期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到20,645篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Stacking deep network for predicting slag compositions in converter with multi-decision boundaries 认领 引用
1
作者 Peng Li Dong-Ping Zhan +3 位作者 Xu-Dong Dou Zhou-Hua Jiang Hui-Shu Zhang Hui Duan 《Journal of Iron and Steel Research International》 SCIE EI CSCD 2026年第2期88-103,共16页
Accurate prediction of slag compositions in converter is essential for optimizing steelmaking efficiency and improving resource utilization.A novel stacking deep network was established to enhance the accuracy of slag... Accurate prediction of slag compositions in converter is essential for optimizing steelmaking efficiency and improving resource utilization.A novel stacking deep network was established to enhance the accuracy of slag compositions prediction in converter.The established network was designed to incorporate deep learning as part of a collection of multiple base models,combined with tree-based models.This network introduced more complex decision boundaries to the axis-aligned geometry,thereby improving model diversity.This network differs from existing ensemble methods by using a first layer to integrate multiple base learners for diverse features capture,while the second layer’s skip connection mechanism reuses input features to address covariate shift and improve model expressiveness and stability.In addition,this network introduced an innovative stacking layer design,replacing the standard linear regression model with more sophisticated tree-based models and deep learning networks.This enhancement allowed the stacking layer not only to weight the outputs of the base models but also to learn deeper patterns and feature interactions.To improve the network’s generalization,K-fold bagging was employed to minimize the risk of overfitting.Feature importance analysis further underscores the established network’s ability to identify the key factors influencing slag compositions,offering valuable insights for optimizing the steelmaking process.Experimental results demonstrated that the established network significantly outperforms existing methods in predicting slag compositions in converter,with mean squared errors of 4.33,2.80,3.39,and 0.49 for CaO,SiO2,MgO and FeO,respectively,highlighting its robust generalization capability.The established network approach offers an effective solution for predicting slag compositions in converters,thereby overcoming the limitation of delayed slag detection. 展开更多
关键词 Slag composition Stacking deep network Covariate shift Skip connection Feature importance
暂未订购 下载PDF
Lightweight deep network and projection loss for eye semantic segmentation 认领 引用
2
作者 Qinjie Wang Tengfei Wang +1 位作者 Lizhuang Yang Hai Li 《中国科学技术大学学报》 CAS CSCD 北大核心 2025年第7期59-68,58,I0002,共10页
Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is cr... Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively. 展开更多
关键词 lightweight deep network projection loss real-time semantic segmentation convolutional neural networks end-to-end
暂未订购 下载PDF
Electroencephalogram Signal Classification and Artifact Removal with Deep Networks and Adaptive Thresholding 认领 引用
3
作者 MATHE Mariyadasu MIDIDODDI Padmaja BATTULA TIRUMALA Krishna 《Journal of Shanghai Jiaotong university(Science)》 EI 2025年第4期693-701,共9页
Physiological signals such as electroencephalogram(EEG)signals are often corrupted by artifacts during the acquisition and processing.Some of these artifacts may deteriorate the essential properties of the signal that... Physiological signals such as electroencephalogram(EEG)signals are often corrupted by artifacts during the acquisition and processing.Some of these artifacts may deteriorate the essential properties of the signal that pertains to meaningful information.Most of these artifacts occur due to the involuntary movements or actions the human does during the acquisition process.So,it is recommended to eliminate these artifacts with signal processing approaches.This paper presents two mechanisms of classification and elimination of artifacts.In the first step,a customized deep network is employed to classify clean EEG signals and artifact-included signals.The classification is performed at the feature level,where common space pattern features are extracted with convolutional layers,and these features are later classified with a support vector machine classifier.In the second stage of the work,the artifact signals are decomposed with empirical mode decomposition,and they are then eliminated with the proposed adaptive thresholding mechanism where the threshold value changes for every intrinsic mode decomposition in the iterative mechanism. 展开更多
关键词 artifact elimination deep network electroencephalogram(EEG)signal classification empirical mode decomposition
