检索结果-内蒙古大学图书馆

State-of-the-Art Review of Life Insurtech: Machine learning for underwriting decisions and a Shift Toward Data-Driven, Society-oriented Environment 6

State-of-the-Art Review of Life Insurtech: Machine learning ...

引用

6th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2024

作者： Kharlamova, Arina Kruglov, Artem Succi, Giancarlo Industrial Software Production Innopolis University Innopolis Russia Computer Science and Engineering University of Bologna Bologna Italy

ISBN: (纸本)9798350394634

Machine learning has been used by insurance companies for nearly a decade to identify potential risks and improve underwriting decisions. Nonetheless, there is a lack of systematic survey articles on state-of-the-art (SoTA) machine learning techniques, especially with respect to Society-oriented Environment models, developed to tackle these problems. This article begins by outlining the limitations of current systems used in this domain, including interpretability and explainability constraints, privacy issues, and the credibility of machine learning constructions along with their solutions. It then provides an extensive review of state-of-the-art machine learning algorithms such as Explainable AI, Privacy-Preserving Techniques, Federated and Transfer Learning, Sharpley, as well as others developed and applied for various Life Insurtech problems. The article also examines the existing challenges and future trends in developing machine-learning-based underwriting decision approaches. We believe that this survey can offer practical guidance for building next-generation insurance risk management systems. © 2024 IEEE.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

A Novel Data Mining Framework for Discovering Association Rules in Multivariate Time Series 7

A Novel Data Mining Framework for Discovering Association Ru...

引用

7th International Conference on Advanced Algorithms and Control engineering, ICAACE 2024

作者： Wang, Shengwei Lyu, Jianhua Zhang, Baili School Of Software Southeast University Nanjing China College Of Computer Science And Engineering Southeast University Nanjing China

ISBN: (纸本)9798350361445

As a significant field within data mining, association rule mining plays a pivotal role in unveiling relationships between items within a dataset. Existing approaches in multivariate time series (MTS) association rule mining primarily emphasize the generation of association rules by combining features from different variables, but neglect to adequately consider the temporal relationship between these features and ignore the trend information of variables, resulting in an incomplete capture of the essential characteristics inherent in MTS data. In this paper, we introduce a novel framework for association rule mining in multivariate time series. First, we discretize the multivariate time series into the symbolic sequence using trend-based symbolic aggregate approximation(TSAX). Then, a rule mining method is introduced to discover association rules that consider the temporal relationship among symbols of different variables. The results of experiments demonstrate the discovery of significant rules within the 'Weather&Traffic' dataset which gives the traffic conditions in France depending on the weather. Further, we also provide the outcomes of the sensitivity analysis conducted on our method, illustrating that significant rules can be mined by adjusting the parameters of TSAX to different settings. The experimental results highlight the utility of our proposed framework in discovering temporal association rules within multivariate time series datasets. © 2024 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

EdgeMob: A Context-Aware Dynamic Service Migration for Wearable IoT in Healthcare 1

EdgeMob: A Context-Aware Dynamic Service Migration for Weara...

引用

1st International Conference on Computing, Internet of Things and Microwave Systems, ICCIMS 2024

作者： Raza, Imran Hussain, Syed Asad Latif, Sana COMSATS University Islamabad Lahore Department of Computer Science Lahore Pakistan Department of Software Engineering Lahore Pakistan

ISBN: (纸本)9798350351736

Edge Computing (EC) is a distributed network architecture offering computation and storage resources at the network edge, addressing cloud computing limitations by optimizing latency and enhancing data safety and privacy for real-time services. It also supports intelligent solutions for IoT-based smart healthcare systems through Deep Learning (DL). DL aids in resource allocation optimization and disease prediction. However, the surge in wearable device usage introduces challenges in user mobility and migration, leading to increased latency and service inconsistencies. To tackle this, we propose EdgeMob, an intelligent and context-aware scheme deployed as a federation of edge servers. EdgeMob utilizes Q-learning-based reinforcement learning for personalized service migration decisions based on user mobility and Quality of Service (QoS). We evaluate our system against existing solutions, considering parameters such as user-perceived latency, migration cost, and network bandwidth utilization. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Enhancement Method Based on CGAN and Parallel Attention Mechanism 3

Underwater Image Enhancement Method Based on CGAN and Parall...

