Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood...Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.展开更多
Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting fo...Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.展开更多
In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This...In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This method combines two core modules:a simple parameter-free self-attention and cross-attention.By analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot conditions.The proposed cross-correlation network integrates these two modules and is trained in an end-to-end manner.The simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between images.Compared with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target objects.Experimental results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.展开更多
Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,...Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,traffic classification is vital for promptly overseeing and controlling applications with sensitive information.In this paper,we propose ETNet,a framework that combines multiple features and leverages self-attention mechanisms to learn deep relationships between packets.ET-Net employs a multisimilarity triplet network to extract features from raw bytes,and exploits self-attention to capture long-range dependencies within packets in a session and contextual information features.Additionally,we utilizing the loss function to more effectively integrate information acquired from both byte sequences and their corresponding lengths.Through simulated evaluations on datasets with similar attributes,ET-Net demonstrates the ability to finely distinguish between nine categories of applications,achieving superior results compared to existing methods.展开更多
With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)da...With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.展开更多
Human faces can convey substantial information about a person,such as his or her age,race,identity,gender,and emotions.Such facial information can be obtained through techniques like human facial tracking and detectio...Human faces can convey substantial information about a person,such as his or her age,race,identity,gender,and emotions.Such facial information can be obtained through techniques like human facial tracking and detection,facial recognition,gender classification,emotion recognition,as well as age estimation.Of these,gender classification is particularly important due to its diverse applications in the fields such as video surveillance and commercial advertising.In this thesis,we propose a method of gender classification based on run-length histograms.The proposed method uses a run-length histogram to record the position information of pixels,thereby efficiently improves the recognition rate and makes the technique suitable for a big-data multimedia database.The experimental results show that the proposed method can achieve better accuracy than a multi-scale based method can.展开更多
Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification...Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.展开更多
A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes...A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.展开更多
In recent years,great breakthroughs have been made in the exploration and development of natural gas in deep coal-rock reservoirs in Junggar,Ordos and other basins in China.In view of the inconsistency between the ind...In recent years,great breakthroughs have been made in the exploration and development of natural gas in deep coal-rock reservoirs in Junggar,Ordos and other basins in China.In view of the inconsistency between the industrial and academic circles on this new type of unconventional natural gas,this paper defines the concept of"coal-rock gas"on the basis of previous studies,and systematically analyzes its characteristics of occurrence state,transport and storage form,differential accumulation,and development law.Coal-rock gas,geologically unlike coalbed methane in the traditional sense,occurs in both free and adsorbed states,with free state in abundance.It is generated and stored in the same set of rocks through short distance migration,occasionally with the accumulation from other sources.Moreover,coal rock develops cleat fractures,and the free gas accumulates differentially.The coal-rock gas reservoirs deeper than 2000 m are high in pressure,temperature,gas content,gas saturation,and free-gas content.In terms of development,similar to shale gas and tight gas,coal-rock gas can be exploited by natural formation energy after the reservoirs connectivity is improved artificially,that is,the adsorbed gas is desorbed due to pressure drop after the high-potential free gas is recovered,so that the free gas and adsorbed gas are produced in succession for a long term without water drainage for pressure drop.According to buried depth,coal rank,pressure coefficient,reserves scale,reserves abundance and gas well production,the classification criteria and reserves/resources estimation method of coal-rock gas are presented.It is preliminarily estimated that the coal-rock gas in place deeper than 2000 m in China exceeds 30×10^(12)m^(3),indicating an important strategic resource for the country.The Ordos,Sichuan,Junggar and Bohai Bay basins are favorable areas for large-scale enrichment of coal-rock gas.The paper summarizes the technical and management challenges and points out the research directions,laying a foundation for the management,exploration,and development of coal-rock gas in China.展开更多
Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior perfo...Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior performances in classification accuracy and robustness. In this paper, we propose a novel, high resolution and multi-scale feature fusion convolutional neural network model with a squeeze-excitation block, referred to as HRSENet,to classify different kinds of modulation signals.The proposed model establishes a parallel computing mechanism of multi-resolution feature maps through the multi-layer convolution operation, which effectively reduces the information loss caused by downsampling convolution. Moreover, through dense skipconnecting at the same resolution and up-sampling or down-sampling connection at different resolutions, the low resolution representation of the deep feature maps and the high resolution representation of the shallow feature maps are simultaneously extracted and fully integrated, which is benificial to mine signal multilevel features. Finally, the feature squeeze and excitation module embedded in the decoder is used to adjust the response weights between channels, further improving classification accuracy of proposed model.The proposed HRSENet significantly outperforms existing methods in terms of classification accuracy on the public dataset “Over the Air” in signal-to-noise(SNR) ranging from-2dB to 20dB. The classification accuracy in the proposed model achieves 85.36% and97.30% at 4dB and 10dB, respectively, with the improvement by 9.71% and 5.82% compared to LWNet.Furthermore, the model also has a moderate computation complexity compared with several state-of-the-art methods.展开更多
Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on t...Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.展开更多
With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recogni...With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recognition model is pre-trained with fixed classes,the pre-trained model tends to predict incorrect results when identifying incremental classes.Moreover,the incremental classes are usually emergent without label information or only a few labeled samples of incremental classes can be obtained.In this context,we propose a graphbased semi-supervised approach to address the fewshot classes-incremental(FSCI)modulation classification problem.Our proposed method is a twostage learning method,specifically,a warm-up model is trained for classifying old classes and incremental classes,where the unlabeled samples of incremental classes are uniformly labeled with the same label to alleviate the damage of the class imbalance problem.Then the warm-up model is regarded as a feature extractor for constructing a similar graph to connect labeled samples and unlabeled samples,and the label propagation algorithm is adopted to propagate the label information from labeled nodes to unlabeled nodes in the graph to achieve the purpose of incremental classes recognition.Simulation results prove that the proposed method is superior to other finetuning methods and retrain methods.展开更多
We apply stochastic seismic inversion and Bayesian facies classification for porosity modeling and igneous rock identification in the presalt interval of the Santos Basin. This integration of seismic and well-derived ...We apply stochastic seismic inversion and Bayesian facies classification for porosity modeling and igneous rock identification in the presalt interval of the Santos Basin. This integration of seismic and well-derived information enhances reservoir characterization. Stochastic inversion and Bayesian classification are powerful tools because they permit addressing the uncertainties in the model. We used the ES-MDA algorithm to achieve the realizations equivalent to the percentiles P10, P50, and P90 of acoustic impedance, a novel method for acoustic inversion in presalt. The facies were divided into five: reservoir 1,reservoir 2, tight carbonates, clayey rocks, and igneous rocks. To deal with the overlaps in acoustic impedance values of facies, we included geological information using a priori probability, indicating that structural highs are reservoir-dominated. To illustrate our approach, we conducted porosity modeling using facies-related rock-physics models for rock-physics inversion in an area with a well drilled in a coquina bank and evaluated the thickness and extension of an igneous intrusion near the carbonate-salt interface. The modeled porosity and the classified seismic facies are in good agreement with the ones observed in the wells. Notably, the coquinas bank presents an improvement in the porosity towards the top. The a priori probability model was crucial for limiting the clayey rocks to the structural lows. In Well B, the hit rate of the igneous rock in the three scenarios is higher than 60%, showing an excellent thickness-prediction capability.展开更多
Phononic crystals,as artificial composite materials,have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity.Among these properties,second-harmonic feature...Phononic crystals,as artificial composite materials,have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity.Among these properties,second-harmonic features exhibit potential applications in acoustic frequency conversion,non-reciprocal wave propagation,and non-destructive testing.Precisely manipulating the harmonic band structure presents a major challenge in the design of nonlinear phononic crystals.Traditional design approaches based on parameter adjustments to meet specific application requirements are inefficient and often yield suboptimal performance.Therefore,this paper develops a design methodology using Softmax logistic regression and multi-label classification learning to inversely design the material distribution of nonlinear phononic crystals by exploiting information from harmonic transmission spectra.The results demonstrate that the neural network-based inverse design method can effectively tailor nonlinear phononic crystals with desired functionalities.This work establishes a mapping relationship between the band structure and the material distribution within phononic crystals,providing valuable insights into the inverse design of metamaterials.展开更多
