{"title":"用手指关节比例预测人身高的新方法","authors":"Merve Güllü, Eyüp Burak Ceyhan, Ceren Ulucan","doi":"10.1145/3033288.3033326","DOIUrl":null,"url":null,"abstract":"This paper presents the existence of relation among the heights of Turkish citizens and joints of fingers. It also investigates the ratios of index fingers and ring fingers. Obtained features such as index fingers and ring fingers taken from right and left hands, heights, genders and age info of 49 male individuals between 18-79 years old, 45 female individuals between 18-55 years old, and total 94 individuals were used for this investigation. A system was also developed for predicting heights from 2D:4D rate of index fingers and ring fingers automatically for the first time. The system has a number of models trained with four algorithms. The results have shown that the proposed system can achieve the task with the highest accuracy having 73.40%.","PeriodicalId":253625,"journal":{"name":"International Conference on Network, Communication and Computing","volume":"65 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A New Approach: Predicting Height of a Person from Joint Ratio of Fingers\",\"authors\":\"Merve Güllü, Eyüp Burak Ceyhan, Ceren Ulucan\",\"doi\":\"10.1145/3033288.3033326\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents the existence of relation among the heights of Turkish citizens and joints of fingers. It also investigates the ratios of index fingers and ring fingers. Obtained features such as index fingers and ring fingers taken from right and left hands, heights, genders and age info of 49 male individuals between 18-79 years old, 45 female individuals between 18-55 years old, and total 94 individuals were used for this investigation. A system was also developed for predicting heights from 2D:4D rate of index fingers and ring fingers automatically for the first time. The system has a number of models trained with four algorithms. The results have shown that the proposed system can achieve the task with the highest accuracy having 73.40%.\",\"PeriodicalId\":253625,\"journal\":{\"name\":\"International Conference on Network, Communication and Computing\",\"volume\":\"65 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Network, Communication and Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3033288.3033326\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Network, Communication and Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3033288.3033326","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A New Approach: Predicting Height of a Person from Joint Ratio of Fingers
This paper presents the existence of relation among the heights of Turkish citizens and joints of fingers. It also investigates the ratios of index fingers and ring fingers. Obtained features such as index fingers and ring fingers taken from right and left hands, heights, genders and age info of 49 male individuals between 18-79 years old, 45 female individuals between 18-55 years old, and total 94 individuals were used for this investigation. A system was also developed for predicting heights from 2D:4D rate of index fingers and ring fingers automatically for the first time. The system has a number of models trained with four algorithms. The results have shown that the proposed system can achieve the task with the highest accuracy having 73.40%.