Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696710
Baoxin Chen, Kan Chen, Xi Wang, Xu Wang
Based on the flood disaster loss data during1980-2019 in various prefectures of Tarim Basin. Disaster loss indicators are: disaster area, collapsed house, deaths toll, dead livestock, collapsed shed. By calculating the catastrophe index and using the gray correlation analysis method to compare the risk level of disaster loss in each prefecture. Disaster loss of Aksu has the greatest correlation with the damage area. In Bazhou prefecture, it has the greatest correlation with the dead livestock. In Hotan prefecture, it has the greatest correlation with the collapsed shed. In Kashgar prefecture, it has the greatest correlation with the disaster area. And in Kezhou prefecture, it has the greatest correlation with the dead livestock. It should be noted that the correlation degree of dead livestock caused by floods in Kezhou prefecture and the correlation degree of collapsed shed caused by floods in Hotan prefecture are higher (R>0.8). The risk analysis of flood disaster loss in Tarim Basin is significant for disaster management.
{"title":"Research on Data Collection and Catastrophe Index Using Grey Relational Analysis","authors":"Baoxin Chen, Kan Chen, Xi Wang, Xu Wang","doi":"10.1109/ICESIT53460.2021.9696710","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696710","url":null,"abstract":"Based on the flood disaster loss data during1980-2019 in various prefectures of Tarim Basin. Disaster loss indicators are: disaster area, collapsed house, deaths toll, dead livestock, collapsed shed. By calculating the catastrophe index and using the gray correlation analysis method to compare the risk level of disaster loss in each prefecture. Disaster loss of Aksu has the greatest correlation with the damage area. In Bazhou prefecture, it has the greatest correlation with the dead livestock. In Hotan prefecture, it has the greatest correlation with the collapsed shed. In Kashgar prefecture, it has the greatest correlation with the disaster area. And in Kezhou prefecture, it has the greatest correlation with the dead livestock. It should be noted that the correlation degree of dead livestock caused by floods in Kezhou prefecture and the correlation degree of collapsed shed caused by floods in Hotan prefecture are higher (R>0.8). The risk analysis of flood disaster loss in Tarim Basin is significant for disaster management.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116413307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696941
Yan Wang, Wanxia Zhong, Hang Su, Fujian Zheng, Yiran Pang, Hongchuan Wen, Kun Cai
The multi-view convolutional neural network architecture represented by MVCNN has achieved great success in 3D shape recognition. Taking the MVCNN architecture as the research goal, this paper proposes a novel 3D shape recognition convolutional neural network Attention-MVCNN that integrates channel attention mechanism, residual structure and Mish activation function. The channel attention machine is used to make the feature extraction network for Attention-MVCNN, which can reduce the feature redundancy caused by traditional convolution. The residual structure can reduce the network over-fitting problem and achieve better gradient information, thereby improving the performance of Attention-MVCNN. We replace the activation function in the Attention-MVCNN network with Mish, a self-regular non-monotonic neural activation function. The smooth activation function allows better information to penetrate the neural network, resulting in better accuracy and generalization. Experiments show that the improved Attention-MVCNN attains the competitive results on ModelNet40 dataset.
{"title":"An Improved MVCNN for 3D Shape Recognition","authors":"Yan Wang, Wanxia Zhong, Hang Su, Fujian Zheng, Yiran Pang, Hongchuan Wen, Kun Cai","doi":"10.1109/ICESIT53460.2021.9696941","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696941","url":null,"abstract":"The multi-view convolutional neural network architecture represented by MVCNN has achieved great success in 3D shape recognition. Taking the MVCNN architecture as the research goal, this paper proposes a novel 3D shape recognition convolutional neural network Attention-MVCNN that integrates channel attention mechanism, residual structure and Mish activation function. The channel attention machine is used to make the feature extraction network for Attention-MVCNN, which can reduce the feature redundancy caused by traditional convolution. The residual structure can reduce the network over-fitting problem and achieve better gradient information, thereby improving the performance of Attention-MVCNN. We replace the activation function in the Attention-MVCNN network with Mish, a self-regular non-monotonic neural activation function. The smooth activation function allows better information to penetrate the neural network, resulting in better accuracy and generalization. Experiments show that the improved Attention-MVCNN attains the competitive results on ModelNet40 dataset.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126846034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696844
Chen Chen, Yan-li Hou, Lianglong Li, Tao Jiang
This paper investigate a newly fault diagnosis system and trainee system based on 3D draft software. Compared to traditional fault diagnosis system, a system established on 3D software enables user easily to control manipulating system and aware of rate of process. In this paper, it firstly lists advantage and disadvantage of traditional fault diagnosis system, secondly introduces 3D draft software and practical application, lastly discusses benefit when combines 3D draft in fault diagnosis.