暂未订购 下载PDF
Face recognition using both visible light image and near-infrared image and a deep network 认领 引用 被引量：4
4
作者 Kai Guo Shuai Wu Yong Xu 《CAAI Transactions on Intelligence Technology》 EI 2017年第1期39-47,共9页
In recent years, deep networks has achieved outstanding performance in computer vision, especially in the field of face recognition. In terms of the performance for a face recognition model based on deep network, ther... In recent years, deep networks has achieved outstanding performance in computer vision, especially in the field of face recognition. In terms of the performance for a face recognition model based on deep network, there are two main closely related factors： 1） the structure of the deep neural network, and 2） the number and quality of training data. In real applications, illumination change is one of the most important factors that significantly affect the performance of face recognition algorithms. As for deep network models, only if there is sufficient training data that has various illumination intensity could they achieve expected performance. However, such kind of training data is hard to collect in the real world. In this paper, focusing on the illumination change challenge, we propose a deep network model which takes both visible light image and near-infrared image into account to perform face recognition. Near- infrared image, as we know, is much less sensitive to illuminations. Visible light face image contains abundant texture information which is very useful for face recognition. Thus, we design an adaptive score fusion strategy which hardly has information loss and the nearest neighbor algorithm to conduct the final classification. The experimental results demonstrate that the model is very effective in realworld scenarios and perform much better in terms of illumination change than other state-of-the-art models. 展开更多
关键词 Deep network Face recognition Illumination change Insufficient training data
暂未订购 下载PDF
Disordered Multi-view Registration Method Based on the Soft Trimmed Deep Network 认领 引用 被引量：2
5
作者 Rui GUO Yuanlong SONG Zhengyao WANG 《Journal of Geodesy and Geoinformation Science》 CSCD 2023年第4期13-26,共14页
Compared with the pair-wise registration of point clouds,multi-view point cloud registration is much less studied.In this dissertation,a disordered multi-view point cloud registration method based on the soft trimmed ... Compared with the pair-wise registration of point clouds,multi-view point cloud registration is much less studied.In this dissertation,a disordered multi-view point cloud registration method based on the soft trimmed deep network is proposed.In this method,firstly,the expression ability of feature extraction module is improved and the registration accuracy is increased by enhancing feature extraction network with the point pair feature.Secondly,neighborhood and angle similarities are used to measure the consistency of candidate points to surrounding neighborhoods.By combining distance consistency and high dimensional feature consistency,our network introduces the confidence estimation module of registration,so the point cloud trimmed problem can be converted to candidate for the degree of confidence estimation problem,achieving the pair-wise registration of partially overlapping point clouds.Thirdly,the results from pair-wise registration are fed into the model fusion to achieve the rough registration of multi-view point clouds.Finally,the hierarchical clustering is used to iteratively optimize the clustering center model by gradually increasing the number of clustering categories and performing clustering and registration alternately.This method achieves rough point cloud registration quickly in the early stage,improves the accuracy of multi-view point cloud registration in the later stage,and makes full use of global information to achieve robust and accurate multi-view registration without initial value. 展开更多
关键词 soft trimmed deep network point cloud registration hierarchical clustering
暂未订购 下载PDF
DNEF:A New Ensemble Framework Based on Deep Network Structure 认领 引用
6
作者 Siyu Yang Ge Song +2 位作者 Yuqiao Deng Changyu Liu Zhuoyu Ou 《Computers, Materials & Continua》 SCIE EI 2023年第12期4055-4072,共18页
