检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Qu, Zhe Duan, Rui Chen, Lixing Xu, Jie Lu, Zhuo Liu, Yao The Department of Electrical Engineering University of South Florida TampaFL33620 United States The Institute of Cyber Science and Technology Shanghai Jiao Tong University Shanghai Shanghai200240 China The Department of Electrical and Computer Engineering University of Miami Coral Gables33146 United States The Department of Computer Science and Engineering University of South Florida Tampa33620 United States

Federated Learning (FL) has been considered as an appealing framework to tackle data privacy issues of mobile devices compared to conventional Machine Learning (ML). Using Edge Servers (ESs) as intermediaries to perform model aggregation in proximity can reduce the transmission overhead, and it enables great potentials in low-latency FL, where the hierarchical architecture of FL (HFL) has been attracted more attention. Designing a proper client selection policy can significantly improve training performance, and it has been extensively used in FL studies. However, to the best of our knowledge, there are no studies focusing on HFL. In addition, client selection for HFL faces more challenges than conventional FL, e.g., the time-varying connection of client-ES pairs and the limited budget of the Network Operator (NO). In this paper, we investigate a client selection problem for HFL, where the NO learns the number of successful participating clients to improve the training performance (i.e., select as many clients in each round) as well as under the limited budget on each ES. An online policy, called Context-aware Online Client Selection (COCS), is developed based on Contextual Combinatorial Multi-Armed Bandit (CC-MAB). COCS observes the side-information (context) of local computing and transmission of client-ES pairs and makes client selection decisions to maximize NO's utility given a limited budget. Theoretically, COCS achieves a sublinear regret compared to an Oracle policy on both strongly convex and non-convex HFL. Simulation results also support the efficiency of the proposed COCS policy on real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

FUIM: Fuzzy utility itemset mining

arXiv

引用

arXiv 2021年

作者： Wan, Shicheng Gan, Wensheng Guo, Xu Chen, Jiahui Yun, Unil School of Computers Guangdong University of Technology Guangzhou510006 China College of Cyber Security Jinan University Guangzhou510632 China Pazhou Laboratory Guangzhou510335 China Department of Computer Engineering Sejong University Seoul Korea Republic of

Because of usefulness and comprehensibility, fuzzy data mining has been extensively studied and is an emerging topic in recent years. Compared with utility-driven itemset mining technologies, fuzzy utility mining not only takes utilities (e.g., profits) into account, but also considers quantities of items in each transaction for discovering high fuzzy utility itemsets (HFUIs). Thus, fuzziness can be regard as a key criterion to select high-utility itemsets, while the exiting algorithms are not efficient enough. In this paper, an efficient one-phase algorithm named Fuzzy-driven Utility Itemset Miner (FUIM) is proposed to find out a complete set of HFUIs effectively. In addition, a novel compact data structure named fuzzy-list keeps the key information from quantitative transaction databases. Using fuzzy-list, FUIM can discover HFUIs from transaction databases efficiently and effectively. Both completeness and correctness of the FUIM algorithm are proved by five theorems. At last, substantial experiments test three terms (runtime cost, memory consumption, and scalability) to confirm that FUIM considerably outperforms the state-of-the-art algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A Principled Design of Image Representation: Towards Forensic Tasks

arXiv

引用

arXiv 2022年

作者： Qi, Shuren Zhang, Yushu Wang, Chao Zhou, Jiantao Cao, Xiaochun The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China The Institute of Information Engineering Chinese Academy of Sciences Beijing China The Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China The State Key Laboratory of Internet of Things for Smart City China The Department of Computer and Information Science Faculty of Science and Technology University of Macau China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China

Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society. Like other vision-related applications, forensic analysis relies heavily on the proper image representation. Despite the importance, current theoretical understanding for such representation remains limited, with varying degrees of neglect for its key role. For this gap, we attempt to investigate the forensic-oriented image representation as a distinct problem, from the perspectives of theory, implementation, and application. Our work starts from the abstraction of basic principles that the representation for forensics should satisfy, especially revealing the criticality of robustness, interpretability, and coverage. At the theoretical level, we propose a new representation framework for forensics, called dense invariant representation (DIR), which is characterized by stable description with mathematical guarantees. At the implementation level, the discrete calculation problems of DIR are discussed, and the corresponding accurate and fast solutions are designed with generic nature and constant complexity. We demonstrate the above arguments on the dense-domain pattern detection and matching experiments, providing comparison results with state-of-the-art descriptors. Also, at the application level, the proposed DIR is initially explored in passive and active forensics, namely copy-move forgery detection and perceptual hashing, exhibiting the benefits in fulfilling the requirements of such forensic tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image representation

来源：评论

学校读者我要写书评

暂无评论

EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms

arXiv

引用

arXiv 2023年

作者： Peng, Mai Yazdani, Delaram She, Zeneng Yazdani, Danial Luo, Wenjian Li, Changhe Branke, Juergen Nguyen, Trung Thanh Gandomi, Amir H. Yang, Shengxiang Jin, Yaochu Yao, Xin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Research Institute Faculty of Engineering and Technology Liverpool John Moores University United Kingdom School of Computer Science and Technology Harbin Institute of Technology China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Peng Cheng Laboratory China School of Artificial Intelligence Anhui University of Sciences & Technology China Information Systems Management and Analytics in Warwick Business School University of Warwick United Kingdom Faculty of Engineering & Information Technology University of Technology Sydney Australia Obuda University Hungary School of Computer Science and Informatics De Montfort University United Kingdom Department of Artificial Intelligence School of Engineering Westlake University China School of Computer Science University of Birmingham United Kingdom

Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization techniques. Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively. However, in existing literature, the reported results for a given EDOA can vary significantly. This inconsistency often arises because the source codes for many EDOAs, which are typically complex, have not been made publicly available, leading to error-prone re-implementations. To support researchers in conducting experiments and comparing their algorithms with various EDOAs, we have developed an open-source MATLAB platform called the Evolutionary Dynamic Optimization LABoratory (EDOLAB). This platform not only facilitates research but also includes an educational module designed for instructional purposes. The education module allows users to observe: a) a 2-dimensional problem space and its morphological changes following each environmental change, b) the behaviors of individuals over time, and c) how the EDOA responds to environmental changes and tracks the moving optimum. The current version of EDOLAB features 25 EDOAs and four fully parametric benchmark generators. © 2023, CC BY-NC-SA.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A survey on security and privacy issues of UAVs

arXiv

引用

arXiv 2021年

作者： Mekdad, Yassine Aris, Ahmet Babun, Leonardo Fergougui, Abdeslam E.L. Conti, Mauro Lazzeretti, Riccardo Uluagac, A. Selcuk Laboratory of Computer Networks and Systems Moulay Ismail University of Meknes Zitoune Meknes11201 Morocco Cyber-Physical Systems Security Lab Department of Electrical and Computer Engineering Florida International University MiamiFL33174 United States Department of Mathematics University of Padua Padua35121 Italy Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Rome00185 Italy

In the 21st century, the industry of drones, also known as Unmanned Aerial Vehicles (UAVs), has witnessed a rapid increase with its large number of airspace users. The tremendous benefits of this technology in civilian applications such as hostage rescue and parcel delivery will integrate smart cities in the future. Nowadays, the affordability of commercial drones expands its usage at a large scale. However, the development of drone technology is associated with vulnerabilities and threats due to the lack of efficient security implementations. Moreover, the complexity of UAVs in software and hardware triggers potential security and privacy issues. Thus, posing significant challenges for the industry, academia, and governments. In this paper, we extensively survey the security and privacy issues of UAVs by providing a systematic classification at four levels: Hardware-level, Software-level, Communication-level, and Sensor-level. In particular, for each level, we thoroughly investigate (1) common vulnerabilities affecting UAVs for potential attacks from malicious actors, (2) existing threats that are jeopardizing the civilian application of UAVs, (3) active and passive attacks performed by the adversaries to compromise the security and privacy of UAVs, (4) possible countermeasures and mitigation techniques to protect UAVs from such malicious activities. In addition, we summarize the takeaways that highlight lessons learned about UAVs’ security and privacy issues. Finally, we conclude our survey by presenting the critical pitfalls and suggesting promising future research directions for security and privacy of UAVs. © 2021, CC BY.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Explainable Verbal Deception Detection using Transformers

