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11,530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：
Phase encoding in parametric nanomechanical resonator via annealing 认领 引用
1
作者 Chen Yang Feng-Nan Chen +4 位作者 Bo Wu Ting-Ting Li Zong-Yi Bao Joel Moser Heng Lu 《Chinese Physics B》 SCIE EI CAS CSCD 2026年第7期609-617,共9页
Nanomechanical resonators driven parametrically enable binary information encoding based on the control of their two possible vibrational phases.We present a protocol to flip the parametric phase in a graphene nanomec... Nanomechanical resonators driven parametrically enable binary information encoding based on the control of their two possible vibrational phases.We present a protocol to flip the parametric phase in a graphene nanomechanical resonator via annealing,offering a novel approach to nanomechanical logic.The core of our methodology involves driving the resonator with a parametric excitation near twice its resonant frequency and applying an external drive to break the symmetry of the dynamical double-well potential of the bistable states.By introducing white force noise to anneal the resonator,its vibrational phase settles into the state with the lower potential.The phase can be deterministically prepared in one of two states,differing by approximately π radians,by controlling the phase of direct drive and annealing.The demonstrated protocol offers a promising approach for nanomechanical logic with potential advantages in efficiency,error resilience,and scalability. 展开更多
关键词 phase encoding parametric amplification mechanical resonator graphene
暂未订购 下载PDF
A Fine-Grained RecognitionModel based on Discriminative Region Localization and Efficient Second-Order Feature Encoding 认领 引用
2
作者 Xiaorui Zhang Yingying Wang +3 位作者 Wei Sun Shiyu Zhou Haoming Zhang Pengpai Wang 《Computers, Materials & Continua》 SCIE EI 2026年第4期946-965,共20页
Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in comp... Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in complex backgrounds,small target objects,and limited training data,leading to poor recognition.Fine-grained images exhibit“small inter-class differences,”and while second-order feature encoding enhances discrimination,it often requires dual Convolutional Neural Networks(CNN),increasing training time and complexity.This study proposes a model integrating discriminative region localization and efficient second-order feature encoding.By ranking feature map channels via a fully connected layer,it selects high-importance channels to generate an enhanced map,accurately locating discriminative regions.Cropping and erasing augmentations further refine recognition.To improve efficiency,a novel second-order feature encoding module generates an attention map from the fourth convolutional group of Residual Network 50 layers(ResNet-50)and multiplies it with features from the fifth group,producing second-order features while reducing dimensionality and training time.Experiments on Caltech-University of California,San Diego Birds-200-2011(CUB-200-2011),Stanford Car,and Fine-Grained Visual Classification of Aircraft(FGVC Aircraft)datasets show state-of-the-art accuracy of 88.9%,94.7%,and 93.3%,respectively. 展开更多
关键词 Fine-grained recognition feature encoding data augmentation second-order feature discriminative regions
暂未订购 下载PDF
DGRDet: Dynamic Gaussian Receptive Field Encoding-Based Spiking Neural Networks for Remote Sensing Object Detection 认领 引用
3
作者 Li Chen Fan Zhang +3 位作者 Guangwei Xie Yanzhao Gao Xiaofeng Qi Mingqian Sun 《Computers, Materials & Continua》 SCIE EI 2026年第8期1247-1271,共25页
Remote sensing object detection aims to identify and localize specific targets in satellite or aerial imagery.Spiking Neural Networks(SNNs),benefiting from their implicit feedback-based and event-driven brain-inspired... Remote sensing object detection aims to identify and localize specific targets in satellite or aerial imagery.Spiking Neural Networks(SNNs),benefiting from their implicit feedback-based and event-driven brain-inspired dynamics,offer a promising solution to alleviate the high energy consumption of conventional ANN-based detection models.However,existing SNN-based approaches for remote sensing object detection—particularly for small,arbitrarily rotated objects—are still in their infancy and suffer from a substantial performance gap compared with ANN counterparts.In this work,we draw inspiration from the hierarchical sparse perception mechanisms of biological vision and integrate dynamic receptive field modulation into the encoding stage,proposing a