检索结果-内蒙古大学图书馆

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Wang, Jun Li, Yanhui Chen, Zhifei Chen, Lin Zhang, Xiaofang Zhou, Yuming Nanjing University State Key Laboratory for Novel Software Technology China School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Technology Soochow University China

ISBN: (纸本)9798400702174

In the wake of developments in the field of Natural Language Processing, Question Answering (QA) software has penetrated our daily lives. Due to the data-driven programming paradigm, QA software inevitably contains bugs, i.e., misbehaving in real-world applications. Current testing techniques for testing QA software include two folds, reference-based testing and metamorphic testing. This paper adopts a different angle to achieve testing for QA software: we notice that answers to questions would have inference relations, i.e., the answers to some questions could be logically inferred from the answers to other questions. If these answers on QA software do not satisfy the inference relations, an inference bug is detected. To generate the questions with the inference relations automatically, we propose a novel testing method Knowledge Graph driven Inference Testing (KGIT), which employs facts in the Knowledge Graph (KG) as the seeds to logically construct test cases containing questions and contexts with inference relations. To evaluate the effectiveness of KGIT, we conduct an extensive empirical study with more than 2.8 million test cases generated from the large-scale KG YAGO4 and three QA models based on the state-of-the-art QA model structure. The experimental results show that our method (a) could detect a considerable number of inference bugs in all three studied QA models and (b) is helpful in retraining QA models to improve their inference ability. © 2024 ACM.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A ROI Based Self-supervised Strategy for Retinal Image Analysis

A ROI Based Self-supervised Strategy for Retinal Image Analy...

引用

2022 International Conference on Optical and Photonic engineering, icOPEN 2022

作者： Dong, Shiyun Chen, Qiang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781510661905

With the maturity of deep learning methods and the collection of a large number of retinal images, many deep learning models have been used for retinopathy analysis, but most of them are supervised methods. That is, the training of the models relies heavily on a large number of annotated retinal images, which is sometimes difficult to satisfy in medical fields including ophthalmology. This paper explores the application of self-supervised methods that do not require a large amount of labeled data in the analysis of retinal images. Firstly, we propose a novel self-supervised task of column dislocation and compare the performance of various self-supervised tasks on the retinopathy classification, verifying our proposed task's effectiveness. Then, by considering the characteristics of retinal images, namely the region of interest (ROI) in spectral domain optical coherence tomography (SD-OCT) images is less than half of the whole images, we also propose a ROI based self-supervised strategy to improve the feature representation ability. The experiments on two public datasets for retinal image classification and segmentation demonstrate that the proposed strategy is effective compared with several existed self-supervised learning methods. © 2022 SPIE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Stochastic Perturbation Averaging Boosts Transferability of Adversarial Examples 10

Stochastic Perturbation Averaging Boosts Transferability of ...

引用

10th IEEE International Conference on Data science and Advanced Analytics, DSAA 2023

作者： Yang, Rongbo Li, Qianmu Meng, Shunmei Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350345032

In image, video and even real physics domains, adversarial examples can mislead deep models to produce wrong predictions. Transfer-based attacks against black-box models are more in line with realistic scenarios, but adversarial examples made on surrogate model have a low success rate when transferred to the target model due to overfitting the source model. We study the Stochastic Weight Averaging strategy in the domain generalization process and propose a Stochastic Perturbation Averaging method (SPA). Specifically, we add stochastic perturbations to the examples during the gradient descent attack, and we design a Central Amplification method (CAM) to enhance this random variation, then SPA stabilizes the iteration direction by computing the gradient average of the perturbed examples to find a relatively flat local minimum of the loss function. SPA is an efficient and general strategy which can significantly improve the transferability of the gradient-based attack methods. For instance, the average attack success rate of the adversarial examples produced based on four single models against seven pre-trained models reached 90.10%, which is the best result so far. Code is available at https://*** yangrongbo/SPA. © 2023 IEEE.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Authorization of Aadhar data using Diffie Helman key with enhanced security concerns

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8639-8658页

作者： Karthika, K. Rangasamy, Devi Priya Anna University Chennai India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