Deep neural networks have achieved tremendous success in various fields,and the structure of these networks is a key factor in their success.In this paper,we focus on the research of ensemble learning based on deep ne... Deep neural networks have achieved tremendous success in various fields,and the structure of these networks is a key factor in their success.In this paper,we focus on the research of ensemble learning based on deep network structure and propose a new deep network ensemble framework(DNEF).Unlike other ensemble learning models,DNEF is an ensemble learning architecture of network structures,with serial iteration between the hidden layers,while base classifiers are trained in parallel within these hidden layers.Specifically,DNEF uses randomly sampled data as input and implements serial iteration based on the weighting strategy between hidden layers.In the hidden layers,each node represents a base classifier,and multiple nodes generate training data for the next hidden layer according to the transfer strategy.The DNEF operates based on two strategies:(1)The weighting strategy calculates the training instance weights of the nodes according to their weaknesses in the previous layer.(2)The transfer strategy adaptively selects each node’s instances with weights as transfer instances and transfer weights,which are combined with the training data of nodes as input for the next hidden layer.These two strategies improve the accuracy and generalization of DNEF.This research integrates the ensemble of all nodes as the final output of DNEF.The experimental results reveal that the DNEF framework surpasses the traditional ensemble models and functions with high accuracy and innovative deep ensemble methods. 展开更多
关键词 Machine learning ensemble learning deep ensemble deep network structure classification
暂未订购 下载PDF
Detecting and Classifying Darknet Traffic Using Deep Network Chains 认领 引用
7
作者 Amr Munshi Majid Alotaibi +2 位作者 Saud Alotaibi Wesam Al-Sabban Nasser Allheeib 《Computer Systems Science & Engineering》 SCIE EI 2023年第10期891-902,共12页
The anonymity of the darknet makes it attractive to secure communication lines from censorship.The analysis,monitoring,and categorization of Internet network traffic are essential for detecting darknet traffic that ca... The anonymity of the darknet makes it attractive to secure communication lines from censorship.The analysis,monitoring,and categorization of Internet network traffic are essential for detecting darknet traffic that can generate a comprehensive characterization of dangerous users and assist in tracing malicious activities and reducing cybercrime.Furthermore,classifying darknet traffic is essential for real-time applications such as the timely monitoring of malware before attacks occur.This paper presents a two-stage deep network chain for detecting and classifying darknet traffic.In the first stage,anonymized darknet traffic,including VPN and Tor traffic related to hidden services provided by darknets,is detected.In the second stage,traffic related to VPNs and Tor services is classified based on their respective applications.The methodology of this paper was verified on a benchmark dataset containing VPN and Tor traffic.It achieved an accuracy of 96.8%and 94.4%in the detection and classification stages,respectively.Optimization and parameter tuning were performed in both stages to achieve more accurate results,enabling practitioners to combat alleged malicious activities and further detect such activities after outbreaks.In the classification stage,it was observed that the misclassifications were due to the audio and video streaming commonly used in shared real-time protocols.However,in cases where it is desired to distinguish between such activities accurately,the presented deep chain classifier can accommodate additional classifiers.Furthermore,additional classifiers could be added to the chain to categorize specific activities of interest further. 展开更多
关键词 Darknet darknet traffic deep network chains Internet traffic
暂未订购 下载PDF
Experimental data-driven deep neural network modeling and prediction for the streaks of turbulent separated shear flow 认领 引用
8
作者 Xingyu Ma Jiateng Pan +1 位作者 Yihong Liu Nan Jiang 《Acta Mechanica Sinica》 SCIE EI CAS CSCD 2026年第7期52-58,共7页
In this paper,we report a recent experimental study of streak structures in the turbulent separated shear flow by datadriven deep neural network.By applying spanwise-aligned tetrahedron vortex generators upstream of a... In this paper,we report a recent experimental study of streak structures in the turbulent separated shear flow by datadriven deep neural network.By applying spanwise-aligned tetrahedron vortex generators upstream of a plane backward-facing step,spanwise-aligned high-and low-speed streaks were generated within the separated shear layer behind the step.The velocity profiles of the shear flow were measured by single-probe hot-wire anemometer in both the streamwise-vertical and the streamwise-spanwise planes in the wind tunnel.Deep neural network models are trained and verified based on the experimental datasets.The input parameter sets include the vortex generator height,spanwise spacing,and the spatial coordinates within the measurement domain,while the output parameter sets are mean and root-mean-square velocities of the shear flow.Mean squared errors between the model-predicted and experimentally measured data are used for quality evaluation of different deep neural network model designs,among which the minimum error of the optimal design descends less than 1%.For other vortex generator parameters,which are not measured in the wind tunnel or used in the training,the model prediction provides reasonable mean velocity contours with streak structures.Thus,we find that the experimental data-driven modeling approach shows reliable robustness for nonlinear fitting of complex datasets as well as considerable generalization for turbulent coherent structures. 展开更多
