检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Nie, Lunyiu Sun, Jiuding Wang, Yanlin Du, Lun Hou, Lei Li, Juanzi Han, Shi Zhang, Dongmei Zhai, Jidong Department of Computer Science and Technology Tsinghua University China School of Software Engineering Sun Yat-Sen University China Microsoft Research Asia China

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising performance, previous PLM-based approaches often suffer from hallucination problems due to their negligence of the structural information contained in the sentence, which essentially constitutes the key semantics of the logical forms. Furthermore, most works treat PLM as a black box in which the generation process of the target logical form is hidden beneath the decoder modules, which greatly hinders the model’s intrinsic interpretability. To address these two issues, we propose to incorporate the current PLMs with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks, namely Semantic Anchor Extraction and Semantic Anchor Alignment, for training the hierarchical decoders and probing the model intermediate representations in a self-adaptive manner alongside the fine-tuning process. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines. More importantly, by analyzing the intermediate representations of the hierarchical decoders, our approach also makes a huge step toward the intrinsic interpretability of PLMs in the domain of semantic parsing. © 2022, CC BY-SA.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Fractional discrete neural networks with variable order: solvability, finite time stability and synchronization

引用

The European Physical Journal Special Topics 2024年 1-14页

作者： Hioual, Amel Alomari, Saleh Al-Tarawneh, Hassan Ouannas, Adel Grassi, Giuseppe Laboratory of Dynamical Systems and Control University of Oum El-Bouaghi Oum El Bouaghi Algeria Faculty of Science and Information Technology Software Engineering Jadara University Irbid Jordan Department of Data Sciences and Artificial Intelligence Al-Ahliyya Amman University Amman Jordan Department of Mathematics and Computer Science University of Oum EL-Bouaghi Oum El Bouaghi Algeria Dipartimento Ingegneria Innovazione Universita del Salento Lecce Italy

Research in the field of dynamic behaviors in neural networks with variable-order differences is currently a thriving area, marked by various significant discoveries. However, when it comes to discrete-time neural networks featuring fractional variable-order nonlocal and nonsingular kernels, there has been limited exploration. This paper stands as one of the initial contributions to this subject, focusing primarily on the topics of stability and synchronization in finite-time within discrete neural networks. The research employs the nabla ABC variable-order difference operator, with a primary approach involving the investigation of a novel Gronwall inequality using the Atangana-Baleanu difference variable-order sum operator. This analysis leads to the development of a uniqueness theorem and a criterion for the stability in finite-time of variable-order discrete neural networks. Furthermore, the requirements stemming from this type of stability and the novel Gronwall inequality serve as the foundation for establishing the conditions necessary for achieving finite-time synchronization in these networks, employing a specific control using state feedback method. Finally, the study utilizes numerical solutions to validate the obtained results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure Data Sharing for Cross-domain Industrial IoT Based on Consortium Blockchain

Secure Data Sharing for Cross-domain Industrial IoT Based on...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Xinze Yu Yunzhou Xie Qiujie Xu Zhuqing Xu Runqun Xiong College of Software Engineering Southeast University Suzhou China Department of Mathematics Imperial College London London UK School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China School of Computer Science and Engineering Southeast University Nanjing China

Industrial Internet of Things (IIoT) is considered one of the most revolutionary technologies that can significantly improve manufacturing efficiency and realize intelligent production. With the increasing complexity of industrial manufacturing, the manufacturing process of a product often involves several different IoT domains (e.g., factories). To achieve a common production goal, devices from various domains share their data for cooperative work, which raises privacy and security concerns for cross-domain communication. Most existing data-sharing schemes rely on a trusted third party. Hence, the privacy and security issues in cross-domain data sharing are still challenging research directions. This paper proposes CBDS, a consortiumblockchain-based cross-domain IIoT data-sharing mechanism. Specifically, we introduce consortium blockchain to construct trust among different domains in IIoT. A group signature is presented to ensure each device’s privacy to achieve anonymous authentication. In addition, the collected data should be stored in the ciphertext. The smart contract and proxy re-encryption are utilized in the CBDS to realize secure cross-domain data sharing. The experimental results demonstrate the effectiveness and efficiency of the proposed CBDS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing

arXiv

引用

arXiv 2022年

作者： Song, Xiangyu Li, Jianxin Lei, Qi Zhao, Wei Chen, Yunliang Mian, Ajmal School of IT Faculty of Science Engineering and Built Environment Deakin University GeelongVIC3220 Australia School of Information Engineering Chang'an University Xi'An China School of Computer Science and Technology Xidian University Xi'An China School of Computer Science China University of Geosciences Wuhan China Department of Computer Science and Software Engineering The University of Western Australia Perth Australia