high-precision spiking object detection framework tailored for remote sensing image.Specifically,we design a Hierarchical Feedback-based Gaussian Encoding(HFG)scheme,in which the parameters of Gaussian kernels are dynamically adjusted through spike-triggered top-down feedback connections.This mechanism enables the encoding process to adaptively respond to complex geometric variations of remote sensing objects,including rotation and scale changes.Based on the proposed encoding strategy,we develop DGRDet(Dynamic Gaussian Receptive Field Encoding-based Spiking Neural Networks for Remote Sensing Object Detection),a directly trained deep SNN detector for remote sensing image.Extensive evaluations on the large-scale public DOTA dataset demonstrate that DGRDet achieves competitive detection accuracy,outperforming existing SNN-based object detection methods.Moreover,compared with ANN models of comparable detection performance,DGRDet reduces spike activity by 81.31%and requires only 0.12%of the inference energy consumption,achieving a favorable balance between detection accuracy,efficiency,and energy efficiency. 展开更多
关键词 Remote sensing image object detection spiking neural networks(SNNs) hierarchical sparse dynamic gaussian encoding
暂未订购 下载PDF
Mesolimbic Dopaminergic Encoding of Decision Value:Linking Phenotype-Specific Signals to Strategic Adaptation 认领 引用 被引量：1
4
作者 Zhengyi Xu Dadao An +2 位作者 Jingjia Liang Lingyan Zheng Zhong Chen 《Neuroscience Bulletin》 SCIE CAS CSCD 2026年第4期937-940,共4页
Numerous neuropsychiatric disorders are characterized by significant impairments in decision-making function.These include impulsive decision-making in attention-deficit hyperactivity disorder(ADHD)[1],excessive risk-... Numerous neuropsychiatric disorders are characterized by significant impairments in decision-making function.These include impulsive decision-making in attention-deficit hyperactivity disorder(ADHD)[1],excessive risk-taking during manic episodes in bipolar disorder,and the distorted prioritization observed in substance use disorders.Decisionmaking involves reflecting on the outcomes of past actions and weighing the potential consequences of future actions.In this complex balancing process,mesolimbic dopamine influences reward value assessment,the strength of motivation,and the initiation of action[2]. 展开更多
关键词 phenotype specific signals bipolar disorderand strategic adaptation decision making reflecting outcomes past actions mesolimbic dopaminergic encoding distorted prioritization balancing processmesolimbic dopamine
暂未订购 下载PDF
Type synthesis method of high-precision double-layer parallel pointing mechanism 认领 引用
5
作者 Sen Wang Jun Cai +1 位作者 Bing Li Fujun Peng 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第2期180-191,共12页
The space pointing mechanism is widely used in radio astronomy,aerospace and other fields,and has high requirements for its pointing accuracy and stability.The pointing mechanism will be affected by external interfere... The space pointing mechanism is widely used in radio astronomy,aerospace and other fields,and has high requirements for its pointing accuracy and stability.The pointing mechanism will be affected by external interference when it works.In order to eliminate the influence of interference force and interference torque on the output accuracy of the pointing mechanism,it is necessary to propose a novel method of type synthesis of highprecision double-layer parallel pointing mechanism which can resist interference force and interference torque.A series of high-precision double-layer parallel pointing mechanisms that can resist interference forces and interference torques have been synthesized.Firstly,based on the idea of decoupling the function of pose adjustment and the function of resisting interference force and interference torque,a new method of type synthesis of high-precision double-layer parallel pointing mechanism is proposed.The type synthesis conditions of the inner translation mechanism and the outer mechanism are given.Then,based on the type synthesis conditions of the inner translation mechanism,the type synthesis of the inner isotropic three-translation parallel mechanism is carried out.Based on the type synthesis conditions of the outer mechanism,the type synthesis of the six-degreeof-freedom parallel mechanism for high-precision pointing and position adjustment is carried out.A series of new configurations of double-layer parallel pointing mechanisms that can resist interference forces and torques are synthesized.Finally,a typical configuration is selected to verify the correctness of the anti-interference function of the double-layer parallel pointing mechanism.The double-layer parallel pointing mechanism has the advantages of both large load and high output precision,and has a good application prospect in the field of radio telescope and antenna radar. 展开更多
