检索结果-内蒙古大学图书馆

IEEE 22nd international conference on Trust, Security and Privacy in Computing and Communications (TrustCom) / BigdataSE conference / CSE conference / EUC conference / ISCI conference

作者： Saka, Samed Al-Ataby, Ali Selis, Valerio Univ Liverpool Dept Elect Engn & Elect Liverpool Merseyside England

ISBN: (纸本)9798350381993;9798350382006

Distributed denial-of-service (DDoS) attacks are a type of cyber attack that overwhelms a target server, service or network with a flood of malicious traffic, making it unavailable to legitimate users. These attacks have become a major threat to the security of computer networks and systems, and effective intrusion detection systems (IDSs) are essential for detecting and mitigating these attacks. IDSs are used to monitor network traffic for malicious activity and can help detect and prevent DDoS attacks. Most IDSs are often designed to identify diverse types of attacks, but their efficacy can be limited when faced with attacks that exhibit extensive variations and sophisticated techniques, such as DDoS. In order to establish an effective IDS capable of identifying DDoS attacks, the acquisition of substantial volumes of labelled network data becomes crucial. This study aims to evaluate the performance of recent generative models in synthesising realistic tabular data to accurately emulate DDoS attack patterns. To achieve this, we used the CIC-DDOS2019 dataset, a comprehensive and modern collection of real-world DDoS attack scenarios. Leveraging state-of-the-art generative models, namely CTGAN, TVAE, and CopulaGAN, we synthesised realistic tabular data that emulated the characteristics and patterns observed in DDoS attack flow. We utilised various statistical metrics such as correlation scores, similarity and distance metrics, along with machine learning performance metrics, to quantitatively measure the performance of the generative models. The findings indicate that all three models have the ability to accurately emulate the patterns found in the real database, resulting in the generation of useful synthetic data. Specifically, among the classification methods used, the Random Forest method showed the most successful performance in detecting attacks with an accuracy of 99% when applied to the original dataset. In comparison, it achieved accuracy levels of 98%, 99%,

关键词： Generative Networks Tabular data Generation CIC-DDoS2019 dataset Intrusion Detection Systems

来源：评论

学校读者我要写书评

暂无评论

Research on machine Vision Defect Detection Algorithm Based on Deep learning

Research on Machine Vision Defect Detection Algorithm Based ...

引用

2024 international conference on Electronics and Devices, Computational science, ICEDCS 2024

作者： Rongqiang, Yang Quanxin, Jiang Jingchu University of Technology Intelligent Manufacturing College Jingmen448000 China

ISBN: (纸本)9798331527624

This paper conducts a detailed exploration of defect recognition algorithms in machine vision supported by deep learning, mainly focusing on the performance and potential optimization paths of Retina Net in industrial environments. This paper conducts a comparative analysis of various convolutional neural network architectures to improve the recognition accuracy and adaptability of the model. At the same time, customized algorithm tuning is implemented based on the types of defects that frequently occur in industrial production, such as surface scratches, cracks, and unevenness. The industrial site's complex background and multidimensional target characteristics prompted this paper to innovate the multi-level feature pyramid structure of Retina Net, significantly enhancing its performance in the recognition of small objects and complex patterns. In the simulation test phase, the effect was verified with the help of actual industrial data sets. The data showed that the optimized and upgraded Retina Net algorithm surpassed traditional technologies in multiple evaluation indicators, especially in recognition accuracy, with an increase of about 7.8%, while the false alarm rate was reduced by 12.3%. In addition, the algorithm showed excellent performance in the recognition task of multi-scale targets, with an average recognition time reduction of about 15%. The experimental results powerfully demonstrate the effectiveness and excellent performance of the improved algorithm in real-world applications. © 2024 IEEE.

关键词： machine vision

来源：评论

学校读者我要写书评

暂无评论

Explaining the effects of non-convergent MCMC in the training of Energy-Based Models 40

Explaining the effects of non-convergent MCMC in the trainin...

