Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems最新文献_第2页

Optimal sensor deployment in complex 3D terrain surface 复杂三维地形表面传感器优化部署

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549186

Hai Chen, Tun Zhao, W. Qian

引用次数: 0

Image Data Augmentation Method based on Style Transfer 基于风格迁移的图像数据增强方法

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549180

Yanyan Wei, Chuwei Li, Hangyu Li, Zhilong Zhang

{"title":"Image Data Augmentation Method based on Style Transfer","authors":"Yanyan Wei, Chuwei Li, Hangyu Li, Zhilong Zhang","doi":"10.1145/3549179.3549180","DOIUrl":"https://doi.org/10.1145/3549179.3549180","url":null,"abstract":"Because there aren't enough accessible images of military vehicles, overfitting is a common occurrence when using a detection model in the military sector. Besides, low-contrast military vehicles are more difficult to be spotted in the field. Therefore, we create a dataset of military vehicles that consists of a training set and two different test sets, and we suggest an efficient method for image data augmentation that is mostly based on style transfer. Specifically, the process of data augmentation contains targets mask generation, style transfer, and details addition, and doesn't need extra annotation work. In the experimental part, YOLO v5s is applied to verify the efficacy of our method. Our method enables us to improve the precisions by 0.101 and 0.134 in the high-contrast situation, and achieve the precisions of 0.729 and 0.515 in the low-contrast situation when using single-style stylized images dataset and multi-style stylized images dataset respectively, in experiments. The results suggest that our method can reduce overfitting and show a rather satisfactory performance on our self-made dataset.","PeriodicalId":105724,"journal":{"name":"Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems","volume":"79 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130840461","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}

引用次数: 1

A Regional Logistics Demand Forecasting Method using KPCA-GA-ELM 基于KPCA-GA-ELM的区域物流需求预测方法

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549194

F. Tu., C. Ju, R. Chen

{"title":"A Regional Logistics Demand Forecasting Method using KPCA-GA-ELM","authors":"F. Tu., C. Ju, R. Chen","doi":"10.1145/3549179.3549194","DOIUrl":"https://doi.org/10.1145/3549179.3549194","url":null,"abstract":"Logistics demand forecasting works as a basis for well operated city governance especially for e-commerce industry. Yet, how to accurately predict the local logistics demand remains further improvement. To deal with it, this paper proposed an KPCA-GA-ELM approach which firstly introduces an extreme learning machine (ELM) approach to build the forecasting model, then incorporate both kernel principal component analysis (KPCA) and genetic algorithm (GA) into it. Taking Shanghai's regional logistics demand prediction as an example, two principal components affecting regional logistics demand are extracted by KPCA, ELM is then used to develop a regional logistics demand forecast model, and the genetic algorithm was applied to make the ELM model arguments be better to avoid the impact of strong randomness in parameter selection on model prediction performance and generalization ability. The results indicate that the accuracy is significantly improved comparing it with other two models. Such model then can be used as the demand forecasting and estimation approaches to estimate the demand of other industries in a region.","PeriodicalId":105724,"journal":{"name":"Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems","volume":"86 35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077269","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}

引用次数: 0

Single image dehazing algorithm based on generative adversarial network 基于生成对抗网络的单幅图像去雾算法

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549184

Donghui Zhao, Bo Mo

引用次数: 0

Online detection of character and 3D surface defect in steel rail production 钢轨生产中特征及三维表面缺陷的在线检测

