Based on conformal construction of physical model in a three-dimensional Cartesian grid,an integral-based conformal convolutional perfectly matched layer(CPML) is given for solving the truncation problem of the open...Based on conformal construction of physical model in a three-dimensional Cartesian grid,an integral-based conformal convolutional perfectly matched layer(CPML) is given for solving the truncation problem of the open port when the enlarged cell technique conformal finite-difference time-domain(ECT-CFDTD) method is used to simulate the wave propagation inside a perfect electric conductor(PEC) waveguide.The algorithm has the same numerical stability as the ECT-CFDTD method.For the long-time propagation problems of an evanescent wave in a waveguide,several numerical simulations are performed to analyze the reflection error by sweeping the constitutive parameters of the integral-based conformal CPML.Our numerical results show that the integral-based conformal CPML can be used to efficiently truncate the open port of the waveguide.展开更多
A convolution perfectly matched layer(CPML)can efficiently absorb boundary reflection in numerical simulation.However,the CPML is suitable for the first-order elastic wave equation and is difficult to apply directly t...A convolution perfectly matched layer(CPML)can efficiently absorb boundary reflection in numerical simulation.However,the CPML is suitable for the first-order elastic wave equation and is difficult to apply directly to the second-order elastic wave equation.In view of this,based on the first-order CPML absorbing boundary condition,we propose a new CPML(NCPML)boundary which can be directly applied to the second-order wave equation.We first systematically extend the first-order CPML technique into second-order wave equations,neglecting the space-varying characteristics of the partial damping coefficient in the complex-frequency domain,avoiding the generation of convolution in the time domain.We then transform the technique back to the time domain through the inverse Fourier transform.Numerical simulation indicates that the space-varying characteristics of the attenuation factor have little influence on the absorption effect and increase the memory at the same time.A number of numerical examples show that the NCPML proposed in this study is effective in simulating elastic wave propagation,and this algorithm is more efficient and requires less memory allocation than the conventional PML absorbing boundary.展开更多
Median filtering is a nonlinear signal processing technique and has an advantage in the field of image anti-forensics.Therefore,more attention has been paid to the forensics research of median filtering.In this paper,...Median filtering is a nonlinear signal processing technique and has an advantage in the field of image anti-forensics.Therefore,more attention has been paid to the forensics research of median filtering.In this paper,a median filtering forensics method based on quaternion convolutional neural network(QCNN)is proposed.The median filtering residuals(MFR)are used to preprocess the images.Then the output of MFR is expanded to four channels and used as the input of QCNN.In QCNN,quaternion convolution is designed that can better mix the information of different channels than traditional methods.The quaternion pooling layer is designed to evaluate the result of quaternion convolution.QCNN is proposed to features well combine the three-channel information of color image and fully extract forensics features.Experiments show that the proposed method has higher accuracy and shorter training time than the traditional convolutional neural network with the same convolution depth.展开更多
Diabetic retinopathy is a critical eye condition that,if not treated,can lead to vision loss.Traditional methods of diagnosing and treating the disease are time-consuming and expensive.However,machine learning and dee...Diabetic retinopathy is a critical eye condition that,if not treated,can lead to vision loss.Traditional methods of diagnosing and treating the disease are time-consuming and expensive.However,machine learning and deep transfer learning(DTL)techniques have shown promise in medical applications,including detecting,classifying,and segmenting diabetic retinopathy.These advanced techniques offer higher accuracy and performance.ComputerAided Diagnosis(CAD)is crucial in speeding up classification and providing accurate disease diagnoses.Overall,these technological advancements hold great potential for improving the management of diabetic retinopathy.The study’s objective was to differentiate between different classes of diabetes and verify the model’s capability to distinguish between these classes.The robustness of the model was evaluated using other metrics such as accuracy(ACC),precision(PRE),recall(REC),and area under the curve(AUC).In this particular study,the researchers utilized data cleansing techniques,transfer learning(TL),and convolutional neural network(CNN)methods to effectively identify and categorize the various diseases associated with diabetic retinopathy(DR).They employed the VGG-16CNN model,incorporating intelligent parameters that enhanced its robustness.The outcomes surpassed the results obtained by the auto enhancement(AE)filter,which had an ACC of over 98%.The manuscript provides visual aids such as graphs,tables,and techniques and frameworks to enhance understanding.This study highlights the significance of optimized deep TL in improving the metrics of the classification of the four separate classes of DR.The manuscript emphasizes the importance of using the VGG16CNN classification technique in this context.展开更多
Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Parti...Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Particle Swarm Optimization(SPSOM)and Incremental Deep Convolution Neural Networks(IDCNN)for detecting multiple objects.However,the study considered opticalflows resulting in assessing motion contrasts.Existing methods have issue with accuracy and error rates in motion contrast detection.Hence,the overall object detection performance is reduced significantly.Thus,consideration of object motions in videos efficiently is a critical issue to be solved.To overcome the above mentioned problems,this research work proposes a method involving ensemble approaches to and detect objects efficiently from video streams.This work uses a system modeled on swarm optimization and ensemble learning called Spatiotemporal Glowworm Swarm Optimization Model(SGSOM)for detecting multiple significant objects.A steady quality in motion contrasts is maintained in this work by using Chebyshev distance matrix.The proposed system achieves global optimization in its multiple object detection by exploiting spatial/temporal cues and local constraints.Its experimental results show that the proposed system scores 4.8%in Mean Absolute Error(MAE)while achieving 86%in accuracy,81.5%in precision,85%in recall and 81.6%in F-measure and thus proving its utility in detecting multiple objects.展开更多
Recently, image representations derived by convolutional neural networks(CNN) have achieved promising performance for instance retrieval, and they outperformthe traditional hand-crafted image features. However, most o...Recently, image representations derived by convolutional neural networks(CNN) have achieved promising performance for instance retrieval, and they outperformthe traditional hand-crafted image features. However, most of existing CNN-based featuresare proposed to describe the entire images, and thus they are less robust to backgroundclutter. This paper proposes a region of interest (RoI)-based deep convolutionalrepresentation for instance retrieval. It first detects the region of interests (RoIs) from animage, and then extracts a set of RoI-based CNN features from the fully-connected layerof CNN. The proposed RoI-based CNN feature describes the patterns of the detected RoIs,so that the visual matching can be implemented at image region-level to effectively identifytarget objects from cluttered backgrounds. Moreover, we test the performance of theproposed RoI-based CNN feature, when it is extracted from different convolutional layersor fully-connected layers. Also, we compare the performance of RoI-based CNN featurewith those of the state-of-the-art CNN features on two instance retrieval benchmarks.Experimental results show that the proposed RoI-based CNN feature provides superiorperformance than the state-of-the-art CNN features for in-stance retrieval.展开更多
Image captioning is an emerging field in machine learning.It refers to the ability to automatically generate a syntactically and semantically meaningful sentence that describes the content of an image.Image captioning...Image captioning is an emerging field in machine learning.It refers to the ability to automatically generate a syntactically and semantically meaningful sentence that describes the content of an image.Image captioning requires a complex machine learning process as it involves two sub models:a vision sub-model for extracting object features and a language sub-model that use the extracted features to generate meaningful captions.Attention-based vision transformers models have a great impact in vision field recently.In this paper,we studied the effect of using the vision transformers on the image captioning process by evaluating the use of four different vision transformer models for the vision sub-models of the image captioning The first vision transformers used is DINO(self-distillation with no labels).The second is PVT(Pyramid Vision Transformer)which is a vision transformer that is not using convolutional layers.The third is XCIT(cross-Covariance Image Transformer)which changes the operation in self-attention by focusing on feature dimension instead of token dimensions.The last one is SWIN(Shifted windows),it is a vision transformer which,unlike the other transformers,uses shifted-window in splitting the image.For a deeper evaluation,the four mentioned vision transformers have been tested with their different versions and different configuration,we evaluate the use of DINO model with five different backbones,PVT with two versions:PVT_v1and PVT_v2,one model of XCIT,SWIN transformer.The results show the high effectiveness of using SWIN-transformer within the proposed image captioning model with regard to the other models.展开更多
Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the da...Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the data from a single monitoring point and neglect the spatial relationships between multiple monitoring points.Besides,most models lack flexibility in providing predictions for multiple days after monitoring activity.This study proposes a sequence-to-sequence(seq2seq)two-dimensional(2D)convolutional long short-term memory neural network(S2SCL2D)for predicting the spatiotemporal wall deflections induced by deep excavations.The model utilizes the data from all monitoring points on the entire wall and extracts spatiotemporal features from data by combining the 2D convolutional layers and long short-term memory(LSTM)layers.The S2SCL2D model achieves a long-term prediction of wall deflections through a recursive seq2seq structure.The excavation depth,which has a significant impact on wall deflections,is also considered using a feature fusion method.An excavation project in Hangzhou,China,is used to illustrate the proposed model.The results demonstrate that the S2SCL2D model has superior prediction accuracy and robustness than that of the LSTM and S2SCL1D(one-dimensional)models.The prediction model demonstrates a strong generalizability when applied to an adjacent excavation.Based on the long-term prediction results,practitioners can plan and allocate resources in advance to address the potential engineering issues.展开更多
