检索结果-内蒙古大学图书馆

19th international Workshop on Data Privacy Management, DPM 2024, 8th international Workshop on Cryptocurrencies and Blockchain Technology, CBT 2024 and 10th Workshop on the Security of Industrial Control systems and of Cyber-Physical systems, CyberICPS 2024 which were held in conjunction with the 29th European symposium on Research in computer Security, ESORICS 2024

作者： Tasaki, Hajime Chao, Jinhui Department of Information and System Engineering Chuo University Bunkyo Tokyo1-13-27 Kasuga Japan

ISBN: (纸本)9783031823619

The existence of so-called adversarial examples has become a serious threat to Deep Neural networks (DNN) and their applications, especially security-sensitive ones. Explanations and defenses mainly focused on inside of the DNN, e.g. its generalization errors and training defects, have been proposed without much success. Recently, we have shown that the extrinsic cause of adversarial examples is due to embedding geometry of the training data manifold, and adversarial examples mainly exist in the orthogonal complementary spaces of the tangent spaces on the data manifold. In this paper, we prove the intrinsic cause of the adversarial examples, i.e. the existence of non-zero manifold-orthogonal components of every weight almost everywhere, as the counterpart of the extrinsic cause. Investigations showed that weights of the DNN always have nonzero and large manifold-orthogonal components at almost every data point, which explains why small adversarial perturbations can lead to misclassifications in well-trained DNN. Then, based on these mechanisms, we propose a new defense against adversarial examples by extracting the manifold structure of the training data and removing the components orthogonal to the tangent spaces of the manifolds from the input data, which successfully prevents misclassification of DNN for major adversarial example attacks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Spiking Neural networks Using Approximate Neuron Circuits and 3D Stacking Memory 17

Energy-Efficient Spiking Neural Networks Using Approximate N...

引用

17th IEEE international symposium on Embedded Multicore/Many-core systems-on-Chip, MCSoC 2024

作者： Kobayashi, Ryoji Nguyen, Ngo-Doanh Vu Doan, Nguyen Anh Dang, Khanh N. University of Aizu School of Computer Science and Engineering Japan Vietnam National University Vnu Information Technology Institute Hanoi Viet Nam Infineon Technologies Ag Germany

ISBN: (纸本)9798331530471

This paper proposes a combination approach of approximate neuron circuits and approximate stacking synaptic memory to evaluate the impact on accuracy and energy consumption. Instead of having accurate adders, this work utilizes approximate versions in the neuron's circuits. Furthermore, we divide the fixed-point weight into several subsets, and each subset is allocated into a different silicon layer of 3D-IC-based stacking memory. Undervoting or power-gating each subset allows us to have approximate stacking memory that works in conjunction with approximate neurons. The evaluation showed that with the proper neuron circuit approximation, energy consumption improved by up to 24.84% per neuron with a 0.7% accuracy loss. Moreover, by combining with approximate stacking memory, we can reduce energy consumption by 55.9% while losing 1.6% of the average accuracy with the appropriate configuration. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

‘KSK’ Algorithm for Optimizing DCS Performance Using ‘R’ 12th

‘KSK’ Algorithm for Optimizing DCS Performance Using ‘R’

引用

12th international Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Khandelwal, Anju Saxena, Suneet Kumar, Avanish Balaji Institute of Management and Human Resource Developement Sri Balaji University MS Pune411033 India SRMS College of Engineering & Technology UP Bareilly243202 India Department of Mathematical Sciences and Computer Applications Bundelkhand University UP Jhansi284001 India

ISBN: (纸本)9789819731794

distributed computing refers to the solution to a problem using distributed systems of autonomous and heterogeneous computers that are important for communication, networking, and workstation functioning. distributed computing helps multiple computers to solve the same problem and through it, problem-solving is achieved by communicating and performing tasks in a distributed environment. This system helps in performing computational tasks much faster than single computers. The objective of the problem present in this paper is to develop an algorithm named ‘KSK’ to obtain overall optimal cost with reliability. Here, algorithm for the optimization problem presented is executed in the open-source R programming language. A comparison between developed ‘KSK’ with existing ‘GBY’ algorithm has also been discussed. The aim is that optimal combination in this distributed computing system provides low processor execution cost and low program service cost as well as reliability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Optimizing Hybrid Energy systems: Employing Smart Monitoring networks with IoT Integration 8

Optimizing Hybrid Energy Systems: Employing Smart Monitoring...