Effective separation of residual carbon and ash is the basis for the resource utilization of coal gasification fine slag(CGFS).The conventional flotation process of CGFS has the bottlenecks of low carbon recovery and ...Effective separation of residual carbon and ash is the basis for the resource utilization of coal gasification fine slag(CGFS).The conventional flotation process of CGFS has the bottlenecks of low carbon recovery and high collector dosage.In order to address these issues,CGFS sample taken from Shaanxi,China was used as the study object in this paper.A new process of size classification-fine grain ultrasonic pretreatment flotation(SC-FGUF)was proposed and its separation effect was compared with that of wholegrain flotation(WGF)as well as size classification-fine grain flotation(SC-FGF).The mechanism of its enhanced separation effect was revealed through flotation kinetic fitting,flotation flow foam layer stability,particle size composition,surface morphology,pore structure,and surface chemical property analysis.The results showed that compared with WGF,pre-classification could reduce the collector dosage by 84.09%and the combination of pre-classification and ultrasonic pretreatment could increase the combustible recovery by 17.29%and up to 93.46%.The SC-FGUF process allows the ineffective adsorption of coarse residual carbon to collector during flotation stage to be reduced by pre-classification,and the tightly embedded state of fine CGFS particles is disrupted and surface oxidizing functional group occupancy was reduced by ultrasonic pretreatment,thus carbon and ash is easier to be separated in the flotation process.In addition,some of the residual carbon particles were broken down to smaller sizes in the ultrasonic pretreatment,which led to an increase in the stability of flotation flow foam layer and a decrease in the probability of detachment of residual carbon particles from the bubbles.Therefore,SCFGUF could increase the residual carbon recovery and reduce the flotation collector dosage,which is an innovative method for carbon-ash separation of CGFS with good application prospect.展开更多
The vector vortex beam(VVB)has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications.However,a VVB is unavoidably a...The vector vortex beam(VVB)has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications.However,a VVB is unavoidably affected by atmospheric turbulence(AT)when it propagates through the free-space optical communication environment,which results in detection errors at the receiver.In this paper,we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT,where a diffractive deep neural network(DDNN)is designed and trained to classify the intensity distribution of the input distorted VVBs,and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN.The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks.The energy distribution percentage remains above 95%from weak to medium AT,and the classification accuracy can remain above 95%for various strengths of turbulence.It has a faster convergence and better accuracy than that based on a convolutional neural network.展开更多
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea...In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.展开更多
The direction-of-arrival(DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number i...The direction-of-arrival(DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number in millimeter wave system,the multi-task deep residual shrinkage network(MTDRSN) and transfer learning-based convolutional neural network(TCNN), namely MDTCNet, are proposed. The sampling covariance matrix based on the received signal is used as the input to the proposed network. A DRSN-based multi-task classifications model is first introduced to estimate signal sources number and multipath number simultaneously. Then, the DoAs with multi-signal and multipath are estimated by the regression model. The proposed CNN is applied for DoAs estimation with the predicted number of signal sources and paths. Furthermore, the modelbased transfer learning is also introduced into the regression model. The TCNN inherits the partial network parameters of the already formed optimization model obtained by the CNN. A series of experimental results show that the MDTCNet-based DoAs estimation method can accurately predict the signal sources number and multipath number under a range of signal-to-noise ratios. Remarkably, the proposed method achieves the lower root mean square error compared with some existing deep learning-based and traditional methods.展开更多
We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantu...We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.展开更多
Building information modeling(BIM)object classification takes a lot of time and energy.Misclassification or omission of any object may lead to the emergence of abnormal results,which have a great impact on the project...Building information modeling(BIM)object classification takes a lot of time and energy.Misclassification or omission of any object may lead to the emergence of abnormal results,which have a great impact on the project workflow and results.Roundly understanding BIM object classification,by improving Swin Transformer classifier algorithm parameters,using the model primitives extracted from IFC format BIM model file,deep learning of 7 types of BIM object categories is taken.Through the performance and evaluation indicators obtained in training,the results improve the classification accuracy.展开更多
基金This study was supported by the Fundamental Research Funds for the Central Universities(No.2572023DJ02).