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549188

W. Gan, Jia-hua Jiao, Hualin Zhu, Ke Xu, Jin-wu Xu, Dongdong Zhou

{"title":"Online detection of character and 3D surface defect in steel rail production","authors":"W. Gan, Jia-hua Jiao, Hualin Zhu, Ke Xu, Jin-wu Xu, Dongdong Zhou","doi":"10.1145/3549179.3549188","DOIUrl":"https://doi.org/10.1145/3549179.3549188","url":null,"abstract":"The surface quality of steel rail is connected to the safety and service life of high-speed rail transportation, and its rail waist character is essential for logistical monitoring and quality traceability. At the moment, it is difficult to use the same set of equipment to recognize features and defects in three dimensions on the complicated surface of the rail. The ring stroboscopic illumination system was devised in this study based on the features of the complicated surface of the rail, and the whole surface image of the rail was gathered by seven linear scan cameras. Create a point cloud model of the rail surface, then re-calibrate the light source's direction based on the rail's fundamental geometry. The normal vector of the rail surface is then calculated to appropriately recreate the 3D surface of the rail. This research provides a method for eliminating gradient error in the direction of motion by using point cloud registration to increase the accuracy of 3D rail surface reconstruction. The breadth and depth of surface defects were assessed using the rail surface's rebuilt 3D model, and the average relative inaccuracy was 7.23%. The Yolo deep learning algorithm is utilized for character identification, and recognition accuracy may reach more than 99%. Experiments suggest that the approach may be used to detect rail surface defects in three dimensions on time. The method not only could be beneficial to the monitoring and optimization of the quality in the rail manufacturing process, but also establish a solid foundation for increasing the safety of high-speed trains.","PeriodicalId":105724,"journal":{"name":"Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127858319","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}

引用次数: 0

A Hybrid Model for Evaluation of D&A System D&A系统评价的混合模型

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549190

Miaolan Zhou, Xian Zhou, Zekun Gao, Gen-Tao Zhang, Yijing Chen

{"title":"A Hybrid Model for Evaluation of D&A System","authors":"Miaolan Zhou, Xian Zhou, Zekun Gao, Gen-Tao Zhang, Yijing Chen","doi":"10.1145/3549179.3549190","DOIUrl":"https://doi.org/10.1145/3549179.3549190","url":null,"abstract":"Considering that talent, technology and process are three important components of a port company. To measure and optimise these three main impacts, we process this data using a system called Data and Analysis (D & A). Our D & A system consists of three key parts. The reasonable decision-making of these elements will well manage, operate, use and protect data resources. Our job is to analyze the success of the system. According to the actual situation of D & A system, this paper establishes the key performance indicators. In the process of processing Tianjin port, we extract key indicators from the data types they regularly process to build a D & A system. At the same time, we use the resources of the school library to collect and download excellent literature in the field of corporate performance research methodology to determine which factors need to be considered. In order to analyze the relationship between various influencing factors and enterprise performance and the size of influencing factors, the weight matrix is established by analytic hierarchy process. In order to judge which index has a greater impact on the company's performance, we use the Delphi method to evaluate the relative importance of the indexes and obtain an evaluation matrix. Then, the fuzzy comprehensive evaluation model of Tianjin Port D & A system is constructed.","PeriodicalId":105724,"journal":{"name":"Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775230","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}

引用次数: 0

A Credit Scoring Ensemble Framework using Adaboost and Multi-layer Ensemble Classification 基于Adaboost和多层集成分类的信用评分集成框架

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2022-07-29 DOI: 10.1145/3549179.3549199

R. Chen, C. Ju, F. Tu.

{"title":"A Credit Scoring Ensemble Framework using Adaboost and Multi-layer Ensemble Classification","authors":"R. Chen, C. Ju, F. Tu.","doi":"10.1145/3549179.3549199","DOIUrl":"https://doi.org/10.1145/3549179.3549199","url":null,"abstract":"The accuracy of classification plays a crucial role in the financial industry, and an increase of 1% in the accuracy of credit scoring in credit customer selection, risk measurement, etc. would significantly reduce the losses of financial institutions. Sometimes one particular classifier perform better than others for a given dataset, while the performance may worse than other classifiers for other datasets. Many studies have shown that classifier ensemble method is a more effective approach. a multi-level weighted voting classification algorithm based on the combination of classifier ranking and Adaboost algorithm is proposed in this paper.. Four feature selection methods are used to select the features, and then seven commonly used heterogeneous classifiers are used to select five classifiers and calculate their ranks, and then AdaBoost is used to boost the performance of the selected base classifiers and calculate the updated F1 and ranks. The effects of ensemble framework Majority Voting (MV), Weighted Voting (WV), Layered Majority Voting (LMV), Layered Weighted Voting (LWV) were all evaluated from the aspects of accuracy, sensitivity, specificity, and G-measure. In addition, the ROC curves of each ensemble framework are plotted for analysis, and the outcome of the experiments shows that our presented method achieves significant results on Australian credit score data and some progress on the German loan approval data.","PeriodicalId":105724,"journal":{"name":"Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129074829","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}

引用次数: 2

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems 2022年模式识别与智能系统国际会议论文集

Proceedings of the 2022 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 1900-01-01 DOI: 10.1145/3549179

引用次数: 0