检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Cybernetics and Innovations, ICCI 2024

作者： Tanapanichkan, Supitchaya Kosolsombat, Somkiat Luangwiriya, Taweewat Thammasat University Data Science And Innovation Pathum Thani Thailand

ISBN: (纸本)9798350370096

This study investigates credit card fraud detection using various machine learning techniques. It emphasizes handling the imbalanced nature of fraud data through a combination of oversampling (10%) and undersampling (50%) methods. The most effective model, Random Forest, was identified using a comparison of different sampling techniques. The findings demonstrate the efficacy of integrating sampling techniques for improved model performance in fraud detection, offering insights into optimal strategies for addressing class imbalance in financial datasets. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Automatic video colorization based on contrastive learning and optical flow

引用

Multimedia Tools and Applications 2024年第21期83卷 59985-60001页

作者： Xiao, Shuyu Wang, Yongfang Wang, Yihan Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University Shanghai200444 China

Video colorization is the process of assigning reasonable color values to gray videos. Most of the existing video colorization methods use an image colorization algorithm directly regardless of correlation between frames in videos. Besides, these methods need reference, but it is difficult to obtain the guidance of users or reference images in practical applications. To overcome this limitation, we propose an automatic video colorization based on contrastive learning and optical flow. Contrastive learning optimizes the temporal correlation loss between the feature vectors of the gray video frame patches and the generated color video frame patches during training, which ensures the consistency of image content at the patch level. The optical flow module maintains the temporal consistency of colored videos by minimizing temporal correlation loss. In particular, the perceptual loss is introduced to improve the subjective colorization effect. Experiments show that the proposed algorithm outperforms the existing methods in terms of subjective quality. To reproduce the results, we release the source code at: https://***/orange-416/CLAC-GAN. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

FedPCGA: A Federated Unlearning Method Based on Projected Conflict Gradient Ascent 1

引用

8th International Scientific Conference on Intelligent Information Technologies for Industry, IITI 2024

作者： Liu, Ying Peng, Jialiang School of Data Science and Technology Heilongjiang University Harbin China

ISBN: (数字)9783031776885

ISBN: (纸本)9783031776878

As data becomes increasingly valuable, the importance of data privacy also grows. Governments and legislators worldwide have established regulations to safeguard users’ "Right to Be Forgotten", which allows users to request the deletion of their data from training datasets. However, merely deleting the data is insufficient, as models may retain implicit information or knowledge about the users’ data acquired during training. Therefore, it is crucial to enable models to specifically forget targeted data information. In Federated Learning, where multiple participants and incremental training are involved, existing centralized machine unlearning methods are not directly applicable. In this paper, we propose a federated unlearning method based on projected conflict gradient ascent that removes the impact of class data from the trained global model. Since the unlearning process conflicts with the gradient of the original training task, we project the conflicting unlearning gradient onto the gradient of the final training round in the target client model, thereby avoiding interference with model performance. Additionally, post-processing approach are proposed to mitigate catastrophic forgetting while maintaining overall model performance. The experimental results demonstrate that our method obtains a performance comparable to federated retraining from scratch in accomplishing the unlearning task, with significantly reduced execution time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Game Theory-Based Fastest Route Plan Method for Transportation Network Applications 6

Game Theory-Based Fastest Route Plan Method for Transportati...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Liu, Zheng-Tan Wu, Ling Chen, Chi-Hua College of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798350306613

This paper presents a vehicle route planning method based on game theory principles and innovative utility functions. By addressing the complexities of real-Time traffic congestion, the proposed framework offers a dynamic allocation strategy for rational decision-making. The utility function, which inte-grates traffic flow volume, road capacity, and congestion effects, provides accurate travel time estimations. Mathematical analysis and validation, including genetic algorithms, underscore the framework's robustness. Equilibrium solutions reveal allocation strategies responsive to varying road conditions. Comparative scenarios demonstrate the utility function's effectiveness in guiding enterprises' decisions. This research extends beyond static models, envisioning a future of data integration, multi-objective optimization, adaptive learning, and eco-friendly navigation. By converging these routes, the paper sets the stage for a smarter, more sustainable transportation landscape. © 2024 IEEE.

