Recently, convolutional neural networks (CNNs) have been utilized in medical imaging research field and have successfully shown their ability in image classification and detection. In this paper we used a CNN combined...Recently, convolutional neural networks (CNNs) have been utilized in medical imaging research field and have successfully shown their ability in image classification and detection. In this paper we used a CNN combined with a wavelet transform approach for classifying a dataset of 448 lung CT images into 4 categories, e.g. lung adenocarcinoma, lung squamous cell carcinoma, metastatic lung cancer, and normal. The key difference between the commonly-used CNNs and the presented method is that in this method, we adopt the use of redundant wavelet coefficients at level 1 as inputs to the CNN, instead of using original images. One of the main advantages of the proposed method is that it is not necessary to extract regions of interest from original images. The wavelet coefficients of the entire image are used as inputs to the CNN. We compare the classification performance of the proposed method to that of an existing CNN classifier and a CNN-based support vector machine classifier. The experimental results show that the proposed method outperforms the other two methods and achieve the highest overall accuracy of 91.9%. It demonstrates the potential for use in classification of lung diseases in CT images.展开更多
Machine learning is an integral technology many people utilize in all areas of human life. It is pervasive in modern living worldwide, and has multiple usages. One application is image classification, embraced across ...Machine learning is an integral technology many people utilize in all areas of human life. It is pervasive in modern living worldwide, and has multiple usages. One application is image classification, embraced across many spheres of influence such as business, finance, medicine, etc. to enhance produces, causes, efficiency, etc. This need for more accurate, detail-oriented classification increases the need for modifications, adaptations, and innovations to Deep Learning Algorithms. This article used Convolutional Neural Networks (CNN) to classify scenes in the CIFAR-10 database, and detect emotions in the KDEF database. The proposed method converted the data to the wavelet domain to attain greater accuracy and comparable efficiency to the spatial domain processing. By dividing image data into subbands, important feature learning occurred over differing low to high frequencies. The combination of the learned low and high frequency features, and processing the fused feature mapping resulted in an advance in the detection accuracy. Comparing the proposed methods to spatial domain CNN and Stacked Denoising Autoencoder (SDA), experimental findings revealed a substantial increase in accuracy.展开更多
In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to t...In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to the opening up, economic prosperity and social stability of Northeast China. In this paper, the remote sensing ecological index (RSEI) of Hailin City in recent 20 years was calculated by using Landsat 5/8/9 series satellite images, and the temporal and spatial changes of the ecological environment in Hailin City were further analyzed and the influencing factors were discussed. From 2003 to 2023, the mean value of RSEI in Hailin City decreased and increased, and the ecological environment decreased slightly as a whole. RSEI declined most significantly from 2003 to 2008, and it increased from 2008 to 2013, decreased from 2013 to 2018, and increased from 2018 to 2023 again, with higher RSEI value in the south and lower RSEI value in the northwest. It is suggested to appropriately increase vegetation coverage in the northwest to improve ecological quality. As a result, the predicted value of Elman dynamic recurrent neural network model is consistent with the change trend of the mean value, and the prediction error converges quickly, which can accurately predict the ecological environment quality in the future study area.展开更多
Object detection(OD)in remote sensing images(RSI)acts as a vital part in numerous civilian and military application areas,like urban planning,geographic information system(GIS),and search and rescue functions.Vehicle ...Object detection(OD)in remote sensing images(RSI)acts as a vital part in numerous civilian and military application areas,like urban planning,geographic information system(GIS),and search and rescue functions.Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions.The latest advancements in deep learning(DL)approaches permit the design of effectual OD approaches.This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection(AEODCNN-VD)model on Remote Sensing Images.The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly.To detect vehicles,the presented AEODCNN-VD model employs single shot detector(SSD)with Inception network as a baseline model.In addition,Multiway Feature Pyramid Network(MFPN)is used for handling objects of varying sizes in RSIs.The features from the Inception model are passed into theMFPNformultiway andmultiscale feature fusion.Finally,the fused features are passed into bounding box and class prediction networks.For enhancing the detection efficiency of the AEODCNN-VD approach,AEO based hyperparameter optimizer is used,which is stimulated by the energy transfer strategies such as production,consumption,and decomposition in an ecosystem.The performance validation of the presentedmethod on benchmark datasets showed promising performance over recent DL models.展开更多