文摘Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.
基金supported by Western Research Interdisciplinary Initiative R6259A03.
文摘Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.
基金Supported by the National Pre-research Program during the 14th Five-Year Plan(514010405)。
文摘In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This method combines two core modules:a simple parameter-free self-attention and cross-attention.By analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot conditions.The proposed cross-correlation network integrates these two modules and is trained in an end-to-end manner.The simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between images.Compared with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target objects.Experimental results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.
基金supported by National Key Research and Development Program of China(2022YFB3104903)S&T Program of Hebei(No.SZX2020034).
文摘Intelligent vehicle applications provide convenience but raise privacy and security concerns.Misuse of sensitive data,including vehicle location,and facial recognition information,poses a threat to user privacy.Hence,traffic classification is vital for promptly overseeing and controlling applications with sensitive information.In this paper,we propose ETNet,a framework that combines multiple features and leverages self-attention mechanisms to learn deep relationships between packets.ET-Net employs a multisimilarity triplet network to extract features from raw bytes,and exploits self-attention to capture long-range dependencies within packets in a session and contextual information features.Additionally,we utilizing the loss function to more effectively integrate information acquired from both byte sequences and their corresponding lengths.Through simulated evaluations on datasets with similar attributes,ET-Net demonstrates the ability to finely distinguish between nine categories of applications,achieving superior results compared to existing methods.
基金supported by the National Key Research and Development Project(No.2020YFC1512000)the General Projects of Key R&D Programs in Shaanxi Province(No.2020GY-060)Xi’an Science&Technology Project(No.2020KJRC 0126)。
文摘With the development of sensors,the application of multi-source remote sensing data has been widely concerned.Since hyperspectral image(HSI)contains rich spectral information while light detection and ranging(LiDAR)data contains elevation information,joint use of them for ground object classification can yield positive results,especially by building deep networks.Fortu-nately,multi-scale deep networks allow to expand the receptive fields of convolution without causing the computational and training problems associated with simply adding more network layers.In this work,a multi-scale feature fusion network is proposed for the joint classification of HSI and LiDAR data.First,we design a multi-scale spatial feature extraction module with cross-channel connections,by which spatial information of HSI data and elevation information of LiDAR data are extracted and fused.In addition,a multi-scale spectral feature extraction module is employed to extract the multi-scale spectral features of HSI data.Finally,joint multi-scale features are obtained by weighting and concatenation operations and then fed into the classifier.To verify the effective-ness of the proposed network,experiments are carried out on the MUUFL Gulfport and Trento datasets.The experimental results demonstrate that the classification performance of the proposed method is superior to that of other state-of-the-art methods.
基金supported by MOST under Grants No.104-2218-E-468-001 and No.105-2221-E-468-008
文摘Human faces can convey substantial information about a person,such as his or her age,race,identity,gender,and emotions.Such facial information can be obtained through techniques like human facial tracking and detection,facial recognition,gender classification,emotion recognition,as well as age estimation.Of these,gender classification is particularly important due to its diverse applications in the fields such as video surveillance and commercial advertising.In this thesis,we propose a method of gender classification based on run-length histograms.The proposed method uses a run-length histogram to record the position information of pixels,thereby efficiently improves the recognition rate and makes the technique suitable for a big-data multimedia database.The experimental results show that the proposed method can achieve better accuracy than a multi-scale based method can.
