检索结果-内蒙古大学图书馆

Credit Card Fraud Detection Based on Machine Learning

Computers, Materials & Continua 2019年第7期61卷 185-195页

作者： Yong Fang Yunyun Zhang Cheng Huang College of Cybersecurity Sichuan UniversityChengdu610065China College of Electronics and Information Engineering Sichuan UniversityChengdu610065China

In recent years,the rapid development of e-commerce exposes great vulnerabilities in online transactions for fraudsters to *** card transactions take a salient role in nowadays’online transactions for its obvious advantages including discounts and earning credit card *** credit card fraudulence has become a target of *** order to deal with the situation,credit card fraud detection based on machine learning is been studied ***,it is difficult to detect fraudulent transactions due to data imbalance(normal and fraudulent transactions),for which smote algorithm is proposed in order to resolve data *** assessment of Light Gradient Boosting Machine model which proposed in the paper depends much on datasets collected from clients’daily ***,to prove the new model’s superiority in detecting credit card fraudulence,Light Gradient Boosting Machine model is compared with Random Forest and Gradient Boosting Machine algorithm in the *** results indicate that Light Gradient Boosting Machine model has a good *** experiment in credit card fraud detection based on Light Gradient Boosting Machine model achieved a total recall rate of 99%in real dataset and fast feedback,which proves the new model’s efficiency in detecting credit card fraudulence.

关键词： Credit card fraud detection imbalanced data LightGBM model smote algorithm

来源：评论

学校读者我要写书评

暂无评论

Reliability-based design optimization of river-sea-going ship based on agent model technology

引用

MARINE STRUCTURES 2024年 94卷

作者： Kang, Yuhan Pei, Zhiyong Ao, Lei Wu, Weiguo Wuhan Univ Technol Sch Naval Architecture Ocean & Energy Power Engn Wuhan 430063 Peoples R China Wuhan Univ Technol Cruise & Yacht Res Ctr Green & Smart River Sea Going Ship Wuhan 430063 Peoples R China Hubei Prov Engn Res Ctr Green & Smart River Sea Go Wuhan 430063 Peoples R China

The common ship structural optimization design is a deterministic method without considering uncertain factors, whereas the Reliability-Based Design Optimization (RBDO) can compensate for this deficiency. The RBDO of ship structure is a multi-parameter, high-dimensional, and high-nonlinear optimization solver. There exists a difficulty in guaranteeing accuracy and efficiency due to massive computation. In this study, the high-precision agent model for the limit state of ship hold structure is established based on agent model technology, including BP neural network, Radial Basis Function neural network, and Support Vector Machine combined with smote oversampling algorithm. Furthermore, the reliability computation program is developed using Monte Carlo Simulation Method. A river-sea-going ship is considered the research object. The definition of rules, structural direct calculation result, and reliability requirement within all life cycles are considered boundary conditions. The RBDO system is constructed by the simulated annealing algorithm to investigate the lightweight structure. The established system can improve the efficiency and accuracy of the RBDO, which is significant for the ship's structural optimization design.

关键词： Reliability-based design optimization River-sea-going ship Agent model smote algorithm Monte Carlo simulation method

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based high-frequency jump test for detecting stock market manipulation: evidence from China's securities market

引用

KYBERNETES 2024年

作者： Huang, Hongyi Wu, Yanhui Guangdong Univ Technol Sch Econ Guangzhou Peoples R China George Washington Univ Sch Business Washington DC USA

Purpose - This study aims to tackle the critical issue of detecting stock market manipulation, which undermines the integrity and stability of financial markets globally. Even enhanced with machine learning, traditional statistical methods often struggle to analyze high-frequency trading data effectively due to inherent noise and the limited availability of publicly known manipulation cases. This leads to poor model generalization and a tendency toward over-fitting. Focusing on China's securities market, our study introduces an innovative approach that employs deep learning-based high-frequency jump tests to overcome these challenges and to develop a more effective method for identifying manipulative activities. Design/methodology/approach - We employed the "Jump Variation - Time-of-Day" (JV-TOD) non- parametric technique for jump tests on high-frequency data, coupled with the synthetic minority over- sampling technique (smote) algorithm for re-balancing sample data. Our approach trains a deep neural network (DNN) on refined data to enhance its ability to identify manipulation patterns accurately. Findings - Our results show that the deep neural network model, calibrated with high-frequency price jump data, identifies manipulation behavior more specifically and accurately than traditional models. The model achieved an accuracy rate of 94.64%, an F1-score of 95.26% and a recall rate of 95.88%, significantly outperforming traditional models. These results demonstrate the effectiveness of our approach in mitigating over-fitting and improving the robustness of market manipulation detection. Practical implications - The proposed model provides regulatory entities and financial institutions with a more efficient tool to monitor and counteract market manipulation, thereby improving market fairness and investor protection. Originality/value - By integrating the JV-TOD jump test with deep learning, this study proposed a new approach to market manipulation detection. The inno

关键词： Market manipulation High-frequency jump test Stratified oversampling smote algorithm Deep neural network

来源：评论

学校读者我要写书评

暂无评论

A study on financial early warning for technology companies incorporating big data and random forest algorithms

引用

INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING 2024年第3-4期15卷 343-351页

作者： Wang, Xuemei Shandong Foreign Trade Vocat Coll Dept Accounting & Finance Qingdao Shandong Peoples R China

This study establishes a model to predict the financial risk and the possibility of fraud of technology enterprises by using the random forest algorithm and smote algorithm. By testing and identifying data sets, the model shows good accuracy and efficiency, with an ACC index of 97.2%, an accuracy of 96.8%, a recall rate of 1, and an F1 index of 98.4%. Compared with the traditional model, the ratio of cash income to main business income is the highest, which shows that the prediction accuracy of this model is obviously better than that of the traditional model. The results show that this model will have some practical value in evaluating the financial status of science and technology enterprises.

