检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Ma, Zhengrui Shao, Chenze Gui, Shangtong Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles the multi-modality problem by introducing dependency between vertices. However, training it with negative log-likelihood loss implicitly requires a strict alignment between reference tokens and vertices, weakening its ability to handle multiple translation modalities. In this paper, we hold the view that all paths in the graph are fuzzily aligned with the reference sentence. We do not require the exact alignment but train the model to maximize a fuzzy alignment score between the graph and reference, which takes captured translations in all modalities into account. Extensive experiments on major WMT benchmarks show that our method substantially improves translation performance and increases prediction confidence, setting a new state of the art for NAT on the raw training data. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Mid-infrared band multi-Fano resonance-based sensing of high-Q concave-convex arrays of metasurface with full control of Fano spectral profile

引用

Photonics and Nanostructures - Fundamentals and Applications 2025年 65卷

作者： Xu, Mengyang Lin, Dong Cai, Haoyuan Wang, Haoran Fan, Zhichun Liu, Jing Chen, Yushan School of Ocean Information Engineering Jimei University Xiamen361021 China Fujian Provincial Key Laboratory of Oceanic Information Perception and Intelligent Processing Jimei University Xiamen361021 China

In this study, a concave-convex array metasurface with a height difference characterized structure is proposed, combining in-plane and out-of-plane asymmetry to achieve a high Q-factor, refractive index sensing, and full control of the Fano spectral profile. Notably, both the concave model and the convex model, can only produce one Fano peak. But it can yield multiple Fano resonance peaks in the mid-infrared band following a simple combination. Herein, we have performed both near-field and far-field analysis for each Fano resonance generation. The designed metasurface achieves a remarkably high Q-factor of 9.63637 × 105. Moreover, it exhibits excellent reflection resonances under different polarization directions. In terms of refractive index sensing, the designed metasurface attains a sensitivity of 600 nm/RIU under TE polarization, while under TM polarization, it achieves full control of the Fano spectral profile by changing the incidence angle. The integration of periodic arrays with height differences in metasurfaces shows tremendous potential in controlling the Fano spectral profile and enhancing sensing capabilities. Additionally, this study will provide new inspirations for the sensing metasurface design with high optical performance. © 2025 Elsevier B.V.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

Low-cost portable dielectric spectrometer based on mini-vector network analyzer and open-ended coaxial probe technology

引用

International Journal of Agricultural and Biological Engineering 2024年第3期17卷 166-172页

作者： Zhuozhuo Zhu Xinhua Zhu Wenchuan Guo College of Mechanical and Electronic Engineering Northwest A&F UniversityYangling 712100ShaanxiChina School of Physics and Electronic Information Yan'an UniversityYan'an 716000ShaanxiChina Shaanxi Research Center of Agricultural Equipment Engineering Technology Yangling 712100ShaanxiChina Key Laboratory of Agricultural Internet of Things Ministry of Agriculture and Rural AffairsYangling 712100ShaanxiChina Shaanxi Key Laboratory of Agricultural Information Perception and Intelligent Service Yangling 712100ShaanxiChina

As a simple,fast,and non-destructive measuring technology,dielectric spectroscopy is usually used to analyze the dielectric properties of agricultural products and food,and then to predict the main components of ***,the large and expensive vector network analyzers(VNA)with expensive analysis software applied in measuring dielectric properties make research limited to the *** acquire dielectric spectra in situ,a model for solving relative complex permittivity was derived,and its performance was ***,a low-cost portable dielectric spectrometer with a mini VNA,a Raspberry Pi,and a coaxial probe as core parts was developed over the frequency range of 100-3000 *** stability and accuracy of the developed spectrometer were tested using milk and *** results indicated that the relative errors of the model were within±5%for dielectric constant(ε′)and loss factor(ε″).The coefficients of variation of measuredε′andε″by the developed spectrometer at 100-3000 MHz were less than 1%and 2%,*** with the dielectric properties obtained by using a commercial dielectric measurement system,the relative errors of measuredε′andε″were within±3.4%and±6.0%,*** study makes fast,non-destructive,and on-site food quality detection using dielectric spectra possible.

关键词： coaxial probe mini vector network analyzer low-cost portable dielectric spectrometer

来源：评论

学校读者我要写书评

暂无评论

An RCG-based study of aspect-level sentiment analysis for hybrid attention 3

An RCG-based study of aspect-level sentiment analysis for hy...