{"title":"Study and Design an Equipment-fault-diagnosis System Based on 3D Draft Software","authors":"Chen Chen, Yan-li Hou, Lianglong Li, Tao Jiang","doi":"10.1109/ICESIT53460.2021.9696844","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696844","url":null,"abstract":"This paper investigate a newly fault diagnosis system and trainee system based on 3D draft software. Compared to traditional fault diagnosis system, a system established on 3D software enables user easily to control manipulating system and aware of rate of process. In this paper, it firstly lists advantage and disadvantage of traditional fault diagnosis system, secondly introduces 3D draft software and practical application, lastly discusses benefit when combines 3D draft in fault diagnosis.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124100709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696972
Xiaoyue Jia, Fengchun Liu
With the rapid development of China's mobile Internet and the advent of 5g era, employees from all walks of life will basically use websites to buy all kinds of goods needed in life. As we all know, big data has become a key direction in the work of various Internet companies and the recommendation system can be said to be one of the best landing applications of big data. The benefits it brings to Internet companies are real and visible. Especially for e-commerce, intelligent recommendation system can directly affect the sales performance of an e-commerce enterprise[1]. How to store these massive data and efficiently mine valuable user information is the real challenge of big data technology[2]. In this paper, based on the modified Chinese Amazon e-commerce data set well-known in the field of recommendation system construction, and based on the real business data architecture of an e-commerce website, the project constructs an integrated e-commerce recommendation system, offline recommendation service and real-time recommendation service provide a variety of methods to achieve mixed recommendation effect. It provides a variety of off-line analysis methods and clever and accurate real-time recommendation model to realize data mining.
{"title":"Research on intelligent recommendation system model supported by data mining and algorithm optimization","authors":"Xiaoyue Jia, Fengchun Liu","doi":"10.1109/ICESIT53460.2021.9696972","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696972","url":null,"abstract":"With the rapid development of China's mobile Internet and the advent of 5g era, employees from all walks of life will basically use websites to buy all kinds of goods needed in life. As we all know, big data has become a key direction in the work of various Internet companies and the recommendation system can be said to be one of the best landing applications of big data. The benefits it brings to Internet companies are real and visible. Especially for e-commerce, intelligent recommendation system can directly affect the sales performance of an e-commerce enterprise[1]. How to store these massive data and efficiently mine valuable user information is the real challenge of big data technology[2]. In this paper, based on the modified Chinese Amazon e-commerce data set well-known in the field of recommendation system construction, and based on the real business data architecture of an e-commerce website, the project constructs an integrated e-commerce recommendation system, offline recommendation service and real-time recommendation service provide a variety of methods to achieve mixed recommendation effect. It provides a variety of off-line analysis methods and clever and accurate real-time recommendation model to realize data mining.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121442004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696663
Lai Zhongrong, H. Wei, Lu Youqin
When an optical pulse is transmitted in an optical fiber, the pulse will be broadened due to the dispersion effect, while the pulse will be compressed due to the nonlinear effect. When the two effects are balanced with each other, a peculiar phenomenon-optical soliton is produced. Optical soliton is a special wave packet that can be transmitted over long distances without distortion. Its uniqueness makes it have huge potential application value in the field of optical fiber communication, and provides a new solution for the optical communication system of ultra-long distance and ultra-large capacity transmission. At the same time, it is studying the dispersion effect and nonlinear effect in the optical fiber (cross-phase modulation XPM, self-phase modulation SPM, four-wave mixing (FWM), it is found that the dispersion and nonlinear characteristics of the fiber can be used to generate a supercontinuum. The transmission of optical pulses in optical fibers can be described by the general nonlinear Schrödinger equation, and then the split-step Fourier method can be used to simulate the transmission of optical pulses in optical fibers in MATLAB. Through simulation, we can see the stable transmission of the optical soliton, and at the same time changing the parameters according to different actual conditions, we can see the influence of dispersion and different nonlinear effects on the transmission of optical pulses.