关键词 Parallel pointing mechanism Type synthesis Double-layer mechanism Anti-interference function High-precision
暂未订购 下载PDF
Multidimensional visual feature encoding and functional organization in the pigeon entopallium 认领 引用
6
作者 Jun-Cai Zhu Min-Jie Zhu +4 位作者 Qing-Zhi He Peng Wu Xiao-Ke Niu Jiang-Tao Wang Zhi-Zhong Wang 《Zoological Research》 SCIE CSCD 2026年第2期487-502,共16页
Understanding how birds perceive and recognize visual objects remains a fundamental question in neuroscience.The entopallium,a key node in the avian tectofugal pathway,has long been implicated in complex visual proces... Understanding how birds perceive and recognize visual objects remains a fundamental question in neuroscience.The entopallium,a key node in the avian tectofugal pathway,has long been implicated in complex visual processing,yet its internal functional architecture remains incompletely understood.In this study,neuronal activity in the pigeon entopallium was systematically mapped using controlled visual stimuli that independently varied in color,shape,and motion.Recordings revealed marked hue selectivity that remained invariant across luminance levels,pronounced orientation tuning in response to shape stimuli,and robust direction selectivity for moving stimuli.Spatial mapping further revealed distinct functional segregation,with color-selective neurons localized anteroventrally,shape-selective neurons dorsally,and motion-selective neurons posteriorly.At the same time,partial overlap among these response classes was observed,with a subset of neurons exhibiting joint tuning across stimulus dimensions,suggesting an organizational scheme characterized by regional specialization and partial cross-feature integration.Notably,entopallium neurons exhibited a moderate level of visual feature integration and shared important functional properties with early to intermediate stages of mammalian visual processing.Together,these findings establish the entopallium as a major site for multidimensional visual analysis in birds and provide evidence for convergent principles underlying the evolution of complex visual systems across vertebrates. 展开更多
关键词 Entopallium Tectofugal pathway Feature encoding Functional organization Object recognition
暂未订购 下载PDF
Anion surfactant-tailored electric double-layer:Toward higher faradaic efficiency in acidic CO2electrolysis 认领 引用
7
作者 Zheng Zhang Lei Tang +3 位作者 Yihua Zhu Wangxin Ge Hongliang Jiang Chunzhong Li 《Chinese Journal of Catalysis》 SCIE EI CAS CSCD 2026年第6期96-105,共10页
Electric double-layer(EDL)structure critically influences electrocatalytic kinetics and performance,yet mechanistic understanding of anion-mediated EDL modulation remains limited,particularly in acidic CO2electroly... Electric double-layer(EDL)structure critically influences electrocatalytic kinetics and performance,yet mechanistic understanding of anion-mediated EDL modulation remains limited,particularly in acidic CO2electrolysis.Here,we demonstrate that the prototypical anionic surfactant sodium dodecyl sulfate(SDS)induces EDL expansion and reconstruct interfacial hydrogen-bonding(H-bond)networks,thereby suppressing the competitive hydrogen evolution reaction(HER)in acidic electrolytes,while achieving 94.1%CO Faradaic efficiency at 250 mA cm–2.Electrochemical kinetics analysis identifies that SDS-induced disruption of interfacial H-bond networks impedes proton transport kinetics,thereby suppressing HER in acid.Integrative electrolyte characterizations combined with in situ spectroscopic analysis revealed that the widening of the EDL stems from Lewis acid-base interactions between SDS and K+.Further,the introduction of SDS modulates interfacial water dissociation activity,thereby facilitating the hydrogenation pathway from CO2to*COOH.These findings establish a rational electrolyte design strategy for manipulating EDL to enhance acidic CO2electrolysis performance. 展开更多
关键词 Acidic CO2electrolysis Anionic surfactants Electrolyte regulation Electric double-layer microenvironment In-situ spectroscopy
暂未订购 下载PDF
FlexCENT:A frequency-flexible CEST imaging network combining frequency offset encoding and three-dimensional U-Net 认领 引用
8
作者 Jingyi Yu Mengying Zhu +2 位作者 Yonggui Yang Congbo Cai Shuhui Cai 《Magnetic Resonance Letters》 EI CAS 2026年第2期40-57,共18页