Computerized tomography (CT) scan is the only screening test recommended by doctors to look for lung cancer. Convolutional neural networks (CNNs) have recently proven their ability to successfully classify medical ima...Computerized tomography (CT) scan is the only screening test recommended by doctors to look for lung cancer. Convolutional neural networks (CNNs) have recently proven their ability to successfully classify medical images. Due to its strong compactness property, the Discrete Wavelet transform (DWT) has been commonly used in image feature extraction applications. This paper presents a novel technique for the classification of Lung cancer in Computerized Tomography (CT) scans using Wavelets to find discriminative features in the CT images and CNN to classify the extracted features. Experimental results prove that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 99.5%.展开更多
Based on pattern recognition theory and neural network technology, moving objects automatic detection and classification method integrating advanced wavelet analysis are discussed in detail. An algorithm of moving tar...Based on pattern recognition theory and neural network technology, moving objects automatic detection and classification method integrating advanced wavelet analysis are discussed in detail. An algorithm of moving targets pattern recognition on the combination of inter-frame difference and wavelet neural network is presented. The experimental results indicate that the designed BP wavelet network using this algorithm can recognize and classify moving targets rapidly and effectively.展开更多
Vehicle emission has been the major source of air pollution in urban areas in the past two decades. This article proposes an artificial neural network model for identifying the taxi gross emitters based on the remote ...Vehicle emission has been the major source of air pollution in urban areas in the past two decades. This article proposes an artificial neural network model for identifying the taxi gross emitters based on the remote sensing data. After carrying out the field test in Guangzhou and analyzing various factors from the emission data, the artificial neural network modeling was proved to be an advisable method of identifying the gross emitters. On the basis of the principal component analysis and the selection of algorithm and architecture, the Back-Propagation neural network model with 8-17-1 architecture was established as the optimal approach for this purpose. It gave a percentage of hits of 93%. Our previous research result and the result from aggression analysis were compared, and they provided respectively the percentage of hits of 81.63% and 75%. This comparison demonstrates the potentiality and validity of the proposed method in the identification of taxi gross emitters.展开更多
How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
Poverty has always been one of the topics concerned by governments and researchers all over the world, especially in developing countries. Remote sensing image is widely used in poverty estimation because of its large...Poverty has always been one of the topics concerned by governments and researchers all over the world, especially in developing countries. Remote sensing image is widely used in poverty estimation because of its large area observation, timeliness and periodicity. In this study, we explore the applicability of convolution neural network (CNN) combined with remote sensing image in regional poverty estimation. In the 2016 economic indicators estimation of Guizhou Province, China, the Pearson coefficient of per capita GDP (PCGDP) reached 0.76, which means that the image features extracted by CNN can explain the change of PCGDP of county level economic indicators up to 76%. Compared with other methods, our method still has high precision. Based on these results, we found that convolutional neural network combined with remote sensing image can be used in regional poverty estimation.展开更多
Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices ...Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD, mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980’s. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used. Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.展开更多
Aiming at the characteristics of remote sensing image classification, the mixed pixel problem is one of the main factors that affect the improvement of classifying precision in remote sensing classification. A BP neur...Aiming at the characteristics of remote sensing image classification, the mixed pixel problem is one of the main factors that affect the improvement of classifying precision in remote sensing classification. A BP neural network was established to solve mixed pixel classifying problems. The aim of our work is to improve the BP network algorithm and set the intensity of training, which changes with training process, because the BP algorithm converyging speed of learning algorithm is rather slow, it is possible to fall into the local minimum, and because the algorithm makes the learning result poor, the global minimum value can’t be reached. The results show that this method effectively solves mixed pixel classifying problem, improves learning speed and classification accuracy of BP network classifier,so it is one kind of effective remote sensing imagery classifying method.展开更多
Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is ...Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.展开更多
Most methods for classification of remote sensing data are based on the statistical parameter evaluation with the assumption that the samples obey the normal distribution. How-ever, more accurate classification result...Most methods for classification of remote sensing data are based on the statistical parameter evaluation with the assumption that the samples obey the normal distribution. How-ever, more accurate classification results can be obtained with the neural network method through getting knowledge from environments and adjusting the parameter (or weight) step by step by a specific measurement. This paper focuses on the double-layer structured Kohonen self-organizing feature map (SOFM), for which all neurons within the two layers are linked one another and those of the competition layers are linked as well along the sides. Therefore, the self-adapting learning ability is improved due to the effective competition and suppression in this method. The SOFM has become a hot topic in the research area of remote sensing data classi-fication. The Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) is a new satellite-borne remote sensing instrument with three 15-m resolution bands and three 30-m resolution bands at the near infrared. The ASTER data of Dagang district, Tianjin Munici-pality is used as the test data in this study. At first, the wavelet fusion is carried out to make the spatial resolutions of the ASTER data identical; then, the SOFM method is applied to classifying the land cover types. The classification results are compared with those of the maximum likeli-hood method (MLH). As a consequence, the classification accuracy of SOFM increases about by 7% in general and, in particular, it is almost as twice as that of the MLH method in the town.展开更多
The non-invasive evaluation of the heart through EectroCardioG-raphy(ECG)has played a key role in detecting heart disease.The analysis of ECG signals requires years of learning and experience to interpret and extract ...The non-invasive evaluation of the heart through EectroCardioG-raphy(ECG)has played a key role in detecting heart disease.The analysis of ECG signals requires years of learning and experience to interpret and extract useful information from them.Thus,a computerized system is needed to classify ECG signals with more accurate results effectively.Abnormal heart rhythms are called arrhythmias and cause sudden cardiac deaths.In this work,a Computerized Abnormal Heart Rhythms Detection(CAHRD)system is developed using ECG signals.It consists of four stages;preprocessing,feature extraction,feature optimization and classifier.At first,Pan and Tompkins algorithm is employed to detect the envelope of Q,R and S waves in the preprocessing stage.It uses a recursive filter to eliminate muscle noise,T-wave interference and baseline wander.As the analysis of ECG signal in the spatial domain does not provide a complete description of the signal,the feature extraction involves using frequency contents obtained from multiple wavelet filters;bi-orthogonal,Symlet and Daubechies at different resolution levels in the feature extraction stage.Then,Black Widow Optimization(BWO)is applied to optimize the hybrid wavelet features in the feature optimization stage.Finally,a kernel based Support Vector Machine(SVM)is employed to classify heartbeats into five classes.In SVM,Radial Basis Function(RBF),polynomial and linear kernels are used.A total of∼15000 ECG signals are obtained from the Massachusetts Institute of Technology-Beth Israel Hospital(MIT-BIH)arrhythmia database for performance evaluation of the proposed CAHRD system.Results show that the proposed CAHRD system proved to be a powerful tool for ECG analysis.It correctly classifies five classes of heartbeats with 99.91%accuracy using an RBF kernel with 2nd level wavelet coefficients.The CAHRD system achieves an improvement of∼6%over random projections with the ensemble SVM approach and∼2%over morphological and ECG segment based features with the RBF classifier.展开更多
Air temperature(Ta)datasets with high spatial and temporal resolutions are needed in a wide range of applications,such as hydrology,ecology,agriculture,and climate change studies.Nonetheless,the density of weather sta...Air temperature(Ta)datasets with high spatial and temporal resolutions are needed in a wide range of applications,such as hydrology,ecology,agriculture,and climate change studies.Nonetheless,the density of weather station networks is insufficient,especially in sparsely populated regions,greatly limiting the accuracy of estimates of spatially distributed Ta.Due to their continuous spatial coverage,remotely sensed land surface temperature(LST)data provide the possibility of exploring spatial estimates of Ta.However,because of the complex interaction of land and climate,retrieval of Ta from the LST is still far from straightforward.The estimation accuracy varies greatly depending on the model,particularly for maximum Ta.This study estimated monthly average daily minimum temperature(Tmin),average daily maximum temperature(Tmax)and average