Parallel acceleration of convolution perfectly matched layer (CPML) algorithm suffers from massive division operation which is widely accepted as one of the most expensive operations for the equipment such as graphi...Parallel acceleration of convolution perfectly matched layer (CPML) algorithm suffers from massive division operation which is widely accepted as one of the most expensive operations for the equipment such as graphic processing unit (GPU), field programmable gate array (FPGA) etc. In pursuit of higher efficiency and lower power consumption, this article revisited the CPML theory and proposed a new fast division-free parallel CPML structure. By optimally rearranging the CPML inner iteration process, all the division operators can be eliminated and replaced by recalculating the related field updating coefficients offline. Experiments show that the proposed division-free structure can save more than 50% arithmetic instructions and 25% execution time of the traditional parallel CPML structure without any accuracy loss.展开更多
In order to solve the problem of truncating the open boundaries of cylindrical waveguides used in the simulation of high power microwave (HPM) sources, this paper studies the convolutional PML (CPML) in the cylind...In order to solve the problem of truncating the open boundaries of cylindrical waveguides used in the simulation of high power microwave (HPM) sources, this paper studies the convolutional PML (CPML) in the cylindrical coordinate system. The electromagnetic field's FDTD equations and the expressions of axis boundary conditions are presented. Numerical experiments are conducted to validate the equations and axis boundary conditions. The performance of CPML is simulated when it is used to truncate the cylindrical waveguides excited by the sources with different frequencies and modes in the 2.5-dimensional problems. Numerical results show that the maximum relative errors are all less than -90 dB. The CPML method is introduced in the 2.5-dimensional electromagnetic PIC software, and the relativistic backward wave oscillator is simulated by using this method. The results show that the property of CPML is much better than that of the Mur-type absorbing boundary condition when they are used to truncate the open boundaries of waveguides. The CPML is especially suitable for truncating the open boundaries of the dispersive waveguide devices in the simulation of HPM sources.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.61231003)
文摘Based on conformal construction of physical model in a three-dimensional Cartesian grid,an integral-based conformal convolutional perfectly matched layer(CPML) is given for solving the truncation problem of the open port when the enlarged cell technique conformal finite-difference time-domain(ECT-CFDTD) method is used to simulate the wave propagation inside a perfect electric conductor(PEC) waveguide.The algorithm has the same numerical stability as the ECT-CFDTD method.For the long-time propagation problems of an evanescent wave in a waveguide,several numerical simulations are performed to analyze the reflection error by sweeping the constitutive parameters of the integral-based conformal CPML.Our numerical results show that the integral-based conformal CPML can be used to efficiently truncate the open port of the waveguide.
基金supported by the National Science and Technology Major Special Sub-project of China(No.2016ZX05024-001-008)the National Natural Science Foundation Joint Fund Prcject of China(No.U1562215).
文摘A convolution perfectly matched layer(CPML)can efficiently absorb boundary reflection in numerical simulation.However,the CPML is suitable for the first-order elastic wave equation and is difficult to apply directly to the second-order elastic wave equation.In view of this,based on the first-order CPML absorbing boundary condition,we propose a new CPML(NCPML)boundary which can be directly applied to the second-order wave equation.We first systematically extend the first-order CPML technique into second-order wave equations,neglecting the space-varying characteristics of the partial damping coefficient in the complex-frequency domain,avoiding the generation of convolution in the time domain.We then transform the technique back to the time domain through the inverse Fourier transform.Numerical simulation indicates that the space-varying characteristics of the attenuation factor have little influence on the absorption effect and increase the memory at the same time.A number of numerical examples show that the NCPML proposed in this study is effective in simulating elastic wave propagation,and this algorithm is more efficient and requires less memory allocation than the conventional PML absorbing boundary.
基金This work was supported in part by the Natural Science Foundation of China under Grants(Nos.61702235,61772281,U1636219,U1636117,61702235,61502241,61272421,61232016,61402235 and 61572258)in part by the National Key R\&D Program of China(Grant Nos.2016YFB0801303 and 2016QY 01W0105)+2 种基金in part by the plan for Scientific Talent of Henan Province(Grant No.2018JR0018)in part by the Natural Science Foundation of Jiangsu Province,China under Grant BK20141006in part by the Natural Science Foundation of the Universities in Jiangsu Province under Grant 14KJB520024,the PAPD fund and the CICAEET fund.