This study proposes a deep learning-based method termed frequency-flexible chemical exchange saturation transfer(CEST)imaging network(FlexCENT),which enables robust CEST quantification across variable frequency offset... This study proposes a deep learning-based method termed frequency-flexible chemical exchange saturation transfer(CEST)imaging network(FlexCENT),which enables robust CEST quantification across variable frequency offset schemes without requiring retraining.FlexCENT integrates frequency offset encoding with a three-dimensional(3D)U-Net to process CEST images and frequency offsets as inputs and predict Lorentzian parameters of the 4-pool model(water,MT,APT,rNOE),including B0 inhomogeneity.By transforming frequency offsets into a continuous spectral feature representation,the frequency offset encoding allows FlexCENT to generalize to unseen frequency offset schemes.Trained on synthetic data generated from the 4-pool Lorentzian model,FlexCENT was validated through numerical simulations,tumor-bearing mouse experiments,and a human brain experiment,alongside comparisons with 4-pool Lorentzian fitting,DeepCEST,and LKAN networks.The results demonstrate that FlexCENT successfully quantified CEST parameters across all experiments,maintaining consistent performance under varying frequency offset conditions without retraining.It exhibited superior noise robustness in numerical simulations and enhanced anatomical delineation in vivo parametric mapping compared to other methods.In conclusion,by combining spectral information with spatial information,FlexCENT provides an efficient,flexible,and robust quantitative approach for CEST imaging.It significantly enhance the quantification capability and clinical potential of CEST imaging. 展开更多
关键词 Chemical exchange saturation transfer Deep learning Three-dimensional U-Net Frequency offset encoding
暂未订购 下载PDF
Beyond Classical Positional Encodings:A Learnable QFT-Inspired Framework for Transformer Language Models 认领 引用
9
作者 Sara Tehsin Tallha Akram +2 位作者 Syed Rameez Naqvi Meshal Alharbi Abdulrahman Alabduljabbar 《Computers, Materials & Continua》 SCIE EI 2026年第9期159-182,共24页
Transformers have become the dominant architecture for sequence modeling in natural language processing;however,their effectiveness critically depends on how positional information is encoded.Conventional positional e... Transformers have become the dominant architecture for sequence modeling in natural language processing;however,their effectiveness critically depends on how positional information is encoded.Conventional positional encodings,while effective,may have limited structural flexibility for capturing complex global sequence relationships.Recent quantum-inspired approaches have sought to address this limitation,yetmany either oversimplify quantum principles or introduce substantial computational or hardware overhead.We introduce a novel Quantum Fourier Transform(QFT)-inspired positional encoding scheme for transformers,motivated by the structured frequency representation of the QFT.Unlike prior approaches that either emulate quantum operations superficially or require complex circuit constructions,the proposed method provides a learnable hybrid encoding that preserves quantuminspired structure while remaining aligned with hardware-efficient circuit primitives and structurally compatible with future near-term quantum implementations.Experiments on WikiText-103 indicate that the proposed encoding achieves competitive perplexity,improved robustness to input scrambling,and stable training behavior relative to alternative quantum-inspired baselines under the evaluated settings.Preliminary circuit-level simulations further suggest favorable noise resilience of the associated encoding primitives.These findings support the potential utility of incorporating quantum-inspired design principles into deep learning architectures and provide a foundation for future exploration at the interface of quantum computing and transformer-based natural language processing(NLP). 展开更多
关键词 LLMs positional encoding Quantum Fourier Transform positional embeddings hybrid quantumclassical models near-term quantum devices quantum transformer
暂未订购 下载PDF
Chaotic-microcomb-based MHz-rate single-pixel 3D imaging via all-optical encoding 认领 引用
10
作者 SHUJIAN GONG XINJIE HAN +10 位作者 XIAOYIN LI YINGHUI GUO ZEWEI WANG MINGBO PU HENG ZHOU PENG TIAN KANGHAO GAI QI ZHANG LIANWEI CHEN HEPING LIU XIANGANG LUO 《Photonics Research》 SCIE EI CAS CSCD 2026年第7期3081-3094,共14页