daily mean temperature(Tmean)over the Loess Plateau in China based on Moderate Resolution Imaging Spectroradiometer(MODIS)LST data(MYD11A2)and some auxiliary data using an artificial neural network(ANN)model.The data from 2003 to 2010 were used to train the ANN models,while 2011 to 2012 weather station temperatures were used to test the trained model.The results showed that the nighttime LST and mean LST provide good estimates of Tmin and Tmean,with root mean square errors(RMSEs)of 1.04℃ and 1.01℃,respectively.Moreover,the best RMSE of Tmax estimation was 1.27℃.Compared with the other two published Ta gridded datasets,the produced 1 km×1 km dataset accurately captured both the temporal and spatial patterns of Ta.The RMSE of Tmin estimation was more sensitive to elevation,while that of Tmax was more sensitive to month.Except for land cover type as the input variable,which reduced the RMSE by approximately 0.01℃,the other vegetation-related variables did not improve the performance of the model.The results of this study indicated that ANN,a type of machine learning method,is effective for long-term and large-scale Ta estimation.展开更多
The fraction of photosynthetically active radiation(FPAR) is a key variable in the assessment of vegetation productivity and land ecosystem carbon cycles.Based on ground-measured corn hyperspectral reflectance and FPA...The fraction of photosynthetically active radiation(FPAR) is a key variable in the assessment of vegetation productivity and land ecosystem carbon cycles.Based on ground-measured corn hyperspectral reflectance and FPAR data over Northeast China,the correlations between corn-canopy FPAR and hyperspectral reflectance were analyzed,and the FPAR estimation performances using vegetation index(VI) and neural network(NN) methods with different two-band-combination hyperspectral reflectance were investigated.The results indicated that the corncanopy FPAR retained almost a constant value in an entire day.The negative correlations between FPAR and visible and shortwave infrared reflectance(SWIR) bands are stronger than the positive correlations between FPAR and near-infrared band reflectance(NIR).For the six VIs,the normalized difference vegetation index(NDVI) and simple ratio(SR) performed best for estimating corn FPAR(the maximum R2 of 0.8849 and 0.8852,respectively).However,the NN method esti-mated results(the maximum R2 is 0.9417) were obviously better than all of the VIs.For NN method,the two-band combinations showing the best corn FPAR estimation performances were from the NIR and visible bands;for VIs,however,they were from the SWIR and NIR bands.As for both the methods,the SWIR band performed exceptionally well for corn FPAR estimation.This may be attributable to the fact that the reflectance of the SWIR band were strongly controlled by leaf water content,which is a key component of corn photosynthesis and greatly affects the absorption of photosynthetically active radiation(APAR),and makes further impact on corn-canopy FPAR.展开更多
A brain tumor is a mass of abnormal cells in the brain. Brain tumors can be benign (noncancerous) or malignant (cancerous). Conventional diagnosis of a brain tumor by the radiologist is done by examining a set of imag...A brain tumor is a mass of abnormal cells in the brain. Brain tumors can be benign (noncancerous) or malignant (cancerous). Conventional diagnosis of a brain tumor by the radiologist is done by examining a set of images produced by magnetic resonance imaging (MRI). Many computer-aided detection (CAD) systems have been developed in order to help the radiologists reach their goal of correctly classifying the MRI image. Convolutional neural networks (CNNs) have been widely used in the classification of medical images. This paper presents a novel CAD technique for the classification of brain tumors in MRI images. The proposed system extracts features from the brain MRI images by utilizing the strong energy compactness property exhibited by the Discrete Wavelet Transform (DWT). The Wavelet features are then applied to a CNN to classify the input MRI image. Experimental results indicate that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 99.3%.展开更多
文摘Recently, convolutional neural networks (CNNs) have been utilized in medical imaging research field and have successfully shown their ability in image classification and detection. In this paper we used a CNN combined with a wavelet transform approach for classifying a dataset of 448 lung CT images into 4 categories, e.g. lung adenocarcinoma, lung squamous cell carcinoma, metastatic lung cancer, and normal. The key difference between the commonly-used CNNs and the presented method is that in this method, we adopt the use of redundant wavelet coefficients at level 1 as inputs to the CNN, instead of using original images. One of the main advantages of the proposed method is that it is not necessary to extract regions of interest from original images. The wavelet coefficients of the entire image are used as inputs to the CNN. We compare the classification performance of the proposed method to that of an existing CNN classifier and a CNN-based support vector machine classifier. The experimental results show that the proposed method outperforms the other two methods and achieve the highest overall accuracy of 91.9%. It demonstrates the potential for use in classification of lung diseases in CT images.
