Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690357
Fan Liu, Kang Zhou
Under the background of the serious grain loss and waste in China, it is of practical significance to design a data analysis system for the loss of grain processing. The system uses JeeSite framework and MySQL database to construct the system, mainly focusing on statistical analysis of the loss data and the cost data in the grain processing.
{"title":"Design of A Data Analysis System for the Grain Processing Loss","authors":"Fan Liu, Kang Zhou","doi":"10.1109/IICSPI.2018.8690357","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690357","url":null,"abstract":"Under the background of the serious grain loss and waste in China, it is of practical significance to design a data analysis system for the loss of grain processing. The system uses JeeSite framework and MySQL database to construct the system, mainly focusing on statistical analysis of the loss data and the cost data in the grain processing.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87535139","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690368
Zhan Hualin, Wang Qiqi, Hu Yujing
Fingerprint attendance system marked by the fingerprint template for authentication, utterly eliminates false phenomenon for fingerprint attendance system by any people’s fingerprint uniqueness, effectively puts an end to the human factors of attendance management, fully embodies the justice of attendance management, and avoids unnecessary personnel disputes. This system uses the STC89C52 microcontroller as the main control chip, 12864 LCD as the man-machine interface, matrix keyboard as input student ID, fingerprint identification module as sensors. Taking students in class as an example, student ID can be displayed on the fingerprint attendance system when fingerprint come input, and record attendance will be stored. The manager has a clear understanding for the students' attendance information in class, in addition, the information stored in this system can be arbitrarily increased or deleted, the function of this system is simple and practical.
{"title":"Design Fingerprint Attendance Machine Based on C51 Single-chip Microcomputer","authors":"Zhan Hualin, Wang Qiqi, Hu Yujing","doi":"10.1109/IICSPI.2018.8690368","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690368","url":null,"abstract":"Fingerprint attendance system marked by the fingerprint template for authentication, utterly eliminates false phenomenon for fingerprint attendance system by any people’s fingerprint uniqueness, effectively puts an end to the human factors of attendance management, fully embodies the justice of attendance management, and avoids unnecessary personnel disputes. This system uses the STC89C52 microcontroller as the main control chip, 12864 LCD as the man-machine interface, matrix keyboard as input student ID, fingerprint identification module as sensors. Taking students in class as an example, student ID can be displayed on the fingerprint attendance system when fingerprint come input, and record attendance will be stored. The manager has a clear understanding for the students' attendance information in class, in addition, the information stored in this system can be arbitrarily increased or deleted, the function of this system is simple and practical.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87714315","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}
Spatial and temporal distribution characteristics, precipitation concentration degree and concentration period distribution characteristics of heavy precipitation in Tibet Plateau region are analyzed with statistical methods, e.g. wavelet analysis, EOF analysis and precipitation concentration degree, etc. on the basis of daily precipitation data of 39 meteorological observation stations in Tibet region from 1980 to2012, and analysis results show that the spatial distribution of precipitation in Tibet region is seriously uneven, showing the distribution characteristics of low precipitation in the west and north and high precipitation in the east and south, and several heavy precipitation centers exist simultaneously; the frequency of heavy precipitation in Tibet shows an upward trend (up to 0.28 time /10a), and has a 11-year significant period; the precipitation concentration degree is 0.2-0.9, showing a gradual progressive increase trend from south to north; the precipitation is mainly concentrated between the 32nd Climate and the 45th Climate, that is, between early May and mid-August every year, in which the the precipitation is highly concentrated in the regions along Yarlung Zangbo River, and the precipitation concentration period in eastern Tibet region changes obviously, and Shigatse region, regions from eastern Nagchu to northern Nyingchi, and Yajiang valley are the main regions where precipitation concentration degree changes abnormally, and these regions are the key regions of power interconnection project in central and eastern Tibet, the study of which plays a science and technology support role in the operation and maintenance of power grid project.
