检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Si, Jiasheng Zhu, Yingjie Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising the veracity prediction. Although extensively explored, existing approaches fall within the scope of the single-granular (tokens or sentences) explanation, which inevitably leads to explanation redundancy and inconsistency. To address such issues, this paper explores the viability of multi-granular rationale extraction with consistency and faithfulness for explainable multi-hop fact verification. In particular, given a pretrained veracity prediction model, both the token-level explainer and sentence-level explainer are trained simultaneously to obtain multi-granular rationales via differentiable masking. Meanwhile, three diagnostic properties (fidelity, consistency, salience) are introduced and applied to the training process, to ensure that the extracted rationales satisfy faithfulness and consistency. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms some state-of-the-art baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

NL2SQL Generation with Noise Labels based on Multi-task Learning 5

NL2SQL Generation with Noise Labels based on Multi-task Lear...

引用

2022 5th International Symposium on Big Data and Applied Statistics, ISBDAS 2022

作者： Long, Lingli Zhu, Yongjin Shao, Jun Kong, Zheng Li, Jian Xiang, Yanzheng Zhang, Xu Jiangsu Frontier Electric Technology Co. Ltd. China School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

With the rapid development of artificial intelligence technology, semantic recognition technology is becoming more and more mature, providing the preconditions for the development of natural language to SQL (NL2SQL) technology. In the latest research on NL2SQL, the use of pre-trained models as feature extractors for natural language and table schema has led to a very significant improvement in the effectiveness of the models. However, the current models do not take into account the degradation of the noisy labels on the overall SQL statement generation. It is crucial to reduce the impact of noisy labels on the overall SQL generation task and to maximize the return of accurate answers. To address this issue, we propose a restrictive constraint-based approach to mitigate the impact of noise-labeled labels on other tasks. In addition, parameter sharing approach is used in noiseless-labeled labels to capture each part's correlations and improve the robustness of the model. In addition, we propose to use Kullback-Leibler divergence to constrain the discrepancy between hard and soft constrained coding of noisy labels. Our model is compared with some recent state-of-the-art methods, and experimental results show a significant improvement over the approach in this paper. © Published under licence by IOP Publishing Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

High responsivity and fast response 8×8β-Ga_(2)O_(3)solar-blind ultraviolet imaging photodetector array

引用

Science China(Technological Sciences) 2023年第11期66卷 3259-3266页

作者： SHEN GaoHui LIU Zeng TANG Kai SHA ShuLin LI Lei TAN Chee-Keong GUO YuFeng TANG WeiHua Innovation Center of Gallium Oxide Semiconductor(IC-GAO) College of Integrated Circuit Science and EngineeringNanjing University of Posts and TelecommunicationsNanjing 210023China National and Local Joint Engineering Laboratory for RF Integration and Micro-Assembly Technologies Nanjing University of Posts and TelecommunicationsNanjing 210023China Key Laboratory of Aerospace Information Materials and Physics(NUAA) MIITNanjing 211106China College of Physics MIIT Key Laboratory of Aerospace Information Materials and PhysicsKey Laboratory for Intelligent Nano Materials and DevicesNanjing University of Aeronautics and AstronauticsNanjing 211106China Advanced Materials Thrust Function HubThe Hong Kong University of Science and Technology(Guangzhou)Nansha 511458China Department of Electronic and Computer Engineering School of EngineeringThe Hong Kong University of Science and TechnologyHong Kong 999077China

In this work,an 8×8 Ga_(2)O_(3)solar-blind ultraviolet photodetector array is introduced for image sensing *** 2-in wafer-scaled Ga_(2)O_(3)thin film was grown by metalorganic chemical vapor deposition technique;and the photodetector array was fabricated through ultraviolet photolithography,lift-off,and electron-beam *** addition to the high solar-blind/visible rejection ratio of 104,every photodetector cell in the array has high performance and fast response speed,such as responsivity of 49.4 A W^(-1),specific detectivity of 6.8×10^(14)Jones,external quantum efficiency of 1.9×10^(4)%,linear dynamic range of 117.8 d B,and response time of 41 ms,respectively,indicating the high photo-response performance of the ***,the photodetector array displayed uniform responsivity with a standard deviation of~6%,and presented a sensing image of low chromatic aberration,owing to the high resolution of the photodetector *** a word,this work may contribute to developing Ga_(2)O_(3)-based optoelectronic device applications.

关键词： Ga_(2)O_(3) photodetector array imaging photo-response

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Smart Water Meter Monitoring System Based on NB-IoT 7

Research and Application of Smart Water Meter Monitoring Sys...