文摘Machine learning is an integral technology many people utilize in all areas of human life. It is pervasive in modern living worldwide, and has multiple usages. One application is image classification, embraced across many spheres of influence such as business, finance, medicine, etc. to enhance produces, causes, efficiency, etc. This need for more accurate, detail-oriented classification increases the need for modifications, adaptations, and innovations to Deep Learning Algorithms. This article used Convolutional Neural Networks (CNN) to classify scenes in the CIFAR-10 database, and detect emotions in the KDEF database. The proposed method converted the data to the wavelet domain to attain greater accuracy and comparable efficiency to the spatial domain processing. By dividing image data into subbands, important feature learning occurred over differing low to high frequencies. The combination of the learned low and high frequency features, and processing the fused feature mapping resulted in an advance in the detection accuracy. Comparing the proposed methods to spatial domain CNN and Stacked Denoising Autoencoder (SDA), experimental findings revealed a substantial increase in accuracy.
文摘In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to the opening up, economic prosperity and social stability of Northeast China. In this paper, the remote sensing ecological index (RSEI) of Hailin City in recent 20 years was calculated by using Landsat 5/8/9 series satellite images, and the temporal and spatial changes of the ecological environment in Hailin City were further analyzed and the influencing factors were discussed. From 2003 to 2023, the mean value of RSEI in Hailin City decreased and increased, and the ecological environment decreased slightly as a whole. RSEI declined most significantly from 2003 to 2008, and it increased from 2008 to 2013, decreased from 2013 to 2018, and increased from 2018 to 2023 again, with higher RSEI value in the south and lower RSEI value in the northwest. It is suggested to appropriately increase vegetation coverage in the northwest to improve ecological quality. As a result, the predicted value of Elman dynamic recurrent neural network model is consistent with the change trend of the mean value, and the prediction error converges quickly, which can accurately predict the ecological environment quality in the future study area.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R136)PrincessNourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4210118DSR28).
文摘Object detection(OD)in remote sensing images(RSI)acts as a vital part in numerous civilian and military application areas,like urban planning,geographic information system(GIS),and search and rescue functions.Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions.The latest advancements in deep learning(DL)approaches permit the design of effectual OD approaches.This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection(AEODCNN-VD)model on Remote Sensing Images.The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly.To detect vehicles,the presented AEODCNN-VD model employs single shot detector(SSD)with Inception network as a baseline model.In addition,Multiway Feature Pyramid Network(MFPN)is used for handling objects of varying sizes in RSIs.The features from the Inception model are passed into theMFPNformultiway andmultiscale feature fusion.Finally,the fused features are passed into bounding box and class prediction networks.For enhancing the detection efficiency of the AEODCNN-VD approach,AEO based hyperparameter optimizer is used,which is stimulated by the energy transfer strategies such as production,consumption,and decomposition in an ecosystem.The performance validation of the presentedmethod on benchmark datasets showed promising performance over recent DL models.
文摘Computerized tomography (CT) scan is the only screening test recommended by doctors to look for lung cancer. Convolutional neural networks (CNNs) have recently proven their ability to successfully classify medical images. Due to its strong compactness property, the Discrete Wavelet transform (DWT) has been commonly used in image feature extraction applications. This paper presents a novel technique for the classification of Lung cancer in Computerized Tomography (CT) scans using Wavelets to find discriminative features in the CT images and CNN to classify the extracted features. Experimental results prove that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 99.5%.