引用

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Lu, Baoqing Yu, Hongzhi Wan, Fucheng Min, Chen Wei, Bin Fen, Yulin Key Laboratory of Linguistic and Cultural Computing Ministry of Education Gansu Lanzhou730000 China Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing Gansu Lanzhou730000 China Lanzhou technology and business college Gansu Lanzhou730000 China

ISBN: (纸本)9781510681880

Aspect-based sentiment analysis (ABSA) is a crucial granular task within sentiment analysis, focusing on the precise identification of sentiment orientations for specific aspects within text. Recognizing that identical context words can express opposing sentiment polarities in different situations, it's essential to delve into the nuanced interactions between target and context words. This study introduces an RCG-based Hybrid Attention Network, a novel architecture that adeptly utilizes lexical attention mechanisms to extract lexical features and fortify the relationship between aspects and their corresponding target words. To assess the efficacy of our proposed approach, we conducted experiments on a well-known public dataset. The results show a significant 3.37% enhancement in accuracy and a 1.38% improvement in Macro-F1 scores compared to related methods, affirming the superiority of our technique in enhancing the performance of aspect-level sentiment analysis. © 2024 SPIE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Four development stages of collective intelligence

引用

Frontiers of information technology & Electronic Engineering 2024年第7期25卷 903-916页

作者： Renbin XIAO School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Image Information Processing and Intelligent Control Ministry of EducationWuhan 430074China

The new generation of artificial intelligence(AI)research initiated by Chinese scholars conforms to the needs of a new information environment changes,and strives to advance traditional artificial intelligence(AI 1.0)to a new stage of AI *** one of the important components of AI,collective intelligence(CI 1.0),i.e.,swarm intelligence,is developing to the stage of CI 2.0(crowd intelligence).Through in-depth analysis and informative argumentation,it is found that an incompatibility exists between CI 1.0 and CI ***,CI 1.5 is introduced to build a bridge between the above two stages,which is based on biocollaborative behavioral *** 1.5 is the transition from CI 1.0 to CI 2.0,which contributes to the compatibility of the two ***,a new interpretation of the meta-synthesis of wisdom proposed by Qian Xuesen is *** meta-synthesis of wisdom,as an improvement of crowd intelligence,is an advanced stage of bionic intelligence,i.e.,CI *** is pointed out that the dual-wheel drive of large language models and big data with deep uncertainty is an evolutionary path from CI 2.0 to CI 3.0,and some elaboration is *** a result,we propose four development stages(CI 1.0,CI 1.5,CI 2.0,and CI 3.0),which form a complete framework for the development of *** different stages are progressively improved and have good *** to the dominant role of cooperation in the development stages of CI,three types of cooperation in CI are discussed:indirect regulatory cooperation in lower organisms,direct communicative cooperation in higher organisms,and shared intention based collaboration in *** division is the main form of achieving cooperation and,for this reason,this paper investigates the relationship between the complexity of behavior and types of labor ***,based on the overall understanding of the four development stages of CI,the future development direction and research issues of CI are explored.

关键词： Collective intelligence Meta-synthesis of wisdom Incompatibility Labor division Cooperative behavior Collective intelligence emergence Large language model

来源：评论

学校读者我要写书评

暂无评论

Nucleation growth quenching for superior cluster catalysts

引用

Nano Research 2022年第9期15卷 7933-7939页

作者： Ruyue Wang Feng Cheng Yonggang Wang Dongyu Fan Bohan Deng Yuanzheng Long Haolin Tang Kai Huang Zhaowei Qu Ming Lei Binghui Ge Hui Wu State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhan 430070China State Key Laboratory of Information Photonics and Optical Communications School of ScienceBeijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Beijing Key Laboratory of Space-ground Interconnection and Convergence Beijing University of Posts and Telecommunications(BUPT)Beijing 100876China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Structure and Functional Regulation of Hybrid Materials of Ministry of EducationInstitutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China

Cluster catalysts are rapidly growing into an important sub-field in heterogeneous catalysis,owing to their distinct geometric structure,neighboring metal sites,and unique electronic *** the thermodynamics and kinetics of the formation of nanoparticles have been largely investigated,the precise synthesis of clusters in wet chemical methods still faces great *** the study,a quenching strategy of asymmetric temperature in solution for the rapid generation of vacancy-defect rich clusters is *** quenching process can be used to synthesize multitudinous metal compound clusters,including metal oxides,fluorides,oxygen-sulfur compounds,and *** oxygen evolution reaction(OER),IrO_(2)clusters with abundant oxygen vacancies were obtained and uniformly dispersed in the *** to commercial IrO_(2),the prepared IrO_(2)cluster can be directly loaded on carbon paper and used as binder-free electrodes,which exhibit higher OER activity and long-term operational stability in alkaline *** quenching strategy provides a simple and efficient method for the synthesis of clusters,which has tremendous potential for industrial-scale preparation and application,especially can be further applied to flow electrochemical generators.