引用

8th international symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Taher, Anmar Yahya Kurnaz, Sefer Ahmed, Saadaldeen Rashid Altinbas University Faculty of Engineering and Natural Sciences Electrical and Computer Engineering Dept Istanbul Turkey Bayan University Computer Science Department Kurdistan Erbil Iraq College of Engineering Al-Ayen University Artificial Intelligence Engineering Department Thi-Qar Iraq

ISBN: (纸本)9798350354423

For effective and sustainable energy solutions, this paper investigates at a hybrid energy system that uses Internet of Things technologies. Three components make up the system: PV system, an AC turbine voltage source, DC batteries, and ThingSpeak, an IoT analytics program hosted on the cloud that allows for real-time monitoring. In order to optimize performance, the study emphasizes the significance of hybrid energy systems as well as the requirement for improved analytics and monitoring. A detailed description of the experimental setup is given, including the measured parameters. The results demonstrate the hybrid system's adaptability to various loads and input voltages. fluctuations in DC battery and turbine voltages cause fluctuations in AC power and AC current, while the AC voltage stays constant at 224.4 V. For efficient analytics and monitoring, the hybrid energy system must include ThingSpeak. The study emphasizes how the system can adjust to changing conditions and how Internet of Things technologies may assist hybrid energy systems grow more powerful. This research adds to the current discourse on the integration of IoT data for enhanced system optimization and sustainable energy solutions. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

Deep learning based detection of collateral circulation in coronary angiographies 36

Deep learning based detection of collateral circulation in c...

引用

36th IEEE international symposium on computer-Based Medical systems (CBMS)

作者： Hatfaludi, Cosmin-Andrei Bunescu, Daniel Ciusdel, Costin Florian Serban, Alex Boese, Karl Oppel, Marc Schroeder, Stephanie Seehase, Christopher Langer, Harald F. Erdmann, Jeanette Nording, Henry Itu, Lucian Mihai Siemens SRL Advanta 15 Noiembrie Bvd Brasov 500097 Romania Transilvania Univ Brasov Automat & Informat Technol Mihai Viteazu 5 Brasov 5000174 Romania Univ Heart Ctr Lubeck Med Clin 2 Cardioimmunol Grp D-23538 Lubeck Germany DZHK German Ctr Cardiovasc Res Partner Site Hamburg Lubeck Kiel D-23562 Lubeck Germany Univ Heart Ctr Lubeck Med Clin 2 Univ Hosp D-23538 Lubeck Germany Heidelberg Univ Univ Med Ctr Mannheim Med Fac Mamtheim Dept Cardiol Angiol Haemostaseol & Med Intens Car Heidelberg Germany German Ctr Cardiovasc Res DZHK Partner Site Heidelberg Mannheim Mannheim Germany

ISBN: (纸本)9798350312249

Coronary artery disease (CAD) is the dominant cause of death and hospitalization across the globe. Atherosclerosis, an inflammatory condition that gradually narrows arteries and has potentially fatal effects, is the most frequent cause of CAD. Nonetheless, the circulation regularly adapts in the presence of atherosclerosis, through the formation of collateral arteries, resulting in significant longterm health benefits. Therefore, timely detection of coronary collateral circulation (CCC) is crucial for CAD personalized medicine. We propose a novel deep learning based method to detect CCC in angiographic images. Our method relies on a convolutional backbone to extract spatial features from each frame of an angiography sequence. The features are then concatenated, and subsequently processed by another convolutional layer that processes embeddings temporally. Due to scarcity of data, we also experiment with pretraining the backbone on coronary artery segmentation, which improves the results consistently. Moreover, we experiment with few-shot learning to further improve performance, given our low data regime. We present our results together with subgroup analyses based on Rentrop grading, collateral flow, and collateral grading, which provide valuable insights into model performance. Overall, the proposed method shows promising results in detecting CCC, and can be further extended to perform landmark based CCC detection and CCC quantification.

关键词： coronary collateral circulation deep learning invasive coronary angiography convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved Paths to Stability for the Stable Marriage Problem 1

引用

25th international symposium on Stabilization, Safety, and Security of distributed systems, SSS 2023

作者： Garg, Vijay K. Hu, Changyong The University of Texas at Austin Austin United States

ISBN: (数字)9783031442742

ISBN: (纸本)9783031442735

The stable marriage problem has wide applications in distributed computing such as the placement of virtual machines in a distributed system. The stable marriage problem requires one to find a marriage with no blocking pair. Given a matching that is not stable, Roth and Vande Vate have shown that there exists a sequence of matchings that leads to a stable matching in which each successive matching is obtained by satisfying a blocking pair. The sequence produced by Roth and Vande Vate’s algorithm is of length O(n3) where n is the number of men (and women). In this paper, we present an algorithm that achieves stability in a sequence of matchings of length O(n2). We also give an efficient algorithm to find the stable matching closest to the given initial matching under an appropriate distance function between matchings. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Sentimental Insight 2.0: Exploring the Frontiers of Opinion Mining with Deep Learning 2

Sentimental Insight 2.0: Exploring the Frontiers of Opinion ...