文摘Based on pattern recognition theory and neural network technology, moving objects automatic detection and classification method integrating advanced wavelet analysis are discussed in detail. An algorithm of moving targets pattern recognition on the combination of inter-frame difference and wavelet neural network is presented. The experimental results indicate that the designed BP wavelet network using this algorithm can recognize and classify moving targets rapidly and effectively.
基金Project supported by the Key Technologies Research and Development Program of Guangdong Province Foundation (No. 2003A3040301).
文摘Vehicle emission has been the major source of air pollution in urban areas in the past two decades. This article proposes an artificial neural network model for identifying the taxi gross emitters based on the remote sensing data. After carrying out the field test in Guangzhou and analyzing various factors from the emission data, the artificial neural network modeling was proved to be an advisable method of identifying the gross emitters. On the basis of the principal component analysis and the selection of algorithm and architecture, the Back-Propagation neural network model with 8-17-1 architecture was established as the optimal approach for this purpose. It gave a percentage of hits of 93%. Our previous research result and the result from aggression analysis were compared, and they provided respectively the percentage of hits of 81.63% and 75%. This comparison demonstrates the potentiality and validity of the proposed method in the identification of taxi gross emitters.
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
文摘Poverty has always been one of the topics concerned by governments and researchers all over the world, especially in developing countries. Remote sensing image is widely used in poverty estimation because of its large area observation, timeliness and periodicity. In this study, we explore the applicability of convolution neural network (CNN) combined with remote sensing image in regional poverty estimation. In the 2016 economic indicators estimation of Guizhou Province, China, the Pearson coefficient of per capita GDP (PCGDP) reached 0.76, which means that the image features extracted by CNN can explain the change of PCGDP of county level economic indicators up to 76%. Compared with other methods, our method still has high precision. Based on these results, we found that convolutional neural network combined with remote sensing image can be used in regional poverty estimation.
基金Project (Nos. 40571115 and 40271078) supported by the National Natural Science Foundation of China
文摘Hyperspectral reflectance (350~2500 nm) data were recorded at two different sites of rice in two experiment fields including two cultivars, and three levels of nitrogen (N) application. Twenty-five Vegetation Indices (VIs) were used to predict the rice agronomic parameters including Leaf Area Index (LAI, m2 green leaf/m2 soil) and Green Leaf Chlorophyll Density (GLCD, mg chlorophyll/m2 soil) by the traditional regression models and Radial Basis Function Neural Network (RBF). RBF emerged as a variant of Artificial Neural Networks (ANNs) in the late 1980’s. A large variety of training algorithms has been tested for training RBF networks. In this study, Original RBF (ORBF), Gradient Descent RBF (GDRBF), and Generalized Regression Neural Network (GRNN) were employed. Results showed that green waveband Normalized Difference Vegetation Index (NDVIgreen) and TCARI/OSAVI have the best prediction power for LAI by exponent model and ORBF respectively, and that TCARI/OSAVI has the best prediction power for GLCD by exponent model and GDRBF. The best performances of RBF are compared with the traditional models, showing that the relationship between VIs and agronomic variables are further improved when RBF is used. Compared with the best traditional models, ORBF using TCARI/OSAVI improves the prediction power for LAI by lowering the Root Mean Square Error (RMSE) for 0.1119, and GDRBF using TCARI/OSAVI improves the prediction power for GLCD by lowering the RMSE for 26.7853. It is concluded that RBF provides a useful exploratory and predictive tool when applied to the sensitive VIs.
基金Project(J00B03) supported by Shandong Province of China
文摘Aiming at the characteristics of remote sensing image classification, the mixed pixel problem is one of the main factors that affect the improvement of classifying precision in remote sensing classification. A BP neural network was established to solve mixed pixel classifying problems. The aim of our work is to improve the BP network algorithm and set the intensity of training, which changes with training process, because the BP algorithm converyging speed of learning algorithm is rather slow, it is possible to fall into the local minimum, and because the algorithm makes the learning result poor, the global minimum value can’t be reached. The results show that this method effectively solves mixed pixel classifying problem, improves learning speed and classification accuracy of BP network classifier,so it is one kind of effective remote sensing imagery classifying method.