关键词： rapid-chilling cluster structure transition metal compounds binder-free electrode oxygen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Distracted driving behaviour recognition based on transfer learning and model fusion

引用

International Journal of Wireless and Mobile Computing 2023年第2期24卷 159-168页

作者： Luo, Guantai Xiao, Wanghui Chen, Xinwei Tao, Jin Zhang, Chentao -HIT Research Institute of Engineering and Technology Quanzhou Fujian China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou Fujian China Department of Instrumental and Electrical Engineering Xiamen University Fujian Xiamen China

In the recognition of distracted driving behaviour, traditional manual feature extraction is subjective and complex;single deep convolutional network also has problems such as insufficient generalisation performance and stability. To solve the above problems, this paper proposes a distracted driving behaviour recognition method based on transfer learning and model fusion. First, based on the transfer learning method, the deep convolutional neural network models ResNet18 and ResNet34 are used to extract the features of some images, respectively. Furthermore, the pre-trained model is fine-tuned to obtain four deep convolutional neural network models. Finally, the four network models are fused by stacking method, using 5-fold cross-validation method to reduce over-fitting. Experimental results show that the recognition accuracy of distracted driving behaviour after model fusion reaches 95.47%. The fusion model has higher model generalisation performance and recognition accuracy, which can provide certain technical support for the research of distracted driving behaviour recognition. © 2023 Inderscience Enterprises Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition based on multilevel acoustic and textual information 5

Multimodal emotion recognition based on multilevel acoustic ...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhou, Ya Xing, Yuyi Huang, Guimin Guo, Qingkai Deng, Nanxiao School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510668621

The study and application of multimodal emotion recognition have gained significant popularity in recent years, representing one of the challenging tasks in the field of affective computing. We propose a multimodal speech emotion recognition model that utilizes multiple acoustic and textual information layers. This model incorporates transcribed textual data to complement speech data and enable accurate emotion recognition. In the unimodal model, we employ AlexNet, BiGRU, and HuBERT to extract multi-layer acoustic feature information from speech, and the RoBERTa encoder to extract text features. Additionally, we perform fusion between speech and text by utilizing the co-attentive mechanism to extract complementary information across modalities and eliminate inter-modality noise. This process ultimately enhances the emotional representation of the target modality. Finally, the fused features are utilized to predict the emotion category. Our model achieved a weighted sentiment recognition accuracy of 77.41% and an unweighted accuracy of 78.66%. © 2023 SPIE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Oil Well Acoustic Dynamic Liquid Level Detection Based on EEMD 3

Oil Well Acoustic Dynamic Liquid Level Detection Based on EE...

引用

3rd International Conference on High Performance Computing and Communication Engineering, HPCCE 2023

作者： Yang, Ming Sha, Zhiqiang Sun, Yanqing School of Information Engineering Harbin University Harbin150086 China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin University Harbin150086 China Daqing Software Technology Research Institute Co. Ltd. Daqing163711 China

ISBN: (数字)9781510674653

ISBN: (纸本)9781510674646

The detection of oil well dynamic liquid level using acoustic methods requires digital signal processing techniques to reduce environmental noises. Most denoising techniques consist of filter-based approaches and spectral methods with time or frequency transformations. In this study, the Ensemble Empirical Mode Decomposition (EEMD) algorithm is implemented at the filtering step within the standard procedures for oil industrial use to detect dynamic liquid level. Five datasets from oil well production are tested using EEMD compared to standard filtering procedures in industrial use. The EEMD algorithm achieves results in good agreement with the reference results in general with worst case relative error reaching 0.51%. In particular, EEMD processed signal visibly displays more salient echo wave feature compared to reference for one case with unknown submerging noises or disturbances. Under such circumstances, the combination of a denoising filter and EEMD furthermore stabilizes the results, the maximum relative error falling to 0.39%. Importantly, the ensemble averaged Intrinsic Mode Functions (IMFs) of frequencies linked to reflected infra-sound could provide good knowledge helping locate the reflection of infra-sound wave. EEMD is a promising method for filtering signals of echo wave based dynamic liquid level detection. Further in-depth investigations are required to better interpret signals mixed with unknown noises or disturbances. © 2024 SPIE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

A personalized test paper generation model for English examination based on knowledge tracking 5

A personalized test paper generation model for English exami...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhou, Ya Shao, Xiuli Huang, Guimin Guo, Qingkai Deng, Nanxiao Lin, Jianxing School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510668621

In recent years, personalized paper grouping is a hot research topic in the field of intelligence education. In this paper, we propose an optimized deep knowledge tracking model Mul-MAKT combined with a genetic algorithm for personalized paper grouping with English practice as the target. Firstly, we use students’ records (exercise labels, response results, learning behaviors, exercise attributes) as input to the knowledge tracking model to predict students’ performance at the next moment and also to obtain students’ mastery level of knowledge points. Based on the students’ mastery levels, we adjust the students’ ability in each type of English exercise and calculate the students’ weaknesses in each type of question, so as to extract the questions from the test bank with the difficulty matching the students’ ability and containing the students’ weaknesses. © 2023 SPIE.

关键词： Students

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：