关键词 Streak Experimental data-driven Deep neural network Vortex generator Backward-facing step
暂未订购 下载PDF
Automated nondestructive evaluation of compressive strength of underground lining structure using hyperspectral imaging and deep neural networks 认领 引用
9
作者 Changsong Wang Mingliang Zhou +1 位作者 Le Zhang Hongwei Huang 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第5期3623-3639,共17页
Evaluation of compressive strength in underground lining structures is critical for ensuring structural integrity and safety.Traditional assessment methods are often destructive,time-consuming,and impractical in confi... Evaluation of compressive strength in underground lining structures is critical for ensuring structural integrity and safety.Traditional assessment methods are often destructive,time-consuming,and impractical in confined environments such as tunnels and utility corridors.This study introduces an automated,nondestructive approach to visualize and estimate the compressive strength of underground concrete lining using hyperspectral imaging(HSI)combined with deep neural network(DNN)models.High-dimensional spectral data of concrete lining are assembled and trained to develop two DNN-based regression models,namely the Mono-Spectrum Deep Neural Regressor(MS-DNR)and the Segmented-Spectrum Deep Neural Regressor(SegS_DNR).Utilizing the SegS_DNR model,two-dimensional(2D)compressive strength distribution heatmaps were generated for visualization and assessment of strength variations.The SegS_DNR model demonstrated excellent predictive performance,achieving a coefficient of determination(Rp²)of 0.925 and a Residual Prediction Deviation(RPD)of 5.28 on the testing set for compressive strength estimation.The idea is further validated in site by investigating the capability of identifying the defect regions of the tunnel concrete lining,namely the cracked,spalling,and leaking areas,and demonstrated promising performance in comparison with experienced inspectors on site.This approach offers a contact-free technique for automated structural health monitoring,contributing to safer and more sustainable underground maintenance practices. 展开更多
关键词 Hyperspectral imaging Underground concrete structure Compressive strength Nondestructive detection Deep neural networks(DNN)
暂未订购 下载PDF
CMo-IABA:Constrained Multi-Objective Invisible and Adaptive Backdoor Attack for Deep Neural Networks-Based SAR Image Classification 认领 引用
10
作者 Guo-Qiang Zeng Hai-Nan Wei +1 位作者 Kang-Di Lu Guang-Gang Geng 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第7期1731-1746,共16页
Deep neural networks(DNNs)have been widely applied in the field of synthetic aperture radar(SAR)image while they are facing more and more serious threats from a variety of malicious attacks.As one of the malicious att... Deep neural networks(DNNs)have been widely applied in the field of synthetic aperture radar(SAR)image while they are facing more and more serious threats from a variety of malicious attacks.As one of the malicious attacks with strong destructiveness and stealth,backdoor attacks have severely affected DNNs,but there are no related research studies concerning the backdoor attacks against the DNNs-based SAR image classification models.In this work,we make the first attempt to automatically design a constrained multi-objective invisible and adaptive backdoor attack termed as CMo-IABA for DNNs-based SAR image classification.In the CMo-IABA,we firstly generate an initial trigger-based backdoor attack randomly by a random combination of pixels with random noise conforming to the Gaussian distribution.Then,we design multi-objective functions by considering the trade-off between maximizing the attack success rate and minimizing L2 distance-based invisibility.The classification error between the backdoor DNN and the clean model is considered as the constraint to maintain the original performance of the model.To solve the optimization problem,a discrete non-dominated sorting genetic algorithm-II is introduced as the search engine with the developed crossover operation and mutation operation.The superiority of the proposed CMo-IABA to five state-of-the-art backdoor attacks on six different types of DNNs-based SAR image classification models has been demonstrated by the experimental results on Fudan University SAR(FUSAR)-ship and moving and stationary target acquisition and recognition(MSTAR)datasets in terms of attack success rate and L2 distance-based invisibility. 展开更多