关键词： financial fraud financial malpractice machine learning random forest algorithm smote algorithm

来源：评论

学校读者我要写书评

暂无评论

MKC-smote: A Novel Synthetic Oversampling Method for Multi-Class Imbalanced Data Classification

引用

IEEE ACCESS 2024年 12卷 196929-196938页

作者： Wang, Jiao Awang, Norhashidah Univ Sains Malaysia Sch Math Sci George Town 11800 Malaysia Puer Univ Sch Math & Stat Puer 665000 Peoples R China

The learning of multi-class imbalance problems presents greater challenges and has fewer research results compared to binary imbalance problems. Resampling techniques are widely employed to address data imbalance problems. However, the majority of existing resampling methods are designed specifically for binary imbalance datasets and demonstrate significant limitations when applied to multi-class imbalance datasets. Therefore, this study introduces the MKC-smote algorithm, a novel and effective method specifically tailored for multi-class imbalanced datasets. During the pre-processing phase, the algorithm takes into account the distribution of all classes and employs the k-nearest neighbors (kNN) algorithm to identify appropriate original samples for synthesizing minority class samples. It then utilizes an enhanced smote algorithm for interpolation. In the post-processing phase, potentially misleading synthesized samples are eliminated by the undersampling technique. Consequently, the MKC-smote algorithm generates high-quality minority class samples by strategically exploring the distributional regions of the classes. Extensive experiments were conducted on 21 real-world datasets, comparing the MKC-smote algorithm with six imbalance problem handling methods and two classifiers. The results demonstrate that the MKC-smote algorithm significantly enhances the classification performance of multi-class imbalanced datasets and outperforms several popular and state-of-the-art oversampling methods.

关键词： Multi-class imbalanced dataset classification smote algorithm synthetic minority oversampling Multi-class imbalanced dataset classification smote algorithm synthetic minority oversampling

来源：评论

学校读者我要写书评

暂无评论

Gas-Liquid Two-Phase Flow Pattern Identification of a Centrifugal Pump Based on smote and Artificial Neural Network

引用

MICROMACHINES 2022年第1期13卷 2-2页

作者： He, Denghui Li, Ruilin Zhang, Zhenduo Sun, Shuaihui Guo, Pengcheng Xian Univ Technol Inst Water Resources & Elect Power Xian 710048 Peoples R China Xian Univ Technol State Key Lab Ecohydraul Northwest Arid Reg China Xian 710048 Peoples R China

The accurate identification of the gas-liquid two-phase flow pattern within the impeller of a centrifugal pump is critical to develop a reliable model for predicting the gas-liquid two-phase performance of the centrifugal pump. The influences of the inlet gas volume fraction, the liquid phase flow rate and the pump rotational speed on the flow characteristics of the centrifugal pump were investigated experimentally. Four typical flow patterns in the impeller of the centrifugal pump, i.e., the bubble flow, the agglomerated bubble flow, the gas pocket flow and the segregated flow, were obtained, and the corresponding flow pattern maps were drawn. After oversampling based on the smote algorithm, a four-layer artificial neural network model with two hidden layers was constructed. By selecting the appropriate network super parameters, including the neuron numbers in the hidden layer, the learning rate and the activation function, the different flow patterns in the centrifugal pump impeller were identified. The identification rate of the model increased from 89.91% to 94.88% when the original data was oversampled by the smote algorithm. It is demonstrated that the smote algorithm is an effective method to improve the accuracy of the artificial neural network model. In addition, the Kappa coefficient, the Macro-F1 and the Micro-F1 were 0.93, 0.95 and 0.95, respectively, indicating that the model established in this paper can well identify the flow pattern in the impeller of a centrifugal pump.

关键词： gas-liquid flow centrifugal pump flow pattern identification smote algorithm neural network

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition for Parkinson's Disease Based on Improved Genetic algorithm and Data Enhancement Technology 8th

Speech Recognition for Parkinson's Disease Based on Improved...

