检索结果-内蒙古大学图书馆

Multi-level Multi-task representation learning with adaptive fusion for multimodal sentiment analysis

Neural Computing and Applications 2025年第3期37卷 1491-1508页

作者： Zhu, Chuanbo Chen, Min Li, Haomin Zhang, Sheng Liang, Han Sun, Chao Liu, Yifan Chen, Jincai Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan430074 China School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510641 China Pazhou Laboratory Guangdong Guangzhou510640 China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Key Laboratory of Information Storage System Ministry of Education of China Hubei Wuhan430074 China

Multimodal sentiment analysis is an active task in multimodal intelligence, which aims to compute the user’s sentiment tendency from multimedia data. Generally, each modality is a specific and necessary perspective to express human sentiment, providing complementary and consensus information unavailable in a single modality. Nevertheless, the heterogeneous multimedia data often contain inconsistent and conflicting sentiment semantics that limits the model performance. In this work, we propose a Multi-level Multi-task Representation Learning with Adaptive Fusion (MuReLAF) network to bridge the semantic gap among different modalities. Specifically, we design a modality adaptive fusion block to adjust modality contributions dynamically. Besides, we build a multi-level multimodal representations framework to obtain modality-specific and modality-shared semantics by the multi-task learning strategy, where modality-specific semantics contain complementary information and modality-shared semantics include consensus information. Extensive experiments are conducted on four publicly available datasets: MOSI, MOSEI, SIMS, and SIMSV2(s), demonstrating that our model exhibits superior or comparable performance to state-of-the-art models. The achieved accuracies are 86.28%, 86.07%, 84.46%, and 82.78%, respectively, showcasing improvements of 0.82%, 0.84%, 1.75%, and 1.83%. Further analyses also indicate the effectiveness of our model in sentiment analysis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

An embedded vertical‐federated feature selection algorithm based on particle swarm optimisation

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 734-754页

作者： Yong Zhang Ying Hu Xiaozhi Gao Dunwei Gong Yinan Guo Kaizhou Gao Wanqiu Zhang School of Information and Control Engineering China University of Mining and TechnologyXuzhouChina The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchunChina School of Computing University of Eastern FinlandKuopioFinland The Macao Institute of Systems Engineering Macao University of Science and TechnologyTaipaChina

In real life,a large amount of data describing the same learning task may be stored in different institutions(called participants),and these data cannot be shared among par-ticipants due to privacy *** case that different attributes/features of the same instance are stored in different institutions is called vertically distributed *** pur-pose of vertical‐federated feature selection(FS)is to reduce the feature dimension of vertical distributed data jointly without sharing local original data so that the feature subset obtained has the same or better performance as the original feature *** solve this problem,in the paper,an embedded vertical‐federated FS algorithm based on particle swarm optimisation(PSO‐EVFFS)is proposed by incorporating evolutionary FS into the SecureBoost framework for the first *** optimising both hyper‐parameters of the XGBoost model and feature subsets,PSO‐EVFFS can obtain a feature subset,which makes the XGBoost model more *** the same time,since different participants only share insensitive parameters such as model loss function,PSO‐EVFFS can effec-tively ensure the privacy of participants'***,an ensemble ranking strategy of feature importance based on the XGBoost tree model is developed to effectively remove irrelevant features on each ***,the proposed algorithm is applied to 10 test datasets and compared with three typical vertical‐federated learning frameworks and two variants of the proposed algorithm with different initialisation ***-mental results show that the proposed algorithm can significantly improve the classifi-cation performance of selected feature subsets while fully protecting the data privacy of all participants.

关键词： Evolutionary optimization feature selection privacy protection vertical‐federated learning

来源：评论

学校读者我要写书评

暂无评论

Design of high-capacity, low-loss, multi-layer few mode fiber with negatively-doped cladding over C-band

Design of high-capacity, low-loss, multi-layer few mode fibe...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on information Photonics and Optical Communications, IPOC 2024

作者： Ye, Haiqin Tu, Jiajing Zhuang, Mingjuan Gao, Shecheng Li, Zhaohui Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Department of Electronic Engineering College of Information Science and Technology Jinan University Guangzhou China

ISBN: (纸本)9798350379266

To accommodate more modes, the refractive index of core material in few mode fiber will become large, causing high Rayleigh scattering loss. To solve this issue, we adopt fluorinedopled quartz cladding to reduce the doping content in the core. In this paper, we design weakly-coupled few-mode fibers with ultra-low loss and 10 mode groups, from the points of numerical simulation and intelligence algorithm. © 2024 IEEE.