基金National Natural Science Foundation of China(No.62201457)Natural Science Foundation of Shaanxi Province(Nos.2022JQ-668,2022JQ-588)。
文摘Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.
基金This study was supported by the National Natural Science Foundation of China(U22B2075,52274056,51974356).
文摘A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.
基金Supported by the Prospective and Basic Research Project of PetroChina(2021DJ23)。
文摘In recent years,great breakthroughs have been made in the exploration and development of natural gas in deep coal-rock reservoirs in Junggar,Ordos and other basins in China.In view of the inconsistency between the industrial and academic circles on this new type of unconventional natural gas,this paper defines the concept of"coal-rock gas"on the basis of previous studies,and systematically analyzes its characteristics of occurrence state,transport and storage form,differential accumulation,and development law.Coal-rock gas,geologically unlike coalbed methane in the traditional sense,occurs in both free and adsorbed states,with free state in abundance.It is generated and stored in the same set of rocks through short distance migration,occasionally with the accumulation from other sources.Moreover,coal rock develops cleat fractures,and the free gas accumulates differentially.The coal-rock gas reservoirs deeper than 2000 m are high in pressure,temperature,gas content,gas saturation,and free-gas content.In terms of development,similar to shale gas and tight gas,coal-rock gas can be exploited by natural formation energy after the reservoirs connectivity is improved artificially,that is,the adsorbed gas is desorbed due to pressure drop after the high-potential free gas is recovered,so that the free gas and adsorbed gas are produced in succession for a long term without water drainage for pressure drop.According to buried depth,coal rank,pressure coefficient,reserves scale,reserves abundance and gas well production,the classification criteria and reserves/resources estimation method of coal-rock gas are presented.It is preliminarily estimated that the coal-rock gas in place deeper than 2000 m in China exceeds 30×10^(12)m^(3),indicating an important strategic resource for the country.The Ordos,Sichuan,Junggar and Bohai Bay basins are favorable areas for large-scale enrichment of coal-rock gas.The paper summarizes the technical and management challenges and points out the research directions,laying a foundation for the management,exploration,and development of coal-rock gas in China.
基金supported by the Beijing Natural Science Foundation (L202003)National Natural Science Foundation of China (No. 31700479)。
文摘Automatic modulation classification(AMC) technology is one of the cutting-edge technologies in cognitive radio communications. AMC based on deep learning has recently attracted much attention due to its superior performances in classification accuracy and robustness. In this paper, we propose a novel, high resolution and multi-scale feature fusion convolutional neural network model with a squeeze-excitation block, referred to as HRSENet,to classify different kinds of modulation signals.The proposed model establishes a parallel computing mechanism of multi-resolution feature maps through the multi-layer convolution operation, which effectively reduces the information loss caused by downsampling convolution. Moreover, through dense skipconnecting at the same resolution and up-sampling or down-sampling connection at different resolutions, the low resolution representation of the deep feature maps and the high resolution representation of the shallow feature maps are simultaneously extracted and fully integrated, which is benificial to mine signal multilevel features. Finally, the feature squeeze and excitation module embedded in the decoder is used to adjust the response weights between channels, further improving classification accuracy of proposed model.The proposed HRSENet significantly outperforms existing methods in terms of classification accuracy on the public dataset “Over the Air” in signal-to-noise(SNR) ranging from-2dB to 20dB. The classification accuracy in the proposed model achieves 85.36% and97.30% at 4dB and 10dB, respectively, with the improvement by 9.71% and 5.82% compared to LWNet.Furthermore, the model also has a moderate computation complexity compared with several state-of-the-art methods.
基金the Natural Science Foundation of China(Grant Numbers 72074014 and 72004012).
文摘Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.