关键词： game theory Nash equilibrium route plan transportation network applications

来源：评论

学校读者我要写书评

暂无评论

Finding Sets of Pareto Sets in Real-World Scenarios - A Multitask Multiobjective Perspective 13

Finding Sets of Pareto Sets in Real-World Scenarios - A Mult...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Liu, Jiao Ong, Yew Soon Wong, Melvin College of Computing & Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798350308365

Recently, evolutionary multitasking has been employed to generate a 'set of Pareto sets' (SOS) for machine learning models, addressing diverse task settings across heterogeneous environments. This involves creating a repository of compact, specialized solution models that are collectively tailored to each specific task setting and environment, enabling users to select the most suitable model based on particular specifications and preferences. In this paper, we further demonstrate the versatility and applicability of the SOS concept across diverse domains, focusing on three real-world problems: engineering design problems, inventory management problems, and hyperparameter optimization problems. Additionally, as evolutionary multitasking has proven effective in generating the SOS, we investigate the performance of current evolutionary multitasking methods on these real-world problems. Subsequently, we present visualizations of the generated SOS in both decision and objective spaces, complemented by the development of a measurement to gauge the similarity between different Pareto sets corresponding to diverse tasks. Finally, we show that by systematically examining the shifts in Pareto optimal designs across different task settings though the SOS solutions, users can gain deeper understandings on the dynamic interplay between design solutions and their performance in different settings or contexts. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

Analysis of Anisotropic Nonlocal Diffusion Models:Well-Posedness of Fractional Problems for Anomalous Transport

引用

Numerical Mathematics(Theory,Methods and Applications) 2022年第4期15卷 851-875页

作者： Marta D’Elia Mamikon Gulian Data Science and Computing Sandia National LaboratoriesCAUSA

We analyze the well-posedness of an anisotropic,nonlocal diffusion *** an equivalence between weighted and unweighted anisotropic nonlocal diffusion operators in the vein of unified nonlocal vector calculus,we apply our analysis to a class of fractional-order operators and present rigorous estimates for the solution of the corresponding anisotropic anomalous diffusion ***,we extend our analysis to the anisotropic diffusion-advection equation and prove well-posedness for fractional orders s∈[0.5,1).We also present an application of the advection-diffusion equation to anomalous transport of solutes.

关键词： Nonlocal models fractional models anomalous diffusion anisotropic diffusion solute transport

来源：评论

学校读者我要写书评

暂无评论

Root Cause Analysis Using Rule Mining on Object-Centric Event Logs

Root Cause Analysis Using Rule Mining on Object-Centric Eve...

引用

International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024

作者： Knopp, Benedikt Pourbafrani, Mahsa van der Aalst, Wil Chair of Process and Data Science RWTH Aachen University Aachen Germany

ISBN: (纸本)9783031822247

In business processes, the behavior, evolution and interactions of objects influence the outcome of process instances, and thus the value that a business user may assign to them. For example, in an order-to-cash process, a complete and timely delivery of a package is desirable, but depends on what happens to other objects upstream, like production batches. Negative outcomes call for a Root Cause Analysis (RCA) on the process. While many approaches for RCA using process mining exist, none is native to object-centric frameworks and thus suitable for capturing dependencies across object types. This work presents a method for RCA that operates on object-centric event logs (OCELs). Given an OCEL, our method returns a set of association rules on the activity level. These rules associate descriptive patterns over the various object types occurring at events with patterns indicating the process outcome. The patterns are abstracted from the log with the help of a first-order logic based query engine. A case study confirmed that our method can identify problematic interactions across various object types in real-life business processes. © The Author(s) 2025.

关键词： Mine safety

来源：评论

学校读者我要写书评

暂无评论

ECSeg: Edge-Cloud Switched Image Segmentation for Autonomous Vehicles 21

ECSeg: Edge-Cloud Switched Image Segmentation for Autonomous...

