检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhou, Hongfang Li, Yijie Guo, Yifan Xue, Haolin School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an710048 China

Electrocardiogram (ECG) synthesis plays a key role in the diagnosis of heart diseases. However, ECG data involves patient privacy and has obvious imbalance issue. This leads to a disconnect between theoretical research methods and practical applications. Based on this, the paper will explore the application of generative adversarial networks (GANs) in ECG signal synthesis. First, the paper proposes a WGAN-SD-GP model that uses the conditional WGAN networks incorporating an attention mechanism to enhance the ability to capture contextual information and effectively focus contextual information by scaling dot products. Secondly, the paper explores whether the design concepts of circular convolution, feature extraction and layer-hopping connection in R2U-Net can be applied to the synthesis of ECGs, and proposes the WGAN-SKD-GP model. The model combines the hopping layer connection with the attention mechanism, which enables it to process the input data more flexibly and enhances the feature expression ability. Finally, the experiments were designed to automatically classify arrhythmia using 1DResNet50 on a mixed dataset of synthetic and real signals, which was evaluated using several metrics, including Precision, Recall, F1 Score, Macro Avg, Weighted Avg, and Overall Accuracy. The experimental results not only verify the effectiveness of WGAN-SKD-GP in ECG signal synthesis, but also provide a new idea for solving the problem of insufficient data of ECG signals, which has significant potential application value. © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Model for Predicting the Time Through Traffic Jams 4th

Model for Predicting the Time Through Traffic Jams

引用

4th International Conference on Innovative computing, IC 2021

作者： Zhou, Miao Pang, Jingxu Zeng, Wenjie Gao, Yuan Yang, Aimin School of Electrical Engineering North China University of Technology Hebei Tangshan063210 China Electrical Engineering and Automation North China University of Technology Tangshan China Information and Computing Science North China University of Technology Tangshan China Chemical Engineering and Technology North China University of Technology Tangshan China Metallurgical Engineering North China University of Technology Tangshan China Tutor Tangshan China

ISBN: (纸本)9789811642579

This paper studies a problem of accurately predicting the time of passing traffic congestion. Through MATLAB programming, considering the relationship between traffic volume, traffic flow density, traffic flow speed and traffic congestion time, a new quantitative prediction method is established, that is, a multivariable BP neural network and time series coupling model (B-T). This mathematical model proposes a time period calculation method with different weights, which can combine the characteristics of BP neural network and time series to approximate the actual driving time as much as possible. The experiment shows that the proposed coupling model can maintain better prediction results under different traffic conditions and reduce the complexity of calculations. The workload has improved the actual engineering accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Predicting the impact of the weather conditions on transportation agility: A case study of an Australian Maritime Port 51

Predicting the impact of the weather conditions on transport...

引用

51st International Conference on Computers and Industrial engineering, CIE 2024

作者： Ordibazar, Amir Hossein Hussain, Omar Chakrabortty, Ripon K. Irannezhad, Elnaz Saberi, Morteza School of Business The University of New South Wales Northcott Drive CanberraACT2600 Australia School of Systems & Computing The University of New South Wales Northcott Drive CanberraACT2600 Australia School of Civil and Environmental Engineering The University of New South Wales High Street SydneyNSW2052 Australia School of Computer Science University of Technology Sydney Ultimo SydneyNSW2007 Australia

Transportation of the products is the primary connection between the different parts of the supply chain network (SCN), and the agility of the movements smooths the SCN operations. Potential risks (e.g., delay, road closure, and vehicle failure) disrupt the transportation process and negatively impact SCN operations. Accurately identifying the potential risks is the first step in Supply Chain Risk management (SCRM). All the factors, especially the external events outside of the SCN boundaries that cannot be controlled, need monitoring. In this paper, we propose a data-driven model to analyse the impact of weather status, as an external event, on the agility of the transportation system. A case study of a maritime port in Australia is considered to validate the model's applicability. For categorising the transportation based on agility, first, the speed of the movements was calculated by dividing distance by time, then by comparing the transportation speed with a defined threshold, the records of the dataset were divided into"Fast" and'Slow". For feature selection, First, seven weather-related attributes for the time of the dataset were collected, and then four criteria were calculated for each attribute. Secondly, by calculating the correlation of the features, the highly correlated ones were removed or justified, and the weather features were aggregated to the SCN dataset. Finally, after the data had been cleaned, Machine Learning (ML) models were used to train and test the aggregated dataset. The results showed 92.7% F1-score and 92.12% accuracy for the XGBoost classifier as the best one. Moreover, the weather features were recognised to be highly influential in predicting the agility of the transportation process. © 2024 Computers and Industrial engineering. All rights reserved.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks

arXiv

引用

arXiv 2024年

作者： Guo, Ji Jiang, Wenbo Zhang, Rui Lu, Guoming Li, Hongwei Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China