关键词： Rayleigh scattering

来源：评论

学校读者我要写书评

暂无评论

Design Of A Weakly Coupled 19-Core 5-Mode-Group Fiber For Dense Space-Division Multiplexing

Design Of A Weakly Coupled 19-Core 5-Mode-Group Fiber For De...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on information Photonics and Optical Communications, IPOC 2024

作者： Chen, Kaihui Tu, Jiajing Gao, Shecheng Li, Zhaohui Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Department of Electronic Engineering College of Information Science and Technology Jinan University Guangzhou China

ISBN: (纸本)9798350379266

Few-mode multi-core fiber is a space-division multiplexing backup solution to address the communication capacity crunch which is limited by the capacity of single-mode fiber. In this paper, we propose a weakly coupled 19-core 5-mode-group trench-assisted ring-core fiber with ultra-high spatial channel number, which can support up to 380 usable spatial mode channels (19 cores × 5 radial first-order OAM mode groups × 4 degenerate modes). To our knowledge, this is the highest channel count reported for few-mode multi-core fibers. The fiber can stably transmit 5 OAM mode groups in the C+L band. The minimum effective index difference between adjacent radial first-order mode groups is 1.35 × 10-3. With limited cladding diameter, when the core pitch is 44 µm, the inter-core crosstalk for the high-order OAM5,1 mode can reach -60.13 dB/100km. © 2024 IEEE.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Open World Recognition of Communication Jamming Signals

引用

China Communications 2023年第6期20卷 199-214页

作者： Yan Tang Zhijin Zhao Jie Chen Shilian Zheng Xueyi Ye Caiyi Lou Xiaoniu Yang School of Communication Engineering Hangzhou Dianzi UniversityHangzhou 310018China Science and Technology on Communication Information Security Control Laboratory Jiaxing 314033China

To improve the recognition ability of communication jamming signals,Siamese Neural Network-based Open World Recognition(SNNOWR)is *** algorithm can recognize known jamming classes,detect new(unknown)jamming classes,and unsupervised cluseter new *** network of SNN-OWR is trained supervised with paired input data consisting of two samples from a known *** the one hand,the network is required to have the ability to distinguish whether two samples are from the same *** the other hand,the latent distribution of known class is forced to approach their own unique Gaussian distribution,which is prepared for the subsequent open set *** the test,the unknown class detection process based on Gaussian probability density function threshold is designed,and an unsupervised clustering algorithm of the unknown jamming is realized by using the prior knowledge of known *** simulation results show that when the jamming-to-noise ratio is more than 0d B,the accuracy of SNN-OWR algorithm for known jamming classes recognition,unknown jamming detection and unsupervised clustering of unknown jamming is about 95%.This indicates that the SNN-OWR algorithm can make the effect of the recognition of unknown jamming be almost the same as that of known jamming.

关键词： communication jamming signals Siamese Neural Network Open World Recognition unsupervised clustering of new jamming type Gaussian probability density function

来源：评论

学校读者我要写书评

暂无评论

Liver Ailment Prediction Using Random Forest Model

引用

Computers, Materials & Continua 2023年第1期74卷 1049-1067页

作者： Fazal Muhammad Bilal Khan Rashid Naseem Abdullah A Asiri Hassan A Alshamrani Khalaf A Alshamrani Samar M Alqhtani Muhammad Irfan Khlood M Mehdar Hanan Talal Halawani Department of Electrical Engineering University of Engineering and TechnologyMardan23200Pakistan City University of Science and Information Technology PeshawarPakistan Department of IT and Computer Science Pak-Austria Fachhochschule Institute of Applied Sciences and TechnologyHaripurPakistan Radiological Sciences Department College of Applied Medical SciencesNajran UniversityNajranSaudi Arabia Department of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Anatomy Department Medicine CollegeNajran UniversityNajranSaudi Arabia Computer Science Department College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia

Today,liver disease,or any deterioration in one’s ability to survive,is extremely common all around the *** research has indicated that liver disease is more frequent in younger people than in older *** the liver’s capability begins to deteriorate,life can be shortened to one or two days,and early prediction of such diseases is *** several machine learning(ML)approaches,researchers analyzed a variety of models for predicting liver disorders in their early *** a result,this research looks at using the Random Forest(RF)classifier to diagnose the liver disease early *** dataset was picked from the University of California,Irvine ***’s accomplishments are contrasted to those of Multi-Layer Perceptron(MLP),Average One Dependency Estimator(A1DE),Support Vector Machine(SVM),Credal Decision Tree(CDT),Composite Hypercube on Iterated Random Projection(CHIRP),K-nearest neighbor(KNN),Naïve Bayes(NB),J48-Decision Tree(J48),and Forest by Penalizing Attributes(Forest-PA).Some of the assessment measures used to evaluate each classifier include Root Relative Squared Error(RRSE),Root Mean Squared Error(RMSE),accuracy,recall,precision,specificity,Matthew’s Correlation Coefficient(MCC),F-measure,and *** has an RRSE performance of 87.6766 and an RMSE performance of 0.4328,however,its percentage accuracy is *** widely acknowledged result of this work can be used as a starting point for subsequent *** a result,every claim that a new model,framework,or method enhances forecastingmay be benchmarked and demonstrated.

关键词： Liver ailment random forest machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive rolling motion for snake robots in unstructured environments based on torque control

引用

Biomimetic Intelligence & Robotics 2023年第3期3卷 59-66页

作者： Shihao Ma Fatao Qin Shufan Chen Longchuan Li Jianming Wang Zengzeng Wang Shuai Li Xuan Xiao School of Electronic and Information Engineering Tiangong UniversityTianjin 300382China College of Mechanical and Electrical Engineering Beijing University of Chemical TechnologyBeijing 100029China College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin 300382China School of Computer Science and Technology Tiangong UniversityTianjin 300382China

Snake robots have great potential for exploring and operating in challenging unstructured environments,such as rubble,caves,and narrow ***,due to the complexity and unpredictability of unstructured environments,designing a controller that can achieve adaptive motion is *** paper proposes a self-adaptive torque-based rolling controller for snake robots,enabling compliant motion in unstructured ***,a controller is designed to modify the torque of each motor by focusing on the different motion states of the rolling ***,an experimental platform is established for snake robots to verify the effectiveness of the ***,a series of rolling experiments are conducted using the torque-based rolling *** conclusion,the self-adaptive torque-based rolling controller enhances snake robot adaptability and mobility.

关键词： Snake robot Torque-based control Self-adaptive rolling gait Unstructured environments

来源：评论

学校读者我要写书评

暂无评论

Photonic neuromorphic architecture for tens-of-task lifelong learning

引用

Light(science & Applications) 2024年第3期13卷 519-530页

作者： Yuan Cheng Jianing Zhang Tiankuang Zhou Yuyan Wang Zhihao Xu Xiaoyun Yuan Lu Fang Sigma Laboratory Department of Electronic EngineeringTsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology(BNRist) Beijing 100084China Institute for Brain and Cognitive Science Tsinghua University(THUIBCS)Beijing 100084China