关键词 Backdoor attack constrained multi-objective optimization deep neural network(DNN) image classification invisibility synthetic aperture radar
暂未订购 下载PDF
Handoff Decision-Making in 5G Cellular Networks Using Deep Learning 认领 引用
11
作者 Muhammad Mukhtar Farizah Yunus +3 位作者 Ahmad Shukri Mohd Noor Zulfiqar Ali Muhammad Junaid Mehmood Ahmed 《Computers, Materials & Continua》 SCIE EI 2026年第6期2558-2582,共25页
The increasing adoption of 5G cellular networks has introduced significant challenges for network operators.The main challenge lies in the management of seamless handoff(HO),which occurs owing to the rapid expansion o... The increasing adoption of 5G cellular networks has introduced significant challenges for network operators.The main challenge lies in the management of seamless handoff(HO),which occurs owing to the rapid expansion of equipment,data,and network complexity.To address this challenge,a model named optimal HO management deep learning neural network(OHMDLNN)is proposed.The model is trained on network activity data,and it uses KPIs(key performance indicators)and system-level parameters to make HO decisions.As demonstrated in the article,OHMDLNN is successful in analyzing the effect and interdependence of KPIs from both the network and user equipment(UE)perspectives.Moreover,the model is evaluated for accuracy(the percentage of correct decisions made by a model on a dataset)in comparison with existing neural network-based HO decision models.These include temporal convolution networks(TCN),recurrent neural networks(RNN),long short-term memory(LSTM),gated recurrent units(GRU),and convolutional neural networks(CNN).The dataset used to evaluate the performance of the model consisted of 65,000 records.The model demonstrates superior performance,with an average improvement on accuracy of 8 percent over TCN,18 percent over RNN,6 percent over LSTM,14 percent over GRU and 4 percent over CNN.Along with accuracy,the model is also tested on important performance indicators,including the packet loss rate,the success rate,latency,and throughput at the time of handover.These results affirm its efficiency in the HO decision-making process.Future research will consider the use of advanced deep learning architectures and simplify the process of integrating system-level inputs to optimize system performance during HO events. 展开更多
关键词 Latency packet loss recurrent neural network deep learning neural network throughput
暂未订购 下载PDF
Random Search Deep Neural Networks Driven Koopman Subspace Modeling of Nonlinear Dynamics 认领 引用
12
作者 Zixiang Yuan Jie Ding +1 位作者 Dezhi Shen Min Xiao 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第7期1770-1772,共3页
Dear Editor,Nonlinear dynamic system is difficult to model by traditional modeling methods,because of high nonlinearity and limited precision.Koopman operator,an effective technique,maps nonlinear dynamic systems to a... Dear Editor,Nonlinear dynamic system is difficult to model by traditional modeling methods,because of high nonlinearity and limited precision.Koopman operator,an effective technique,maps nonlinear dynamic systems to a higher-dimensional linear space,allowing complex nonlinear behavior to be described linearly.However,conventional Koopman-based approaches often suffer from computational complexity,this paper employs a deep neural network with random search to learn feature mappings and estimates the Koopman operator by subspace identification.Experimental results show the approach simplifies modeling and significantly improves modeling accuracy over traditional methods. 展开更多
关键词 feature mappings nonlinear dynamic systems dynamic system complex nonlinear behavior nonlinear dynamics deep neural network random search modeling methodsbecause
暂未订购 下载PDF
A Deep Learning Approach to Pedestrian Dead Reckoning:Accounting for Latent Variables with Deep Belief Networks 认领 引用
13
作者 Kyeonghyun Yoo SangminLee Hwangnam Kim 《Computers, Materials & Continua》 SCIE EI 2026年第9期2396-2412,共17页