{"title":"Propagation characteristics of optical solitons","authors":"Lai Zhongrong, H. Wei, Lu Youqin","doi":"10.1109/ICESIT53460.2021.9696663","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696663","url":null,"abstract":"When an optical pulse is transmitted in an optical fiber, the pulse will be broadened due to the dispersion effect, while the pulse will be compressed due to the nonlinear effect. When the two effects are balanced with each other, a peculiar phenomenon-optical soliton is produced. Optical soliton is a special wave packet that can be transmitted over long distances without distortion. Its uniqueness makes it have huge potential application value in the field of optical fiber communication, and provides a new solution for the optical communication system of ultra-long distance and ultra-large capacity transmission. At the same time, it is studying the dispersion effect and nonlinear effect in the optical fiber (cross-phase modulation XPM, self-phase modulation SPM, four-wave mixing (FWM), it is found that the dispersion and nonlinear characteristics of the fiber can be used to generate a supercontinuum. The transmission of optical pulses in optical fibers can be described by the general nonlinear Schrödinger equation, and then the split-step Fourier method can be used to simulate the transmission of optical pulses in optical fibers in MATLAB. Through simulation, we can see the stable transmission of the optical soliton, and at the same time changing the parameters according to different actual conditions, we can see the influence of dispersion and different nonlinear effects on the transmission of optical pulses.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127881926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696712
Xiaozhong Chen
The significant advantage of human long bone feature model is anatomical semantics, which can help medical personnel quickly identify and describe individual bone feature information. In this study, a constraint construction method of femoral surface model based on hierarchical parameter mapping is proposed to ensure the rationality of the deformed model by associating the variation range of characteristic parameters. The experimental results show that based on the modification of feature parameters, users can realize the rapid deformation of local feature regions and the constraint reconstruction of the whole model.
{"title":"A novel method for constraint creation of human long bone model based on hierarchical semantic mapping","authors":"Xiaozhong Chen","doi":"10.1109/ICESIT53460.2021.9696712","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696712","url":null,"abstract":"The significant advantage of human long bone feature model is anatomical semantics, which can help medical personnel quickly identify and describe individual bone feature information. In this study, a constraint construction method of femoral surface model based on hierarchical parameter mapping is proposed to ensure the rationality of the deformed model by associating the variation range of characteristic parameters. The experimental results show that based on the modification of feature parameters, users can realize the rapid deformation of local feature regions and the constraint reconstruction of the whole model.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127720155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696997
Liang Kaiwu, Chen Xingyu, Wang Maolin
Pipeline transportation, as a common method of oil and gas transportation in China, is generating economic and social benefits, while inhabiting huge potential risks at the same time. In order to make sure the acceptable level of social risks in oil and gas pipeline, it is extremely necessary to formulate a reasonable and feasible standard for acceptable risks. This essay, on the basis of as-low-as-reasonably-practicable (ALARP) principle, proposes a relation chart between “cumulative death frequency (F)” and “the number of death (N)” - improved F-N curve, which is combined with the risk chart. While drawing the curve, four variables in the risk chart are used to grade the risk level, the oil and gas pipeline related regulations are also considered. The research indicates that, improved F-N curve has a more objective and reasonable drawing process as well as a more accurate acceptable level of social risks. With stronger universality, it is able to be applied to different regions and industries.
{"title":"Research on Acceptable Level of Social Risks in Oil and Gas Pipeline","authors":"Liang Kaiwu, Chen Xingyu, Wang Maolin","doi":"10.1109/ICESIT53460.2021.9696997","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696997","url":null,"abstract":"Pipeline transportation, as a common method of oil and gas transportation in China, is generating economic and social benefits, while inhabiting huge potential risks at the same time. In order to make sure the acceptable level of social risks in oil and gas pipeline, it is extremely necessary to formulate a reasonable and feasible standard for acceptable risks. This essay, on the basis of as-low-as-reasonably-practicable (ALARP) principle, proposes a relation chart between “cumulative death frequency (F)” and “the number of death (N)” - improved F-N curve, which is combined with the risk chart. While drawing the curve, four variables in the risk chart are used to grade the risk level, the oil and gas pipeline related regulations are also considered. The research indicates that, improved F-N curve has a more objective and reasonable drawing process as well as a more accurate acceptable level of social risks. With stronger universality, it is able to be applied to different regions and industries.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127575788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696940
Yi Wang, Zongfeng Li
In order to meet the measurement requirements of the end force of the robot finger, this paper designs a miniature six-axis force/torque sensor based on the Y-shaped beam. Mechanical modeling, static analysis, bridge selection and least square method decoupling are carried out on the proposed six-axis force/torque sensor, which ensures the feasibility of the scheme and measurement accuracy.