Recently, the success of Text-to-Image (T2I) models has led to the rise of numerous third-party platforms, which claim to provide cheaper API services and more flexibility in model options. However, this also raises a new security concern: Are these third-party services truly offering the models they claim? To address this problem, we propose the first T2I model verification method named Text-to-Image Model Verification via Non-Transferable Adversarial Attacks (TVN). The non-transferability of adversarial examples means that these examples are only effective on a target model and ineffective on other models, thereby allowing for the verification of the target model. TVN utilizes the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize the cosine similarity of a prompt’s text encoding, generating non-transferable adversarial prompts. By calculating the CLIP-text scores between the non-transferable adversarial prompts without perturbations and the images, we can verify if the model matches the claimed target model, based on a 3-sigma threshold. The experiments showed that TVN performed well in both closed-set and open-set scenarios, achieving a verification accuracy of over 90%. Moreover, the adversarial prompts generated by TVN significantly reduced the CLIP-text scores of the target model, while having little effect on other models. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Randomness and Interpolation Improve Gradient Descent: A Simple Exploration in CIFAR Datasets

Randomness and Interpolation Improve Gradient Descent: A Sim...

引用

International Conference on Cyber-Enabled Distributed computing and Knowledge Discovery, CyberC

作者： Jiawen Li Pascal Lefevre Anwar PP Abdul Majeed School of AI and Advanced Computing XJTLU Entrepreneur College (Taicang) Xi’an Jiaotong-Liverpool University Suzhou China School of Engineering and Technology Sunway University Malaysia

ISBN: (数字)9798331506896

ISBN: (纸本)9798331506902

Based on Stochastic Gradient Descent (SGD), the paper introduces two optimizers, named Interpolational Accelerating Gradient Descent (IAGD) as well as Noise-Regularized Stochastic Gradient Descent (NRSGD). IAGD leverages second-order Newton Interpolation to expedite the convergence process during training, assuming relevancy in gradients between iterations. To avoid over-fitting, NRSGD incorporates a noise regularization technique that introduces controlled noise to the gradients during the optimization process. Comparative experiments of this research are conducted on the CIFAR-10, and CIFAR-100 datasets, benchmarking different CNNs(Convolutional Neural Networks) with IAGD and NRSGD against classical optimizers in Keras Package. Results demonstrate the potential of those two viable improvement methods in SGD, implicating the effectiveness of the advancements.

关键词： Training Interpolation Noise Neural networks Process control Computer architecture Knowledge discovery Distributed computing Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Automated Skin Lesion Analysis and Classification Using AI 4

Automated Skin Lesion Analysis and Classification Using AI

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Pattnayak, Parthasarathi Patnaik, Sanghamitra Patra, Sudhansu Shekhar Gourisaria, Mahendra Kumar Singh, Satyendr Barik, Lalbihari School of Computer Applications Kiit Deemed to be University Bhubaneswar India School of Law Kiit Deemed to be University Bhubaneswar India School of Computer Engineering Kiit Deemed to be University Bhubaneswar India Bml Munjal University Computer Science & Engg Department Gurugram India King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Rabigh21911 Saudi Arabia

ISBN: (纸本)9798331540364

Skin lesions are becoming a major global health concern, and survival rates can be greatly increased by employing dermoscopic pictures for early identification. It is a difficult undertaking to classify these skin lesions from dermoscopic images. The application of deep learning models has significantly improved this classification's accuracy. Because convolutional neural networks (CNNs) are better at extracting features, which improves classification results, they have been shown to be quite useful in this field. In light of this, the article attempts to create deep learning (DL) algorithms using artificial intelligence (AI) to differentiate between skin lesions as benign or malignant in dermoscopic pictures. The study presents OSSAE-BPNN, an automated method for the detection and classification of skin lesions. This method uses a backpropagation neural network (BPNN) for classification and an optimized stacked sparse autoencoder (OSSAE) for feature extraction. To determine the damaged lesion region, the multi-level thresholding segmentation methodology is part of the proposed OSSAE-BPNN method. The OSSAE performs the feature extraction, and the BPNN handles the categorization. Furthermore, the SGO (seagull optimization) technique is used to optimize the SSAE model's parameters. Extensive testing were conducted on a standard dataset to show the OSSAE-BPNN method's efficacy. The OSSAE-BPNN methodology fared better than other current methods across a range of evaluation parameters, according to the results. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

KESMR: A Knowledge Enrichment Semantic Model For Recommending Microblogs 10

KESMR: A Knowledge Enrichment Semantic Model For Recommendin...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer engineering, UPCON 2023

作者： Ranjan, Himanshu Mishra, Sushruta Al-Khasawneh, Mahmoud Ahmad Singhal, Megh Sharma, Vandana Alkhayyat, Ahmed Kalinga Institute of Industrial Technology Deemed to Be University India School of Computing Skyline University College University City Sharjah Sharjah1797 United Arab Emirates Delhi India College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (纸本)9798350382471

In today's world, there's an enormous amount of information available on the Internet. Because of this, it's become really important to come up with better and smarter ways to search for things online. The old-fashioned methods, like just matching certain words or using statistics, don't work so well anymore. They often suggest web pages that are irrelevant. As the Semantic Web keeps getting bigger, it needs algorithms for the best fit. In this paper, a way to measure how different the words used for web search. This helps in suggesting the most relevant web pages. A special algorithm that can change its settings. Our proposed method demonstrates 94% accuracy. © 2023 IEEE.