引用

2nd international Conference on distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Murugan, S.Karthick Jayachandran, S. Mageshwari, G. Latha, J. Naveen, G. R. M. D. Engineering College Kavaraipettai Department of Computer Science and Engineering Tamilnadu Thiruvallur India Srm Institute of Science and Technology Department of Computer Science and Application Chennai Ramapuram India R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamilnadu Tiruvallur India R. M. K. Engineering College Department of Computer Science and Engineering Tiruvallur Tamilnadu Kavaraipettai India Madha Institute of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350382952

'Sentimental Insight 2.0' emerges as revolutionary research using deep learning techniques in response to the increasing demand for more complex sentiment analysis in the age of information abundance. Traditional sentiment analysis methods sometimes fail to accurately capture the particulars of emotions, sarcasm, and context, demanding a more advanced technique. The existing system's limitations include its inability to detect minor sentiment variations and its vulnerability to noisy and distorted data. The proposed system integrates cutting-edge deep learning architectures such as recurrent neural networks (RNNs), extended short-term memory networks (LSTMs), and transformer models into an extensive structure. The result showcases the advanced sentiment analysis, outperforming existing systems with 94% accuracy, 93% precision, 91% recall, and 93% F1 score, demonstrating superior computational efficiency and emotion classification across diverse sentiments. In the information-centric world, the study's results significantly expand sentiment analysis skills, providing a vital resource for applications in social media analytics, consumer feedback, and market sentiment prediction. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Finite-horizon energy allocation scheme in energy harvesting-based linear wireless sensor network

引用

FUTURE GENERATION computer systems-THE international JOURNAL OF ESCIENCE 2025年 162卷

作者： Chen, Shengbo Li, Shuai Wang, Guanghui Yu, Keping Henan Univ Sch Comp & Informat Engn Kaifeng Henan Peoples R China Henan Univ Sch Software Kaifeng Henan Peoples R China Henan Univ Henan Engn Res Ctr Intelligent Technol & Applicat Kaifeng Henan Peoples R China Henan Univ Henan Int Joint Lab Intelligent Network Theory & K Kaifeng Henan Peoples R China Hosei Univ Grad Sch Sci & Engn Tokyo Japan

Linear wireless sensor networks (LWSNs) are a specialized topology of wireless sensor networks (WSNs) widely used for environmental monitoring. Traditional WSNs rely on batteries for energy supply, limiting their performance due to battery capacity constraints, while renewable energy harvesting technology is an effective approach to alleviating the battery capacity bottleneck. However, the stochastic nature of renewable energy makes designing an efficient energy management scheme for network performance improvement a compelling research problem. In this paper, we investigate the problem of maximizing throughput over a finite-horizon time period for an energy harvesting-based linear wireless sensor network (EH-LWSN). The solution to the original problem is very complex, and this complexity mainly arises from two factors. First, the optimal energy allocation scheme has temporal coupling, i.e., the current optimal strategy relies on the energy harvested in the future. Second, the optimal energy allocation scheme has spatial coupling, i.e., the current optimal strategy of any node relies on the available energy of other nodes in the network. To address these challenges, we propose an iterative energy allocation algorithm for EH-LWSN. Firstly, we theoretically prove the optimality of the algorithm and analyze the time complexity of the algorithm. Next, we design the corresponding distributed version and consider the case of estimating the energy harvest. Finally, through experiments using a real-world renewable energy dataset, the results show that the proposed algorithm outperforms the other two heuristics energy allocation schemes in terms of network throughput.

关键词： Energy harvesting Linear wireless sensor networks Optimal energy allocation Throughput maximization

来源：评论

学校读者我要写书评

暂无评论

Shared Information for the Cliqueylon Graph

Shared Information for the Cliqueylon Graph

引用

2023 IEEE international symposium on Information Theory, ISIT 2023

作者： Bhattacharya, Sagnik Narayan, Prakash University of Maryland The Department of Electrical and Computer Engineering The Institute for Systems Research College ParkMD20742 United States

ISBN: (纸本)9781665475549

Shared information is a measure of mutual dependence among m=2 jointly distributed discrete random variables. A new undirected probabilistic graphical model, a cliqueylon graph, is introduced, with potential applications in leader-follower swarms and neuron clusters with correlations of varying strength. Shared information is characterized explicitly for the cliqueylon, relying on structural properties of an underlying optimization. Implications for the data compression problem of omniscience are highlighted. © 2023 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Probing with a Generic MAC Address: An Alternative to MAC Address Randomisation 32

Probing with a Generic MAC Address: An Alternative to MAC Ad...

引用

32nd international Conference on Software, Telecommunications and computer networks, SoftCOM 2024

作者： McDougall, Johanna Ansohn Brighente, Alessandro Kunstmann, Anne Zapatka, Niklas Schambach, Hanna Federrath, Hannes University of Hamburg Security in Distributed Systems Hamburg Germany University of Padova Department of Mathematics Padua Italy

ISBN: (纸本)9789532901382

Active scanning via probe requests is a means for mobile devices to detect known networks. To protect the device from being tracked via an unchanging identifier contained in the probe request, MAC address randomisation is used. While it has been in use since 2014, the standardisation of MAC address randomisation is still in its draft stage. This also leads to manufacturers devising their own randomisation schemes, some of which have been proven insufficient to prevent tracking. In this paper, we strive to reignite the discussion on standardising the use of Locally Administered Addresses (LAAs) like randomised MAC addresses. To overcome the limitations of MAC address randomisation, we propose the use of one generic address over all devices. We implement and test this scheme, and additionally ascertain that a generic MAC address not only enhances user anonymity during probing but also offers operational efficiency comparable to MAC address randomisation. In conclusion, this contribution highlights the need for a standardised approach to preserve device anonymity, and simultaneously introduces a novel alternative of employing a single generic address across devices. © 2024 University of Split, FESB.

关键词： Probes

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：