引用

40th international conference on machine learning

作者： Agoritsas, Elisabeth Catania, Giovanni Decelle, Aurelien Seoane, Beatriz Univ Geneva Dept Quantum Matter Phys CH-1211 Geneva Switzerland Univ Complutense Madrid Dept Fis Teor Madrid 28040 Spain Univ Paris Saclay CNRS INRIA Tau Team LISN F-91190 Gif Sur Yvette France

In this paper, we quantify the impact of using non-convergent Markov chains to train Energy-Based models (EBMs). In particular, we show analytically that EBMs trained with non-persistent short runs to estimate the gradient can perfectly reproduce a set of empirical statistics of the data, not at the level of the equilibrium measure, but through a precise dynamical process. Our results provide a first-principles explanation for the observations of recent works proposing the strategy of using short runs starting from random initial conditions as an efficient way to generate high-quality samples in EBMs, and lay the groundwork for using EBMs as diffusion models. After explaining this effect in generic EBMs, we analyze two solvable models in which the effect of the non-convergent sampling in the trained parameters can be described in detail. Finally, we test these predictions numerically on a ConvNet EBM and a Boltzmann machine.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional spatiotemporal demand forecasting and service vehicle dispatching for online car-hailing platforms

引用

international JOURNAL OF PRODUCTION RESEARCH 2022年第6期60卷 1832-1853页

作者： Guo, Yuhan Zhang, Yu Boulaksil, Youssef Tian, Ning Liaoning Tech Univ Sch Software Fuxing Peoples R China UAE Univ Coll Business & Econ Al Ain U Arab Emirates

Forecasting transportation demands can aid online car-hailing platforms to dispatch their service vehicles in advance to areas with more potential orders. This results in a reduction in passengers' waiting time and better utilisation of transportation resources. However, the complexity and dynamics of multi-dimensional influential factors make the forecasting and dispatching procedures challenging. This paper addresses these issues by using machine learning techniques and an effective probabilistic dispatching strategy. Multiple influential factors were identified in spatial, temporal, and meteorological dimensions, and effective machine learning algorithms were applied to predict the number of passenger orders. The fusion of the multi-dimensional features enables the proposed algorithms to better reveal the spatiotemporal characteristics and their correlations. A sensing-area-based strategy was introduced to dispatch available service vehicles to high demand-intensity regions efficiently with respect to the global demand-supply-balance and the individual probability of receiving orders. Finally, extensive experiments with large-scale real-world datasets were conducted to evaluate the performance of the machine learning algorithms and the effectiveness of the dispatching strategy. Overall, this paper extensively studies the forecasting of the spatiotemporal demand in multiple cities using point-of-interest data and the dispatching of available service vehicles based on such information for online car-hailing platforms.

关键词： Online car-hailing demand forecasting spatiotemporal machine learning vehicle dispatching sensing area

来源：评论

学校读者我要写书评

暂无评论

A review paper on the diagnosis of lung cancer using machine learning

A review paper on the diagnosis of lung cancer using machine...

引用

international conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Kukreja, Sonia Kumar, Anish Khan, Ghufran Ahmad Galgotias University India

ISBN: (纸本)9781032669663

Lung cancer could be caused by lung cells that grow out of control. To beat lung cancer, you need to find it early. Lung cancer has been the leading cause of cancer-related deaths this century. Many reliable systems for the treatment of lung cancer that are simple to use and lower in cost have been developed using the data science technology. This research compares a number of machine learning-based methods for accurately detecting lung cancer from 2019 to 2022. There are too many ways to find lung cancer now, and most of them rely on CT scans or x-rays. Almost all of them use image classification methods to find lung cancer nodules. This is combined with several segmentation methods and a wide range of classifier algorithms to get a more accurate result. Based on the results of this study, it seems that CT scan images are more accurate. Because of this, CT scan pictures are often used to find cancer [6]. In terms of accuracy, a random forest-based model does better than other machine learning techniques. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

LongCoder: A Long-Range Pre-trained Language Model for Code Completion 40

LongCoder: A Long-Range Pre-trained Language Model for Code ...