基金supported in part by the National Natural Science Foundation of China under Grant No.62171334,No.11973077 and No.12003061。
文摘With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recognition model is pre-trained with fixed classes,the pre-trained model tends to predict incorrect results when identifying incremental classes.Moreover,the incremental classes are usually emergent without label information or only a few labeled samples of incremental classes can be obtained.In this context,we propose a graphbased semi-supervised approach to address the fewshot classes-incremental(FSCI)modulation classification problem.Our proposed method is a twostage learning method,specifically,a warm-up model is trained for classifying old classes and incremental classes,where the unlabeled samples of incremental classes are uniformly labeled with the same label to alleviate the damage of the class imbalance problem.Then the warm-up model is regarded as a feature extractor for constructing a similar graph to connect labeled samples and unlabeled samples,and the label propagation algorithm is adopted to propagate the label information from labeled nodes to unlabeled nodes in the graph to achieve the purpose of incremental classes recognition.Simulation results prove that the proposed method is superior to other finetuning methods and retrain methods.
基金Equinor for financing the R&D projectthe Institute of Science and Technology of Petroleum Geophysics of Brazil for supporting this research。
文摘We apply stochastic seismic inversion and Bayesian facies classification for porosity modeling and igneous rock identification in the presalt interval of the Santos Basin. This integration of seismic and well-derived information enhances reservoir characterization. Stochastic inversion and Bayesian classification are powerful tools because they permit addressing the uncertainties in the model. We used the ES-MDA algorithm to achieve the realizations equivalent to the percentiles P10, P50, and P90 of acoustic impedance, a novel method for acoustic inversion in presalt. The facies were divided into five: reservoir 1,reservoir 2, tight carbonates, clayey rocks, and igneous rocks. To deal with the overlaps in acoustic impedance values of facies, we included geological information using a priori probability, indicating that structural highs are reservoir-dominated. To illustrate our approach, we conducted porosity modeling using facies-related rock-physics models for rock-physics inversion in an area with a well drilled in a coquina bank and evaluated the thickness and extension of an igneous intrusion near the carbonate-salt interface. The modeled porosity and the classified seismic facies are in good agreement with the ones observed in the wells. Notably, the coquinas bank presents an improvement in the porosity towards the top. The a priori probability model was crucial for limiting the clayey rocks to the structural lows. In Well B, the hit rate of the igneous rock in the three scenarios is higher than 60%, showing an excellent thickness-prediction capability.
基金supported by the National Key Research and Development Program of China(Grant No.2020YFA0211400)the State Key Program of the National Natural Science of China(Grant No.11834008)+2 种基金the National Natural Science Foundation of China(Grant Nos.12174192,12174188,and 11974176)the State Key Laboratory of Acoustics,Chinese Academy of Sciences(Grant No.SKLA202410)the Fund from the Key Laboratory of Underwater Acoustic Environment,Chinese Academy of Sciences(Grant No.SSHJ-KFKT-1701).
文摘Phononic crystals,as artificial composite materials,have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity.Among these properties,second-harmonic features exhibit potential applications in acoustic frequency conversion,non-reciprocal wave propagation,and non-destructive testing.Precisely manipulating the harmonic band structure presents a major challenge in the design of nonlinear phononic crystals.Traditional design approaches based on parameter adjustments to meet specific application requirements are inefficient and often yield suboptimal performance.Therefore,this paper develops a design methodology using Softmax logistic regression and multi-label classification learning to inversely design the material distribution of nonlinear phononic crystals by exploiting information from harmonic transmission spectra.The results demonstrate that the neural network-based inverse design method can effectively tailor nonlinear phononic crystals with desired functionalities.This work establishes a mapping relationship between the band structure and the material distribution within phononic crystals,providing valuable insights into the inverse design of metamaterials.
基金supported by the National Natural Science Foundation of China(No.52374279)the Natural Science Foundation of Shaanxi Province(No.2023-YBGY-055).