InertialMeasurement Unit(IMU)-based Pedestrian Dead Reckoning(PDR)enables infrastructure-free indoor positioning and requires heading-drift compensation associated with gyroscope bias.This paper proposes a stationary-... InertialMeasurement Unit(IMU)-based Pedestrian Dead Reckoning(PDR)enables infrastructure-free indoor positioning and requires heading-drift compensation associated with gyroscope bias.This paper proposes a stationary-window-based Deep Belief Network(DBN)framework that learns a gyroscope bias representation from z-axis angular-velocity and sampling-interval sequences observed during stationary intervals and applies it to heading correction during walking.The learned representation captures the residual angular-velocity offset under stationary conditions and serves as an adaptive correction term for subsequent heading integration.Experiments on short-term,three-lap long-term,and complex indoor paths show that stationary-window-basedDBNbias estimation is particularly effective in accumulated-drift regimes,such as long-term repeated walking and complex multi-turn trajectories.The proposed DBN method achieved an average absolute trajectory error(ATE)of 3.9587 m in the long-term experiment and 0.9126 m in the complex path experiment.Stationary detection sensitivity analysis further shows that falsepositive stationary decisions have a stronger influence on trajectory consistency than false-negative stationary decisions.These results show that the proposed framework maintains stable waypoint-level trajectory behavior in long-term and complex PDR scenarios where heading drift becomes more pronounced. 展开更多
关键词 Indoor positioning system pedestrian dead reckoning machine learning deep belief network
暂未订购 下载PDF
Meson Properties and Symmetry Emergence Based on the Deep Neural Network 认领 引用
14
作者 Xin Tong Wei Feng +3 位作者 Weiwei Xu Chao-Hsi Chang Guo-Li Wang Qiang Li 《Chinese Physics Letters》 SCIE EI CAS CSCD 2026年第2期32-50,共19页
As a key property of hadrons,the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions.In this work,a deep neural network model with the Transforme... As a key property of hadrons,the total width is quite difficult to obtain in theory due to the extreme complexity of the strong and electroweak interactions.In this work,a deep neural network model with the Transformer architecture is built to precisely predict meson widths in the range of 10-14-625 Me V based on meson quantum numbers and masses.The relative errors of the predictions are 0.12%,2.0%,and 0.54% in the training set,the test set,and all the data,respectively.We present the predicted meson width spectra for the currently discovered states and some theoretically predicted ones.The model is also used as a probe to study the quantum numbers and inner structures for some undetermined states,including the exotic states.Notably,this data-driven model is found to spontaneously exhibit good charge conjugation symmetry and approximate isospin symmetry consistent with physical principles.The results indicate that the deep neural network can serve as an independent complementary research paradigm to describe and explore the hadron structures and the complicated interactions in particle physics alongside traditional experimental measurements,theoretical calculations,and lattice simulations. 展开更多
关键词 transformer architecture charge conjugation symmetry deep neural network model symmetry emergence deep neural network meson widths strong electroweak interactionsin meson properties
暂未订购 下载PDF
Physics-guided deep unfolding network for snapshot 3D imaging using double-helix point spread function 认领 引用
15
作者 Gang Qu Pengwei Wang +4 位作者 Xing Liu Haomiao Zhang Mengyuan Liu Zhentao Liu Xin Yuan 《Advanced Photonics Nexus》 CSCD 2026年第5期175-191,共17页
Point spread function(PSF)engineering is a promising approach for passive,snapshot 3D imaging with a single detector.A widely used technique is the double-helix PSF(DH-PSF),which employs a specialized phase mask at th... Point spread function(PSF)engineering is a promising approach for passive,snapshot 3D imaging with a single detector.A widely used technique is the double-helix PSF(DH-PSF),which employs a specialized phase mask at the pupil plane to modulate incident light,generating rotationally varying PSFs with defocus.By leveraging a precalibrated depth-dependent PSF model,the depth information of the target surface can be recovered from a snapshot measurement.However,existing reconstruction algorithms often lack efficiency and accuracy,primarily due to the block-wise processing of conventional methods or the failure to incorporate physical priors in end-to-end neural networks.To address these limitations,we propose a physics-guided deep unfolding network(PG-DUN)for snapshot 3D imaging with DH-PSFs.By explicitly embedding the imaging model into the deep neural network,our DUN can naturally reconstruct the 2D image and depth map simultaneously,contributing to more accurate and efficient reconstruction than previous approaches.The feasibility and effectiveness of the proposed method are validated through extensive experiments on simulated and real-world data.The proposed method can serve as a prototype for a deep learning-based reconstruction model in similar deconvolution tasks.Its key innovation—an accelerated deconvolutional gradient descent design—functions as a plug-and-play component that enhances the reconstruction accuracy of any deep neural network with negligible added computational cost. 展开更多