引用

21st Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2024

作者： Zhou, Siyuan Van Le, Duc Tan, Rui College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798331519186

Existing autonomous vehicles have not utilized the cloud computing for execution of their deep learning-based driving tasks due to the long vehicle-to-cloud communication latency. Meanwhile, the vehicles are in general equipped with the resource-constrained edge computing devices which may be unable to execute the compute-intensive deep learning models in real time. The increasing data transmission speed of the commercial mobile networks sheds light upon the feasibility of using the cloud computing for autonomous driving. Our city-scale real-world measurements show that the vehicles can partially use the cloud computing via the fifth generation (5G) mobile network with the low data transmission latency. In this paper, we present the design and implementation of ECSeg, an edge-cloud switched image segmentation system that dynamically switches between the edge and cloud for executing the deep learning-based semantic segmentation models to understand the vehicle’s visual scenes in real time. The switching decision-making is challenging due to the intricate interdependencies among various factors including the dynamic wireless channel condition, vehicle’s movement and visual scene change. To this end, we employ deep reinforcement learning to learn an optimal switching policy. Extensive evaluation based on both real-world experiments and trace-driven simulations demonstrates that ECSeg achieves superior image segmentation accuracy for autonomous vehicles, compared with four baseline approaches. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on Embedding Intelligent Models in EEG data Platform 17

Research on Embedding Intelligent Models in EEG Data Platfor...

引用

17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Wu, Qikai Lin, Binghui Cheng, Ye Huang, ZhiHua College of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798331507398

With the rapid development of artificial intelligence (AI) technology, its application in the field of clinical electroen-cephalography (EEG) diagnosis shows remarkable prospects. It has become an urgent need to assist medical experts in clinical EEG diagnosis practice by constructing EEG intelligent models to automatically identify and diagnose EEG signals. This process involves the differences of AI algorithms and the complexity for practical applications. Therefore, the key lies in how to embed the EEG intelligent models into the EEG data platform of practical applications, manage these intelligent models in a unified and standardised way, and enhance their practicality and effectiveness in clinical EEG diagnosis. To this end, we have designed and developed an EEG data platform application that aims to provide services for the embedding of intelligent models and provide a standardised interface in terms of intelligent algorithms. Users can register algorithms according to their own needs, construct models on the platform in combination with EEG datasets to achieve the embedding of intelligent models, and provide convenient services for the unified management of models. This platform provides conditions for standardising the process of embedding EEG intelligent models and supports the auxiliary application of intelligent models in clinical diagnosis. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Contemporary CNN Implanted Deep Learning Framework for Crop Protection from Animal Intrusion in Farming Environment

A Contemporary CNN Implanted Deep Learning Framework for Cro...

引用

2024 International Conference on Advances in data Engineering and Intelligent Computing Systems, ADICS 2024

作者： Pavitra, A.Rehash Rushmi Panimalar, K. Rajalakshmi, D. Chinnasamy, A. Srm Institute Of Science And Technology Data Science And Business Systems Chennai India

ISBN: (纸本)9798350364828

In general, monitoring wild animal behavior at reasonable outlay is necessary for both managing human wildlife conflicts and protecting wildlife thereby reliable method is needed to detect wild animals. On the other side, Indian farmers endure severe risks from pests, natural disasters and animal damage resulting decreases the production process. To inspect crops and prevent animals from roaming farmers find it difficult to hire security and their standard approaches tend to be highly effective. Therefore, by applying efficient Deep Learning (DL) framework facilitate to develop Convolutional Neural Network CNN algorithm that can identify wild animal intrusion and provide an indication to end user. Further research highlights smart agriculture applications that significantly minimize losses in production by utilizing DL to make digital notifications that protect fields against mammalian attack. In addition to implementing into consideration the constraints imposed by the farming environment in terms of power supply and network connection, the proposed system is built on image processing platform that provide an optimal combination of efficiency, expense, and power consumption. Ultimately, significant advancement toward cutting-edge technology and sustainable crop protection offers farmers can able to minimize the negative effects of wildlife on the farming industry while reducing adverse ecological implications. © 2024 IEEE.

关键词： Deep learning

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：