文摘Effective separation of residual carbon and ash is the basis for the resource utilization of coal gasification fine slag(CGFS).The conventional flotation process of CGFS has the bottlenecks of low carbon recovery and high collector dosage.In order to address these issues,CGFS sample taken from Shaanxi,China was used as the study object in this paper.A new process of size classification-fine grain ultrasonic pretreatment flotation(SC-FGUF)was proposed and its separation effect was compared with that of wholegrain flotation(WGF)as well as size classification-fine grain flotation(SC-FGF).The mechanism of its enhanced separation effect was revealed through flotation kinetic fitting,flotation flow foam layer stability,particle size composition,surface morphology,pore structure,and surface chemical property analysis.The results showed that compared with WGF,pre-classification could reduce the collector dosage by 84.09%and the combination of pre-classification and ultrasonic pretreatment could increase the combustible recovery by 17.29%and up to 93.46%.The SC-FGUF process allows the ineffective adsorption of coarse residual carbon to collector during flotation stage to be reduced by pre-classification,and the tightly embedded state of fine CGFS particles is disrupted and surface oxidizing functional group occupancy was reduced by ultrasonic pretreatment,thus carbon and ash is easier to be separated in the flotation process.In addition,some of the residual carbon particles were broken down to smaller sizes in the ultrasonic pretreatment,which led to an increase in the stability of flotation flow foam layer and a decrease in the probability of detachment of residual carbon particles from the bubbles.Therefore,SCFGUF could increase the residual carbon recovery and reduce the flotation collector dosage,which is an innovative method for carbon-ash separation of CGFS with good application prospect.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.62375140 and 62001249)the Open Research Fund of National Laboratory of Solid State Microstructures(Grant No.M36055).
文摘The vector vortex beam(VVB)has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications.However,a VVB is unavoidably affected by atmospheric turbulence(AT)when it propagates through the free-space optical communication environment,which results in detection errors at the receiver.In this paper,we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT,where a diffractive deep neural network(DDNN)is designed and trained to classify the intensity distribution of the input distorted VVBs,and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN.The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks.The energy distribution percentage remains above 95%from weak to medium AT,and the classification accuracy can remain above 95%for various strengths of turbulence.It has a faster convergence and better accuracy than that based on a convolutional neural network.
文摘In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
基金funded by Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center。
文摘The direction-of-arrival(DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number in millimeter wave system,the multi-task deep residual shrinkage network(MTDRSN) and transfer learning-based convolutional neural network(TCNN), namely MDTCNet, are proposed. The sampling covariance matrix based on the received signal is used as the input to the proposed network. A DRSN-based multi-task classifications model is first introduced to estimate signal sources number and multipath number simultaneously. Then, the DoAs with multi-signal and multipath are estimated by the regression model. The proposed CNN is applied for DoAs estimation with the predicted number of signal sources and paths. Furthermore, the modelbased transfer learning is also introduced into the regression model. The TCNN inherits the partial network parameters of the already formed optimization model obtained by the CNN. A series of experimental results show that the MDTCNet-based DoAs estimation method can accurately predict the signal sources number and multipath number under a range of signal-to-noise ratios. Remarkably, the proposed method achieves the lower root mean square error compared with some existing deep learning-based and traditional methods.
基金Project supported by the Natural Science Foundation of Shandong Province,China (Grant No. ZR2021MF049)the Joint Fund of Natural Science Foundation of Shandong Province (Grant Nos. ZR2022LLZ012 and ZR2021LLZ001)。
文摘We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.
文摘Building information modeling(BIM)object classification takes a lot of time and energy.Misclassification or omission of any object may lead to the emergence of abnormal results,which have a great impact on the project workflow and results.Roundly understanding BIM object classification,by improving Swin Transformer classifier algorithm parameters,using the model primitives extracted from IFC format BIM model file,deep learning of 7 types of BIM object categories is taken.Through the performance and evaluation indicators obtained in training,the results improve the classification accuracy.
