检索结果-内蒙古大学图书馆

DGHNL: A new deep genetic hierarchical network of learners for prediction of credit scoring

INFORMATION SCIENCES 2020年第0期516卷 401-418页

作者： Plawiak, Pawel Abdar, Moloud Plawiak, Joanna Makarenkov, Vladimir Acharya, U. Rajendra Polish Acad Sci Inst Theoret & Appl Informat Baltycka 5 PL-44100 Gliwice Poland Cracow Univ Technol Fac Comp Sci & Telecommun Dept Informat & Commun Technol Warsaw 24 StF-3 PL-31155 Krakow Poland Univ Quebec Montreal Dept Comp Sci Montreal PQ H2X 3Y7 Canada AGH Univ Sci & Technol Dept Biocybernet & Biomed Engn Fac Elect Engn Automat Comp Sci & Biomed Engn PL-30059 Krakow Poland Ngee Ann Polytech Dept Elect & Comp Engn Clementi 599491 Singapore SUSS Univ Sch Sci & Technol Dept Biomed Engn Clementi 599491 Singapore Kumamoto Univ IROAST Kumamoto Japan

Credit scoring (CS) is an effective and crucial approach used for risk management in banks and other financial institutions. It provides appropriate guidance on granting loans and reduces risks in the financial area. Hence, companies and banks are trying to use novel automated solutions to deal with CS challenge to protect their own finances and customers. Nowadays, different machine learning (ML) and data mining (DM) algorithms have been used to improve various aspects of CS prediction. In this paper, we introduce a novel methodology, named Deep Genetic Hierarchical Network of Learners (DGHNL). The proposed methodology comprises different types of learners, including Support Vector machines (SVM), k-Nearest Neighbors (kNN), Probabilistic Neural Networks (PNN), and fuzzy systems. The statlog German (1000 instances) credit approval dataset available in the UCI machine learning repository is used to test the effectiveness of our model in the CS domain. Our DGHNL model encompasses five kinds of learners, two kinds of data normalization procedures, two extraction of features methods, three kinds of kernel functions, and three kinds of parameter optimizations. Furthermore, the model applies deep learning, ensemble learning, supervised training, layered learning, genetic selection of features (attributes), genetic optimization of learners parameters, and novel genetic layered training (selection of learners) approaches used along with the cross-validation (CV) train-ingtesting method (stratified 10-fold). The novelty of our approach relies on a proper flow and fusion of information (DGHNL structure and its optimization). We show that the proposed DGHNL model with a 29-layer structure is capable to achieve the prediction accuracy of 94.60% (54 errors per 1000 classifications) for the statlog German credit approval data. It is the best prediction performance for this well-known credit scoring dataset, compared to the existing work in the field. (C) 2019 The Authors. Publish

关键词： Credit scoring machine learning data mining Ensemble learning Deep learning Genetic algorithm Feature extraction and selection

来源：评论

学校读者我要写书评

暂无评论

Speeding up Heterogeneous Federated learning with Sequentially Trained Superclients 26

Speeding up Heterogeneous Federated Learning with Sequential...

引用

26th international Conference on pattern recognition / 8th international workshop on Image mining - Theory and Applications (IMTA)

作者： Zaccone, Riccardo Rizzardi, Andrea Caldarola, Debora Ciccone, Marco Caputo, Barbara Politecnico Torino Turin Italy

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Federated learning (FL) allows training machine learning models in privacy-constrained scenarios by enabling the cooperation of edge devices without requiring local data sharing. This approach raises several challenges due to the different statistical distribution of the local datasets and the clients' computational heterogeneity. In particular, the presence of highly non-i.i.d. data severely impairs both the performance of the trained neural network and its convergence rate, increasing the number of communication rounds requested to reach a performance comparable to that of the centralized scenario. As a solution, we propose FedSeq, a novel framework leveraging the sequential training of subgroups of heterogeneous clients, Le. superclients, to emulate the centralized paradigm in a privacy-compliant way. Given a fixed budget of communication rounds, we show that FedSeq outperforms or match several state-of-the-art federated algorithms in terms of final performance and speed of convergence. Finally, our method can be easily integrated with other approaches available in the literature. Empirical results show that combining existing algorithms with FedSeq further improves its final performance and convergence speed. We test our method on CIFAR-10 and CIFAR-100 and prove its effectiveness in both i.i.d. and non-i.i.d. scenarios.(1)

关键词： Training Performance evaluation Federated learning Computational modeling Neural networks statistical distributions data models

来源：评论

学校读者我要写书评

暂无评论

SHM data anomaly classification using machine learning strategies: A comparative study

引用

SMART stRUCTURES AND SYstEMS 2022年第1期29卷 77-91页

作者： Chou, Jau-Yu Fu, Yuguang Huang, Shieh-Kung Chang, Chia-Ming Natl Taiwan Univ Dept Civil Engn 1 Sec 4Roosevelt Rd Taipei 10617 Taiwan Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore 639798 Singapore Natl Chung Hsing Univ Dept Civil Engn 145 Xingda Rd Taichung 40227 Taiwan

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changi

关键词： data anomaly classification ensemble neural network GoogLeNet machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Credit Risk Prediction Technology Based on Deep learning 24

Research on Credit Risk Prediction Technology Based on Deep ...