In today’s digital era, the security of sensitive data such as Aadhaar data is of utmost importance. To ensure the privacy and integrity of this data, a conceptual framework is proposed that employs the Diffie-Hellman key exchange protocol and Hash-based Message Authentication Code (HMAC) to enhance the security. The proposed system begins with the preprocessing phase, which includes removing noise, standardizing formats and validating the integrity of the data. Next, the data is segmented into appropriate sections to enable efficient storage and retrieval in the cloud. Each segment is further processed to extract meaningful features, ensuring that the relevant information is preserved while reducing the risk of unauthorized access. For safeguarding the stored Aadhaar data, the system employs the Diffie-Hellman key exchange protocol which allows the data owner and the cloud service provider to establish a shared secret key without exposing it to potential attackers. Additionally, HMAC is implemented to verify the identity of users during the login process. HMAC enhances security by leveraging cryptographic hash functions and a shared secret key to produce a distinct code for each login attempt. This mechanism effectively protects the confidentiality and integrity of stored data. The combination of Diffie-Hellman key exchange and HMAC authentication provides a robust security framework for Aadhaar data. It ensures that the data remains encrypted and inaccessible without the secret key, while also verifying the identity of users during the login process. This comprehensive approach helps preventing unauthorized access thereby protecting against potential attacks, instilling trust and confidence in the security of Aadhaar data stored in the cloud. Results of the article depict that the proposed scheme achieve 0.19 s of encryption time and 0.05 s of decryption time. © 2024 – IOS Press. All rights reserved.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Learning Temporal User Features for Repost Prediction with Large Language Models

引用

computers, Materials & Continua 2025年第3期82卷 4117-4136页

作者： Wu-Jiu Sun Xiao Fan Liu School of Computer Science and Engineering Southeast UniversityNanjing11189China Department of Media and Communication City University of Hong KongHong Kong999077 China

Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising *** methods use deep neural networks to make predictions based on features related to user topic interests and social ***,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging *** overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction ***,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user ***,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural *** results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.

关键词： Reposting prediction large language model semantic adaptation temporal adaptation

来源：评论

学校读者我要写书评

暂无评论

A deep Q-learning model for sequential task offloading in edge AI systems

引用

Intelligent and Converged Networks 2024年第3期5卷 207-221页

作者： Dong Liu Shiheng Gu Xinyu Fan Xu Zheng Department of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610000China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhen 515100China Department of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610000China

Currently,edge Artificial Intelligence(AI)systems have significantly facilitated the functionalities of intelligent devices such as smartphones and smart cars,and supported diverse applications and *** fundamental supports come from continuous data analysis and computation over these *** the resource constraints of terminal devices,multi-layer edge artificial intelligence systems improve the overall computing power of the system by scheduling computing tasks to edge and cloud servers for *** efforts tend to ignore the nature of strong pipelined characteristics of processing tasks in edge AI systems,such as the encryption,decryption and consensus algorithm supporting the implementation of Blockchain ***,this paper proposes a new pipelined task scheduling algorithm(referred to as PTS-RDQN),which utilizes the system representation ability of deep reinforcement learning and integrates multiple dimensional information to achieve global task ***,a co-optimization strategy based on Rainbow Deep Q-Learning(RainbowDQN)is proposed to allocate computation tasks for mobile devices,edge and cloud servers,which is able to comprehensively consider the balance of task turnaround time,link quality,and other factors,thus effectively improving system performance and user *** addition,a task scheduling strategy based on PTS-RDQN is proposed,which is capable of realizing dynamic task allocation according to device *** results based on many simulation experiments show that the proposed method can effectively improve the resource utilization,and provide an effective task scheduling strategy for the edge computing system with cloud-edge-end architecture.

关键词： edge computing task scheduling reinforcement learning Rainbow Deep Q-Learning(RainbowDQN)

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Hierarchical Graph Convolutional Networks for Traffic Forecasting

Spatial-Temporal Hierarchical Graph Convolutional Networks f...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Qingyuan, Shao Hui, Yan Yuxin, Chen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

Traffic forecasting is a critical task in transportation planning and management, which requires modeling the complex spatial and temporal dependencies in traffic data. Most current methods employ Graph Convolutional Networks (GCN) to model spatial dependencies, and Recurrent Neural Networks (RNN) or Temporal Convolutional Networks (TCN) to model temporal dependencies. However, the representation ability of such methods is limited due to: 1) the conventional temporal extract models, such as RNN and TCN, suffer from limited flexibility, specifically, RNN can only capture temporal dependencies sequentially, while TCN is constrained by its multi-layer dilated convolution structure;2) spatial and temporal dependencies are intricately intertwined in the real world, but most methods fail to capture this spatial-temporal correlation resulting in sub-optimal performance. To this end, we propose the Spatial-Temporal Hierarchical Graph Convolutional Networks (STHGCN), in which we design Spatial-Temporal Hierarchical Graph (STHG) to simultaneously model spatial and temporal dependencies. Specifically, to model temporal dependencies more flexibly, we introduce two crucial components: the Local Temporal Transmission Matrix (LTTM) and the Multi-hop Temporal Similarity Matrix (MTSM). The LTTM captures adjacent temporal dependencies, while the MTSM captures multi-hop temporal dependencies. We further propose a Temporal Neighbor Fusion model that combines the LTTM and MTSM to obtain the adjacency matrix of STHG. Additionally, accounting for spatial-temporal correlation, we exploit the spatial GCN results as the STHG nodes which allows us to learn spatial and temporal dependencies simultaneously via the temporal GCN. Our experiments on four real-world datasets demonstrate that STHGCN outperforms the state-of-the-art methods for traffic forecasting. The code is available at https://***/sqy123qwer/STHGCN © 2023 IEEE.

