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
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
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
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
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
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
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
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
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
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
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
Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve it...Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve its reliability.A data enhancement module(DEM)is designed by a convolutional layer to supplement frequency-domain information as well as providing nonlinear mapping that is beneficial for AMC.Multimodal network is designed to have multiple residual blocks,where each residual block has multiple convolutional kernels of different sizes for diverse feature extraction.Moreover,a deep supervised loss function is designed to supervise all parts of the network including the hidden layers and the DEM.Since different model may output different results,cooperative classifier is designed to avoid the randomness of single model and improve the reliability.Simulation results show that this few-shot learning-based AMC method can significantly improve the AMC accuracy compared to the existing methods.展开更多
The ability to predict the anti-interference communications performance of unmanned aerial vehicle(UAV)data links is critical for intelligent route planning of UAVs in real combat scenarios.Previous research in this a...The ability to predict the anti-interference communications performance of unmanned aerial vehicle(UAV)data links is critical for intelligent route planning of UAVs in real combat scenarios.Previous research in this area has encountered several limitations:Classifiers exhibit low training efficiency,their precision is notably reduced when dealing with imbalanced samples,and they cannot be applied to the condition where the UAV’s flight altitude and the antenna bearing vary.This paper proposes the sequential Latin hypercube sampling(SLHS)-support vector machine(SVM)-AdaBoost algorithm,which enhances the training efficiency of the base classifier and circumvents local optima during the search process through SLHS optimization.Additionally,it mitigates the bottleneck of sample imbalance by adjusting the sample weight distribution using the AdaBoost algorithm.Through comparison,the modeling efficiency,prediction accuracy on the test set,and macro-averaged values of precision,recall,and F1-score for SLHS-SVM-AdaBoost are improved by 22.7%,5.7%,36.0%,25.0%,and 34.2%,respectively,compared with Grid-SVM.Additionally,these values are improved by 22.2%,2.1%,11.3%,2.8%,and 7.4%,respectively,compared with particle swarm optimization(PSO)-SVM-AdaBoost.Combining Latin hypercube sampling with the SLHS-SVM-AdaBoost algorithm,the classification prediction model of anti-interference performance of UAV data links,which took factors like three-dimensional position of UAV and antenna bearing into consideration,is established and used to assess the safety of the classical flying path and optimize the flying route.It was found that the risk of loss of communications could not be completely avoided by adjusting the flying altitude based on the classical path,whereas intelligent path planning based on the classification prediction model of anti-interference performance can realize complete avoidance of being interfered meanwhile reducing the route length by at least 2.3%,thus benefiting both safety and operation efficiency.展开更多
This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor(KNN),random forest(RF),decision tree(DT),and support vector machine(SVM)for ar...This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor(KNN),random forest(RF),decision tree(DT),and support vector machine(SVM)for arrhythmia detection.The proposed classifier leverages the Chi-square distance as a primary metric,providing a specialized and original approach for precise arrhythmia detection.To optimize feature selection and refine the classifier’s performance,particle swarm optimization(PSO)is integrated with the Chi-square distance as a fitness function.This synergistic integration enhances the classifier’s capabilities,resulting in a substantial improvement in accuracy for arrhythmia detection.Experimental results demonstrate the efficacy of the proposed method,achieving a noteworthy accuracy rate of 98% with PSO,higher than 89% achieved without any previous optimization.The classifier outperforms machine learning(ML)and deep learning(DL)techniques,underscoring its reliability and superiority in the realm of arrhythmia classification.The promising results render it an effective method to support both academic and medical communities,offering an advanced and precise solution for arrhythmia detection in electrocardiogram(ECG)data.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
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
Although modulation classification based on deep neural network can achieve high Modulation Classification(MC)accuracies,catastrophic forgetting will occur when the neural network model continues to learn new tasks.In...Although modulation classification based on deep neural network can achieve high Modulation Classification(MC)accuracies,catastrophic forgetting will occur when the neural network model continues to learn new tasks.In this paper,we simulate the dynamic wireless communication environment and focus on breaking the learning paradigm of isolated automatic MC.We innovate a research algorithm for continuous automatic MC.Firstly,a memory for storing representative old task modulation signals is built,which is employed to limit the gradient update direction of new tasks in the continuous learning stage to ensure that the loss of old tasks is also in a downward trend.Secondly,in order to better simulate the dynamic wireless communication environment,we employ the mini-batch gradient algorithm which is more suitable for continuous learning.Finally,the signal in the memory can be replayed to further strengthen the characteristics of the old task signal in the model.Simulation results verify the effectiveness of the method.展开更多