The goal of Knowledge Tracing (KT) is to estimate how well students have mastered a concept based on their historical learning of related exercises. The benefit of knowledge tracing is that students' learning plans can be better organised and adjusted, and interventions can be made when necessary. With the recent rise of deep learning, Deep Knowledge Tracing (DKT) has utilised Recurrent Neural Networks (RNNs) to accomplish this task with some success. Other works have attempted to introduce Graph Neural Networks (GNNs) and redefine the task accordingly to achieve significant improvements. However, these efforts suffer from at least one of the following drawbacks: 1) they pay too much attention to details of the nodes rather than to high-level semantic information;2) they struggle to effectively establish spatial associations and complex structures of the nodes;and 3) they represent either concepts or exercises only, without integrating them. Inspired by recent advances in self-supervised learning, we propose a Bi-Graph Contrastive Learning based Knowledge Tracing (Bi-CLKT) to address these limitations. Specifically, we design a two-layer comparative learning scheme based on an "exercise-to-exercise" (E2E) relational subgraph. It involves node-level contrastive learning of subgraphs to obtain discriminative representations of exercises, and graph-level contrastive learning to obtain discriminative representations of concepts. Moreover, we designed a joint contrastive loss to obtain better representations and hence better prediction performance. Also, we explored two different variants, using RNN and memory-augmented neural networks as the prediction layer for comparison to obtain better representations of exercises and concepts respectively. Extensive experiments on four real-world datasets show that the proposed Bi-CLKT and its variants outperform other baseline models. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel sentiment classification based on 'word-phrase' attention mechanism 24

A novel sentiment classification based on 'word-phrase' atte...

引用

24th IEEE International Conference on Computational science and engineering, CSE 2021

作者： Panga, Guangyao Peng, Guobei Peng, Zizhen He, Jie Yang, Yan Mo, Zhiyi Wuzhou University School of Data Science and Software Engineering Wuzhou543002 China Guangxi University School of Computer Electronics and Information NanNing530004 China WuZhou Vocational College Department of Mechanical and Electrical Engineering Wuzhou543002 China

ISBN: (纸本)9781665416603

With the rapid development of the COVID-19 epidemic, people are prone to panic due to delayed and incomplete information received. In order to quickly identify the sentiments of massive Internet users, it provides a good reference for government agencies to formulate healthy public opinion guidance strategies. This paper proposes a novel sentiment classification based on 'word-phrase' attention mechanism (SC-WPAtt). On the basis of TCN, we propose a shallow feature extraction model based on the word attention mechanism, and a deep extraction model based on the phrase attention mechanism. These models can effectively mine the auxiliary information contained in words, phrases (i.e. combined words) and overall comments, as well as their different contributions, so as to achieve more accurate emotion classification. Experiments show that the performance of the SC-WPAtt method proposed in this paper is better than that of the HN-Att method. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Image Inpainting with GAN Inversion

arXiv

引用

arXiv 2022年

作者： Yu, Yongsheng Zhang, Libo Fan, Heng Luo, Tiejian Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China Nanjing Institute of Software Technology China Department of Computer Science and Engineering University of North Texas United States

Image inpainting seeks a semantically consistent way to recover the corrupted image in the light of its unmasked content. Previous approaches usually reuse the well-trained GAN as effective prior to generate realistic patches for missing holes with GAN inversion. Nevertheless, the ignorance of a hard constraint in these algorithms may yield the gap between GAN inversion and image inpainting. Addressing this problem, in this paper, we devise a novel GAN inversion model for image inpainting, dubbed InvertFill, mainly consisting of an encoder with a pre-modulation module and a GAN generator with F&W+ latent space. Within the encoder, the pre-modulation network leverages multi-scale structures to encode more discriminative semantics into style vectors. In order to bridge the gap between GAN inversion and image inpainting, F&W+ latent space is proposed to eliminate glaring color discrepancy and semantic inconsistency. To reconstruct faithful and photorealistic images, a simple yet effective Soft-update Mean Latent module is designed to capture more diverse in-domain patterns that synthesize high-fidelity textures for large corruptions. Comprehensive experiments on four challenging datasets, including Places2, CelebA-HQ, MetFaces, and Scenery, demonstrate that our InvertFill outperforms the advanced approaches qualitatively and quantitatively and supports the completion of out-of-domain images well. Copyright © 2022, The Authors. All rights reserved.