{"title":"A Study on Distribution Characteristics of Heavy Precipitation in the Regions Supplied with Electric Power in Central and Eastern Tibet*","authors":"Li Yuan, Tiangui Xiao, Sunjun Liu, Xie Jun-hu, Bian Ba, Xiao Yong","doi":"10.1109/IICSPI.2018.8690476","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690476","url":null,"abstract":"Spatial and temporal distribution characteristics, precipitation concentration degree and concentration period distribution characteristics of heavy precipitation in Tibet Plateau region are analyzed with statistical methods, e.g. wavelet analysis, EOF analysis and precipitation concentration degree, etc. on the basis of daily precipitation data of 39 meteorological observation stations in Tibet region from 1980 to2012, and analysis results show that the spatial distribution of precipitation in Tibet region is seriously uneven, showing the distribution characteristics of low precipitation in the west and north and high precipitation in the east and south, and several heavy precipitation centers exist simultaneously; the frequency of heavy precipitation in Tibet shows an upward trend (up to 0.28 time /10a), and has a 11-year significant period; the precipitation concentration degree is 0.2-0.9, showing a gradual progressive increase trend from south to north; the precipitation is mainly concentrated between the 32nd Climate and the 45th Climate, that is, between early May and mid-August every year, in which the the precipitation is highly concentrated in the regions along Yarlung Zangbo River, and the precipitation concentration period in eastern Tibet region changes obviously, and Shigatse region, regions from eastern Nagchu to northern Nyingchi, and Yajiang valley are the main regions where precipitation concentration degree changes abnormally, and these regions are the key regions of power interconnection project in central and eastern Tibet, the study of which plays a science and technology support role in the operation and maintenance of power grid project.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85811317","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690511
Ning Ouyang, Xian Wang, Xiaodong Cai, Leping Lin
To improve the accuracy in low resolution face recognition, a method based on super-resolution joint feature mapping is proposed. Firstly, a two-branch convolutional neural network is designed to extract features of high and low resolution face images. A super-resolution enhanced network cascading feature extraction network is used for feature mapping of low resolution face images. In this way, the high frequency information of low resolution image can be reconstructed, and features are extracted. Secondly, a fusion loss method is utilized, in which the loss of cosine and the image reconstruction are weighted and fusioned to increase the cosine similarity between image features of different resolutions. Finally, the experimental results based on FERET dataset validate that the test accuracy of two-branch framework is up to 98.2%, 99.1%, 99.5% with resolutions of 20× 20, 24× 24, and 36× 36 obtained by smooth downsampling. The proposed model outperforms up-to-date low resolution face recognition methods.
{"title":"Deep joint super-resolution and feature mapping for low resolution face recognition","authors":"Ning Ouyang, Xian Wang, Xiaodong Cai, Leping Lin","doi":"10.1109/IICSPI.2018.8690511","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690511","url":null,"abstract":"To improve the accuracy in low resolution face recognition, a method based on super-resolution joint feature mapping is proposed. Firstly, a two-branch convolutional neural network is designed to extract features of high and low resolution face images. A super-resolution enhanced network cascading feature extraction network is used for feature mapping of low resolution face images. In this way, the high frequency information of low resolution image can be reconstructed, and features are extracted. Secondly, a fusion loss method is utilized, in which the loss of cosine and the image reconstruction are weighted and fusioned to increase the cosine similarity between image features of different resolutions. Finally, the experimental results based on FERET dataset validate that the test accuracy of two-branch framework is up to 98.2%, 99.1%, 99.5% with resolutions of 20× 20, 24× 24, and 36× 36 obtained by smooth downsampling. The proposed model outperforms up-to-date low resolution face recognition methods.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79561528","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690497
Duan Juan, Liu Runsheng, Jin Fei
Aiming at the sensitivity of the road centerline extraction algorithm using directional texture to the disturbance in the images, a modified method for road centerlines on highresolution remote sensing images is proposed based on the directional texture and Kalman Filter. After the initial center points of the road are obtained by directional texture matching, Kalman Filter combined with priori information and observation information of the road center points is applied to track the accurate road center points iteratively. Multiple experiments are designed to verify the reliability and robustness of the algorithm, showing that it can reduce the covering impact of vehicles, trees and shadow on road extraction in high-resolution images with relatively strong robustness and flexibility. The average position deviation is 1.9 pixels, and the average position deviation error is 1.7 pixels.