A distributed acoustic sensing(DAS)system is proposed and a data processing method for vibration is designed in this paper.The proposed DAS system is based on the Rayleigh scattering signal and utilizes phase-sensitiv...A distributed acoustic sensing(DAS)system is proposed and a data processing method for vibration is designed in this paper.The proposed DAS system is based on the Rayleigh scattering signal and utilizes phase-sensitive optical time-domain reflectometry(φ-OTDR)to demodulate the environmental vibration.It can collect the vibration information in railways and implement vibration classification based on the feature of sensed vibration signals.This system has been deployed in Guangzhou Shenzhen High-Speed Railway,and the experimental results validate its effectiveness.展开更多
Sixteen different vegetation types of grassland and shrubland were selected to study the component and diversity of plant species of riparian plant communities along main channel in the Three-Gorges areas. Species ric...Sixteen different vegetation types of grassland and shrubland were selected to study the component and diversity of plant species of riparian plant communities along main channel in the Three-Gorges areas. Species richness (s), Simpson index (D), and Shannon-Weiner index (H) were used to study the biodiversity and the hierarchical classification was carried out by the methods of TWINSPAN and DCA ordination. The results showed that the components of flora were complex and dominated by the temperate type in the riparian plant communities. Species diversity was not different between the communities, but Shannon-Weiner indexes of different layers in some grassland were significantly different. TWINSPAN and DCA indicated that riparian plant communities distributed along the gradient of moisture.展开更多
A new arrival and departure flight classification method based on the transitive closure algorithm （TCA） is proposed. Firstly, the fuzzy set theory and the transitive closure algorithm are introduced. Then four diff...A new arrival and departure flight classification method based on the transitive closure algorithm （TCA） is proposed. Firstly, the fuzzy set theory and the transitive closure algorithm are introduced. Then four different factors are selected to establish the flight classification model and a method is given to calculate the delay cost for each class. Finally, the proposed method is implemented in the sequencing problems of flights in a terminal area, and results are compared with that of the traditional classification method（TCM）. Results show that the new classification model is effective in reducing the expenses of flight delays, thus optimizing the sequences of arrival and departure flights, and improving the efficiency of air traffic control.展开更多
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 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 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.
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.
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supported in part by National Key Research and Development Program of China under Grant 2021YFB2900404.
文摘Due to the limited computational capability and the diversity of the Internet of Things devices working in different environment,we consider fewshot learning-based automatic modulation classification(AMC)to improve its reliability.A data enhancement module(DEM)is designed by a convolutional layer to supplement frequency-domain information as well as providing nonlinear mapping that is beneficial for AMC.Multimodal network is designed to have multiple residual blocks,where each residual block has multiple convolutional kernels of different sizes for diverse feature extraction.Moreover,a deep supervised loss function is designed to supervise all parts of the network including the hidden layers and the DEM.Since different model may output different results,cooperative classifier is designed to avoid the randomness of single model and improve the reliability.Simulation results show that this few-shot learning-based AMC method can significantly improve the AMC accuracy compared to the existing methods.
文摘The ability to predict the anti-interference communications performance of unmanned aerial vehicle(UAV)data links is critical for intelligent route planning of UAVs in real combat scenarios.Previous research in this area has encountered several limitations:Classifiers exhibit low training efficiency,their precision is notably reduced when dealing with imbalanced samples,and they cannot be applied to the condition where the UAV’s flight altitude and the antenna bearing vary.This paper proposes the sequential Latin hypercube sampling(SLHS)-support vector machine(SVM)-AdaBoost algorithm,which enhances the training efficiency of the base classifier and circumvents local optima during the search process through SLHS optimization.Additionally,it mitigates the bottleneck of sample imbalance by adjusting the sample weight distribution using the AdaBoost algorithm.Through comparison,the modeling efficiency,prediction accuracy on the test set,and macro-averaged values of precision,recall,and F1-score for SLHS-SVM-AdaBoost are improved by 22.7%,5.7%,36.0%,25.0%,and 34.2%,respectively,compared with Grid-SVM.Additionally,these values are improved by 22.2%,2.1%,11.3%,2.8%,and 7.4%,respectively,compared with particle swarm optimization(PSO)-SVM-AdaBoost.Combining Latin hypercube sampling with the SLHS-SVM-AdaBoost algorithm,the classification prediction model of anti-interference performance of UAV data links,which took factors like three-dimensional position of UAV and antenna bearing into consideration,is established and used to assess the safety of the classical flying path and optimize the flying route.It was found that the risk of loss of communications could not be completely avoided by adjusting the flying altitude based on the classical path,whereas intelligent path planning based on the classification prediction model of anti-interference performance can realize complete avoidance of being interfered meanwhile reducing the route length by at least 2.3%,thus benefiting both safety and operation efficiency.