关键词： graph convolutional network spatial-temporal data traffic forecasting

来源：评论

学校读者我要写书评

暂无评论

A novel method for indian vehicle registration number plate detection and recognition using CNN

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8563-8585页

作者： Pandey, Vibha Choubey, Siddhartha Patra, Jyotiprakash Mall, Shachi Choubey, Abha Department of Computer Science Engineering Shri Shankaracharya Technical Campus Chhattisgarh Bhilai India Department of Computer Science Engineering Shri Shankaracharya Institute of Professional Management and Technology Chhattisgarh Raipur India School of Computer Science and Engineering Galgotias University Greater Noida India

Automated reading of license plate and its detection is a crucial component of the competent transportation system. Toll payment and parking management e-payment systems may benefit from this software’s features. License plate detection and identification algorithms abound, and each has its own set of strengths and weaknesses. computer vision has advanced rapidly in terms of new breakthroughs and techniques thanks to the emergence and proliferation of deep learning principles across several branches of AI. The practice of automating the monitoring process in traffic management, parking management, and police surveillance has become much more effective thanks to the development of Automatic License Plate Recognition (ALPR). Even though license plate recognition (LPR) is a technology that is extensively utilized and has been developed, there is still a significant amount of work to be done before it can achieve its full potential. In the last several years, there have been substantial advancements in both the scientific community’s methodology and its level of efficiency. In this era of deep learning, there have been numerous developments and techniques established for LPR, and the purpose of this research is to review and examine those developments and approaches. In light of this, the authors of this study suggest a four-stage technique to automated license plate detection and identification (ALPDR), which includes, image pre-processing, license plate extraction, character segmentation, and character recognition. And the first three phases are known as "extraction," "preprocessing," and "segmentation," and each of these processes has been shown to benefit from its own unique technique. In light of the fact that character recognition is an essential component of license plate identification and detection, the Convolution Neural Network (CNN), MobileNet, Inception V3, and ResNet 50 have all been put through their paces in this regard. © 2024 – IOS Press. All rights re

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

DD-SPP: Dynamic and Distributed Service Placement Policy for Optimal Scheduling in Fog-Edge Computing

引用

SN computer science 2024年第7期5卷 801页

作者： Kaur, Navjeet Bhardwaj, Vivek Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University School of Computer Science and Engineering Manipal University Jaipur

The existing cloud model unable to handle abundant amount of Internet of Things (IoT) services placed by the end users due to its far distant location from end user and centralized nature. The edge and fog computing are the latest technologies for developing smart cities that are becoming popular to efficiently support latency-sensitive IoT application services. But these advanced technologies suffer from limited size and computation capabilities;therefore, optimal placement of services among available resources is an open issue. Therefore, the proposed work target the stated issue and presents a Dynamic and Distributed Service Placement Policy (DD-SPP) considering the edge and fog devices. The model is divided into three main phases, that is, the Service Type Estimator (STE), the Service Dependency Estimator & Resolution (SDER), and Resource Demand Estimator & Scheduling (RDES). STE and RDES modules depend on each other to perform optimal service placement. The results of the implementation showed satisfactory improvement with respect to present state-of-the-art policy where delay is improved by around 41%, energy is improved by 27%, response time by 28% and overall cost by 28%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cloud computing DD-SPP Edge computing Fog computing IoT Scheduling Service placement policy

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Fixed-Time Adaptive Fuzzy Control for Nontriangular Nonlinear Systems With Unknown Control Directions

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2397-2409页

作者： Cui, Guozeng Xu, Hui Yu, Jinpeng Ma, Qian Jian, Muwei Suzhou University of Science and Technology School of Electronic and Information Engineering Suzhou215009 China Qingdao University School of Automation Qingdao266071 China Nanjing University of Science and Technology School of Automation Nanjing210094 China Shandong University of Finance and Economics School of Computer Science and Technology Jinan250014 China

This article focuses on the problem of fixed-time adaptive fuzzy control for a class of nontriangular nonlinear systems with unknown control directions under the event-triggered framework. To tackle the algebraic loop issue arising from the nontriangular structure, the property of the fuzzy logic system is employed. The command filter and the error compensation signals, which have the feature of fixed-time convergence, are constructed to eliminate the 'explosion of complexity' phenomenon and the effect of filtered error, respectively. By integrating the Nussbaum gain technique into the relative threshold-based event-triggered mechanism, a singularity-free fixed-time adaptive fuzzy control scheme is devised to ensure that the closed-loop system is practically fixed-time stable, and the tracking error converges to a small region near the origin in a fixed time. Finally, simulation examples are presented to demonstrate the effectiveness and superiority of the proposed fixed-time control algorithm. © 2020 IEEE.

关键词： Backstepping

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：