High-speed 3D imaging via light detection and ranging(LiDAR)is critical for autonomous driving,which demands a high point acquisition rate(PAR)with extended non-ambiguity ranges.Random-modulation continuous-wave(RMCW)... High-speed 3D imaging via light detection and ranging(LiDAR)is critical for autonomous driving,which demands a high point acquisition rate(PAR)with extended non-ambiguity ranges.Random-modulation continuous-wave(RMCW)schemes leverage chaotic orthogonality to enable robust parallelization for LiDAR.However,existing RMCW parallel architectures face key limitations:parallel detection requires one detector per channel(increasing complexity),and slow-axis mechanical scanning restricts practically achievable 3D PAR to merely tens of kHz,despite nominal MHz-level PAR via spectral scanning.Here,we propose a time-stretching enhanced parallel chaotic LiDAR(TEPCL)architecture to address these issues.With an integrated microcomb configured as the pulsed chaotic source,all-optical encoding based on time-stretching assigns multi-channel chaotic pulses to distinct temporal slots,enabling single-pixel recording of all-channel signals and eliminating multi-detector needs.By introducing acousto-optic scanning to achieve inter-axis rate matching with fast-axis spectral scanning,we realize MHz-rate all-solid-state biaxial scanning.As a result,we achieve a genuine 1 MHz overall system PAR for 3D imaging via single-pixel parallel detection,with five parallel channels,a ranging accuracy of∼6 mm,and a frame rate of 432.9 fps with 2310 points per frame.Benefiting from the intrinsic orthogonality of the comb lines,the system realizes absolute unambiguous ranging and robust anti-interference capability,which can independently demodulate each channel even when their echoes are completely overlapped temporally.This compact,allsolid-state,low-complexity TEPCL system holds promise for multi-user intelligent driving and paves the way for highly integrated on-chip LiDAR. 展开更多
关键词 all optical encoding chaotic microcomb parallel architectures light detection time stretching d par parallel chaotic lidar autonomous drivingwhich
暂未订购 下载PDF
Thermally Driven Soliton Tuning and State Transition in Bi2TeSe2-Based Ultrafast Fiber Lasers for Encoding Applications 认领 引用
11
作者 Bin Shen Rui Diao +4 位作者 Chong-Zhou Zhao Xin Guo Xiao-Bo Ma Chao-Qing Dai Yue-Yue Wang 《Chinese Physics Letters》 SCIE EI CAS CSCD 2026年第2期99-110,共12页
We demonstrate a thermally tunable mode-locked fiber laser integrating a polarization-sensitive SMF-PMFSMF modulator and a Bi2TeSe2 saturable absorber(SMF:single-mode fiber;PMF:polarization-maintaining fiber).By... We demonstrate a thermally tunable mode-locked fiber laser integrating a polarization-sensitive SMF-PMFSMF modulator and a Bi2TeSe2 saturable absorber(SMF:single-mode fiber;PMF:polarization-maintaining fiber).By controlling the PMF temperature,reversible switching among conventional,dissipative,and boundstate solitons is achieved.The wavelength tuning ranges are about 5 nm and 2.8 nm for conventional and dissipative solitons,respectively,with a tuning efficiency of 0.35 nm/℃.Numerical simulations based on temperatureinduced birefringence variation reproduce the observed dynamics.Furthermore,a wavelength-encoding scheme utilizing thermally driven soliton shifts is proposed,providing a feasible approach for soliton-state-controlled optical communication. 展开更多
关键词 polarization sensitive smf pmfsmf modulator wavelength tuning bi tese based ultrafast fiber lasers soliton shifts birefringence variation thermally driven soliton tuning state transition encoding applications
暂未订购 下载PDF
Three-party semi-quantum dialogue enhanced with Grover's algorithm based encoding and hypergraph access control 认领 引用
12
作者 Rui Tao Jin-Zhe Jiang Zhi-Hua Zhang 《Chinese Physics B》 SCIE EI CAS CSCD 2026年第7期435-447,共13页
We introduce a new three-party semi-quantum dialogue(3P-SQD)protocol that combines GHZ-state-based semiquantum communication,a Grover's algorithm-driven 2-bit encoding scheme,and hypergraph-based access control.In... We introduce a new three-party semi-quantum dialogue(3P-SQD)protocol that combines GHZ-state-based semiquantum communication,a Grover's algorithm-driven 2-bit encoding scheme,and hypergraph-based access control.In each round,the fully quantum participant Alice sends two bits,whereas the semi-quantum participants Bob and Charlie,restricted to semi-quantum operations such as measurements in the computational basis and reflection,each transmit one bit.The protocol incorporates probe state checking,Grover's algorithm-based encoding,and hypergraph-based authorization.It achieves information-theoretic security and controlled access,while preserving high message throughput and imposing no additional requirements on the semi-quantum users. 展开更多