引用

7th IEEE information Technology and Mechatronics Engineering Conference, ITOEC 2023

作者： Zhao, Yuanyuan Zhang, Tixiang Hao, Huijuan Zhang, Xiaojie Shandong Computer Science Center Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science No. 19 Keyuan Road Shandong Jinan250014 China Shandong Yonate Environmental Technology Co. Ltd. Shandong Jinan250014 China

ISBN: (纸本)9798350334197

With the increasing shortage of water resources and the improvement of environmental awareness, intelligent water meter monitoring systems have become a hot research topic in the field of water conservation. This paper studies and designs a smart water meter system based on NB-IoT, and discusses its effect in practical applications. This smart water meter monitoring system adopts STM8 microcontroller as the main control chip of the water meter, and adopts the low-power NB-IoT module BC28 module to upload the monitored voltage data, network signal quantity, current water consumption and collection time to the TLink cloud platform in real time, which solves the problems of unstable communication in the working environment, high power consumption of long-term sensor collection and transmission data. At the same time, the water meter can achieve the function of remote control of the water valve switch by driving the stepper motor, which perfectly solves the problems and shortcomings of the current traditional water meter and smart water meter, and greatly meets the development needs of the water industry. © 2023 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Vision-language models are strong noisy label detectors 24

Vision-language models are strong noisy label detectors

引用

Proceedings of the 38th International Conference on Neural information Processing Systems

作者： Tong Wei Hao-Tian Li Chun-Shu Li Jiang-Xin Shi Yu-Feng Li Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and National Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China and School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798331314385

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Association Rule Guided Web API Complementary Function Recommendation for Mashup Creation: An Explainable Perspective 17th

Association Rule Guided Web API Complementary Function Recom...

引用

17th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2022

作者： He, Pengfei Qi, Wenchao Liu, Xiaowei Liu, Linlin You, Dianlong Shen, Limin Chen, Zhen School of Information Science and Engineering Yanshan University Qinhuangdao China National Science Libraries Chinese Academy of Sciences Beijing China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China

ISBN: (纸本)9789819923557

As more and more service providers encapsulate and publish their data and services on the internet in the form of Web APIs, the number of Web APIs is ever-increasing. For this reason, Web API recommendation is gaining momentum and has achieved high performance in accuracy. However, few studies paid attention to function recommendation. As an indispensable entity in the mashup-API ecosystem, function is not only the in-facto basis of API taxonomy, but also determines the compatibility and the internal construction pattern of mashup composition. Considering that users adopt multiple function invocations during a development cycle and the number of functions is also increasing, we propose the complementary function recommendation(CFR), a function-to-function problem. To solve the CFR, we regard each mashup as a transaction set for frequent pattern mining and propose an association rule-based complementary function recommendation(ARCFR) system, which provides function recommendation and corresponding probability explanation. Our experiments show that ARCFR can recommend complementary function effectively, and we give two applicable scenarios to demonstrate the practical value of our method in more aspects. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Computation Meets Network Coding: Optimal Scheduling in Parallel Computing

Fault-Tolerant Computation Meets Network Coding: Optimal Sch...

引用

作者： Li, Congduan Zhang, Yiqian Tan, Chee Wei School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen518107 China Guangxi Key Laboratory of Multi-Source Information Mining and Security Shenzhen Key Laboratory of Navigation and Communication Integration Shenzhen518107 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

In large-scale parallel computing systems, machines and the network suffer from non-negligible faults, often leading to system crashes. The traditional method to increase reliability is to restart the failed jobs. To avoid unnecessary time wasted on reboots, we propose an optimal scheduling strategy to enable fault-tolerant reliable computation to protect the integrity of computation. Specifically, we determine the optimal redundancy-failure rate tradeoff to incorporate redundancy into parallel computing units running multiple-precision arithmetics, like the Chinese Remainder Theorem, that are useful for applications such as asymmetric cryptography and fast integer multiplication. Inspired by network coding in distributed storage for disk failures, we propose coding matrices to strategically map partial computation to available computing units, so that the central unit can reliably reconstruct the results of any failed machine without recalculations to yield the final correct computation output. We propose optimization-based algorithms to efficiently construct the optimal coding matrices subject to fault tolerance specifications. Performance evaluation demonstrates that the optimal scheduling effectively reduces the overall running time of parallel computing while resisting wide-ranging failure rates. © 2023 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

A Parallel Color Image Encryption Algorithm Based on a 2-D Logistic-Rulkov Neuron Map

