检索结果-内蒙古大学图书馆

MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection

computers, Materials & Continua 2023年第6期75卷 5573-5595页

作者： Zhanyang Xu Jianchun Cheng Luofei Cheng Xiaolong Xu Muhammad Bilal School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory Novel Software Technology Nanjing UniversityNanjing210023China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea

Federated learning has been used extensively in business inno-vation scenarios in various *** research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment ***,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise *** proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model ***,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and *** addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global *** results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify ***,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.

关键词： Federated learning feature selection credit risk assessment MSEs

来源：评论

学校读者我要写书评

暂无评论

Real-Time Road Signs Detection and Recognition for Enhanced Road Safety 15

Real-Time Road Signs Detection and Recognition for Enhanced ...

引用

15th International Conference on Innovations in Information Technology, IIT 2023

作者： Teklesenbet, Hermon B. Demoz, Nahom H. Jabiro, Igor H. Tesfay, Yonatan R. Badidi, Elarbi UAE University CIT Department of Computer Science and Software Engineering Al-Ain United Arab Emirates

ISBN: (纸本)9798350382396

Road sign detection and recognition play a critical role in improving driver safety and awareness in the modern traffic era. This paper describes the development and evaluation of a Road Sign Detection and Recognition System (RSDRS). Our system leverages computer vision techniques and mobile application technology to provide drivers with real-Time visual and auditory feedback based on detected traffic signs. The implementation of RSDRS involves two basic phases: developing a robust recognition model and creating an Android application. The model, trained with the German Traffic Sign Recognition Benchmark (GTSRB) dataset and the YOLOv5s object detection algorithm, serves as the core component for accurate traffic sign recognition. The Android application captures live video frames, integrates seamlessly with the recognition model, and provides intuitive feedback to the driver. The performance evaluation reveals the exceptional capabilities of our system, with an average accuracy of 99.3% and a fast response time of 0.73 milliseconds. Metrics such as recall, precision, and F1 score highlight the model's ability to maintain accuracy while minimizing false positives. Real-world applicability is paramount, and our system excels in a variety of environments and lighting conditions, as evidenced by rigorous testing. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

MA-MFIF: When misaligned multi-focus Image fusion meets deep homography estimation

引用

Multimedia Tools and Applications 2025年第12期84卷 10877-10898页

作者： Zhao, Baojun Luo, Fei Fuentes, Joel Ding, Weichao Gu, Chunhua School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Department of Computer Science and Information Technologies Universidad del Bio-Bio Chillán3780000 Chile

Multi-focus image fusion is a technique that combines multiple out-of-focus images to enhance the overall image quality. It has gained significant attention in recent years, thanks to the advancements in deep learning. However, one of the persistent challenges in this field is the processing of misaligned data, which can negatively impact the fusion results. To overcome this problem, a novel fusion framework with pre-registration is proposed for the fusion of misaligned multi-focus images. For pre-registration, content-aware deep homography estimation is used, which performs transfer learning on a real multi-focus image dataset to adapt to registration under defocused conditions. For fusion, a fusion module with dual-branch feature interaction is utilized to avoid invalid feature fusion and trained on real light field dataset to achieve better fusion performance. Qualitative and quantitative experimental results show that the proposed method has a 2-3 percentage point improvement in multiple evaluation metrics compared to existing advanced registration and fusion methods, and a maximum improvement of 4.83 percentage points in fusion performance when tested independently on the Lytro dataset. Additionally, We find that the value of the Qcv metric is greatly influenced by the alignment status of the input images, leading to its inability to reflect the fusion quality of aligned images. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Graph-Aware Unsupervised Feature Scoring Using Reconstruction Errors in GNN Embeddings

Graph-Aware Unsupervised Feature Scoring Using Reconstructio...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Sehee Kim, So Yeon Sohn, Kyung-Ah Ajou University Department of Artificial Intelligence Suwon Korea Republic of Ajou University Department of Artificial Intelligence Department of Software and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9798350386226

Graph neural networks (GNNs) have recently gained significant attention for their ability to model and analyze complex relationships, leading to numerous applications in a variety of fields. In line with this, explainable models such as GNNExplainer have been developed to provide insights into how GNN models make decisions. However, much of the research has focused on identifying important edges and subgraphs, with relatively less emphasis on feature importance. To address this gap, we propose a novel unsupervised feature scoring method aimed at extracting features that are well-aligned with graph structures. Our approach leverages the distinction between features that explain the overall structural characteristics of the graph and those that do not. Through comparative experiments with other algorithms, we demonstrated that our proposed method is effective in selecting important features in unsupervised settings. Additionally, empirical analysis of gene expression data confirmed that our method could aid in biomarker discovery, highlighting its potential for practical applications in biological studies. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Maximum Weight Convex Polytope 34