引用

3rd International Conference on Neural Networks, Information and Communication engineering, NNICE 2023

作者： Ma, Chi Yang, Le Hu, Hui Chen, Yuenai Bu, Anxu The School of Computer Science and Engineering Huizhou University Huizhou516007 China The School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

ISBN: (纸本)9798350335972

Due to the absorption and scattering of light in water, the underwater image has some problems such as colour distortion, serious colour difference and ambiguity, which seriously affects the detection of underwater resources and object recognition. At present, the latest underwater image enhancement methods are all based on deep learning, but they do not take into account the diversity of channel information and pixel features. In order to achieve better enhancement effect, a parallel attention mechanism combining Channel Attention and Pixel Attention is introduced based on Conditional Generative Adversarial Network consisting of multi-scale generator and double discriminator. Compared with other latest methods, the enhancement effect of the proposed method is closer to the real image, and the necessity of each module of the proposed model is proved by ablation study. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformers 27

Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D V...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Li, Mengke Li, Da Yang, Guoqing Cheung, Yiu-Ming Huang, Hui Shenzhen China VCC College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong

ISBN: (纸本)9781643685489

Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories of images, poses a challenge for the development of 3D pre-trained models. This paper therefore attempts to directly leverage pre-trained models with 2D prior knowledge to accomplish the tasks for 3D point cloud analysis. Accordingly, we propose the Adaptive PointFormer (APF), which fine-tunes pre-trained 2D models with only a modest number of parameters to directly process point clouds, obviating the need for mapping to images. Specifically, we convert raw point clouds into point embeddings for aligning dimensions with image tokens. Given the inherent disorder in point clouds, in contrast to the structured nature of images, we then sequence the point embeddings to optimize the utilization of 2D attention priors. To calibrate attention across 3D and 2D domains and reduce computational overhead, a trainable PointFormer with a limited number of parameters is subsequently concatenated to a frozen pre-trained image model. Extensive experiments on various benchmarks demonstrate the effectiveness of the proposed APF. The source code and more details are available at https://***/research/2024/PointFormer. © 2024 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improve Robustness of Safe Reinforcement Learning Against Adversarial Attacks 4

Improve Robustness of Safe Reinforcement Learning Against Ad...

引用

4th International Conference on Electronic Information engineering and computer science, EIECS 2024

作者： Wang, Xiaoyan Zhang, Yujuan Huang, Lan College of Computer Science and Technology Jilin University Changchun China Jilin University Software Engineering Changchun China

ISBN: (纸本)9798331531409

Models trained with adversarial attack can be significantly improved stability and performance when faced with new uncertain environment. In this paper, we propose the robust training framework based on Wasserstein SA-MDP for safe RL, which combines ideas from reinforcement learning, adversarial examples generation, Wasserstein metric and robust training. This framework can improve the robustness of safe RL models against adversarial attacks by considering the dynamics of the adversarial interaction as a sequential decision-making process. We made the experiment in safety gym based on the proposed framework and report the experimental results. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection 38

Revisiting Adversarial Patches for Designing Camera-Agnostic...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wei, Hui Wang, Zhixiang Zhang, Kewei Hou, Jiaqi Liu, Yuanwei Tang, Hao Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China The University of Tokyo Japan School of Computer Science Peking University China

Physical adversarial attacks can deceive deep neural networks (DNNs), leading to erroneous predictions in real-world scenarios. To uncover potential security risks, attacking the safety-critical task of person detection has garnered significant attention. However, we observe that existing attack methods overlook the pivotal role of the camera, involving capturing real-world scenes and converting them into digital images, in the physical adversarial attack workflow. This oversight leads to instability and challenges in reproducing these attacks. In this work, we revisit patch-based attacks against person detectors and introduce a camera-agnostic physical adversarial attack to mitigate this limitation. Specifically, we construct a differentiable camera Image Signal Processing (ISP) proxy network to compensate for the physical-to-digital transition gap. Furthermore, the camera ISP proxy network serves as a defense module, forming an adversarial optimization framework with the attack module. The attack module optimizes adversarial patches to maximize effectiveness, while the defense module optimizes the conditional parameters of the camera ISP proxy network to minimize attack effectiveness. These modules engage in an adversarial game, enhancing cross-camera stability. Experimental results demonstrate that our proposed Camera-Agnostic Patch (CAP) attack effectively conceals persons from detectors across various imaging hardware, including two distinct cameras and four smartphones. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models 41