文摘Median filtering is a nonlinear signal processing technique and has an advantage in the field of image anti-forensics.Therefore,more attention has been paid to the forensics research of median filtering.In this paper,a median filtering forensics method based on quaternion convolutional neural network(QCNN)is proposed.The median filtering residuals(MFR)are used to preprocess the images.Then the output of MFR is expanded to four channels and used as the input of QCNN.In QCNN,quaternion convolution is designed that can better mix the information of different channels than traditional methods.The quaternion pooling layer is designed to evaluate the result of quaternion convolution.QCNN is proposed to features well combine the three-channel information of color image and fully extract forensics features.Experiments show that the proposed method has higher accuracy and shorter training time than the traditional convolutional neural network with the same convolution depth.
文摘Diabetic retinopathy is a critical eye condition that,if not treated,can lead to vision loss.Traditional methods of diagnosing and treating the disease are time-consuming and expensive.However,machine learning and deep transfer learning(DTL)techniques have shown promise in medical applications,including detecting,classifying,and segmenting diabetic retinopathy.These advanced techniques offer higher accuracy and performance.ComputerAided Diagnosis(CAD)is crucial in speeding up classification and providing accurate disease diagnoses.Overall,these technological advancements hold great potential for improving the management of diabetic retinopathy.The study’s objective was to differentiate between different classes of diabetes and verify the model’s capability to distinguish between these classes.The robustness of the model was evaluated using other metrics such as accuracy(ACC),precision(PRE),recall(REC),and area under the curve(AUC).In this particular study,the researchers utilized data cleansing techniques,transfer learning(TL),and convolutional neural network(CNN)methods to effectively identify and categorize the various diseases associated with diabetic retinopathy(DR).They employed the VGG-16CNN model,incorporating intelligent parameters that enhanced its robustness.The outcomes surpassed the results obtained by the auto enhancement(AE)filter,which had an ACC of over 98%.The manuscript provides visual aids such as graphs,tables,and techniques and frameworks to enhance understanding.This study highlights the significance of optimized deep TL in improving the metrics of the classification of the four separate classes of DR.The manuscript emphasizes the importance of using the VGG16CNN classification technique in this context.
文摘Recent developments in computer vision applications have enabled detection of significant visual objects in video streams.Studies quoted in literature have detected objects from video streams using Spatiotemporal Particle Swarm Optimization(SPSOM)and Incremental Deep Convolution Neural Networks(IDCNN)for detecting multiple objects.However,the study considered opticalflows resulting in assessing motion contrasts.Existing methods have issue with accuracy and error rates in motion contrast detection.Hence,the overall object detection performance is reduced significantly.Thus,consideration of object motions in videos efficiently is a critical issue to be solved.To overcome the above mentioned problems,this research work proposes a method involving ensemble approaches to and detect objects efficiently from video streams.This work uses a system modeled on swarm optimization and ensemble learning called Spatiotemporal Glowworm Swarm Optimization Model(SGSOM)for detecting multiple significant objects.A steady quality in motion contrasts is maintained in this work by using Chebyshev distance matrix.The proposed system achieves global optimization in its multiple object detection by exploiting spatial/temporal cues and local constraints.Its experimental results show that the proposed system scores 4.8%in Mean Absolute Error(MAE)while achieving 86%in accuracy,81.5%in precision,85%in recall and 81.6%in F-measure and thus proving its utility in detecting multiple objects.
基金supported by the National Natural Science Foundation ofChina under Grant 61602253, U1836208, U1536206, U1836110, 61672294, in part by theNational Key R&D Program of China under Grant 2018YFB1003205, in part by the PriorityAcademic Program Development of Jiangsu Higher Education Institutions (PAPD) fund, inpart by the Collaborative Innovation Center of Atmospheric Environment and EquipmentTechnology (CICAEET) fund, China, and in part by MOST under contracts 108-2634-F-259-001- through Pervasive Artificial Intelligence Research (PAIR) Labs, Taiwan.
文摘Recently, image representations derived by convolutional neural networks(CNN) have achieved promising performance for instance retrieval, and they outperformthe traditional hand-crafted image features. However, most of existing CNN-based featuresare proposed to describe the entire images, and thus they are less robust to backgroundclutter. This paper proposes a region of interest (RoI)-based deep convolutionalrepresentation for instance retrieval. It first detects the region of interests (RoIs) from animage, and then extracts a set of RoI-based CNN features from the fully-connected layerof CNN. The proposed RoI-based CNN feature describes the patterns of the detected RoIs,so that the visual matching can be implemented at image region-level to effectively identifytarget objects from cluttered backgrounds. Moreover, we test the performance of theproposed RoI-based CNN feature, when it is extracted from different convolutional layersor fully-connected layers. Also, we compare the performance of RoI-based CNN featurewith those of the state-of-the-art CNN features on two instance retrieval benchmarks.Experimental results show that the proposed RoI-based CNN feature provides superiorperformance than the state-of-the-art CNN features for in-stance retrieval.