文摘This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor(KNN),random forest(RF),decision tree(DT),and support vector machine(SVM)for arrhythmia detection.The proposed classifier leverages the Chi-square distance as a primary metric,providing a specialized and original approach for precise arrhythmia detection.To optimize feature selection and refine the classifier’s performance,particle swarm optimization(PSO)is integrated with the Chi-square distance as a fitness function.This synergistic integration enhances the classifier’s capabilities,resulting in a substantial improvement in accuracy for arrhythmia detection.Experimental results demonstrate the efficacy of the proposed method,achieving a noteworthy accuracy rate of 98% with PSO,higher than 89% achieved without any previous optimization.The classifier outperforms machine learning(ML)and deep learning(DL)techniques,underscoring its reliability and superiority in the realm of arrhythmia classification.The promising results render it an effective method to support both academic and medical communities,offering an advanced and precise solution for arrhythmia detection in electrocardiogram(ECG)data.
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.
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.
文摘Although modulation classification based on deep neural network can achieve high Modulation Classification(MC)accuracies,catastrophic forgetting will occur when the neural network model continues to learn new tasks.In this paper,we simulate the dynamic wireless communication environment and focus on breaking the learning paradigm of isolated automatic MC.We innovate a research algorithm for continuous automatic MC.Firstly,a memory for storing representative old task modulation signals is built,which is employed to limit the gradient update direction of new tasks in the continuous learning stage to ensure that the loss of old tasks is also in a downward trend.Secondly,in order to better simulate the dynamic wireless communication environment,we employ the mini-batch gradient algorithm which is more suitable for continuous learning.Finally,the signal in the memory can be replayed to further strengthen the characteristics of the old task signal in the model.Simulation results verify the effectiveness of the method.
文摘A distributed acoustic sensing(DAS)system is proposed and a data processing method for vibration is designed in this paper.The proposed DAS system is based on the Rayleigh scattering signal and utilizes phase-sensitive optical time-domain reflectometry(φ-OTDR)to demodulate the environmental vibration.It can collect the vibration information in railways and implement vibration classification based on the feature of sensed vibration signals.This system has been deployed in Guangzhou Shenzhen High-Speed Railway,and the experimental results validate its effectiveness.
基金This study was supported by the Chinese Academy of Sciences (A grant KZCX2-406) the National Natural Science Foundation of China (NSFC39970123) and Changbai Mountain Open Research Station.
文摘Sixteen different vegetation types of grassland and shrubland were selected to study the component and diversity of plant species of riparian plant communities along main channel in the Three-Gorges areas. Species richness (s), Simpson index (D), and Shannon-Weiner index (H) were used to study the biodiversity and the hierarchical classification was carried out by the methods of TWINSPAN and DCA ordination. The results showed that the components of flora were complex and dominated by the temperate type in the riparian plant communities. Species diversity was not different between the communities, but Shannon-Weiner indexes of different layers in some grassland were significantly different. TWINSPAN and DCA indicated that riparian plant communities distributed along the gradient of moisture.
文摘A new arrival and departure flight classification method based on the transitive closure algorithm （TCA） is proposed. Firstly, the fuzzy set theory and the transitive closure algorithm are introduced. Then four different factors are selected to establish the flight classification model and a method is given to calculate the delay cost for each class. Finally, the proposed method is implemented in the sequencing problems of flights in a terminal area, and results are compared with that of the traditional classification method（TCM）. Results show that the new classification model is effective in reducing the expenses of flight delays, thus optimizing the sequences of arrival and departure flights, and improving the efficiency of air traffic control.