Maximum Weight Convex Polytope

引用

34th Canadian Conference on Computational Geometry, CCCG 2022

作者： Abam, Mohammad Ali Lavasani, Ali Mohammad Pankratov, Denis Department of Computer Engineering Sharif University of Technology Iran Department of Computer Science and Software Engineering Concordia University Canada

We study the maximum weight convex polytope problem, in which the goal is to find a convex polytope maximizing the total weight of enclosed points. Prior to this work, the only known result for this problem was an O(n3) algorithm for the case of 2 dimensions due to Bautista et al. We show that the problem becomes NP-hard to solve exactly in 3 dimensions, and NPhard to approximate within n1/2-Ε for any Ε > 0 in 4 or more dimensions. We also give a new algorithm for 2 dimensions, albeit with the same O(n3) running time complexity as that of the algorithm of Bautsita et al. © 2022 Yeganeh Bahoo and Konstantinos Georgiou.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Detection for False Data Injection, and Man in the Middle Attacks in IoT and IIoT

A Novel Approach Detection for False Data Injection, and Man...

引用

2023 IEEE PES Generation, Transmission and Distribution International Conference and Exposition, GTD 2023

作者： Gonen, Serkan Bariskan, Mehmet Ali Kaplan, Derya Yiltas Yilmaz, Ercan Nurcan Cetin, Aydin Istanbul Gelişim University Department of Computer and Software Engineering Istanbul Turkey Istanbul University-Cerrahpasa Department of Computer Engineering Istanbul Turkey Gazi University Faculty of Technology Ankara Turkey

ISBN: (纸本)9781728170251

Human beings have gone through stages that have made significant contributions to their lives with technological developments. One of the most important of these close to the present day is the introduction of IoTs, and IIoTs into our lives with the industry 4.0 process. From smart homes to smart grids, we are faced with a world that is getting smarter in every aspect of our lives. In this cyber environment where our data, including our personal data, is transferred to the virtual environment, the biggest threat is the attacks that can be made on this existing environment. The biggest methods used by attackers are to exploit the vulnerabilities that the existing system brings in addition to the old vulnerabilities. With the IoT process, there have been very important developments, and all operations can be carried out remotely via mobile phone or computer, such as checking the missing needs in the refrigerator, washing, drying clothes, and even in the most advanced dimension, reducing the temperature if it is too high, or increasing it if it is low, without people coming to their homes, and with these renovations, new types of threads become part of our lives. With this study we focus on one of more dangerous part of these attacks, False Data Injection (FDI), and Men in the Middle (MitM) attacks. With this study we detected MitM, and FDI attacks with success rate of %95 percent. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

An Efficient Character-Level Adversarial Attack Inspired by Textual Variations in Online Social Media Platforms

引用

computer Systems Science & engineering 2023年第12期47卷 2869-2894页

作者： Jebran Khan Kashif Ahmad Kyung-Ah Sohn Department of Artificial Intelligence Ajou UniversitySuwonKorea Department of Computer Science Munster Technological UniversityCorkIreland Department of Software and Computer Engineering Ajou UniversitySuwonKorea

In recent years,the growing popularity of social media platforms has led to several interesting natural language processing(NLP)***,these social media-based NLP applications are subject to different types of adversarial attacks due to the vulnerabilities of machine learning(ML)and NLP *** work presents a new low-level adversarial attack recipe inspired by textual variations in online social media *** variations are generated to convey the message using out-of-vocabulary words based on visual and phonetic similarities of characters and words in the shortest possible *** intuition of the proposed scheme is to generate adversarial examples influenced by human cognition in text generation on social media platforms while preserving human robustness in text understanding with the fewest possible *** intentional textual variations introduced by users in online communication motivate us to replicate such trends in attacking text to see the effects of such widely used textual variations on the deep learning *** this work,the four most commonly used textual variations are chosen to generate adversarial ***,this article introduced a word importance ranking-based beam search algorithm as a searching method for the best possible perturbation *** effectiveness of the proposed adversarial attacks has been demonstrated on four benchmark datasets in an extensive experimental setup.