关键词 semi-quantum dialogue Grover’s algorithm based encoding hypergraph access structure quantum communication
暂未订购 下载PDF
Autonomous inverse encoding guides 4D nanoprinting for highly programmable shape morphing 认领 引用 被引量：3
13
作者 Shuaiqi Ren Zhiang Zhang +6 位作者 Ruokun He Jiahao Fan Guangming Wang Hesheng Wang Bing Han Yong-Lai Zhang Zhuo-Chen Ma 《International Journal of Extreme Manufacturing》 SCIE EI CAS CSCD 2025年第3期467-482,共16页
Highly programmable shape morphing of 4D-printed microanostructures is urgently desired for applications in robotics and intelligent systems.However,due to the lack of autonomous holistic strategies throughout the tar... Highly programmable shape morphing of 4D-printed microanostructures is urgently desired for applications in robotics and intelligent systems.However,due to the lack of autonomous holistic strategies throughout the target shape input,optimal material distribution generation,and fabrication program output,4D nanoprinting that permits arbitrary shape morphing remains a challenging task for manual design.In this study,we report an autonomous inverse encoding strategy to decipher the genetic code for material property distributions that can guide the encoded modeling toward arbitrarily pre-programmed 4D shape morphing.By tuning the laser power of each voxel at the nanoscale,the genetic code can be spatially programmed and controllable shape morphing can be realized through the inverse encoding process.Using this strategy,the 4D-printed structures can be designed and accurately shift to the target morphing of arbitrarily hand-drawn lines under stimulation.Furthermore,as a proof-of-concept,a flexible fiber micromanipulator that can approach the target region through pre-programmed shape morphing is autonomously inversely encoded according to the localized spatial environment.This strategy may contribute to the modeling and arbitrary shape morphing of microanostructures fabricated via 4D nanoprinting,leading to cutting-edge applications in microfluidics,micro-robotics,minimally invasive robotic surgery,and tissue engineering. 展开更多
关键词 femtosecond laser fabrication 4D printing two-photon polymerization autonomous inverse encoding stimuli-responsive materials
暂未订购 下载PDF
Enhancing the genomic prediction accuracy of swine agricultural economic traits using an expanded one-hot encoding in CNN models 认领 引用 被引量：3
14
作者 Zishuai Wang Wangchang Li Zhonglin Tang 《Journal of Integrative Agriculture》 SCIE CAS CSCD 2025年第9期3574-3582,共9页
Deep learning(DL)methods like multilayer perceptrons(MLPs)and convolutional neural networks(CNNs)have been applied to predict the complex traits in animal and plant breeding.However,improving the genomic prediction ac... Deep learning(DL)methods like multilayer perceptrons(MLPs)and convolutional neural networks(CNNs)have been applied to predict the complex traits in animal and plant breeding.However,improving the genomic prediction accuracy still presents signifcant challenges.In this study,we applied CNNs to predict swine traits using previously published data.Specifcally,we extensively evaluated the CNN model's performance by employing various sets of single nucleotide polymorphisms(SNPs)and concluded that the CNN model achieved optimal performance when utilizing SNP sets comprising 1,000 SNPs.Furthermore,we adopted a novel approach using the one-hot encoding method that transforms the 16 different genotypes into sets of eight binary variables.This innovative encoding method signifcantly enhanced the CNN's prediction accuracy for swine traits,outperforming the traditional one-hot encoding techniques.Our fndings suggest that the expanded one-hot encoding method can improve the accuracy of DL methods in the genomic prediction of swine agricultural economic traits.This discovery has significant implications for swine breeding programs,where genomic prediction is pivotal in improving breeding strategies.Furthermore,future research endeavors can explore additional enhancements to DL methods by incorporating advanced data pre-processing techniques. 展开更多
关键词 swine agricultural economic traits genomic prediction deep learning one-hot encoding convolutional neural networks(CNNs)
暂未订购 下载PDF
Enhanced Multimodal Sentiment Analysis via Integrated Spatial Position Encoding and Fusion Embedding 认领 引用 被引量：1
15
