检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Zheqi Feng Tao Peng Guojun Wang Kejian Guan Shool of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (数字)9781665464970

ISBN: (纸本)9781665464987

In mobile crowdsensing (MCS), information fusion is necessary to obtain data aggregation results. In information fusion, most of the existing personalized mechanisms only consider meeting the personalized requirements of data collectors and rarely consider the potential personalized requirements of data users. Furthermore, how to provide personalized data aggregation results for data users with different data quality requirements has not been addressed. This paper proposes a personalized privacy-preserving information fusion (P3IF) mechanism based on the personalized sampling mechanism in the MCS. P3IF provides personalized data aggregation results for data users with different data quality requirements while ensuring personalized privacy protection for data collectors. Specifically, we design a personalized privacy-preserving information fusion scheme based on the personalized differential privacy mechanism. Considering on the privacy requirements of the data collectors, we conduct personalized privacy sampling on the raw data from the data collectors and obtain a subset of sensing data. According to the data quality requirements of data users and the quality of each data, the obtained subset is sampled for personalized data quality requirements, and the final data set is obtained. Simulation experiments verify the feasibility and effectiveness of P3IF.

关键词： Differential privacy Crowdsensing Data integrity Data aggregation Sensors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Fake Detection using Transfer Learning: A Comparative study of Multiple Neural Networks

Deep Fake Detection using Transfer Learning: A Comparative s...

引用

Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT), International Conference on

作者： Abhineswari M Kurupati Sai Charan Shrikarti BN Sujithra Kanmani R Shool of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798331540685

ISBN: (纸本)9798331540692

With the proliferation of sophisticated AI techniques, the creation and dissemination of deep fake images and videos have emerged as a pressing concern in today's digital landscape. Deep fake technology employs advanced machine learning algorithms to manipulate or synthesize realistic-looking media, often with malicious intent. This study evaluates the effectiveness of various pre-trained deep learning models using transfer learning for detecting deep fake images on the Face Forensics++ dataset. The models considered include MobileN etV2, ResN et50, Inception V3, EfficientN et, Xception, NASNetMobile, and a Custom CNN. Accuracies obtained from these models are compared to assess their performance in distinguishing between real and fake images. With the highest performance in MobileNetV2 with 89% followed by ResNet50 with 83 % and other models.

关键词： Deepfakes Accuracy Computational modeling Transfer learning Neural networks Pressing Signal processing

来源：评论

学校读者我要写书评

暂无评论

PoW and PoS and Related Applications

PoW and PoS and Related Applications

引用

2021 International Conference on Electronic Information engineering and computer science, EIECS 2021

作者： Ouyang, Zhiqiang Shao, Jie Zeng, Yifeng School of Computer Science and Engineering Sun Yat-sen University Guangzhou China University of Washington Department of Mathematics WA United States Shool of Software Dalian University of Technology Dalian China

ISBN: (纸本)9781665416740

Consensus protocols can help guarantee security and sustainability to maintain the decentralized Blockchain system used in different scenarios and applications due to their different features. There are two main prevalent protocols, Proof of Work (PoW) used in Bitcoin and Proof of Stake (PoS) used in Ethereum. This paper reviews these two consensus protocols, PoW and PoS, and their related improvements and applications. We first introduce the basic concepts, implementations, advantages, and disadvantages of PoW and PoW and make a detailed comparison between these two protocols. We find that though providing security when honest participants are the majority, PoW may lead to excessive power consumption. While PoS is relatively insecure and leads to monopoly (centralization), though energy efficient by discarding complex hash operations. Therefore, some newly proposed consensus protocols have attempted to find a pleasant compromise between these two classic protocols. After a detailed analysis, we investigate the researches related to the defect improvements of PoS and PoW. Finally, we describe various applications of PoS and PoW, including cryptocurrencies and information storage. © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Association Rules Mining with Multiple Constraints