Scalable,high-capacity,and low-power computing architecture is the primary assurance for increasingly manifold and large-scale machine learning *** electronic artificial agents by conventional power-hungry processors have faced the issues of energy and scaling walls,hindering them from the sustainable performance improvement and iterative multi-task *** to another modality of light,photonic computing has been progressively applied in high-efficient neuromorphic ***,we innovate a reconfigurable lifelong-learning optical neural network(L2 ONN),for highly-integrated tens-of-task machine intelligence with elaborated algorithm-hardware *** from the inherent sparsity and parallelism in massive photonic connections,L2 ONN learns each single task by adaptively activating sparse photonic neuron connections in the coherent light field,while incrementally acquiring expertise on various tasks by gradually enlarging the *** multi-task optical features are parallelly processed by multi-spectrum representations allocated with different *** evaluations on freespace and on-chip architectures confirm that for the first time,L2 ONN avoided the catastrophic forgetting issue of photonic computing,owning versatile skills on challenging tens-of-tasks(vision classification,voice recognition,medical diagnosis,etc.)with a single ***,L2 ONN achieves more than an order of magnitude higher efficiency than the representative electronic artificial neural networks,and 14×larger capacity than existing optical neural networks while maintaining competitive performance on each individual *** proposed photonic neuromorphic architecture points out a new form of lifelong learning scheme,permitting terminal/edge AI systems with light-speed efficiency and unprecedented scalability.

关键词： life neural versatile

来源：评论

学校读者我要写书评

暂无评论

Novel Sum-of-Sinusoids Simulation Channel Modeling for 6G Multiple-Input Multiple-Output Vehicle-to-Everything Communications

引用

China Communications 2024年第1期21卷 242-259页

作者： Hao Jiang Hongming Zhang Ting Liu College of Artificial Intelligence Nanjing University of Information Science and Technology210044China National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsChina

In this paper,a statistical cluster-based simulation channel model with a finite number of sinusoids is proposed for depicting the multiple-input multiple-output(MIMO)communications in vehicleto-everything(V2X)*** the proposed sum-of-sinusoids(SoS)channel model,the waves that emerge from the transmitter undergo line-of-sight(LoS)and non-line-of-sight(NLoS)propagation to the receiver,which makes the model suitable for describing numerous V2X wireless communication scenarios for sixth-generation(6G).We derive expressions for the real and imaginary parts of the complex channel impulse response(CIR),which characterize the physical propagation characteristics of V2X wireless *** statistical properties of the real and imaginary parts of the complex CIRs,i.e.,autocorrelation functions(ACFs),Doppler power spectral densities(PSDs),cross-correlation functions(CCFs),and variances of ACFs and CCFs,are derived and *** results are generated and match those predicted by the underlying theory,demonstrating the accuracy of our derivation and *** proposed framework and underlying theory arise as an efficient tool to investigate the statistical properties of 6G MIMO V2X communication systems.

关键词： complex CIRs LoS and NLoS propagation components MIMO V2X communication environments SoS simulation channel model statistical properties

来源：评论

学校读者我要写书评

暂无评论

Adaptive cubature Kalman filter with the estimation of correlation between multiplicative noise and additive measurement noise

引用

Chinese Journal of Aeronautics 2022年第5期35卷 40-52页

作者： Quanbo GE Zhongcheng MA Jinglan LI Qinmin YANG Zhenyu LU Hong LI School of Electronics and Information Engineering Tongji UniversityShanghai 201804China Institute of Systems Science and Control Engineering School of AutomationHangzhou Dianzi UniversityHangzhou 310018China State Key Laboratory of Industrial Control Technology and the College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Jiangsu Key Laboratory of Meteorological Observation and Information Processing Nanjing University of Information Science and TechnologyNanjing 210044China Chinese Flight Test Establishment Xi’an 710089China

Mobile robots are often subject to multiplicative noise in the target tracking tasks,where the multiplicative measurement noise is correlated with additive measurement *** this paper,first,a correlation multiplicative measurement noise model is *** is able to more accurately represent the measurement error caused by the distance sensor dependence ***,the estimated performance mismatch problem of Cubature Kalman Filter(CKF)under multiplicative noise is *** improved Gaussian filter algorithm is introduced to help obtain the CKF algorithm with correlated multiplicative *** practice,the model parameters are unknown or inaccurate,especially the correlation of noise is difficult to obtain,which can lead to a decrease in filtering accuracy or even *** address this,an adaptive CKF algorithm is further provided to achieve reliable state estimation for the unknown noise correlation coefficient and thus the application of the CKF algorithm is ***,the estimated performance is analyzed theoretically,and the simulation study is conducted to validate the effectiveness of the proposed algorithm.

关键词： Adaptive CKF Correlated noise Estimation accuracy Multiplicative noise Performance analysis Target tracking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：