{"title":"Structure design of elastomer of miniature six-axis force/torque sensor based on Y-type beam","authors":"Yi Wang, Zongfeng Li","doi":"10.1109/ICESIT53460.2021.9696940","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696940","url":null,"abstract":"In order to meet the measurement requirements of the end force of the robot finger, this paper designs a miniature six-axis force/torque sensor based on the Y-shaped beam. Mechanical modeling, static analysis, bridge selection and least square method decoupling are carried out on the proposed six-axis force/torque sensor, which ensures the feasibility of the scheme and measurement accuracy.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122216639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696488
Pan Feng, Qu Qiang
This article systematically discusses the importance of the ecological environment dynamic monitoring and management information system, the goals, principles and specific content of the system construction, technical routes and implementation plans, and the significance and role of the system after it is completed. The article describes the solution to several key technical problems in the research and development process of this system, including the integration and fusion of multi-source and multi-type data, the monitoring and refining of the status of the ecological environment and its change information based on remote sensing images, and the scale conversion of ecological environment information. Ecological environment evaluation model, ecological environment dynamic simulation and virtual expression, etc. Through the design of this system, it can provide a theoretical basis for the protection, governance, monitoring, and planning of the ecological environment, and also serve for the rational deployment and utilization of land resources and water resources.
{"title":"Research on Application of Computer Artificial Intelligence Technology in Remote Dynamic Monitoring of Environment","authors":"Pan Feng, Qu Qiang","doi":"10.1109/ICESIT53460.2021.9696488","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696488","url":null,"abstract":"This article systematically discusses the importance of the ecological environment dynamic monitoring and management information system, the goals, principles and specific content of the system construction, technical routes and implementation plans, and the significance and role of the system after it is completed. The article describes the solution to several key technical problems in the research and development process of this system, including the integration and fusion of multi-source and multi-type data, the monitoring and refining of the status of the ecological environment and its change information based on remote sensing images, and the scale conversion of ecological environment information. Ecological environment evaluation model, ecological environment dynamic simulation and virtual expression, etc. Through the design of this system, it can provide a theoretical basis for the protection, governance, monitoring, and planning of the ecological environment, and also serve for the rational deployment and utilization of land resources and water resources.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130647606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696813
Jiang Xiangjian
With the rapid development of economics, consumer lending and trust loan have gained unprecedented growth all over the world. Due to the serious consequence of borrowers' breach of contract, banks need a valid method to help managing credit risk. Till now, the most common way is to set up blacklist and whitelist according to previous loan records to assist bank in deciding whether to offer loan to someone or not. In other words, there is a fixed threshold to filter customers. Once borrower has a number of violations beyond the threshold, the bank will add him into the blacklist which means the man cannot get debt in the future according to his poor credit. This simple method may be useful but it also has some inevitable downsides resulting from its empirical nature. For instance, this approach still needs to be conducted with countless bank workers, accounting for its failure in satisfying soaring need in current changeable loan scenario. Meanwhile, the manually set threshold is not sensitive to massive data, which is more than unavoidable in today's life. To the best of our knowledge, machine learning methods are suitable to deal with huge amount of data and make accurate predictions. Considering the characteristics in consumer lending and trust loan, we put forward a new algorithm model implemented with machine learning knowledge to determine whether or not a loan should be granted. The method contains some cutting-edge machine learning ideas such as tree model and neural network. This new credit scoring framework can solve above problems effectively and control the expenditure within an acceptable range. In the experiments, we evaluate our method extensively on bank credit dataset, and the results demonstrate that it outperforms most credit scoring and risk prediction methods, achieving an AUC of 0.840 on the Test Set.
{"title":"Research on Computer Intelligent Risk Prediction Model and Identification Algorithm with Machine Learning","authors":"Jiang Xiangjian","doi":"10.1109/ICESIT53460.2021.9696813","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696813","url":null,"abstract":"With the rapid development of economics, consumer lending and trust loan have gained unprecedented growth all over the world. Due to the serious consequence of borrowers' breach of contract, banks need a valid method to help managing credit risk. Till now, the most common way is to set up blacklist and whitelist according to previous loan records to assist bank in deciding whether to offer loan to someone or not. In other words, there is a fixed threshold to filter customers. Once borrower has a number of violations beyond the threshold, the bank will add him into the blacklist which means the man cannot get debt in the future according to his poor credit. This simple method may be useful but it also has some inevitable downsides resulting from its empirical nature. For instance, this approach still needs to be conducted with countless bank workers, accounting for its failure in satisfying soaring need in current changeable loan scenario. Meanwhile, the manually set threshold is not sensitive to massive data, which is more than unavoidable in today's life. To the best of our knowledge, machine learning methods are suitable to deal with huge amount of data and make accurate predictions. Considering the characteristics in consumer lending and trust loan, we put forward a new algorithm model implemented with machine learning knowledge to determine whether or not a loan should be granted. The method contains some cutting-edge machine learning ideas such as tree model and neural network. This new credit scoring framework can solve above problems effectively and control the expenditure within an acceptable range. In the experiments, we evaluate our method extensively on bank credit dataset, and the results demonstrate that it outperforms most credit scoring and risk prediction methods, achieving an AUC of 0.840 on the Test Set.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：