引用

Procedia engineering 2011年 15卷 1678-1683页

作者： Li Guang-yuan Cao Dan-yang Guo Jian-wei School of Computer and Communication Engineering University of Science&Technology Beijing Beijing China Shool of Computer and Information Engineering Guangxi Teachers Education University Nanning China

Association rules mining(ARM) is an important task in the field of data mining, mining frequent itemsets is a key step of many algorithms for ARM. In a very large dataset, rules generated may be very large, but some of them are useless to the users, to improve the effectiveness and efficiency of mining tasks, constraint-based mining enables users to concentrate on mining their interested association rules instead of the complete set of association rules. Most of previously proposed methods are mainly deal with a single constraint. In this paper, we present an algorithm for mining association rules with multiple constraints, the proposed algorithm simultaneously copes with two different kinds of constraints, it consists of three phases, first, the frequent 1-itemset are generated, second, we exploit the properties of the given constraints to prune search space or save constraint checking in the conditional databases. Third, for each itemset possible to satisfy the constraint, we generate its conditional database and perform the three phases in the conditional database recursively. Experimental results show that the proposed method outperform the revised FP-growth algorithm.

关键词： Data mining Association rules mining Constraints-based mining

来源：评论

学校读者我要写书评

暂无评论

Efficient-Learning Grasping and Pushing in Dense Stacking via Mask Function and Pixel Overlap Rate

Efficient-Learning Grasping and Pushing in Dense Stacking vi...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Jie Lian Juncheng Jiang Chaochao Qiu Qinghui Pan Yongxiang Dong Zhao Wang Dong Wang School of Control Science and Engineering Dalian University of Technology Dalian China Shool of Computer Science and Software Engineering University of Science and Technology Liaoning

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

In the field of robotic grasping, grasping tightly stacked objects is a formidable challenge. The presence of non-target objects significantly increases the risk of grasping failure. To solve this problem, the aim is to take action while grasping, reduce clutter, and effectively complete grasping tasks. Based on deep reinforcement learning, the Efficient Learning Grasping(ELG) framework is proposed that integrates pushing actions alongside grasping to efficiently pick up objects from cluttered environments with reduced training time. However, in the process of grasping, the agent is rewarded only when the grasp is successful, so the data collection is extremely inefficient and spends a lot of time on the training of grasping strategy. In our work, two strategies are proposed to improve the training efficiency. First, two mask functions are introduced as prior knowledge to enable the agent to focus on more meaningful regions while ignoring some unnecessary regions, aiming at effective learning. Second, The Pixel Overlap Rate (POR) is introduced to quantify the environment clutter level, and set a new push action reward function based on the POR. The implementation of the above ideas in a simulation environment and transferred the learned models to the real world and verified them in practice. Compared with existing method, our method improves the training efficiency of the initial algorithm while having a higher success rate of grasping. Detailed grasping video at https://***/CqtSvaVl60M.

关键词： Training Stacking Grasping Production Data collection Deep reinforcement learning Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Discrete Opinion Dynamics with Social Bots on Signed Network

Discrete Opinion Dynamics with Social Bots on Signed Network

引用

第三十九届中国控制会议

作者： Yun Luo Chun Cheng Changbin Yu School of Engineering Westlake University Shool of Resource and Environment Sciences Wuhan University School of Computer Science Fudan University

Individuals’ opinions are affected by their friends or enemies and the relationship can be abstracted as a signed network. However, the emergence of social bots can bring adverse effect to people on the signed network, like misleading the public opinion. In this paper, in order to study the mechanism by which social bots can influence public opinion, we proposed a opinion dynamics model of signed network to study the how the opinion dynamics evolves based on multi-agent ***, we give the condition when the probabilities of individuals’ selection of opinions will converge in this model. At last, we simulated to show the convergence of our model, and study the effect of different number of social bots and confidence level to the public opinion. The results shows with the increase of the number of social bots, the public opinion is lead out of balance more severely, and as the proportion of social bots reaches 20%, the public opinion of human agents are mislead, and the opinion held by social bots will be the final opinion in the human population. For the population of human agents and social bots, 17% social bots is needed to lead the public opinion. The value of self-confidence has no effect on the final opinion in the signed network, but only whether people are affected by others has influence on the final opinion.