引用

40th international conference on machine learning

作者： Guo, Daya Xu, Canwen Duan, Nan Yin, Jian McAuley, Julian Sun Yat Sen Univ Guangzhou Peoples R China Univ Calif San Diego San Diego CA 92103 USA Microsoft Res Asia Beijing Peoples R China

In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task. LongCoder employs a sliding window mechanism for self-attention and introduces two types of globally accessible tokens - bridge tokens and memory tokens - to improve performance and efficiency. Bridge tokens are inserted throughout the input sequence to aggregate local information and facilitate global interaction, while memory tokens are included to highlight important statements that may be invoked later and need to be memorized, such as package imports and definitions of classes, functions, or structures. We conduct experiments on a newly constructed dataset that contains longer code context and the publicly available CodeXGLUE benchmark. Experimental results demonstrate that LongCoder achieves superior performance on code completion tasks compared to previous models while maintaining comparable efficiency in terms of computational resources during inference.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Privacy Assessment Methodology for machine learning Models and data Sources 19th

Privacy Assessment Methodology for Machine Learning Models ...

引用

19th international conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2024

作者： Erdei, Rudolf Pasca, Emil Delinschi, Daniela Avram, Anca Chereja, Ionela Matei, Oliviu Technical University of Cluj Napoca North University Centre of Baia Mare Baia Mare Romania

ISBN: (纸本)9783031750090

machine learning and data Mining imply notable privacy vulnerabilities since they have the potential to expose confidential details about people or collectives that have contributed to the data. This paper proposes a Generalised Privacy Assessment Methodology that can be universally applied to any machine learning model and its corresponding data Source. The suggested technique facilitates the quantification of the Vulnerability Score for any given data source or model. We demonstrate the practicality and efficacy of the concept by implementing it in several scenarios, ranging from a small-scale IoT project to a hypothetical extensive database, like those used by governmental entities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on the Influence Mechanism of Excess Cash Holding on Enterprise Value Based on Big data Analysis 5

Research on the Influence Mechanism of Excess Cash Holding o...

引用

5th international conference on applied machine learning, ICAML 2023

作者： Zhan, Shaorui Shanghai University Shanghai China

ISBN: (纸本)9798350341416

Based on big data analysis, this paper takes the empirical data of listed companies in China from 2019 to 2021 as samples, and draws lessons from the idea of classical enterprise value regression model to study the influence mechanism of excess cash holdings on enterprise value of listed companies in China and the influence of company growth on the relationship between them. The results show that the company size and leverage are negatively correlated with the cash holding level, which is significant at the level of 0.1, while the relationship between investment opportunities and dividend indicators and cash holding level and cash holding level is not significant. The level of excess cash holdings of listed companies in China is negatively correlated with company value. The influence of excess cash on enterprise value is nonlinear, showing obvious stage characteristics. For enterprises with negative growth and high growth, the excess cash held by them has not yet reached the level that hinders the promotion of enterprise value, and the cash value can be fully explored. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Towards Detection of Anomalies in Automated Guided Vehicles Based on Telemetry data 24th

Towards Detection of Anomalies in Automated Guided Vehicles ...

引用

24th international conference on Computational science (ICCS)

作者： Benecki, Pawel Kostrzewa, Daniel Drewniak, Marek Shubvn, Bohdan Grzesik, Piotr Sunderam, Vaidy Pochopien, Boleslaw Kwiecien, Andrzej Malysiak-Mrozek, Bozena Mrozele, Dariusz Silesian Tech Univ Dept Appl Informat Gliwice Poland Lviv Polytech Natl Univ Dept Telecommun Lvov Ukraine AIUT Sp Zoo Ltd Gliwice Poland Emory Univ Dept Comp Sci Atlanta GA 30322 USA Silesian Tech Univ Dept Graph Comp Vis & Digital Syst Gliwice Poland Silesian Tech Univ Dept Distributed Syst & Informat Devices Gliwice Poland

