检索结果-内蒙古大学图书馆

Auto Insurance Fraud Detection with Multimodal Learning

Data Intelligence 2023年第2期5卷 388-412页

作者： Jiaxi Yang Kui Chen Kai Ding Chongning Na Meng Wang Financial Technological Research Center Zhejiang LabHangzhou 361005China School of Computer Science and Engineering Southeast UniversityNanjing 211189China

In recent years,feature engineering-based machine learning models have made significant progress in auto insurance fraud ***,most models or systems focused only on structural data and did not utilize multi-modal data to improve fraud detection *** solve this problem,we adapt both natural language processing and computer vision techniques to our knowledge-based algorithm and construct an Auto Insurance Multi-modal Learning(AIML)*** then apply AIML to detect fraud behavior in auto insurance cases with data from real scenarios and conduct experiments to examine the improvement in model performance with multi-modal data compared to baseline model with structural data only.A selfdesigned Semi-Auto Feature Engineer(SAFE)algorithm to process auto insurance data and a visual data processing framework are embedded within *** show that AIML substantially improves the model performance in detecting fraud behavior compared to models that only use structural data.

关键词： Auto Insurance Multi-modal Learning Fraud detection Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Clinical deep model to analyse medical multivariate time-series data for health diagnosis

引用

Cyber-Physical Systems 2025年第2期11卷 139-164页

作者： Almahadeen, Layth Vijay, Richa Shabaz, Mohammad Soni, Mukesh Singh, Pavitar Parkash Patel, Pavan Byeon, Haewon Department of Financial and Administrative Sciences Al- Balqa’Applied University Al-Salt Jordan Department of computer science Amity University UP Noida India Department of Computer Science Engineering Model Institute of Engineering and Technology Jammu Jammu and Kashmir India Department of Computer Science Engineering University Centre for Research & Development Chandigarh University Mohali India Department of Management Lovely Professional University Phagwara India Department of Computer Science Engineering Ahmedabad Institute of Technology Ahmedabad India Department of Digital Anti-Aging Healthcare Inje University Gimhae Korea Republic of

Clinical auxiliary decision-making is related to life and health of patients, so the deep model needs to extract the personalised representation of patients to ensure high analysis and prediction accuracy;and provide a basis for prediction conclusions. In this context, a clinical deep model proposed an interpretable assessment method of patient health status based on contextual learning of medical features, encoding the time-series features of each variable separately, and using a multi-head de-coordination self-attention mechanism for learning Relationships between different features;feature skip-connection encoding based on a compressed excitation mechanism is proposed to improve the sensitivity of the model. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

The role of ESG rating divergence and independent directors in predicting future stock price crash risk

Journal of Derivatives and Quantitative Studies

引用

Journal of Derivatives and Quantitative Studies 2025年第1期33卷 45-66页

作者： Sun, Han Lee, JaeHo Kang, Hyoung-Goo Fan, Zengrui Department of Computer Science and Financial Engineering Hanyang University Seoul South Korea Department of Finance Hanyang University Business School Seoul South Korea

This study investigates the impact of ESG rating disagreements on stock performance in the Chinese A-share market, focusing on immediate and short-term market reactions and the risk of future stock price crashes. Using data from the Shanghai and Shenzhen stock exchanges, we analyze 17,006 firm-year observations from 2010 to 2021. Stock return data are sourced from the Wind database, while additional financial metrics are obtained from the China Stock Market and Accounting Research (CSMAR) database. Corporate governance information is drawn from the China National Research Data Service (CNRDS) database. Our findings indicate that higher levels of ESG divergence significantly increase the risk of future stock price crashes. Furthermore, the presence of independent directors moderates this relationship, reducing the likelihood of such crashes. Immediate market reactions to ESG rating disagreements are also significant, underscoring the need for transparency and alignment among rating agencies. The study highlights the importance of robust corporate governance and standardized ESG rating methodologies to mitigate associated risks. Policy recommendations include promoting transparency in ESG rating processes and enhancing the role of independent directors in corporate governance. © 2024, Han Sun, JaeHo Lee, Hyoung-Goo Kang and Zengrui Fan.