arXiv

引用

arXiv 2022年

作者： Ilias, Loukas Soldner, Felix Kleinberg, Bennett Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Athens15780 Greece GESIS Leibniz Institute for the Social Science Köln Germany Department of Security and Crime Science Dawes Centre for Future Crime University College London United Kingdom Department of Methodology and Statistics Tilburg University Netherlands

People are regularly confronted with potentially deceptive statements (e.g., fake news, misleading product reviews, or lies about activities). Only few works on automated text-based deception detection have exploited the potential of deep learning approaches. A critique of deep-learning methods is their lack of interpretability, preventing us from understanding the underlying (linguistic) mechanisms involved in deception. However, recent advancements have made it possible to explain some aspects of such models. This paper proposes and evaluates six deep-learning models, including combinations of BERT (and RoBERTa), MultiHead Attention, co-attentions, and transformers. To understand how the models reach their decisions, we then examine the model’s predictions with LIME. We then zoom in on vocabulary uniqueness and the correlation of LIWC categories with the outcome class (truthful vs deceptive). The findings suggest that our transformer-based models can enhance automated deception detection performances (+2.11% in accuracy) and show significant differences pertinent to the usage of LIWC features in truthful and deceptive statements. © 2022, CC BY-NC-ND.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Curriculum Self-supervised Learning for Weakly-supervised Histopathological Image Segmentation 2021

Curriculum Self-supervised Learning for Weakly-supervised Hi...

引用

2021 10th International Conference on Internet Computing for science and engineering

作者： Jijun Cheng Jinhai Mai Xipeng Pan Xin Chen Chu Han Zaiyi Liu Changhong Liang School of Computer Science and Information Security Guilin University of Electronic Technology China School of Automation Science and Engineering South China University of Technology China and Department of Radiology Guangdong Provincial People's HospitalGuangdong Academy of Medical Sciences China School of Computer Science and Information Security Guilin University of Electronic Technology China and Department of Radiology Guangdong Provincial People's HospitalGuangdong Academy of Medical Sciences China Department of Radiology Guangzhou First People's HospitalSchool of MedicineSouth China University of Technology China Department of Radiology Guangdong Provincial People's HospitalGuangdong Academy of Medical Sciences China

ISBN: (纸本)9781450384957

Histopathological image segmentation is the basic upstream task of pathomics cancer research. However, acquiring pixel-level annotations is extremely difficult and time-consuming. Moreover, it is also expertise-dependent. Researchers pay a lot of attention on how to reduce the annotation effort. One feasible solution is self-supervised learning. In this paper, we proposed a novel self-supervised learning strategy for histopathological image segmentation, which called Curriculum Self-supervised Learning (CSSL). In CSSL, we set up several pretext tasks which are highly related to the characteristics of histopathological images for the CNN model. And then, these pretext tasks are trained in a curriculum manner (easy to hard). By combining CSSL with Class Activation Map (CAM), we can achieve outstanding performance on a weakly-supervised tissue segmentation task, with no need of pixel-level annotation. We achieved Frequency-weighted Intersection over Union (FIoU) score of 0.6886 and Mean Intersection over Union (MIoU) score of 0.6985 for semantic segmentation, which exceeded the common self-supervised learning methods. Experiments were conducted to prove the effectiveness of proposed CSSL.