作者 Chenquan Gan Xu Liu +3 位作者 Yu Tang Xianrong Yu Qingyi Zhu Deepak Kumar Jain 《Computers, Materials & Continua》 SCIE EI 2025年第12期5399-5421,共23页
Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the vary... Multimodal sentiment analysis aims to understand emotions from text,speech,and video data.However,current methods often overlook the dominant role of text and suffer from feature loss during integration.Given the varying importance of each modality across different contexts,a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process.In response to these critical limitations,we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues.In our model,text is treated as the core modality,while speech and video features are selectively incorporated through a unique position-aware fusion process.The spatial position encoding strategy preserves the internal structural information of speech and visual modalities,enabling the model to capture localized intra-modal dependencies that are often overlooked.This design enhances the richness and discriminative power of the fused representation,enabling more accurate and context-aware sentiment prediction.Finally,we conduct comprehensive evaluations on two widely recognized standard datasets in the field—CMU-MOSI and CMU-MOSEI to validate the performance of the proposed model.The experimental results demonstrate that our model exhibits good performance and effectiveness for sentiment analysis tasks. 展开更多
关键词 Multimodal sentiment analysis spatial position encoding fusion embedding feature loss reduction
暂未订购 下载PDF
基于CNN-Transformer encoder-BiLSTM模型的轴承剩余寿命预测 认领 引用 被引量：8
16
作者 张代林 孔康 +1 位作者 朱晨曦 杨奕婷 《华中科技大学学报（自然科学版）》 EI CAS CSCD 北大核心 2026年第5期1-8,共8页
针对复杂工况下轴承退化过程非线性强且长期依赖关系难以有效建模的问题,提出一种基于改进的CNNTransformer encoder-BiLSTM模型的剩余寿命预测方法.在该方法中,卷积神经网络(CNN)关注局部信息以更好地提取特征;改进的Transformer enco... 针对复杂工况下轴承退化过程非线性强且长期依赖关系难以有效建模的问题,提出一种基于改进的CNNTransformer encoder-BiLSTM模型的剩余寿命预测方法.在该方法中,卷积神经网络(CNN)关注局部信息以更好地提取特征;改进的Transformer encoder引入三种不同的注意力掩码机制,计算过程仅关注长期信息中重要的部分;使用双向长短期记忆网络(BiLSTM)关注所有信息的长期依赖关系.在C-MAPSS和XJTU-SY数据集上验证了模型的精度,实验结果表明:在加入高斯噪声后,该模型的估计效果优于其他方法,具有更好的稳定性. 展开更多
关键词 剩余寿命预测 注意力掩码机制 卷积神经网络 Transformer encoder 双向长短期记忆网络
暂未订购 下载PDF
Encoding converters for quantum communication networks 认领 引用
17
作者 Hua-Xing Xu Shao-Hua Wang +2 位作者 Ya-Qi Song Ping Zhang Chang-Lei Wang 《Chinese Physics B》 SCIE EI CAS CSCD 2025年第5期64-69,共6页
Quantum communication networks,such as quantum key distribution(QKD)networks,typically employ the measurement-resend mechanism between two users using quantum communication devices based on different quantum encoding ... Quantum communication networks,such as quantum key distribution(QKD)networks,typically employ the measurement-resend mechanism between two users using quantum communication devices based on different quantum encoding types.To achieve direct communication between the devices with different quantum encoding types,in this paper,we propose encoding conversion schemes between the polarization bases(rectilinear,diagonal and circular bases)and the time-bin phase bases(two phase bases and time-bin basis)and design the quantum encoding converters.The theoretical analysis of the encoding conversion schemes is given in detail,and the basis correspondence of encoding conversion and the property of bit flip are revealed.The conversion relationship between polarization bases and time-bin phase bases can be easily selected by controlling a phase shifter.Since no optical switches are used in our scheme,the converter can be operated with high speed.The converters can also be modularized,which may be utilized to realize miniaturization in the future. 展开更多
关键词 quantum communication networks encoding conversion polarization encoding time-bin phase encoding
暂未订购 下载PDF
Joint Feature Encoding and Task Alignment Mechanism for Emotion-Cause Pair Extraction 认领 引用
18
作者 Shi Li Didi Sun 《Computers, Materials & Continua》 SCIE EI 2025年第1期1069-1086,共18页
With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions... With the rapid expansion of social media,analyzing emotions and their causes in texts has gained significant importance.Emotion-cause pair extraction enables the identification of causal relationships between emotions and their triggers within a text,facilitating a deeper understanding of expressed sentiments and their underlying reasons.This comprehension is crucial for making informed strategic decisions in various business and societal contexts.However,recent research approaches employing multi-task learning frameworks for modeling often face challenges such as the inability to simultaneouslymodel extracted features