关键词： Corporate governance ESG rating Independent directors Market reactions Stock performance

来源：评论

学校读者我要写书评

暂无评论

Accelerating local SGD for non-IID data using variance reduction

引用

Frontiers of computer science 2023年第2期17卷 73-89页

作者： Xianfeng LIANG Shuheng SHEN Enhong CHEN Jinchang LIU Qi LIU Yifei CHENG Zhen PAN Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China Ant Financial Services Group Hangzhou 310000China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China

Distributed stochastic gradient descent and its variants have been widely adopted in the training of machine learning models,which apply multiple workers in *** them,local-based algorithms,including Local SGD and FedAvg,have gained much attention due to their superior properties,such as low communication cost and ***,when the data distribution on workers is non-identical,local-based algorithms would encounter a significant degradation in the convergence *** this paper,we propose Variance Reduced Local SGD(VRL-SGD)to deal with the heterogeneous *** extra communication cost,VRL-SGD can reduce the gradient variance among workers caused by the heterogeneous data,and thus it prevents local-based algorithms from slow convergence ***,we present VRL-SGD-W with an effectivewarm-up mechanism for the scenarios,where the data among workers are quite *** from eliminating the impact of such heterogeneous data,we theoretically prove that VRL-SGD achieves a linear iteration speedup with lower communication complexity even if workers access non-identical *** conduct experiments on three machine learning *** experimental results demonstrate that VRL-SGD performs impressively better than Local SGD for the heterogeneous data and VRL-SGD-W is much robust under high data variance among workers.

关键词： distributed optimization variance reduction local SGD federated learning non-IID data

来源：评论

学校读者我要写书评

暂无评论

A bitcoin service community classification method based on Random Forest and improved KNN algorithm

IET Blockchain

引用

IET Blockchain 2024年第3期4卷 276-286页

作者： Gao, Muyun Lin, Shenwen Tian, Xin He, Xi He, Ketai Chen, Shifeng School of Mechanical Engineering University of Science and Technology Beijing Beijing China Internet Financial Security Technology Key Laboratory National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China

There are service communities with different functions in the Bitcoin transactions system. Identifying community categories helps to further understand the Bitcoin transactions system and facilitates targeted regulation of anonymized Bitcoin transactions. To this end, a Bitcoin service community classification method based on Random Forest and improved K-Nearest Neighbor (KNN) algorithm is proposed. First, the transaction characteristics of different types of communities are analyzed and summarized, and the corresponding transaction features are extracted from the address and entity levels;then multiple classification algorithms are compared, the optimal model to filter the effective features is selected, and the feature vector of entity addresses is constructed. Finally, a classification model is constructed based on Random Forest and improved KNN algorithm to classify the entities. By constructing different classification models for experimental comparison, the accuracy and stability advantages of the proposed method for classification in service community classification research are verified. © 2024 The Authors. IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Facial Micro-Expression Recognition Method Based on Box-Attention Mechanism and MultiScale Feature Fusion 1

A Facial Micro-Expression Recognition Method Based on Box-At...

引用

1st IEEE International Conference on Data Intelligence and Innovative Application, DIIA 2024

作者： Tang, Mengyao Huang, Jiangtao Tang, Li Tang, Qingkai School of Digital Commerce Guangxi Financial Vocational College Nanning China School of Computer Science and Information Engineering Nanning Normal University Nanning China