{"title":"A Modified Road Centerlines Search Method from Remote Sensing Images","authors":"Duan Juan, Liu Runsheng, Jin Fei","doi":"10.1109/IICSPI.2018.8690497","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690497","url":null,"abstract":"Aiming at the sensitivity of the road centerline extraction algorithm using directional texture to the disturbance in the images, a modified method for road centerlines on highresolution remote sensing images is proposed based on the directional texture and Kalman Filter. After the initial center points of the road are obtained by directional texture matching, Kalman Filter combined with priori information and observation information of the road center points is applied to track the accurate road center points iteratively. Multiple experiments are designed to verify the reliability and robustness of the algorithm, showing that it can reduce the covering impact of vehicles, trees and shadow on road extraction in high-resolution images with relatively strong robustness and flexibility. The average position deviation is 1.9 pixels, and the average position deviation error is 1.7 pixels.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79579810","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690429
Ji-bin Chang, Zhiming Dong
The accuracy of fault diagnosis is directly determined by the accuracy of fault information classification of rotating machinery. Based on the analysis of the basic theories of sample entropy and multi-scale entropy, and through the comparative analysis of sample entropy and multi-scale entropy on the original experimental data, it can be seen that multi-scale entropy is able to classify fault information more effectively. The optimal scale was determined through Matlab analysis. Under this scale, the fault differentiation capability under different similar tolerance was simulated, and the optimal scale and similar show that the multi-scale entropy is effective in differentiating various faults under the same scale and similarity tolerance.
{"title":"Fault Diagnosis of Rotating Machinery Based on Multiscale Entropy","authors":"Ji-bin Chang, Zhiming Dong","doi":"10.1109/IICSPI.2018.8690429","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690429","url":null,"abstract":"The accuracy of fault diagnosis is directly determined by the accuracy of fault information classification of rotating machinery. Based on the analysis of the basic theories of sample entropy and multi-scale entropy, and through the comparative analysis of sample entropy and multi-scale entropy on the original experimental data, it can be seen that multi-scale entropy is able to classify fault information more effectively. The optimal scale was determined through Matlab analysis. Under this scale, the fault differentiation capability under different similar tolerance was simulated, and the optimal scale and similar show that the multi-scale entropy is effective in differentiating various faults under the same scale and similarity tolerance.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79728952","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690502
Xu Kehang, Tang Jun, Tang Yuanyuan, Liao Hongyun
For the large number of meteorological information business products, the data needs to be shared. Based on the actual needs of meteorological information monitoring and warning, this paper analyzes the characteristics of meteorological services and implements a function-rich product production system, including design product production, task prompts, and weather Business, weather SMS, weather certification, weather data, 30-year consolidated data, product template production, etc. The purpose of this paper is to study the influence of plateau climatic environment and regional microclimate environment on the operation parameters of power grid communication system and power supply in Tibetan region, and provide basis for the selection and development of communication system and communication power supply for Tibet region.
{"title":"Design and Implementation of Real-time Tracking Monitoring and Warning Platform for Meteorological Information in Central Tibet","authors":"Xu Kehang, Tang Jun, Tang Yuanyuan, Liao Hongyun","doi":"10.1109/IICSPI.2018.8690502","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690502","url":null,"abstract":"For the large number of meteorological information business products, the data needs to be shared. Based on the actual needs of meteorological information monitoring and warning, this paper analyzes the characteristics of meteorological services and implements a function-rich product production system, including design product production, task prompts, and weather Business, weather SMS, weather certification, weather data, 30-year consolidated data, product template production, etc. The purpose of this paper is to study the influence of plateau climatic environment and regional microclimate environment on the operation parameters of power grid communication system and power supply in Tibetan region, and provide basis for the selection and development of communication system and communication power supply for Tibet region.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82443333","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690465
Chen Li, Congrui Li, Junwen Liu
The latest video compression reference software Joint Exploration Model (JEM) achieved outperforming performance in intra prediction. It mainly benefits from the increase of intra direction prediction modes, which changed from 33 to 65 and more flexible CU partition structure quadtree plus binary tree (QTBT). However, these technologies caused very high computational complexity at the same time. This paper, proposed a fast intra candidate selection algorithm based on the Sum of Absolute Hadamard Transformed Difference (SATD) and an early quadtree split termination algorithm to reduce the computational complexity in JEM-7.1. Experimental results show that our first proposed algorithm reduces 10% encoding time on average with only 0.5% loss in terms of Bjøntegaard delta bit rate (BDBR), and the second algorithm shows up to 21% time saving with 0.6% coding performance loss. These experimental results show the efficiency of our proposed algorithms.