关键词 snapshot 3D imaging physics-guided deep unfolding network double-helix point spread function
暂未订购 下载PDF
Retraction: A Lightweight Multimodal Deep Fusion Network for Face Antis Poofing with Cross-Axial Attention and Deep Reinforcement Learning Technique 认领 引用
16
作者 无 《Computers, Materials & Continua》 SCIE EI 2026年第7期1981-1981,共1页
The published article titled“A Lightweight Multimodal Deep Fusion Network for Face Antis Poofing with Cross-Axial Attention and Deep Reinforcement Learning Technique”has been retracted from Computers,Materials&C... The published article titled“A Lightweight Multimodal Deep Fusion Network for Face Antis Poofing with Cross-Axial Attention and Deep Reinforcement Learning Technique”has been retracted from Computers,Materials&Continua,Vol.85,No.3,2025,pp.5671-5702. 展开更多
关键词 face antis poofing deep reinforcement learning technique deep reinforcement learning face antispoofing lightweight multimodal deep fusion network cross axial attention
暂未订购 下载PDF
Action Recognition in Surveillance Videos with Combined Deep Network Models 认领 引用
17
作者 ZHANG Diankai ZHAO Rui-Wei +3 位作者 SHEN Lin CHEN Shaoxiang SUN Zhenfeng JIANG Yu-Gang 《ZTE Communications》 2016年第B12期54-60,共7页
Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, mos... Action recognition is an important topic in computer vision. Recently, deep learning technologies have been successfully used in lots of applications including video data for sloving recognition problems. However, most existing deep learning based recognition frameworks are not optimized for action in the surveillance videos. In this paper, we propose a novel method to deal with the recognition of different types of actions in outdoor surveillance videos. The proposed method first introduces motion compensation to improve the detection of human target. Then, it uses three different types of deep models with single and sequenced images as inputs for the recognition of different types of actions. Finally, predictions from different models are fused with a linear model. Experimental results show that the proposed method works well on the real surveillance videos. 展开更多
关键词 action recognition deep network models model fusion surveillance video
暂未订购 下载PDF
Integration of deep neural network modeling and LC-MS-based pseudo-targeted metabolomics to discriminate easily confused ginseng species 认领 引用 被引量：2
18
作者 Meiting Jiang Yuyang Sha +8 位作者 Yadan Zou Xiaoyan Xu Mengxiang Ding Xu Lian Hongda Wang Qilong Wang Kefeng Li De-an Guo Wenzhi Yang 《Journal of Pharmaceutical Analysis》 SCIE CAS CSCD 2025年第1期126-137,共12页
Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments invo... Metabolomics covers a wide range of applications in life sciences,biomedicine,and phytology.Data acquisition(to achieve high coverage and efficiency)and analysis(to pursue good classification)are two key segments involved in metabolomics workflows.Various chemometric approaches utilizing either pattern recognition or machine learning have been employed to separate different groups.However,insufficient feature extraction,inappropriate feature selection,overfitting,or underfitting lead to an insufficient capacity to discriminate plants that are often easily confused.Using two ginseng varieties,namely Panax japonicus(PJ)and Panax japonicus var.major(PJvm),containing the similar ginsenosides,we integrated pseudo-targeted metabolomics and deep neural network(DNN)modeling to achieve accurate species differentiation.A pseudo-targeted metabolomics approach was optimized through data acquisition mode,ion pairs generation,comparison between multiple reaction monitoring(MRM)and scheduled MRM(sMRM),and chromatographic elution gradient.In total,1980 ion pairs were monitored within 23 min,allowing for the most comprehensive ginseng metabolome analysis.The established DNN model demonstrated excellent classification performance(in terms of accuracy,precision,recall,F1 score,area under the curve,and receiver operating characteristic(ROC))using the entire metabolome data and feature-selection dataset,exhibiting superior advantages over random forest(RF),support vector machine(SVM),extreme gradient boosting(XGBoost),and multilayer perceptron(MLP).Moreover,DNNs were advantageous for automated feature learning,nonlinear modeling,adaptability,and generalization.This study confirmed practicality of the established strategy for efficient metabolomics data analysis and reliable classification performance even when using small-volume samples.This established approach holds promise for plant metabolomics and is not limited to ginseng. 展开更多