文摘Image captioning is an emerging field in machine learning.It refers to the ability to automatically generate a syntactically and semantically meaningful sentence that describes the content of an image.Image captioning requires a complex machine learning process as it involves two sub models:a vision sub-model for extracting object features and a language sub-model that use the extracted features to generate meaningful captions.Attention-based vision transformers models have a great impact in vision field recently.In this paper,we studied the effect of using the vision transformers on the image captioning process by evaluating the use of four different vision transformer models for the vision sub-models of the image captioning The first vision transformers used is DINO(self-distillation with no labels).The second is PVT(Pyramid Vision Transformer)which is a vision transformer that is not using convolutional layers.The third is XCIT(cross-Covariance Image Transformer)which changes the operation in self-attention by focusing on feature dimension instead of token dimensions.The last one is SWIN(Shifted windows),it is a vision transformer which,unlike the other transformers,uses shifted-window in splitting the image.For a deeper evaluation,the four mentioned vision transformers have been tested with their different versions and different configuration,we evaluate the use of DINO model with five different backbones,PVT with two versions:PVT_v1and PVT_v2,one model of XCIT,SWIN transformer.The results show the high effectiveness of using SWIN-transformer within the proposed image captioning model with regard to the other models.
基金supported by the National Natural Science Foundation of China(Grant No.42307218)the Foundation of Key Laboratory of Soft Soils and Geoenvironmental Engineering(Zhejiang University),Ministry of Education(Grant No.2022P08)the Natural Science Foundation of Zhejiang Province(Grant No.LTZ21E080001).
文摘Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the data from a single monitoring point and neglect the spatial relationships between multiple monitoring points.Besides,most models lack flexibility in providing predictions for multiple days after monitoring activity.This study proposes a sequence-to-sequence(seq2seq)two-dimensional(2D)convolutional long short-term memory neural network(S2SCL2D)for predicting the spatiotemporal wall deflections induced by deep excavations.The model utilizes the data from all monitoring points on the entire wall and extracts spatiotemporal features from data by combining the 2D convolutional layers and long short-term memory(LSTM)layers.The S2SCL2D model achieves a long-term prediction of wall deflections through a recursive seq2seq structure.The excavation depth,which has a significant impact on wall deflections,is also considered using a feature fusion method.An excavation project in Hangzhou,China,is used to illustrate the proposed model.The results demonstrate that the S2SCL2D model has superior prediction accuracy and robustness than that of the LSTM and S2SCL1D(one-dimensional)models.The prediction model demonstrates a strong generalizability when applied to an adjacent excavation.Based on the long-term prediction results,practitioners can plan and allocate resources in advance to address the potential engineering issues.
基金sponsored by the National Natural Science Foundation of China (30870577)
文摘Parallel acceleration of convolution perfectly matched layer (CPML) algorithm suffers from massive division operation which is widely accepted as one of the most expensive operations for the equipment such as graphic processing unit (GPU), field programmable gate array (FPGA) etc. In pursuit of higher efficiency and lower power consumption, this article revisited the CPML theory and proposed a new fast division-free parallel CPML structure. By optimally rearranging the CPML inner iteration process, all the division operators can be eliminated and replaced by recalculating the related field updating coefficients offline. Experiments show that the proposed division-free structure can save more than 50% arithmetic instructions and 25% execution time of the traditional parallel CPML structure without any accuracy loss.
文摘In order to solve the problem of truncating the open boundaries of cylindrical waveguides used in the simulation of high power microwave (HPM) sources, this paper studies the convolutional PML (CPML) in the cylindrical coordinate system. The electromagnetic field's FDTD equations and the expressions of axis boundary conditions are presented. Numerical experiments are conducted to validate the equations and axis boundary conditions. The performance of CPML is simulated when it is used to truncate the cylindrical waveguides excited by the sources with different frequencies and modes in the 2.5-dimensional problems. Numerical results show that the maximum relative errors are all less than -90 dB. The CPML method is introduced in the 2.5-dimensional electromagnetic PIC software, and the relativistic backward wave oscillator is simulated by using this method. The results show that the property of CPML is much better than that of the Mur-type absorbing boundary condition when they are used to truncate the open boundaries of waveguides. The CPML is especially suitable for truncating the open boundaries of the dispersive waveguide devices in the simulation of HPM sources.