Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is cr...Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.展开更多
The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional ch...The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional channel estimation methods do not always yield reliable estimates. The methodology of this paper consists of deep residual shrinkage network (DRSN)neural network-based method that is used to solve this problem.Thus, the channel estimation approach, based on DRSN with its learning ability of noise-containing data, is first introduced. Then,the DRSN is used to train the noise reduction process based on the results of the least square (LS) channel estimation while applying the pilot frequency subcarriers, where the initially estimated subcarrier channel matrix is considered as a three-dimensional tensor of the DRSN input. Afterward, a mixed signal to noise ratio (SNR) training data strategy is proposed based on the learning ability of DRSN under different SNRs. Moreover, a joint mixed scenario training strategy is carried out to test the multi scenarios robustness of DRSN. As for the findings, the numerical results indicate that the DRSN method outperforms the spatial-frequency-temporal convolutional neural networks (SF-CNN)with similar computational complexity and achieves better advantages in the full SNR range than the minimum mean squared error (MMSE) estimator with a limited dataset. Moreover, the DRSN approach shows robustness in different propagation environments.展开更多
To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network ...To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network inputs are the apparent resistivities of known models,and the outputs are the model parameters.The optimal network structure is achieved by determining the numbers of hidden layers and network nodes.Secondly,the learning process of the DBN is implemented to obtain the optimal solution of network connection weights for known geoelectric models.Finally,the trained DBN is verified through inversion tests,in which the network inputs are the apparent resistivities of unknown models,and the outputs are the corresponding model parameters.The experiment results show that the DBN can make full use of the global searching capability of the restricted Boltzmann machine(RBM)unsupervised learning and the local optimization of the back propagation(BP)neural network supervised learning.Comparing to the traditional neural network inversion,the calculation accuracy and stability of the DBN for MT data inversion are improved significantly.And the tests on synthetic data reveal that this method can be applied to MT data inversion and achieve good results compared with the least-square regularization inversion.展开更多
With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and th...With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.展开更多
A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spect...A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.展开更多
Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face ...Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions.This paper presents an effective DOA estimation approach based on a deep residual network(DRN)for the underdetermined case.We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays.We then provide the input feature to the trained DRN to construct the super resolution spectrum.The DRN learns the mapping relationship between the input feature and the spatial spectrum by training.The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency,independence of source sparseness and adaptive capacity to non-ideal conditions(e.g.,low signal to noise ratio,short bit sequence).Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.展开更多
An enhanced algorithm is proposed to recognize multi-channel electromyography(EMG) patterns using deep belief networks(DBNs). It is difficult to classify the EMG features because an EMG signal has nonlinear and time-v...An enhanced algorithm is proposed to recognize multi-channel electromyography(EMG) patterns using deep belief networks(DBNs). It is difficult to classify the EMG features because an EMG signal has nonlinear and time-varying characteristics.Therefore, in several previous studies, various machine-learning methods have been applied. A DBN is a fast, greedy learning algorithm that can find a fairly good set of weights rapidly, even in deep networks with a large number of parameters and many hidden layers. To evaluate this model, we acquired EMG signals, extracted their features, and then compared the model with the DBN and other conventional classifiers. The accuracy of the DBN is higher than that of the other algorithms. The classification performance of the DBN model designed is approximately 88.60%. It is 7.55%(p=9.82×10-12) higher than linear discriminant analysis(LDA) and 2.89%(p=1.94×10-5) higher than support vector machine(SVM). Further, the DBN is better than shallow learning algorithms or back propagation(BP), and this model is effective for an EMG-based user-interfaced system.展开更多
It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly eval...It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.展开更多
Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of...Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.展开更多
Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention an...Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention and control measures.The self-potential(SP)stands out for its sensitivity to contamination plumes,offering a solution for monitoring and detecting the movement and seepage of subsurface pollutants.However,traditional SP inversion techniques heavily rely on precise subsurface resistivity information.In this study,we propose the Attention U-Net deep learning network for rapid SP inversion.By incorporating an attention mechanism,this algorithm effectively learns the relationship between array-style SP data and the location and extent of subsurface contaminated sources.We designed a synthetic landfill model with a heterogeneous resistivity structure to assess the performance of Attention U-Net deep learning network.Additionally,we conducted further validation using a laboratory model to assess its practical applicability.The results demonstrate that the algorithm is not solely dependent on resistivity information,enabling effective locating of the source distribution,even in models with intricate subsurface structures.Our work provides a promising tool for SP data processing,enhancing the applicability of this method in the field of near-subsurface environmental monitoring.展开更多
A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monito...A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.展开更多
为在稀疏测点超孔隙水压力数据条件下预测饱和软土的固结行为,引入物理信息深度算子网络(physics-informed deep operator network,PI-DeepONet)方法,并利用稀疏孔隙水压力测点数据对饱和土体全域内超孔隙水压力分布进行实时预测。通过...为在稀疏测点超孔隙水压力数据条件下预测饱和软土的固结行为,引入物理信息深度算子网络(physics-informed deep operator network,PI-DeepONet)方法,并利用稀疏孔隙水压力测点数据对饱和土体全域内超孔隙水压力分布进行实时预测。通过分析常规黏土变形固结及软弱黏土大变形固结2个实例进行预测,引入相对L2误差和R2这2个评估指标,验证了PI-DeepONet算法在预测全域超孔隙水压力演化方面的性能,并与纯数据驱动的DeepONet算法的计算结果进行了对比。预测结果表明:在相同的测点数目和各测点拥有相同超孔隙水压力数据量的条件下,DeepONet算法对全域超孔隙水压力的预测绝对误差在10^(-2)~10^(-1)左右,而PI-DeepONet算法的绝对误差范围则在10^(−3)~10^(-2)左右,表现出更好的预测效果。其次,在常规黏土变形固结行为研究中,通过对超孔隙水压力数据添加3种不同噪声水平来模拟现场监测环境,观察到即使噪声水平达到5%,PI-DeepONet算法仍能在水压力数据稀疏且带噪声的条件下提供高质量的全域超孔隙水压力实时预测。最后,在软弱黏土大变形固结行为研究中,将PI-DeepONet算法运用于上下边界排水速率不同的固结问题中,发现训练好的一维模型在单一测点条件下,能对其他界面参数条件下饱和土体全域内超孔隙水压力分布规律进行准确预测,表明PIDeepONet算法能为岩土工程中相关问题提供新的解决办法。展开更多
基金supported by the HFIPS Director’s Foundation(YZJJ202207-TS),the National Natural Science Foundation of China(82371931)the Natural Science Foundation of Anhui Province(2008085MC69)+3 种基金the Natural Science Foundation of Hefei City(2021033)the General Scientific Research Project of Anhui Provincial Health Commission(AHWJ2021b150)the Collaborative Innovation Program of Hefei Science Center,CAS(2021HSC-CIP013)the Anhui Province Key Research and Development Project(202204295107020004).
文摘Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.
基金supported by the National Key Scientific Instrument and Equipment Development Project(61827801).
文摘The fifth-generation (5G) communication requires a highly accurate estimation of the channel state information (CSI)to take advantage of the massive multiple-input multiple-output(MIMO) system. However, traditional channel estimation methods do not always yield reliable estimates. The methodology of this paper consists of deep residual shrinkage network (DRSN)neural network-based method that is used to solve this problem.Thus, the channel estimation approach, based on DRSN with its learning ability of noise-containing data, is first introduced. Then,the DRSN is used to train the noise reduction process based on the results of the least square (LS) channel estimation while applying the pilot frequency subcarriers, where the initially estimated subcarrier channel matrix is considered as a three-dimensional tensor of the DRSN input. Afterward, a mixed signal to noise ratio (SNR) training data strategy is proposed based on the learning ability of DRSN under different SNRs. Moreover, a joint mixed scenario training strategy is carried out to test the multi scenarios robustness of DRSN. As for the findings, the numerical results indicate that the DRSN method outperforms the spatial-frequency-temporal convolutional neural networks (SF-CNN)with similar computational complexity and achieves better advantages in the full SNR range than the minimum mean squared error (MMSE) estimator with a limited dataset. Moreover, the DRSN approach shows robustness in different propagation environments.
基金Project(41304090)supported by the National Natural Science Foundation of ChinaProject(2016YFC0303104)supported by the National Key Research and Development Project of ChinaProject(DY135-S1-1-07)supported by Ocean 13th Five-Year International Marine Resources Survey and Development of China
文摘To improve magnetotelluric(MT)nonlinear inversion accuracy and stability,this work introduces the deep belief network(DBN)algorithm.Firstly,a network frame is set up for training in different 2D MT models.The network inputs are the apparent resistivities of known models,and the outputs are the model parameters.The optimal network structure is achieved by determining the numbers of hidden layers and network nodes.Secondly,the learning process of the DBN is implemented to obtain the optimal solution of network connection weights for known geoelectric models.Finally,the trained DBN is verified through inversion tests,in which the network inputs are the apparent resistivities of unknown models,and the outputs are the corresponding model parameters.The experiment results show that the DBN can make full use of the global searching capability of the restricted Boltzmann machine(RBM)unsupervised learning and the local optimization of the back propagation(BP)neural network supervised learning.Comparing to the traditional neural network inversion,the calculation accuracy and stability of the DBN for MT data inversion are improved significantly.And the tests on synthetic data reveal that this method can be applied to MT data inversion and achieve good results compared with the least-square regularization inversion.
文摘With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.
基金supported by the KERI Primary Research Program through the Korea Research Council for Industrial Science & Technology funded by the Ministry of Science,ICT and Future Planning (No.15-12-N0101-46)
文摘A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.