关键词： Adversarial attack text classification social media character-level attack phonetic similarity visual similarity word importance rank beam search

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Agreement Using Enhanced Kerberos Authentication Protocol on M-Health

引用

computer Systems Science & engineering 2022年第11期43卷 833-847页

作者： A.S.Anakath S.Ambika S.Rajakumar R.Kannadasan K.S.Sendhil Kumar School of Computing E.G.S.Pillay Engineering CollegeNagapattinam611002India Department of Computer Science and Engineering University College of Engineering AriyalurAriyalur621705India Department of Mathematics University College of Engineering AriyalurAriyalur621705India Department of Software Systems School of Computer Science and Engineering(SCOPE)Vellore Institute of Technology UniversityVellore632014India Department of IoT School of Computer Science and Engineering(SCOPE)Vellore Institute of Technology UniversityVellore632014India

Cloud computing becomes an important application development platform for processing user data with high *** providers are accustomed to providing storage centers outside the trusted location preferred by the data ***,ensuring the security and confidentiality of the data while processing in the centralized network is very *** secured key transmission between the sender and the receiver in the network is a huge challenge in managing most of the sensitive data transmission among the cloud *** are very active over the network like real authenticated user to hack the personal sensitive data,such as bank balance,health data,personal data,and confidential documents over the cloud *** this research,a secured key agreement between the sender and the receiver using Kerberos authentication protocol with fingerprint is proposed to ensure security in *** of patients are monitored using wireless sensor devices and are then transferred to the *** protocol helps in avoiding unnecessary communication of authenticated data over the cloud *** security process is a procedure with the best security in most of the authentication *** node is responsible in carrying data packets from the sender to the receiver in the cloud *** Kerberos protocol is used in trust node to ensure *** communication between the local health center and the healthcare server is ensured by using a fingerprint feature called minutiae form,which refers to the fingerprint image of both sender and *** computational and communicational cost of the proposed system is lesser when compared with other existing authentication methods.

关键词： Protocol security m-health cloud computing biometric fingerprint kerberos protocol

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement in Blood Cell Segmentation with Deep Learning-based Image Fusion Approach 8

Performance Improvement in Blood Cell Segmentation with Deep...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Dogu, Fatma Tuana Dogan, Hulya Dogan, Ramazan Ozgur Sezen, F. Sena Karadeniz Technical University Faculty of Engineering Department of Electrical and Electronics Engineering Trabzon Turkey Karadeniz Technical University Faculty of Engineering Department of Software Engineering Trabzon Turkey Trabzon University Faculty of Computer and Information Sciences Department of Artificial Intelligence Engineering Trabzon Turkey Karadeniz Technical University Faculty of Pharmacy Department of Pharmacology Trabzon Turkey

ISBN: (纸本)9798331531492

To overcome the limitations of examining blood cells under a microscope, several investigations have been carried out using artificial intelligence techniques. These investigations aim to automate the processes of detecting, counting, segmenting, and classifying blood cells. Typically, these investigations employ two-dimensional (2D) images to apply artificial intelligence and image processing techniques. Nevertheless, these 2D images occasionally lack optimal focus as a result of the microscope's depth of focus (DOF). Inadequate achievement of optimally focused imaging has a detrimental impact on the efficiency of automated processes. In this context, the objective of this study is founded around two primary roles. The first of these is the performance improvement of blood cell segmentation by developing a deep learning-based image fusion approach. The second is the preparation of new data sets containing images with different focuses for optimally focused imaging of blood cells. In the study, four different performance evaluation criteria, namely Accuracy (ACC), Sensitivity (SEN), Specificity (SPE), and Jaccard, are utilized to demonstrate the efficacy of the deep learning-based image fusion approach in blood cell segmentation. Both the experimental results of the performance evaluation criteria and the visual findings obtained in the study indicate that the performance in blood cell segmentation is improved with a deep learning-based approach. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detecting Code Smell with a Deep Learning System

Detecting Code Smell with a Deep Learning System

引用

2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023

作者： Nizam, Ali Avar, Muhammed Yahya Adas, Omer Kaan Yanik, Ahmet Fatih Sultan Mehmet Vakif University Department of Software Engineering İstanbul Turkey Fatih Sultan Mehmet Vakif University Department of Computer Engineering İstanbul Turkey

ISBN: (纸本)9798350306590

Code smell detection is one of the most significant issues in the software industry. Metric-based static code analysis tools are used to detect undesirable coding practices known as code smells and guide refactoring requirements. Furthermore, the usage of deep learning-based techniques has emerged in code analysis tasks. The line and block level detection capability of metric-based tools provides an advantage over deep learning system systems. This study aims to develop a deep learning-based system for inter-procedural code smell detection supporting line and block of code. We created an experimental dataset by gathering code from GitHub repositories and detecting code smell on these codes using the metric-based SonarQube tool. Recurrent neural networks and transformers implementations of deep neural networks were applied to detect code smells. We also employed cosine similarity and k-Nearest Neighbor machine learning techniques for a comprehensive comparison. The proposed system achieves an average accuracy of approximately 80%. These findings indicate that the proposed system can help software teams in identifying potential interprocedural code smells. © 2023 IEEE.

关键词： Learning 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：