ISBN: (纸本)9798331504434

As a special form of emotional expression, microexpressions are usually inadvertently revealed in facial expressions and body movements when human beings try to hide their true emotions. However, due to the fact that characteristics of micro-expressions such as short duration and low expression amplitude, it is complicated to capture the features of micro-expressions' subtle changes, which leads to a low recognition accuracy. To address this problem, a face micro-expression recognition network model based on dual-branch multi-scale feature fusion network (DmffNet) is proposed. To begin with, the first network branch of this model is based on the constructed YOLOv5-Box network to extract the three key regions of the face, namely the left eyebrow, the right eyebrow, and the mouth, and the local features of these three key regions are extracted by Vision Transformer. The second network branch firstly obtains fourlayer multi-scale facial features by a deep neural network which combining residual network and progressive pyramid, and then obtains the global features of the face by multi-scale feature fusion based on progressive pyramid network. And then, the local and global features extracted from the two network branches are fused by the attention gate module. Finally, the fused micro-expression features are input into a classifier to implemen micro-expression recognition. The DmffNet model achieves an average accuracy of 98.71 % on the Micro-Macro-Expression Warehouse (MMEW) dataset, and the experimental results demonstrate that the model possesses a superior micro-expression recognition performance. © 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

IoT Based Smart Framework Monitoring System for Power Station

引用

computers, Materials & Continua 2023年第3期74卷 6019-6037页

作者： Arodh Lal Karn Panneer Selvam Manickam R.Saravanan Roobaea Alroobaea Jasem Almotiri Sudhakar Sengan Department of Financial and Actuarial Mathematics School of ScienceXi’an Jiaotong-Liverpool UniversityChina Department of Electrical and Electronics Engineering Sona College of TechnologySalem636005Tamil NaduIndia Department of Computer Science and Engineering Vel Tech Multi Tech Dr RR Dr SR Engineering CollegeChennai600062Tamil NaduIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia

Power Station(PS)monitoring systems are becoming critical,ensuring electrical safety through early warning,and in the event of a PS fault,the power supply is quickly *** technologies are based on relays and don’t have a way to capture and store user data when there is a *** proposed framework is designed with the goal of providing smart environments for protecting electrical types of *** paper proposes an Internet of Things(IoT)-based Smart Framework(SF)for monitoring the Power Devices(PD)which are being used in power substations.A Real-Time Monitoring(RTM)system is proposed,and it uses a state-of-the-art smart IoT-based System on Chip(SoC)sensors,a Hybrid Prediction Model(HPM),and it is being used in Big Data Processing(BDP).The Cloud Server(CS)processes the data and does the data analytics by comparing it with the historical data already stored in the ***-Structural Query Language Mongo Data Base(MDB)is used to store Sensor Data(SD)from the *** proposed HPM combines the Density-Based Spatial Clustering of Applications with Noise(DBSCAN)-algorithm for Outlier Detection(OD)and the Random Forest(RF)classification algorithm for removing the outlier SD and providing Fault Detection(FD)when the PD isn’t *** suggested work is assessed and tested under various fault circumstances that happened in *** simulation outcome proves that the proposed model is effective in monitoring the smooth functioning of the ***,the suggested HPM has a higher Fault Prediction(FP)*** means that faults can be found earlier,early warning signals can be sent,and the power supply can be turned off quickly to ensure electrical safety.A powerful RTM and event warning system can also be built into the system before faults happen.

关键词： System-on-chip cloud server apache kafka apache strom NoSQL MongoDB

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Node Velocity on Communication Overhead and Energy Consumption in WSNs Using Fuzzy Clustering

Exploring the Impact of Node Velocity on Communication Overh...

引用

2024 International Conference on Advances in Computing Research on science engineering and Technology, ACROSET 2024

作者： Sharma, Dilip Kumar Yadav, Aaditya Patidar, Mukesh Patil, Pooja Sanjay Patidar, Praveen Kumar Mandloi, Devendra Singh Sheikh, Rashid Rajpoot, Shivshankar Ujjain Engineering College Department of Electronics and Communication Engineering Ujjain India Piet Parul University Department of Computer Science and Engineering Vadodara India Credit Acceptance Financial Institution in Southfield Michigan United States Parul Institute of Technology Parul University Department of Computer Science & Engineering Vadodara India Indore Institute of Science and Technology Department of Electronics and Communication Engineering Indore India Acropolis Institute of Technology and Research Department of Computer Science and Engineering Indore India