and their interactions,or inconsistencies in label prediction between emotion-cause pair extraction and independent assistant tasks like emotion and cause extraction.To address these issues,this study proposes an emotion-cause pair extraction methodology that incorporates joint feature encoding and task alignment mechanisms.The model consists of two primary components:First,joint feature encoding simultaneously generates features for emotion-cause pairs and clauses,enhancing feature interactions between emotion clauses,cause clauses,and emotion-cause pairs.Second,the task alignment technique is applied to reduce the labeling distance between emotion-cause pair extraction and the two assistant tasks,capturing deep semantic information interactions among tasks.The proposed method is evaluated on a Chinese benchmark corpus using 10-fold cross-validation,assessing key performance metrics such as precision,recall,and F1 score.Experimental results demonstrate that the model achieves an F1 score of 76.05%,surpassing the state-of-the-art by 1.03%.The proposed model exhibits significant improvements in emotion-cause pair extraction(ECPE)and cause extraction(CE)compared to existing methods,validating its effectiveness.This research introduces a novel approach based on joint feature encoding and task alignment mechanisms,contributing to advancements in emotion-cause pair extraction.However,the study’s limitation lies in the data sources,potentially restricting the generalizability of the findings. 展开更多
关键词 Emotion-cause pair extraction interactive information enhancement joint feature encoding label consistency task alignment mechanisms
暂未订购 下载PDF
Validity of the Gaussian phase distribution approximation for analysis of isotropic diffusion encoding applied to restricted diffusion in a cylinder 认领 引用
19
作者 Daniel Topgaard 《Magnetic Resonance Letters》 EI CAS 2025年第4期20-27,共8页
The Gaussian phase distribution approximation enables analysis of restricted diffusion encoded by general gradient waveforms but fails to account for the diffraction-like features that may occur for simple pore geomet... The Gaussian phase distribution approximation enables analysis of restricted diffusion encoded by general gradient waveforms but fails to account for the diffraction-like features that may occur for simple pore geometries.We investigate the range of validity of the approximation by random walk simulations of restricted diffusion in a cylinder using isotropic diffusion encoding sequences as well as conventional single gradient pulse pairs and oscillating gradient waveforms.The results show that clear deviations from the approximation may be observed at relative signal attenuations below 0.1 for onedimensional sequences with few oscillation periods.Increasing the encoding dimensionality and/or number of oscillations while extending the total duration of the waveform diminishes the non-Gaussian effects while preserving the low apparent diffusivities characteristic of restriction. 展开更多
关键词 NMR Diffusion Porous media Pulsed gradient spin echo Tensor-valued encoding
暂未订购 下载PDF
Improved Sensitivity Encoding Parallel Magnetic Resonance Imaging Reconstruction Algorithm Based on Efficient Sum of Outer Products Dictionary Learning 认领 引用
20
作者 DUAN Jizhong SU Yan 《Journal of Shanghai Jiaotong university(Science)》 EI 2025年第3期561-571,共11页
Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstr... Sensitivity encoding(SENSE)is a parallel magnetic resonance imaging(MRI)reconstruction model by utilizing the sensitivity information of receiver coils to achieve image reconstruction.The existing SENSE-based reconstruction algorithms usually used nonadaptive sparsifying transforms,resulting in a limited reconstruction accuracy.Therefore,we proposed a new model for accurate parallel MRI reconstruction by combining the L0 norm regularization term based on the efficient sum of outer products dictionary learning(SOUPDIL)with the SENSE model,called SOUPDIL-SENSE.The SOUPDIL-SENSE model is mainly solved by utilizing the variable splitting and alternating direction method of multipliers techniques.The experimental results on four human datasets show that the proposed algorithm effectively promotes the image sparsity,eliminates the noise and artifacts of the reconstructed images,and improves the reconstruction accuracy. 展开更多
关键词 parallel magnetic resonance imaging(MRI) sensitivity encoding(SENSE) efficient sum of outer products dictionary learning(SOUPDIL) alternating direction method of multipliers
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