ELTA: An Enhancer against Long-Tail for Aesthetics-oriented ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Limin He, Shuai Ming, Anlong Xie, Rui Ma, Huadong School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing China

Real-world datasets often exhibit long-tailed distributions, compromising the generalization and fairness of learning-based models. This issue is particularly pronounced in Image Aesthetics Assessment (IAA) tasks, where such imbalance is difficult to mitigate due to a severe distribution mismatch between features and labels, as well as the great sensitivity of aesthetics to image variations. To address these issues, we propose an Enhancer against Long-Tail for Aesthetics-oriented models (ELTA). ELTA first utilizes a dedicated mixup technique to enhance minority feature representation in high-level space while preserving their intrinsic aesthetic qualities. Next, it aligns features and labels through a similarity consistency approach, effectively alleviating the distribution mismatch. Finally, ELTA adopts a specific strategy to refine the output distribution, thereby enhancing the quality of pseudo-labels. Experiments on four representative datasets (AVA, AADB, TAD66K, and PARA) show that our proposed ELTA achieves state-of-the-art performance by effectively mitigating the long-tailed issue in IAA datasets. Moreover, ELTA is designed with plug-and-play capabilities for seamless integration with existing methods. To our knowledge, this is the first contribution in the IAA community addressing long-tail. All resources are available in here. Copyright 2024 by the author(s)

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Innovations: Transforming Data Support and Environmental Management for the Future

AI-Driven Innovations: Transforming Data Support and Environ...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Mahfuri, Mahmoud Ibrahim, Amer International University for Science and Technology Computer and Information Technology Department Syria United Arab Emirates University Department of Computer Science and Software Engineering United Arab Emirates

ISBN: (纸本)9798350369106

This paper presents the evolving role of artificial intelligence (AI) in improving internal control and management processes. AI-driven technologies, including Generative Adversarial Networks (GANs) and ontologies, in addition to enabling data-supported decision-making, and empowering local governments to execute administrative tasks more efficiently and effectively. The study explores the wide range of opportunities that AI offers, highlighting the potential for optimizing internal workflows. Besides, it delves into key challenges, models, and methods for fully integrating AI into organizational processes, providing actionable insights for achieving streamlined, data-driven management systems. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Real-time Volume Preserving Constraints for Volumetric Model on GPU

引用

computers, Materials & Continua 2022年第10期73卷 831-848页

作者： Hongly Va Min-Hyung Choi Min Hong Department of Software Convergence Soonchunhyang UniversityAsan31538Korea Department of Computer Science and Engineering University of Colorado DenverDenver80217COUSA Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Korea

This paper presents a parallel method for simulating real-time 3D deformable objects using the volume preservation mass-spring system method on tetrahedron *** general,the conventional mass-spring system is manipulated as a force-driven method because it is fast,simple to implement,and the parameters can be ***,the springs in traditional mass-spring system can be excessively elongated which cause severe stability and robustness issues that lead to shape restoring,simulation blow-up,and huge volume loss of the deformable *** addition,traditional method that uses a serial process of the central processing unit(CPU)to solve the system in every frame cannot handle the complex structure of deformable object in ***,the first order implicit constraint enforcement for a mass-spring model is utilized to achieve accurate visual realism of deformable objects with tough constraint *** this paper,we applied the distance constraint and volume conservation constraints for each tetrahedron element to improve the stability of deformable object simulation using the mass-spring system and behave the same as its real-world *** reduce the computational complexity while ensuring stable simulation,we applied a method that utilizes OpenGL compute shader,a part of OpenGL Shading Language(GLSL)that executes on the graphic processing unit(GPU)to solve the numerical problems *** applied the proposed methods to experimental volumetric models,and volume percentages of all objects are *** average volume percentages of all models during the simulation using the mass-spring system,distance constraint,and the volume constraint method were 68.21%,89.64%,and 98.70%,*** proposed approaches are successfully applied to improve the stability of mass-spring system and the performance comparison from our experimental tests also shows that the GPU-based method is faster than CPU-based implementation for all cases.

关键词： Deformable object simulation mass-spring system implicit constraint enforcement volume conservation constraint GPU parallel computing

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：