最新的视频压缩参考软件Joint Exploration Model (JEM)在帧内预测方面取得了优异的成绩。这主要得益于内部方向预测模式的增加，从33种增加到65种，以及更灵活的CU划分结构四叉树加二叉树(QTBT)。然而，这些技术同时也造成了非常高的计算复杂度。为了降低JEM-7.1的计算复杂度，提出了一种基于绝对Hadamard变换差分(SATD)和早期四叉树分割终止算法的快速候选序列选择算法。实验结果表明，第一种算法平均减少10%的编码时间，仅损失0.5%的Bjøntegaard delta比特率(BDBR);第二种算法平均节省21%的编码时间，编码性能损失0.6%。实验结果表明了算法的有效性。
{"title":"Fast Intra Candidate Selection and CU Split in Intra Prediction for Future Video Coding","authors":"Chen Li, Congrui Li, Junwen Liu","doi":"10.1109/IICSPI.2018.8690465","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690465","url":null,"abstract":"The latest video compression reference software Joint Exploration Model (JEM) achieved outperforming performance in intra prediction. It mainly benefits from the increase of intra direction prediction modes, which changed from 33 to 65 and more flexible CU partition structure quadtree plus binary tree (QTBT). However, these technologies caused very high computational complexity at the same time. This paper, proposed a fast intra candidate selection algorithm based on the Sum of Absolute Hadamard Transformed Difference (SATD) and an early quadtree split termination algorithm to reduce the computational complexity in JEM-7.1. Experimental results show that our first proposed algorithm reduces 10% encoding time on average with only 0.5% loss in terms of Bjøntegaard delta bit rate (BDBR), and the second algorithm shows up to 21% time saving with 0.6% coding performance loss. These experimental results show the efficiency of our proposed algorithms.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83810352","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690404
Bo Li, ChengCheng Guo, Hui Ren
Images can convey rich semantics and induce various emotions to viewers. Several studies have been introduced recently that apply the deep learning technology to predict image emotion. In this paper, by extracting and combing the different levels of features, we build an emotion classification model based on feed forward deep neural network to classify image emotion. Experiments confirm the effectiveness of our network in predicting the emotion of images.
{"title":"Image Emotion Recognition Based on Deep Neural Network","authors":"Bo Li, ChengCheng Guo, Hui Ren","doi":"10.1109/IICSPI.2018.8690404","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690404","url":null,"abstract":"Images can convey rich semantics and induce various emotions to viewers. Several studies have been introduced recently that apply the deep learning technology to predict image emotion. In this paper, by extracting and combing the different levels of features, we build an emotion classification model based on feed forward deep neural network to classify image emotion. Experiments confirm the effectiveness of our network in predicting the emotion of images.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81814085","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 : 2018-12-01DOI: 10.1109/IICSPI.2018.8690500
Chao Xu, Daiwei Li, Haiqing Zhang, Wenfeng Hou, Tianrui Li
Upper and lower approximation of fuzzy-rough set membership degree is used to solve uncertainty of classification problem in FRNN (Fuzzy Rough Nearest Neighbor) algorithm. Although FRNN is the current leading classification algorithm, misjudgments still tend to occur when handling similar attribute values. Combining multiple interpolation algorithms and similarity attribute analysis, this paper proposes a new classification algorithm, which is called weighted Fuzzy Rough Nearest Neighbor (WFRNN) classification algorithm. WFRNN adds the corresponding weight of each attribute for the sample, and then multiple interpolations are used to fill data sets and the other four kinds of packing method are adopted to fill the missing data set. Then five completely random missing data sets from UCI were used in comparison experiments. We have compared WFRNN with classic KNN, decision tree, FRNN, J48, and random forests. Experimental performances show that the WFRNN algorithm can predict more accuracy classification results.
{"title":"A Weighted Fuzzy Rough Nearest Neighbor Classification Algorithm Based on Multiple Interpolation and Similarity Attribute Analysis","authors":"Chao Xu, Daiwei Li, Haiqing Zhang, Wenfeng Hou, Tianrui Li","doi":"10.1109/IICSPI.2018.8690500","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690500","url":null,"abstract":"Upper and lower approximation of fuzzy-rough set membership degree is used to solve uncertainty of classification problem in FRNN (Fuzzy Rough Nearest Neighbor) algorithm. Although FRNN is the current leading classification algorithm, misjudgments still tend to occur when handling similar attribute values. Combining multiple interpolation algorithms and similarity attribute analysis, this paper proposes a new classification algorithm, which is called weighted Fuzzy Rough Nearest Neighbor (WFRNN) classification algorithm. WFRNN adds the corresponding weight of each attribute for the sample, and then multiple interpolations are used to fill data sets and the other four kinds of packing method are adopted to fill the missing data set. Then five completely random missing data sets from UCI were used in comparison experiments. We have compared WFRNN with classic KNN, decision tree, FRNN, J48, and random forests. Experimental performances show that the WFRNN algorithm can predict more accuracy classification results.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86084609","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：