关键词： Modulation

来源：评论

学校读者我要写书评

暂无评论

Determinants of under-five mortality in Zimbabwe: Evidence from the 2015–2016 Zimbabwe demographic Health Survey data

Women and Children Nursing

引用

Women and Children Nursing 2024年第1期2卷 1-8页

作者： Elliot Mbunge Garikayi Chemhaka Tafadzwa Dzinamarira Enos Moyo Stephen Fashoto Benhildah Muchemwa Jolly Buwerimwe Ester Petrus Department of Computer Science Faculty of Science and Engineering University of Eswatini Kwaluseni Campus Kwaluseni M201 South Africa Department of Statistics and Demography Faculty of Social Sciences University of Eswatini Kwaluseni Campus Kwaluseni M201 South Africa School of Health Systems and Public Health University of Pretoria Pretoria 0002 South Africa StellenBosch University Matieland 7602 Stellenbosch South Africa Software Department Faculty of ICT International University of Management Windhoek Namibia

Background Child mortality is an important measure of a population’s health status. It is included in the third sustainable development goal that aims to improve global health by reducing under-five mortality to at least as low as 25 per 1000 live births by 2030. The study determines the factors associated with under-five child mortality in Zimbabwe. Methods Cross-sectional secondary data from the 2015 Zimbabwe Demographic Health Survey (ZDHS) were analyzed. The sample included 5,806 women aged 15–49 years of reproductive age. The Chi-square test was used to analyze the association between child death and independent variables. We identified the individual and contextual factors associated with child deaths in Zimbabwe using the Cox proportional hazard model. Results The risks of under-five mortality were highest among children of first birth order (adjusted hazard ratio (aHR) = 2.37, P = 0.04), multiple births (aHR = 2.37, P = 0.04), mothers with primary or less maternal education (aHR = 1, Ref), mothers below 18 years old (aHR = 1, Ref), apostolic mothers (aHR = 2.90, P = 0.002), mothers who do not use contraceptives (aHR = 2.20, P < 0.001), formerly married women (aHR = 6.42, P = 0.005), women with 5 or more children (aHR = 15.84, P < 0.001), women who read newspapers less than once a week (aHR = 1.75, P = 0.13), and households that use high-polluting fuels (aHR = 1.92, P = 0.023). Conclusion This study establishes that child health, maternal, socioeconomic, household, and ecological factors are important determinants of under-five mortality in Zimbabwe. Understanding these determinants is crucial for designing effective interventions and policies to reduce child mortality rates. This requires comprehensive approaches such as improving access to healthcare, education, and basic sanitation facilities; prioritizing nutrition; providing clean water; enhancing poverty reduction and immunization; and promoting breastfeeding and social empo

关键词： Child mortality Survival analysis Hazard ratio Cox proportional model

来源：评论

学校读者我要写书评

暂无评论

A cooperative heterogeneous vehicular clustering framework for

引用

Frontiers of Information Technology & Electronic engineering 2021年第9期22卷 1247-1259页

作者： Iftikhar AHMAD Rafidah Md NOOR Zaheed AHMED Umm-e-HABIBA Naveed AKRAM Fausto Pedro GARCIA MARQUEZ Department of Computer Science and Information Technology MirpurUniversity of Science and TechnologyMirpur-10250(AJK)Pakistan Facultyof Computer Science and Information Technology University of MalayaKualaLumpur 50603Malaysia Departmentof Software Engineering University of KotliAJK 11100Pakistan Department of Mechanical Engineering Mirpur University of Science andTechnologyMirpur-10250(AJK)Pakistan Department of MechanicalEngineering Faculty of Mechanical EngineeringUniversity of MalayaKualaLumpur 50603Malaysia Ingenium Research Group University of Castilla-LaManchaSpain