ISBN: (纸本)9798350388800

Clustering, an unsupervised machine learning technique with numerous practical applications, has received a great deal of research attention. Along with deterministic and probabilistic approaches, fuzzy C-means clustering (FCM) is commonly employed. Over time, improvements to the FCM approach have been implemented to improve clustering efficiency. In this paper, we perform the results of communication overhead, energy consumption, and link distance travel in WSN with different velocities for the clustering-based protocol. In this performance, we are considering the number of nodes in the networks as 100, 175, and 200, having considered the start node as five using fuzzy clustering methodology in the unsupervised ML technique. In the communication overhead result analysis, we observed that the communication overhead increases as the nodes velocity increases, and another case of energy consumption also increases with the rising trend as node velocity increases. The results presented in this paper have been simulated using the Matlab R2020a tool. © 2024 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Effectiveness of Deep Learning Models in Network Intrusion Detection

Evaluating the Effectiveness of Deep Learning Models in Netw...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Kumar, Gaurav Gupta, Pankaj Yadav, Ganesh Kumar Verma, Richa Bhati, Jai Prakash Bhakuni, Vihan Singh IIMT College of Engineering Department of CSE Uttar Pradesh Greater Noida India Manager Data Engineer Discover Financial Services United States JSS Academy of Technical Education Department of Computer Science and Engineering UP Noida201301 India Computer Science and Engineering BBDITM Lucknow India Greater Noida India Computer Science and Engineering Graphic Era Hill University Dehradun India

ISBN: (纸本)9798331542344

Network security is now a significant concern in the current digital era since the increasing volume of cyber-attacks in day-to-day life has become a potential threat for the integrity and privacy of data. Most traditional intrusion detection systems face problems when it comes to detecting new and sophisticated attacks. The paper goes ahead to elaborate on how the concepts of machine learning and deep learning can be utilized to enhance the process of detecting and classifying network attacks. For instance, we experimented on the UNSW-NB15 dataset with different models: Decision Tree, Random Forest, SVM, KNN, MLP, and DNN. We have proved through our results that such kinds of models can considerably enhance the accuracy and robustness of IDS. With an average accuracy of 94.91%, the Decision Tree model took second place as the Deep Neural Network was closely followed. We will outline performance metrics based on the respective strengths and weaknesses of the models. This research is used to construct more effective and reliable network intrusion detection systems, which lead further into advancements of cybersecurity. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Fusion Network for Student Emotion Recognition Based on Transformer and Tensor Product 2

A Multimodal Fusion Network for Student Emotion Recognition ...

引用

2nd IEEE International Conference on Sensors, Electronics and computer engineering, ICSECE 2024

作者： Xiang, Ao Qi, Zongqing Wang, Han Yang, Qin Ma, Danqing School of Computer Science & Engineering University of Electronic Science and Technology of China Sichuan Chengdu China Computer Science Stevens Institute of Technology HobokenNJ United States Financial Mathematics University of Southern California LA United States School of Integrated Circult Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China

ISBN: (纸本)9798350373646

This paper introduces a new multi-modal model based on the Transformer architecture and tensor product fusion strategy, combining BERT's text vectors and ViT's image vectors to classify students psychological conditions, with an accuracy of 93.65%. The purpose of the study is to accurately analyze the mental health status of students from various data sources. This paper discusses modal fusion methods, including early, late and intermediate fusion, to overcome the challenges of integrating multi-modal information. Ablation studies compare the performance of different models and fusion techniques, showing that the proposed model outperforms existing methods such as CLIP and ViLBERT in terms of accuracy and inference speed. Conclusions indicate that while this model has significant advantages in emotion recognition, its potential to incorporate other data modalities provides areas for future research. © 2024 IEEE.

关键词： Tensors

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：