引用

1st international Conference on Image Processing machine learning and pattern recognition

作者： Huang, Xinyu HSBC Bank China Co Ltd Shanghai Peoples R China

ISBN: (纸本)9798400707032

The number of institutions engaged in credit business is increasing, the types of credit products are constantly enriched, and the credit balance is growing rapidly, which has led to an increasing demand for intelligent credit risk management. Pre-loan review is the most core stage in credit risk management, and a good pre-loan risk prediction model can minimize future risks. Some small and medium-sized banks still use traditional mathematical and statistical methods for risk prediction, which can neither meet the growing business needs of credit risk prediction nor guarantee the quality of prediction. Based on the research results of domestic and foreign scholars in the field of customer credit default prediction, this paper proposes a bank credit risk prediction management model based on a multi-level deep neural network to address the limitations of small and medium-sized banks using traditional methods based on mathematical statistics for risk prediction. Using the actual loan data of a commercial bank as experimental data, the simulation experimental results show that the model has a high prediction accuracy.

关键词： Artificial intelligence machine learning deep learning credit risk prediction

来源：评论

学校读者我要写书评

暂无评论

Character based pattern mining for neology detection 1

Character based pattern mining for neology detection

引用

EMNLP 2017 1st workshop on Subword and Character Level Models in NLP, SCLeM 2017

作者： Lejeune, Gael Cartier, Emmanuel Lipn Paris Xiii University 99 avenue Jean-Baptiste Clement Villetaneuse93430 France

ISBN: (纸本)9781945626913

Detecting neologisms is essential in real-time natural language processing applications. Not only can it enable to follow the lexical evolution of languages, but it is also essential for updating linguistic resources and parsers. In this paper, neology detection is considered as a classification task where a system has to assess whether a given lexical item is an actual neologism or not. We propose a combination of an unsupervised data mining technique and a supervised machine learning approach. It is inspired by current researches in stylometry and on tokenlevel and character-level patterns. We train and evaluate our system on a manually designed reference dataset in French and Russian. We show that this approach is able to outperform stateof- the-art neology detection systems. Furthermore, character-level patterns exhibit good properties for multilingual extensions of the system. © EMNLP *** right reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Defect Detection of Forming Mesh Based on YOLOV8N Model 24

Defect Detection of Forming Mesh Based on YOLOV8N Model

引用

1st international Conference on Image Processing machine learning and pattern recognition

作者： Li, Jing Wang, Lijuan Zhang, Peng Guangdong Mech & Elect Polytech Guangzhou Guangdong Peoples R China Macao Polytech Univ Macau Peoples R China

ISBN: (纸本)9798400707032

A method for detecting defects in forming mesh based on the YOLOV8N model is proposed. Firstly, an illumination system is designed, and then image data with defects is collected to construct an image dataset. The constructed image dataset is annotated and augmented to build a corresponding image sample set. The YOLOV8N model is trained using the sample set to obtain a defect recognition and localization model. The original image to be recognized is input into the defect recognition and localization model, which then outputs the corresponding defect recognition and localization results. Experimental results show that this method provides accurate localization and fast speed.

关键词： Forming mesh 1 YOLOV8N model 2 Illumination system 3 Sample set 4

来源：评论

学校读者我要写书评

暂无评论

Sensor Fusion and Multimodal learning for Robotic Grasp Verification Using Neural Networks 26

Sensor Fusion and Multimodal Learning for Robotic Grasp Veri...

引用

26th international Conference on pattern recognition / 8th international workshop on Image mining - Theory and Applications (IMTA)

作者： Gohil, Priteshkumar Thoduka, Santosh Ploeger, Paul G. Bonn Rhein Sieg Univ Appl Sci Dept Comp Sci Autonomous Syst St Augustin Germany

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Different sensors on a robot help in understanding different aspects of the environment they are working in;however, each sensor modality is often processed individually and information from other sensors is not utilized jointly. One of the reasons is different sampling rates and different dimensions of input modalities. In this paper, we use multimodal data fusion techniques such as early, late and intermediate fusion for grasp failure identification using four different 3D convolution-based multimodal neural networks (3D-MNN). Our results on a visualtactile dataset shows that the performance of the classification task is improved while using multimodal data. In addition, a neural network trained with 30:22 train-test split of multimodal data achieved accuracy comparable to a network trained with 78:22 train-test split of unimodal data(1).

关键词： Visualization Three-dimensional displays Fuses Neural networks Sensor fusion Robot sensing systems Minimization

来源：评论

学校读者我要写书评

暂无评论

Optimization of Intelligent Substation Location Scheme Based on data Fusion Technology and Artificial Intelligence 24

Optimization of Intelligent Substation Location Scheme Based...