关键词： Histopathological image segmentation Self-supervised learning Computational pathology

来源：评论

学校读者我要写书评

暂无评论

Learning linear policies for robust bipedal locomotion on terrains with varying slopes

arXiv

引用

arXiv 2021年

作者： Krishna, Lokesh Mishra, Utkarsh A. Castillo, Guillermo A. Hereid, Ayonga Kolathaya, Shishir Varanasi India The Mechanical and Industrial Engineering Department Indian Institute of Technology Roorkee India The department of Mechanical and Aerospace Engineering Ohio State University ColumbusOH United States The department of Computer Science and Automation The Centre for Cyber-Physical Systems Indian Institute of Science Bengaluru India

In this paper, with a view toward deployment of light-weight control frameworks for bipedal walking robots, we realize end-foot trajectories that are shaped by a single linear feedback policy. We learn this policy via a model-free and a gradient free learning algorithm, Augmented Random Search (ARS), in the two robot platforms Rabbit and Digit. Our contributions are two-fold: a) By using torso and support plane orientation as inputs, we achieve robust walking on slopes of upto 20◦ in simulation. b) We demonstrate additional behaviors like walking backwards, stepping-in-place, and recovery from external pushes of upto 120 N. The end-result is a robust and a fast feedback control law for bipedal walking on terrains with varying slopes. Towards the end, we also provide preliminary results of hardware transfer to Digit. © 2021, CC BY-NC-ND.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Author Correction: AndroDex: Android Dex Images of Obfuscated Malware

引用

Scientific data 2024年第1期11卷 729页

作者： Sana Aurangzeb Muhammad Aleem Muhammad Taimoor Khan George Loukas Georgia Sakellari National University of Computing and Emerging Sciences (FAST-NUCES) Department of Computer Science Islamabad 44000 Pakistan. Centre for Sustainable Cyber Security School of Computing and Mathematical Sciences University of Greenwich London UK. m.khan@greenwich.ac.uk. Centre for Sustainable Cyber Security School of Computing and Mathematical Sciences University of Greenwich London UK.

来源：评论

学校读者我要写书评

暂无评论

IFA-EO: An improved firefly algorithm hybridized with extremal optimization for continuous unconstrained optimization problems

Research Square

引用

Research Square 2021年

作者： Chen, Min-Rong Yang, Liu-Qing Zeng, Guo-Qiang Lu, Kang-Di Huang, Yi-Yuan School of Computer Science South China Normal University Guangzhou510631 China National-Local Joint Engineering Laboratory of Digitalize Electrical Design Technology Wenzhou University Wenzhou325035 China College of Cyber Security Jinan University Guangzhou510632 China Institute of Cyber Systems and Control Zhejiang University Hangzhou310018 China

As one of the evolutionary algorithms, firefly algorithm (FA) has been widely used to solve various complex optimization problems. However, FA has significant drawbacks in slow convergence rate and is easily trapped into local optimum. To tackle these defects, this paper proposes an improved FA combined with extremal optimization (EO), named IFA-EO, where three strategies are incorporated. First, to balance the tradeoff between exploration ability and exploitation ability, we adopt a new attraction model for FA operation, which combines the full attraction model and the single attraction model through the probability choice strategy. In the single attraction model, small probability accepts the worse solution to improve the diversity of the offspring. Second, the adaptive step size is proposed based on the number of iterations to dynamically adjust the attention to the exploration model or exploitation model. Third, we combine an EO algorithm with powerful ability in local-search into FA. Experiments are tested on two group popular benchmarks including complex unimodal and multimodal functions. Our experimental results demonstrate that the proposed IFA-EO algorithm can deal with various complex optimization problems and has similar or better performance than the other eight FA variants, three EO-based algorithms, and one advanced differential evolution variant in terms of accuracy and statistical results. © 2021, CC BY.

关键词： Probability

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：