关键词： Algorithm Semantic Heterogeneity Semantic Web Statistical Techniques Web 3.0

来源：评论

学校读者我要写书评

暂无评论

Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability

arXiv

引用

arXiv 2024年

作者： Ying, Zijian Li, Qianmu Wang, Tao Lian, Zhichao Meng, Shunmei Zhang, Xuyun The School of Cyber Science and Technology Nanjing University of Science and Technology Nanjing210094 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The School of Computing Faculty of Science and Engineering Macquarie University NSW2109 Australia

Various methods try to enhance adversarial transferability by improving the generalization from different perspectives. In this paper, we rethink the optimization process and propose a novel sequence optimization concept, which is named Looking From the Future (LFF). LFF makes use of the original optimization process to refine the very first local optimization choice. Adapting the LFF concept to the adversarial attack task, we further propose an LFF attack as well as an MLFF attack with better generalization ability. Furthermore, guiding with the LFF concept, we propose an LLFN attack which entends the LFF attack to a multi-order attack, further enhancing the transfer attack ability. All our proposed methods can be directly applied to the iteration-based attack methods. We evaluate our proposed method on ImageNet1k datasets by applying several SOTA adversarial attack methods under four kinds of tasks. Experimental results show that our proposed method can greatly enhance the attack transferability. Ablation experiments are also applied to verify the effectiveness of each component. The source code will be released after this paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Surface Extraction and Boundary Detection Based on DBSCAN Clustering in 3D Point Clouds 16

Surface Extraction and Boundary Detection Based on DBSCAN Cl...

引用

16th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2023

作者： Chen, Hui Xie, Tingting Menhas, Muhammad Llyas Ahmad, Bilal Huang, Heping Li, Qilin College of Automation Engineering Shanghai University of Electric Power Shanghai China Mirpur University of Science and Technology Department of Electrical Engineering Mirpur Pakistan College of Electrical Engineering University of Poonch Rawalakot Mirpur Pakistan Zhengtai Instrument Co. Ltd Hangzhou China School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia

ISBN: (纸本)9798350327144

Surface extraction from point clouds has many applications in product design, reverse engineering, industrial manufacturing and more. One of the key challenges is the detection and segmentation of overlapping areas of different surfaces. Existing methods are mainly on local judgment of similarity features, which can lead to either over- or under-segmentation. The proposed method in this paper utilizes DBSCAN for 3D point clouds surface extraction and boundary detection. Prior to extraction, the normal vector at sharp features is estimated based on a voting method. The surface extraction process is comprises two stages. First, the local quadric surface is determined based on the candidate sample points, and the points belonging to the same local surface are clustered. Second, in the merging stage, where the local surfaces are combined into a single smooth surface using three merging conditions. To demonstrate its effectiveness, the proposed approach is accessed on synthetic and real datasets, showing that the method can address the problem of insufficient and excessive segmentation of curved point clouds, and achieve high extraction accuracy. © 2023 IEEE.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

AI Based Optimization of Fault Tolerance in Multipath Routing for Medical Application 4

AI Based Optimization of Fault Tolerance in Multipath Routin...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Prasad, Lakkakula Hari Shobana, G. Bhardwai, Aniul Lakshmi Sireesha, C.H. Bais, Parikshit Kumar Kothapalli, Balakrishna Anurag Engineering College Department of ECE India Loyola Icam College of Engineering and Technology Department of It India Uic - University Institute of Computing Chandigarh University India Cbit Hyderabad Department of Mathematics Hyderabad India LNCT University Bhopal Computer Application Faculty of Engineering India School of Engineering Sr University Department of Eee Warangal India

ISBN: (纸本)9798350300888

Artificial Intelligence (AI) has had a substantial influence on the process of pharmaceutical research and development over the course of the last decade. Several applications that are connected to drug discovery, such as virtual screening and drug design, have made use of a number of AI's varied approaches. One of these applications is drug discovery. In the first section of this study, we are going to present an overview of drug discovery and discuss applications that are relevant to this field. These applications may be divided into two major tasks, which are synthesizing new compounds and making predictions about the characteristics of existing molecules. After that, this study will discuss about the standard data resources, different representations of molecules, and benchmark platforms. As a crucial component of the investigation, the methodologies of artificial intelligence are dissected into a variety of model architectures and learning paradigms. The reviewed papers have been arranged in a chronological manner to demonstrate the development of the technical features of AI in drug discovery throughout the course of time. According to our anticipations, the results of this study should provide a comprehensive analysis of the use of AI in drug development. An additional instructional resource that we make accessible to users is a repository that can be found on GitHub and is comprised of a variety of publications (and codes, if relevant). This archival storage space is regularly upgraded. © 2023 IEEE.

关键词： Expert systems

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：