development. Micro-seismic monitoring requires high precision detection of micro-seismic events with a low signal-to-noise ratio. Because of this requirement, we propose a recurrent neural network model named gated recurrent unit and support vector machine(GRU;VM). The proposed model ensures high accuracy while reducing the parameter number and hardware requirement in the training process. Since micro-seismic events in hot dry rock produce large wave amplitudes and strong vibrations, it is difficult to reverse the onset of each individual event. In this study, we utilize a support vector machine(SVM) as a classifier to improve the micro-seismic event detection accuracy. To validate the methodology, we compare the simulation results of the short-term-average to the long-term-average(STA/LTA) method with GRU;VM method by using hot dry rock micro-seismic event data in Qinghai Province, China. Our proposed method has an accuracy of about 95% for identifying micro-seismic events with low signal-to-noise ratios. By ignoring smaller micro-seismic events, the detection procedure can be processed more efficiently, which is able to provide a real-time observation on the types of hydraulic fracturing in the reservoirs.
文摘A program of adaptive quadrature demodulation is proposed to supply the gaps in the traditional analog detection technology of a silicon micro-machined gyroscope (SMG). This program is suitable for digital phase locked loop (DPLL) drive technology that proposed in other papers. In addition the program adopts an adaptive filtering algorithm, which selects the in-phase and quadrature components that are outputs of the DPLL of the SMG's drive mode as reference signals to update the amplitude of the in-phase and quadrature components of the input signal by iteratively. An objective of the program is to minimize the mean square error of the accurate amplitudes and the estimated amplitudes of SMG's detection mode. The simulation and test results prove the feasibility of the program that lays the foundation for the further improvement of the SMG's system performance and the implementation of the SMG system's self-calibration and self-demarcation in future.
文摘Conductive cementitious composites are innovated materials that have improved electrical conductivity compared to general types of cement,and are expected to be used in a variety of future infrastructures with unique functionalities such as self-heating,electromagnetic shielding,and piezoelectricity.In the present study,machine learning methods that have been recently applied in various fields were proposed for the prediction of piezoelectric characteristics of carbon nanotubes(CNTs)-incorporated cement composites.Data on the resistivity change of CNTs/cement composites according to various water/binder ratios,loading types,and CNT content were considered as training values.These data were applied to numerous machine learning techniques including linear regression,decision tree,support vector machine,deep belief network,Gaussian process regression,genetic algorithm,bagging ensemble,random forest ensemble,boosting ensemble,long short-term memory,and gated recurrent units to estimate the time-independent and-dependent electrical properties of conductive cementitious composites.By comparing and analyzing the computed results of the proposed methods,an optimal algorithm suitable for application to CNTs-embedded cementitious composites was derived.
文摘在机器阅读理解任务中,如何在包含不可回答问题的情况下提高答案的准确性是自然语言处理领域的一项重要挑战.虽然基于深度学习的机器阅读理解模型展现出很好的性能,但是这些模型仍然存在抽取特征冗余、语义信息不全面、问题分类任务和答案抽取任务耦合性不强的问题.为了解决以上问题,本文提出一种结合门控机制和多级残差结构的多任务联合训练模型GMRT(Gated Mechanism and Multi-level Residual Structure for Multi-task Joint Training),以提升机器阅读理解任务中答案预测的准确性.GMRT构建门控机制来筛选交互后的关联特征,从而控制信息的流动.采用多级残差结构分别连接注意力机制和门控机制,保证每个阶段都保留原始语义信息.同时,通过边缘损失函数对问题分类任务和答案抽取任务联合训练,确保预测答案过程中任务之间的强耦合性.在SQuAD2.0数据集上的实验结果表明,GMRT模型的EM值和F1值均优于对比模型.
基金the Deanship of Scientific Research at Shaqra University for funding this research work through the project number(SU-ANN-2023051).
文摘In recent years,machine learning(ML)and deep learning(DL)have significantly advanced intrusion detection systems,effectively addressing potential malicious attacks across networks.This paper introduces a robust method for detecting and categorizing attacks within the Internet of Things(IoT)environment,leveraging the NSL-KDD dataset.To achieve high accuracy,the authors used the feature extraction technique in combination with an autoencoder,integrated with a gated recurrent unit(GRU).Therefore,the accurate features are selected by using the cuckoo search algorithm integrated particle swarm optimization(PSO),and PSO has been employed for training the features.The final classification of features has been carried out by using the proposed RF-GNB random forest with the Gaussian Naïve Bayes classifier.The proposed model has been evaluated and its performance is verified with some of the standard metrics such as precision,accuracy rate,recall F1-score,etc.,and has been compared with different existing models.The generated results that detected approximately 99.87%of intrusions within the IoT environments,demonstrated the high performance of the proposed method.These results affirmed the efficacy of the proposed method in increasing the accuracy of intrusion detection within IoT network systems.