ISBN: (纸本)9783031637858;9783031637834

The rapid evolution of smart manufacturing and the pivotal role of Automated Guided Vehicles (AGVs) in enhancing operational efficiency, underscore the necessity for robust anomaly detection mechanisms. This paper presents a comprehensive approach to detecting anomalies based on AGV telemetry data, leveraging the potential of machine learning (ML) algorithms to analyze complex data streams and time series signals. By focusing on the unique challenges posed by real-world AGV environments, we propose a methodology that integrates data collection, preprocessing, and the application of specific AI/ML models to accurately identify deviations from normal operations. Our approach is validated through extensive experiments on datasets featuring anomalies caused by mechanical wear or excessive friction and issues related to tire and wheel damage, employing LSTM and GRU networks, alongside traditional classifiers like K-nearest neighbors and SVM. The results demonstrate the efficacy of our method in forecasting momentary power consumption as an indicator of mechanical anomalies, and in classifying wheel-related issues with high accuracy. This work not only contributes to the enhancement of predictive maintenance strategies but also provides valuable insights for the development of more resilient and efficient AGV systems in smart manufacturing environments.

关键词： automated guided vehicles anomaly detection telemetry anomaly detection machine learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic User-Scheduling and Power Allocation for SWIPT Aided Federated learning: A Deep learning Approach

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2023年第12期22卷 6956-6969页

作者： Li, Yang Wu, Yuan Song, Yuxiao Qian, Liping Jia, Weijia Univ Macau State Key Lab Internet Things Smart City Macau 999078 Peoples R China Zhuhai UM Sci & Technol Res Inst Zhuhai 519031 Peoples R China Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Peoples R China Beijing Normal Univ Inst Artificial Intelligence & Future Networks Zhuhai 519087 Peoples R China BNU HKBU United Int Coll Guangdong Key Lab AI & Multimodal Data Proc Zhuhai 519087 Peoples R China

Federated learning (FL) has been considered as a promising paradigm for enabling distributed machine learning (ML) in wireless networks. To address the limited energy capacity of wireless devices, we propose a simultaneous wireless information and power transfer (SWIPT) aided FL, in which one FL server (FLS) co-located at a cellular base station (BS) uses SWIPT to simultaneously broadcast the global model to wireless user-devices (UDs) and provide wireless power transfer to them. The UDs then use the harvested energy to train their local models and further transmit the local models to the FLS for aggregation. To improve the spectrum efficiency, we consider that the UDs form a non-orthogonal multiple access (NOMA) group for simultaneously sending their local models over the same spectrum channel. Taking the UDs' time-varying available energy and channel conditions into account, we propose a dynamic optimization of the UDs-scheduling, the BS's transmit-power allocation, and the UDs' power-splitting factors for SWIPT, with the objective of minimizing the long-term energy consumption while ensuring the FL convergence. The optimization problem, however, is challenging to solve since it is a finite-horizon dynamic programming problem but with an unknown stopping time, and moreover, the action space covers both discrete and continuous variables. To address these difficulties, we first execute a series of equivalent transformations to reduce the number of decision variables and then formulate the problem as a stochastic shortest path problem, based on which we propose an actor-critic deep reinforcement learning algorithm with the proximal policy optimization to efficiently learn the policy that dynamically adjusts the UDs-scheduling for FL as well as the BS's transmit-power for SWIPT. Numerical results validate the effectiveness and performance of our proposed algorithm. The results demonstrate that our proposed algorithm can effectively reduce the long-term energy consumpt

关键词： Optimization Resource management NOMA Training Heuristic algorithms Energy consumption Simultaneous wireless information and power transfer Federated learning SWIPT dynamic user-scheduling stochastic shortest path deep reinforcement learning and proximal policy optimization

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：