基金supported by the Program for Innovative Research Groups of the Hunan Provincial Natural Science Foundation of China(2019JJ10004)。
文摘Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions.This paper presents an effective DOA estimation approach based on a deep residual network(DRN)for the underdetermined case.We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays.We then provide the input feature to the trained DRN to construct the super resolution spectrum.The DRN learns the mapping relationship between the input feature and the spatial spectrum by training.The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency,independence of source sparseness and adaptive capacity to non-ideal conditions(e.g.,low signal to noise ratio,short bit sequence).Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.
基金supported by Inha University Research Grant,Korea
文摘An enhanced algorithm is proposed to recognize multi-channel electromyography(EMG) patterns using deep belief networks(DBNs). It is difficult to classify the EMG features because an EMG signal has nonlinear and time-varying characteristics.Therefore, in several previous studies, various machine-learning methods have been applied. A DBN is a fast, greedy learning algorithm that can find a fairly good set of weights rapidly, even in deep networks with a large number of parameters and many hidden layers. To evaluate this model, we acquired EMG signals, extracted their features, and then compared the model with the DBN and other conventional classifiers. The accuracy of the DBN is higher than that of the other algorithms. The classification performance of the DBN model designed is approximately 88.60%. It is 7.55%(p=9.82×10-12) higher than linear discriminant analysis(LDA) and 2.89%(p=1.94×10-5) higher than support vector machine(SVM). Further, the DBN is better than shallow learning algorithms or back propagation(BP), and this model is effective for an EMG-based user-interfaced system.
基金supported by the National Natural Science Foundation of China (12072365)the Natural Science Foundation of Hunan Province of China (2020JJ4657)。
文摘It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.
基金supported by the National Natural Science Foundation of China (42027805)National Aeronautical Fund (ASFC-2017 2080005)National Key R&D Program of China (2017YFC03 07100)。
文摘Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.
基金Projects(42174170,41874145,72088101)supported by the National Natural Science Foundation of ChinaProject(CX20200228)supported by the Hunan Provincial Innovation Foundation for Postgraduate,China。
文摘Landfill leaks pose a serious threat to environmental health,risking the contamination of both groundwater and soil resources.Accurate investigation of these sites is essential for implementing effective prevention and control measures.The self-potential(SP)stands out for its sensitivity to contamination plumes,offering a solution for monitoring and detecting the movement and seepage of subsurface pollutants.However,traditional SP inversion techniques heavily rely on precise subsurface resistivity information.In this study,we propose the Attention U-Net deep learning network for rapid SP inversion.By incorporating an attention mechanism,this algorithm effectively learns the relationship between array-style SP data and the location and extent of subsurface contaminated sources.We designed a synthetic landfill model with a heterogeneous resistivity structure to assess the performance of Attention U-Net deep learning network.Additionally,we conducted further validation using a laboratory model to assess its practical applicability.The results demonstrate that the algorithm is not solely dependent on resistivity information,enabling effective locating of the source distribution,even in models with intricate subsurface structures.Our work provides a promising tool for SP data processing,enhancing the applicability of this method in the field of near-subsurface environmental monitoring.
基金funded by National Natural Science Foundation of China(Grant No. 51805146)the Fundamental Research Funds for the Central Universities (Grant No. B200202221)+1 种基金Jiangsu Key R&D Program (Grant Nos. BE2018004-1, BE2018004)College Students’ Innovative Entrepreneurial Training Plan Program (Grant No. 2020102941513)。
文摘A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.
文摘为在稀疏测点超孔隙水压力数据条件下预测饱和软土的固结行为,引入物理信息深度算子网络(physics-informed deep operator network,PI-DeepONet)方法,并利用稀疏孔隙水压力测点数据对饱和土体全域内超孔隙水压力分布进行实时预测。通过分析常规黏土变形固结及软弱黏土大变形固结2个实例进行预测,引入相对L2误差和R2这2个评估指标,验证了PI-DeepONet算法在预测全域超孔隙水压力演化方面的性能,并与纯数据驱动的DeepONet算法的计算结果进行了对比。预测结果表明:在相同的测点数目和各测点拥有相同超孔隙水压力数据量的条件下,DeepONet算法对全域超孔隙水压力的预测绝对误差在10^(-2)~10^(-1)左右,而PI-DeepONet算法的绝对误差范围则在10^(−3)~10^(-2)左右,表现出更好的预测效果。其次,在常规黏土变形固结行为研究中,通过对超孔隙水压力数据添加3种不同噪声水平来模拟现场监测环境,观察到即使噪声水平达到5%,PI-DeepONet算法仍能在水压力数据稀疏且带噪声的条件下提供高质量的全域超孔隙水压力实时预测。最后,在软弱黏土大变形固结行为研究中,将PI-DeepONet算法运用于上下边界排水速率不同的固结问题中,发现训练好的一维模型在单一测点条件下,能对其他界面参数条件下饱和土体全域内超孔隙水压力分布规律进行准确预测,表明PIDeepONet算法能为岩土工程中相关问题提供新的解决办法。