关键词 Liquid chromatography-mass spectrometry Pseudo-targeted metabolomics Deep neural network Species differentiation Ginseng
暂未订购 下载PDF
Cuckoo Search-Deep Neural Network Hybrid Model for Uncertainty Quantification and Optimization of Dielectric Energy Storage in Na1/2Bi1/2TiO3-Based Ceramic Capacitors 认领 引用 被引量：1
19
作者 Shige Wang Yalong Liang +1 位作者 Lian Huang Pei Li 《Computers, Materials & Continua》 SCIE EI 2025年第11期2729-2748,共20页
This study introduces a hybrid Cuckoo Search-Deep Neural Network(CS-DNN)model for uncertainty quantification and composition optimization of Na1/2Bi1/2TiO3(NBT)-based dielectric energy storage ceramics.Addres... This study introduces a hybrid Cuckoo Search-Deep Neural Network(CS-DNN)model for uncertainty quantification and composition optimization of Na1/2Bi1/2TiO3(NBT)-based dielectric energy storage ceramics.Addressing the limitations of traditional ferroelectric materials—such as hysteresis loss and low breakdown strength under high electric fields—we fabricate(1−x)NBBT8-xBMT solid solutions via chemical modification and systematically investigate their temperature stability and composition-dependent energy storage performance through XRD,SEM,and electrical characterization.The key innovation lies in integrating the CS metaheuristic algorithm with a DNN,overcoming localminima in training and establishing a robust composition-property prediction framework.Our model accurately predicts room-temperature dielectric constant(εr),maximum dielectric constant(εmax),dielectric loss(tanδ),discharge energy density(Wrec),and charge-discharge efficiency(η)from compositional inputs.A Monte Carlo-based uncertainty quantification framework,combined with the 3σ statistical criterion,demonstrates that CSDNN outperforms conventional DNN models in three critical aspects:Higher prediction accuracy(R2=0.9717 vs.0.9382 for εmax);Tighter error distribution,satisfying the 99.7% confidence interval under the 3σprinciple;Enhanced robustness,maintaining stable predictions across a 25% composition span in generalization tests.While the model’s generalization is constrained by both the limited experimental dataset(n=45)and the underlying assumptions of MC-based data augmentation,the CS-DNN framework establishes a machine learning-guided paradigm for accelerated discovery of high-temperature dielectric capacitors through its unique capability in quantifying composition-level energy storage uncertainties. 展开更多
关键词 Cuckoo search deep neural network ferroelectric ceramics dielectric energy storage uncertainty analysis monte Carlo simulation
暂未订购 下载PDF
A Modified Deep Residual-Convolutional Neural Network for Accurate Imputation of Missing Data 认领 引用 被引量：1
20
作者 Firdaus Firdaus Siti Nurmaini +8 位作者 Anggun Islami Annisa Darmawahyuni Ade Iriani Sapitri Muhammad Naufal Rachmatullah Bambang Tutuko Akhiar Wista Arum Muhammad Irfan Karim Yultrien Yultrien Ramadhana Noor Salassa Wandya 《Computers, Materials & Continua》 SCIE EI 2025年第2期3419-3441,共23页
Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attentio... Handling missing data accurately is critical in clinical research, where data quality directly impacts decision-making and patient outcomes. While deep learning (DL) techniques for data imputation have gained attention, challenges remain, especially when dealing with diverse data types. In this study, we introduce a novel data imputation method based on a modified convolutional neural network, specifically, a Deep Residual-Convolutional Neural Network (DRes-CNN) architecture designed to handle missing values across various datasets. Our approach demonstrates substantial improvements over existing imputation techniques by leveraging residual connections and optimized convolutional layers to capture complex data patterns. We evaluated the model on publicly available datasets, including Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV), which contain critical care patient data, and the Beijing Multi-Site Air Quality dataset, which measures environmental air quality. The proposed DRes-CNN method achieved a root mean square error (RMSE) of 0.00006, highlighting its high accuracy and robustness. We also compared with Low Light-Convolutional Neural Network (LL-CNN) and U-Net methods, which had RMSE values of 0.00075 and 0.00073, respectively. This represented an improvement of approximately 92% over LL-CNN and 91% over U-Net. The results showed that this DRes-CNN-based imputation method outperforms current state-of-the-art models. These results established DRes-CNN as a reliable solution for addressing missing data. 展开更多
关键词 Data imputation missing data deep learning deep residual convolutional neural network
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