基金National Natural Science Foundation of China(No.61101202)
文摘Remote sensing image classification is the basis of remote sensing image analysis and understanding.It aims to assign each pixel an object class label.To achieve satisfactory classification accuracy,single feature is not enough.Multiple features are usually integrated in remote sensing image classification.In this paper,a method based on neural network to combine multiple features was proposed.A single network was used to perform the task instead of ensemble of neural networks.A special architecture of network was designed to fit the task.The method effectively avoids the problems in direct conjunction of multiple features.Experiments on Indian93 data set show that the method has obvious advantages over conjunction of features on both recognition rate and training time.
文摘Most methods for classification of remote sensing data are based on the statistical parameter evaluation with the assumption that the samples obey the normal distribution. How-ever, more accurate classification results can be obtained with the neural network method through getting knowledge from environments and adjusting the parameter (or weight) step by step by a specific measurement. This paper focuses on the double-layer structured Kohonen self-organizing feature map (SOFM), for which all neurons within the two layers are linked one another and those of the competition layers are linked as well along the sides. Therefore, the self-adapting learning ability is improved due to the effective competition and suppression in this method. The SOFM has become a hot topic in the research area of remote sensing data classi-fication. The Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) is a new satellite-borne remote sensing instrument with three 15-m resolution bands and three 30-m resolution bands at the near infrared. The ASTER data of Dagang district, Tianjin Munici-pality is used as the test data in this study. At first, the wavelet fusion is carried out to make the spatial resolutions of the ASTER data identical; then, the SOFM method is applied to classifying the land cover types. The classification results are compared with those of the maximum likeli-hood method (MLH). As a consequence, the classification accuracy of SOFM increases about by 7% in general and, in particular, it is almost as twice as that of the MLH method in the town.
文摘The non-invasive evaluation of the heart through EectroCardioG-raphy(ECG)has played a key role in detecting heart disease.The analysis of ECG signals requires years of learning and experience to interpret and extract useful information from them.Thus,a computerized system is needed to classify ECG signals with more accurate results effectively.Abnormal heart rhythms are called arrhythmias and cause sudden cardiac deaths.In this work,a Computerized Abnormal Heart Rhythms Detection(CAHRD)system is developed using ECG signals.It consists of four stages;preprocessing,feature extraction,feature optimization and classifier.At first,Pan and Tompkins algorithm is employed to detect the envelope of Q,R and S waves in the preprocessing stage.It uses a recursive filter to eliminate muscle noise,T-wave interference and baseline wander.As the analysis of ECG signal in the spatial domain does not provide a complete description of the signal,the feature extraction involves using frequency contents obtained from multiple wavelet filters;bi-orthogonal,Symlet and Daubechies at different resolution levels in the feature extraction stage.Then,Black Widow Optimization(BWO)is applied to optimize the hybrid wavelet features in the feature optimization stage.Finally,a kernel based Support Vector Machine(SVM)is employed to classify heartbeats into five classes.In SVM,Radial Basis Function(RBF),polynomial and linear kernels are used.A total of∼15000 ECG signals are obtained from the Massachusetts Institute of Technology-Beth Israel Hospital(MIT-BIH)arrhythmia database for performance evaluation of the proposed CAHRD system.Results show that the proposed CAHRD system proved to be a powerful tool for ECG analysis.It correctly classifies five classes of heartbeats with 99.91%accuracy using an RBF kernel with 2nd level wavelet coefficients.The CAHRD system achieves an improvement of∼6%over random projections with the ensemble SVM approach and∼2%over morphological and ECG segment based features with the RBF classifier.