关键词： Opinion Dynamics Multi-agent System Signed Network Social Bots

来源：评论

学校读者我要写书评

暂无评论

A modeling approach of mobile ad hoc networks survivability model

A modeling approach of mobile ad hoc networks survivability ...

引用

1st International Conference on Information science and engineering, ICISE2009

作者： Wang, Haiquan Ma, Xinyi Xia, Chunhe Hao, Senshen State Key Laboratory of Virtual Reality Technology and System Beihang University Beijing China Key Laboratory of Beijing Network Technology Beihang University Beijing China College of Software Beihang University Beijing China Shool of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9780769538877

Survivability has become a focal point of research. Simulation is a common method for experimental verification to identify the advantages and deficiencies of survivability models and architectures. This paper proposes a modeling approach of mobile ad hoc network survivability model which support the automatic transformation to a simulation instance. A new survivability model MARC based on the idea of ARC model is conducted. Within this model, the concepts of network services and events are analyzed and formally descript in details. Base on these works, we design MARCDL and outline the important EBNF in this paper. Use of this language is illustrated by a case study. ©2009 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Scalable Hash Ripple Join on Spark

Scalable Hash Ripple Join on Spark

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Hao Liu Jiang Xiao Fengchao Peng The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Services Computing Technology and System Lab Cluster and Grid Computing Lab Shool of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (纸本)9781538632086

Hash Ripple join is an online aggregation algorithm that can rapidly give good approximate join results increases with the progress of the join operation and converges to the real result when the join finishes. Luo et al. proposed a parallel hash ripple join (PHRJ) that runs in a distributed setting. However, the PHRJ has two drawbacks when handling large-scale data: 1) PHRJ updates approximate results in fine grain which induces extra communication cost in a distributed environment 2) When data is out of memory, PHRJ cannot provide unbiased approximate result. In this thesis, a scalable hash ripple join is proposed that 1) runs on a distributed framework that can process distributed data in coarse-grain to speed up the join performance; 2) continuously gives unbiased and consistent approximate join results even in the presence of memory overflow; and 3) has good scalability handling growing amount of data. We have implemented a prototype of the scalable hash ripple join (SHRJ) algorithm on Spark. Experiment results show that SHRJ can give good approximate join result while taking less than 10% of the time of Spark's own join operator.

关键词： Sparks Distributed databases Approximation algorithms Clustering algorithms Indexes Standards computer science

来源：评论

学校读者我要写书评

暂无评论

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

arXiv

引用

arXiv 2024年

作者： Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shool of Information Technology Carleton University Canada

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: https://***/howard-hou/VisualRWKV. Copyright © 2024, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Software design of intelligent solar drying system for agricultural and sideline products

Software design of intelligent solar drying system for agric...

引用

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Sijie Ouyang Jianping Chen Qijun Xiao Shun Cheng Shool of Electronic Information & Mechanical Electrical Engineering Zhaoqing University Zhaoqing China School of Computer Science Zhaoqing University Zhaoqing China

ISBN: (纸本)9781479952007

Solar energy is renewable energy which can be used in the drying of agricultural and sideline products. The lower computer measurement and control subsystem is designed and the improved binary table lookup algorithm is designed to realize the tank water temperature detection. The main program flow is demonstrated, furthermore, the host computer monitoring subsystem is constructed, in which the system database and communication mechanism are designed, and the algorithm design of host computer communication module is demonstrated. The man-machine interface is quite friendly for the user. Using this solar dring system, some drying experiments for longan and red pepper are done. Experiments show that the drying system can run reliably, therefore, software design of the intelligent solar drying system is effective.

关键词： computers Temperature measurement Humidity Storage tanks Monitoring Artificial intelligence Temperature distribution

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：