引用

8th International Conference on Pioneering Computer Scientists, Engineers and Educators (ICPCSEE)

作者： Qin, Jing Liu, Tong Wang, Zumin Zou, Qijie Chen, Liming Hong, Chang Dalian Univ Dalian 116000 Peoples R China Ulster Univ Belfast 100166 North Ireland Third Peoples Hosp Dalian Dalian 116000 Peoples R China

ISBN: (纸本)9789811951947;9789811951930

Parkinson's disease is one of the most destructive diseases to the nervous system. Speech disorder is one of the typical symptoms of Parkinson's disease. Approximately 90% of Parkin-son's patients develop some degree of speech disorder, which affects speech function faster than any other subsystem of the body. Screening Parkinson's disease by sound is a very effective method that has attracted a growing number of researchers over the past decade. Patients with Parkinson's disease could be identified by recording the sound signal of the pronunciation of words, extracting appropriate features and identifying the disturbance in their voices. This paper proposes an improved genetic algorithm combined with a data enhancement method for Parkinson's speech signal recognition. Specifically, the methods first extract representative speech signal features through the L1 regularization SVM and then enhance the representative feature data by the smote algorithm. Following this, both original and enhanced features are used to train an SVM classifier for speech signal recognition. An improved genetic algorithm was applied to find the optimal parameters of the SVM. The effectiveness of our proposed model is demonstrated by using Parkinson's disease audio data set from the UCI machine learning library, and compared with the most advanced methods, our proposed method has the best performance.

关键词： Parkinson's disease speech signal detection Support vector machine smote algorithm Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Data Balancing Process to Strengthen a Malaria Control Prediction System in Senegal 9th

Data Balancing Process to Strengthen a Malaria Control Predi...

引用

9th International Conference on Ubiquitous Networking (UNet)

作者： Parkoo, Kodzo Gueye, Bamba Sarr, Cheikh Dia, Ibrahima Univ Iba Der Thiam Thies Senegal Univ Cheikh Anta Diop Dakar Senegal Inst Pasteur Dakar Senegal

ISBN: (纸本)9783031624872;9783031624889

Malaria is a public health problem in Senegal. Despite the implementation of prevention and treatment programs, the prevalence rate remains high, although there has been a noticeable decrease over the years. To further strengthen our efforts in the fight against malaria, we have previously developed a prediction system aimed at assessing the presence or absence of Anopheles larvae in specific sites. This system, is a crucial component of our anti-larval control (ALC) strategy, which involves gathering physico-chemical parameters from the site and using them to predict the likelihood of larvae presence. Given that, our prediction system relies on these physico-chemical parameters, ensuring the reliability and quality of the data is paramount. In our previous study, although we had access to reliable and high-quality data, we encountered an issue with data imbalance. To validate the accuracy of our prediction system, it is essential to address this data imbalance.

关键词： smote algorithm balanced data data prediction malaria

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification of Rainfall Weather Based on Deep Learning-Mod 39

Multi-Classification of Rainfall Weather Based on Deep Learn...

引用

39th Chinese Control Conference (CCC)

作者： Lu, Zhiying Ding, Xudong Ren, Yimo Sun, Xiaolei Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Tianjin Ocean Ctr Meteorol Observ Tianjin 300074 Peoples R China

ISBN: (纸本)9789881563903

Rain is one of the common weather conditions in the meteorological field, and at the same time it will have an important impact on people's daily life, industry and agricultural development. Rainfall is related to physical parameters of weather conditions, such as temperature, saturated water pressure, water vapor density, temperature and humidity. This paper constructs a rainfall multi-classification model based on physical quantities and deep learning model DBNs. Firstly, to resolve the problem of uneven distribution of the samples of the original data, some rainfall samples were synthesized using the smote algorithm. Secondly, the observation data encrypted hourly by the automatic ground monitoring station and physical quantities commonly used in weather forecast analysis are used to construct a deep learning model containing a Gauss Boltzmann machine to extract the intrinsic characteristics of the original data. Finally, a multi-class identification model of DBNs rainfall weather was realized. Experiments show that compared with other methods, the model can more accurately identify rainfall weather, and the POD, FAR and CSI indicators all perform well.

关键词： Rainfall classification Physical quantity calculation smote algorithm Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving User's Quality of Experience in Imbalanced Dataset 12

Improving User's Quality of Experience in Imbalanced Dataset

引用

12th International Wireless Communications & Mobile Computing Conference (IWCMC)

作者： Liu, Ronghua Huang, Ruocheng Qian, Yi Wei, Xin Lu, Ping Nanjing Univ Posts & Telecommun Coll Telecommun & Informat Engn Nanjing 210003 Jiangsu Peoples R China Jiangsu High Technol Res Key Lab Wireless Sensor Nanjing 210003 Jiangsu Peoples R China ZTE CORP Shenzhen Peoples R China

ISBN: (纸本)9781509003044

Good Quality of Experience is critical to the success of IPTV business development and promotion. To this end, the paper combines status data from the set-top box with the data of user's complaints and then selects the appropriate model to predict user's QoE. Firstly, we clean and conduct some statistical analysis for the dataset. Then, random under-sampling and synthetic over-sampling are applied to the dataset after these procedures. In order to get better performance, this paper improves the Synthetic Minority Over-sampling Technique (smote) algorithm. In addition, we compare the decision tree model and k-Nearest Neighbors (k-NN) model in user's complaint dataset. Through rigorous modeling and prediction, extensive experimental results show that k-NN model performs better than the decision tree in terms of predicting the user's complaint.

关键词： QoE smote algorithm decision tree k-NN

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：