引用

1st international Conference on Image Processing machine learning and pattern recognition

作者： Wang, Zhipeng Xie, Dan Feng, Cai He, Chunhui Lan, Feng State Grid Shandong Elect Power Co Econ &Technol Res Inst Beijing Peoples R China

ISBN: (纸本)9798400707032

At present, the world is experiencing the second information wave with data as the core and the Internet as the means, and the society is shifting from IT (information) era to DT (data) era. The planning of substation location is mainly based on the existing satellite vector data through the software simulation platform, and the optimal scheme and path planning are often based on the experience of designers in actual design and erection. However, with the continuous expansion of the project scale and increasing complexity, it has brought great challenges to the design work. Therefore, substation location needs to be combined with current data fusion technology and artificial intelligence technology to effectively improve the intelligent level of substation location.

关键词： Substation location data fusion technology Artificial intelligence technology Weighted Voronoi diagram

来源：评论

学校读者我要写书评

暂无评论

Design of Health data Monitoring System Based on stM32 24

Design of Health Data Monitoring System Based on STM32

引用

1st international Conference on Image Processing machine learning and pattern recognition

作者： Zhang, Fuyan Zhai, Lingling Dalian Neusoft Univ Informat Dept Comp Sci & Technol Dalian Peoples R China

ISBN: (纸本)9798400707032

Given the impact of the learning and lifestyle of contemporary student groups on their physical health quality, as well as the unique characteristics of the elderly population, effective monitoring methods are needed. At the same time, health data should be visualized and uploaded to cloud platforms. Through real-time tracking and precise analysis of data, a clearer understanding of health status can be obtained, and scientific life adjustments can be made. This article designs a health monitoring system for real-time data measurement and remote data transmission. The system is mainly divided into two parts: device side and OneNET cloud platform server. The device side uses stM32 as the control core, mainly collecting, displaying, and uploading health data. If the data is abnormal, the device promptly reminds relevant personnel. The device uses a WIFI module to connect to the network and uploads data to OneNET cloud platform through the MQTT protocol. This article focuses on device side design, and also briefly introduce the configuration of the OneNET platform.

关键词： stM32 Health data Monitoring Device Side MQTT

来源：评论

学校读者我要写书评

暂无评论

6th international workshop on Cyber-Security and Functional Safety in Cyber-Physical Systems, IWCFS 2022, 4th international workshop on machine learning and Knowledge Graphs, MLKgraphs 2022, 2nd international workshop on Time Ordered data, ProTime2022, 2nd international workshop on AI System Engineering: Math, Modelling and Software, AISys2022, 1st international workshop on Distributed Ledgers and Related Technologies, DLRT2022 and 1st international workshop on Applied Research, Technology Transfer and Knowledge Exchange in Software and data Science, ARTE2022 held at 33rd international Conference on database and Expert Systems Applications, DEXA 2022

6th International Workshop on Cyber-Security and Functional ...

引用

6th international workshop on Cyber-Security and Functional Safety in Cyber-Physical Systems, IWCFS 2022, 4th international workshop on machine learning and Knowledge Graphs, MLKgraphs 2022, 2nd international workshop on Time Ordered data, ProTime2022, 2nd international workshop on AI System Engineering: Math, Modelling and Software, AISys2022, 1st international workshop on Distributed Ledgers and Related Technologies, DLRT2022 and 1st international workshop on Applied Research, Technology Transfer and Knowledge Exchange in Software and data Science, ARTE2022 held at 33rd international Conference on database and Expert Systems Applications, DEXA 2022

ISBN: (纸本)9783031143427

The proceedings contain 40 papers. The special focus in this conference is on database and Expert Systems Applications. The topics include: Synthetic data in Automatic Number Plate recognition;An Untold Tale of Scientific Collaboration: SCCH and AC 2 T;on the Creation and Maintenance of a Documentation Generator in an Applied Research Context;towards the Digitalization of Additive Manufacturing;Twenty Years of Successful Translational Research: A Case study of Three COMET Centers;data Integration, Management, and Quality: From Basic Research to Industrial Application;building a YouTube Channel for Science Communication;introduction of Visual Regression Testing in Collaboration Between Industry and Academia;vibration Analysis for Rotatory Elements Wear Detection in Paper Mill machine;applying Time-Inhomogeneous Markov Chains to Math Performance Rating;introducing data Science Techniques into a Company Producing Electrical Appliances;a Technology Transfer Portal to Promote Industry-Academia Collaboration in South-Tyrol;fast and Automatic Object Registration for Human-Robot Collaboration in Industrial Manufacturing;sending Spies as Insurance Against Bitcoin Pool mining Block Withholding Attacks;risks in DeFi-Lending Protocols - An Exploratory Categorization and Analysis of Interest Rate Differences;battling the Bullwhip Effect with Cryptography;Reporting of Cross-Border Transactions for Tax Purposes via DLT;securing File System Integrity and Version History Via Directory Merkle Trees and Blockchains;taxation of Blockchain staking Rewards: Propositions Based on a Comparative Legal Analysis;comparison Framework for Blockchain Interoperability Implementations;A Comparative Analysis of Anomaly Detection Methods for Predictive Maintenance in SME;towards strategies for Secure data Transfer of IoT Devices with Limited Resources;application of Validation Obligations to Security Concerns;mode Switching for Secure Edge Devices;a Lifecycle Framework for Semantic Web machine Learn

关键词：

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：