引用

IEEE Internet of Things Journal 2025年第11期12卷 18115-18124页

作者： Gao, Suo Zhang, Zheyi Iu, Herbert Ho-Ching Ding, Siqi Mou, Jun Erkan, Uğur Toktas, Abdurrahim Li, Qi Wang, Chunpeng Cao, Yinghong Dalian Polytechnic University School of Information Science and Engineering Dalian116034 China The University of Western Australia School of Electrical Electronic and Computer Engineering PerthWA6009 Australia Dalian University of Technology School of Mathematical Sciences Dalian116024 China Karamanoglu Mehmetbey University Faculty of Engineering Department of Computer Engineering Karaman70200 Turkey Ankara University Engineering Faculty Department of Artificial Intelligence and Data Engineering Ankara06830 Turkey Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250000 China

Images are widely used in social networks, necessitating efficient and secure transmission, especially in bandwidth-constrained environments. This article aims to develop a color image encryption algorithm that enhances security while optimizing computational efficiency. A novel parallel color image encryption algorithm based on the 2-D logistic-Rulkov neuron map (2D-LRNM) is proposed. In this approach, the three channels of the color image are first separated. Cross-channel information interaction is introduced to form three new channels, which are then processed in parallel. During the encryption process of each channel, a block-wise parallel encryption mechanism is applied, ensuring simultaneous encryption of each block. This block-wise strategy effectively leverages parallel computing resources and balances the task load. To meet the demand for a large number of keystreams during encryption, the 2D-LRNM is introduced. It combines the simplicity and chaotic properties of the Logistic map with the multitimescale dynamics and neurodynamic behaviors of the Rulkov map. By overcoming the dimensional limitations inherent in the single Logistic map, this approach extends the system to a 2-D framework, significantly increasing the complexity of chaotic behavior and improving its unpredictability. Experimental results demonstrate that the proposed encryption algorithm achieves high security and reduces computation time by approximately 83.3%. © 2014 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

GrayINT – Detection and Localization of Gray Failures via Hybrid In-band Network Telemetry 24

GrayINT – Detection and Localization of Gray Failures via H...

引用

24th Asia-Pacific Network Operations and Management Symposium, APNOMS 2023

作者： Zhang, Kuichao Su, Wei Shi, Huiling Zhang, Kai Zhang, Wei Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Electronics and Information Engineering Beijing Jiaotong University Beijing China

ISBN: (纸本)9788995004395

As the underlying infrastructure, data center networks (DCNs) provide an important platform for cloud computing and next-generation networks. However, due to the influence of many factors, such as network, hardware, and software, various failures may occur during the operation of the DCN, which brings great challenges to its reliability. Particularly, a more insidious type of network failure, known as gray failure, presents a significant threat to system stability. In response to this challenge, in this work, we propose GrayINT, a gray failure detection and localization system that leverages In-band Network Telemetry (INT) technology to monitor all paths within the data center network in real-time. To verify the feasibility of our design, we build a fat-tree data center network on a virtual network testbed. A large number of experimental results demonstrate that our system can monitor device and link status in real-time, achieving gray failure detection and localization. Copyright 2023 KICS.

关键词： Next generation networks

来源：评论

学校读者我要写书评

暂无评论

Time Series Anomaly Detection Based on Normalized Flow and Bayesian networks 9

Time Series Anomaly Detection Based on Normalized Flow and B...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Yao, Honglei Liu, Donglan Chang, Yingxian Liu, Xin Tang, Chaofan State Grid Shandong Electric Power Research Institute Jinan China State Grid Shandong Electric Power Company Jinan China Qilu University of Technology Shandong Academy of Sciences Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China

ISBN: (纸本)9798350391367

Time series anomaly detection often faces significant challenges due to the high dimensionality, interdependence, and label sparsity of the data. Traditional methods struggle to model the intricate relationships between multiple time series components and often fail to accurately detect anomalies due to insufficient data dependence mining. To address these issues, we introduce GCRNF, a novel Graph-Enhanced Standardized Flow Model that incorporates a Bayesian network for causality modeling. This model decomposes joint probabilities into conditional probabilities and utilizes a graph dependency encoder with hybrid CNN-RNN models and Graph Convolutional networks (GCNs). Our experimental results demonstrate that GCRNF outperforms existing methods in density estimation, anomaly detection, and drift identification within time series distributions. Specifically, GCRNF showed a significant improvement in detection accuracy and robustness compared to traditional methods, providing a more effective solution for identifying anomalies in complex multivariate time series data. © 2024 IEEE.

关键词： Markov processes

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：