Heterogeneous vehicular clustering integrates multiple types of communication networks to work efficiently for various vehicular *** popular form of heterogeneous network is the integration of long-term evolution(LTE)and dedicated short-range *** heterogeneity of such a network infrastructure and the non-cooperation involved in sharing cost/data are potential problems to solve.A vehicular clustering framework is one solution to these problems,but the framework should be formally verified and validated before being deployed in the real *** solve these issues,first,we present a het-erogeneous framework,named destination and interest-aware clustering,for vehicular clustering that integrates vehicular ad hoc networks with the LTE network for improving road traffic ***,we specify a model system of the proposed *** model is formally verified to evaluate its performance at the functional level using a model checking *** evaluate the performance of the proposed framework at the micro-level,a heterogeneous simulation environment is created by integrating state-of-the-art *** comparison of the simulation results with those of other known approaches shows that our proposed framework performs better.

关键词： Vehicular cluster Heterogeneity Cooperation Formal verification System model

来源：评论

学校读者我要写书评

暂无评论

"Talking Books" : A Sinhala Abstractive Text Summarization Approach for Sinhala Textbooks

"Talking Books" : A Sinhala Abstractive Text Summarization A...

引用

International Conference for Convergence of Technology (I2CT)

作者： B.R.M.S.R.B. Rathnayake Kalpani Manathunga Dharshana Kasthurirathna Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

The ability for books to talk would be an exciting concept, and this research discussion paves the path for an identical approach. The research objectives discussed in this paper address several burning problems, solve them and adapt them to future technological enhancements from a Sri Lankan context. Burning problems include reducing printing costs for textbooks, addressing students’ health, promoting green technology, and identifying a suitable summarising approach to the native language, Sinhala resulting in students’ learning ease. Other symptoms for the betterment indicate paths taken to reduce the weight of school bags carried by students, reduce paper usage by the government on printing textbooks, and spread technological awareness to teenagers regarding e-Learning. Textbooks issued by the government will be digitized and centralized into a single system that the government officials themselves can administer. The paper discusses limited hindsight literature and proposes 2 new algorithms for abstractive and extractive summarization for Sinhala text. The 2 algorithms are compared against one another in terms of performance, efficiency, precision and accuracy. Experts in the education domain have verified the derived summary of both algorithms. The deliverable artefacts are the mobile application, a RESTful auto-summarization plugin service, and new data sets extracted to train the GPT-3 models.

关键词： Printing Electronic learning Costs Government Education Data models Mobile applications

来源：评论

学校读者我要写书评

暂无评论

CDGNet: A Cross-Time Dynamic Graph-Based Deep Learning Model for Vehicle-Based Traffic Speed Forecasting

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Fang, Yuchen Luo, Haiyong Zhao, Fang Sun, Poly Z.H. Qin, Yanjun Zeng, Liang Hui, Bo Wang, Chenxing School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of Industrial Engineering School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China Tsinghua University Beijing China University of Tulsa Tulsa USA

Vehicle-based traffic speed forecasting aims to predict the average speed of vehicles on the road in the future, which is an essential side information in intelligent vehicles and beneficial to safe autonomous driving, yet is very challenging due to the complex and dynamic spatio-temporal dependencies in real-world vehicle-based traffic. To extract intricate correlations among multiple vehicle-based speed time series, previous methods have used graph convolution networks. However, the conventional static and dynamic graphs fail to reflect the traffic evolution and the hysteresis spatial influence caused by vehicle movement. To address this issue, we propose a novel cross-time dynamic graph-based deep learning model, named CDGNet, for vehicle-based traffic speed forecasting. The model is able to effectively capture hysteresis spatial dependencies between each time slice and its historical time slices through the cross-time dynamic graph-based GCN. Meanwhile, a gating mechanism is integrated into our cross-time dynamic graph, which conforms to the sparse correlation in the real world. Besides, GCNs are incorporated into a novel encoder-decoder architecture to forecast multi-step speed. Experimental results on three real-world vehicle-based traffic speed datasets demonstrate the superiority of our CDGNet over various state-of-the-art spatio-temporal forecasting methods and the effectiveness of each component. We additionally provide a visualization of our cross-time dynamic graph to show the capability of assisting intelligent vehicles to avoid congestion. IEEE

关键词： Forecasting

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：