基金Under the auspices of the‘Beautiful China’Ecological Civilization Construction Science and Technology Project(No.XDA23100203)National Natural Science Foundation of China(No.42071289)Henan Postdoctoral Foundation(No.20180087)。
文摘Air temperature(Ta)datasets with high spatial and temporal resolutions are needed in a wide range of applications,such as hydrology,ecology,agriculture,and climate change studies.Nonetheless,the density of weather station networks is insufficient,especially in sparsely populated regions,greatly limiting the accuracy of estimates of spatially distributed Ta.Due to their continuous spatial coverage,remotely sensed land surface temperature(LST)data provide the possibility of exploring spatial estimates of Ta.However,because of the complex interaction of land and climate,retrieval of Ta from the LST is still far from straightforward.The estimation accuracy varies greatly depending on the model,particularly for maximum Ta.This study estimated monthly average daily minimum temperature(Tmin),average daily maximum temperature(Tmax)and average daily mean temperature(Tmean)over the Loess Plateau in China based on Moderate Resolution Imaging Spectroradiometer(MODIS)LST data(MYD11A2)and some auxiliary data using an artificial neural network(ANN)model.The data from 2003 to 2010 were used to train the ANN models,while 2011 to 2012 weather station temperatures were used to test the trained model.The results showed that the nighttime LST and mean LST provide good estimates of Tmin and Tmean,with root mean square errors(RMSEs)of 1.04℃ and 1.01℃,respectively.Moreover,the best RMSE of Tmax estimation was 1.27℃.Compared with the other two published Ta gridded datasets,the produced 1 km×1 km dataset accurately captured both the temporal and spatial patterns of Ta.The RMSE of Tmin estimation was more sensitive to elevation,while that of Tmax was more sensitive to month.Except for land cover type as the input variable,which reduced the RMSE by approximately 0.01℃,the other vegetation-related variables did not improve the performance of the model.The results of this study indicated that ANN,a type of machine learning method,is effective for long-term and large-scale Ta estimation.
基金Under the auspices of National Key Research Program of Global Change Research (No.2010CB951302)National Natural Science Fundation of China (No.40771146)China Postdoctoral Science Foundation Funded Project (No.07Z7601MZ1)
文摘The fraction of photosynthetically active radiation(FPAR) is a key variable in the assessment of vegetation productivity and land ecosystem carbon cycles.Based on ground-measured corn hyperspectral reflectance and FPAR data over Northeast China,the correlations between corn-canopy FPAR and hyperspectral reflectance were analyzed,and the FPAR estimation performances using vegetation index(VI) and neural network(NN) methods with different two-band-combination hyperspectral reflectance were investigated.The results indicated that the corncanopy FPAR retained almost a constant value in an entire day.The negative correlations between FPAR and visible and shortwave infrared reflectance(SWIR) bands are stronger than the positive correlations between FPAR and near-infrared band reflectance(NIR).For the six VIs,the normalized difference vegetation index(NDVI) and simple ratio(SR) performed best for estimating corn FPAR(the maximum R2 of 0.8849 and 0.8852,respectively).However,the NN method esti-mated results(the maximum R2 is 0.9417) were obviously better than all of the VIs.For NN method,the two-band combinations showing the best corn FPAR estimation performances were from the NIR and visible bands;for VIs,however,they were from the SWIR and NIR bands.As for both the methods,the SWIR band performed exceptionally well for corn FPAR estimation.This may be attributable to the fact that the reflectance of the SWIR band were strongly controlled by leaf water content,which is a key component of corn photosynthesis and greatly affects the absorption of photosynthetically active radiation(APAR),and makes further impact on corn-canopy FPAR.
文摘A brain tumor is a mass of abnormal cells in the brain. Brain tumors can be benign (noncancerous) or malignant (cancerous). Conventional diagnosis of a brain tumor by the radiologist is done by examining a set of images produced by magnetic resonance imaging (MRI). Many computer-aided detection (CAD) systems have been developed in order to help the radiologists reach their goal of correctly classifying the MRI image. Convolutional neural networks (CNNs) have been widely used in the classification of medical images. This paper presents a novel CAD technique for the classification of brain tumors in MRI images. The proposed system extracts features from the brain MRI images by utilizing the strong energy compactness property exhibited by the Discrete Wavelet Transform (DWT). The Wavelet features are then applied to a CNN to classify the input MRI image. Experimental results indicate that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 99.3%.