Andrea Viel, Andrea Brunello, A. Montanari, Federico Pittino
{"title":"一种基于决策树集成的蜂窝指纹定位方法","authors":"Andrea Viel, Andrea Brunello, A. Montanari, Federico Pittino","doi":"10.1080/17489725.2018.1553313","DOIUrl":null,"url":null,"abstract":"ABSTRACT In addition to being a fundamental infrastructure for communication, cellular networks are increasingly employed for outdoor positioning through signal fingerprinting. In this respect, the choice of the specific strategy used to obtain a position estimation from fingerprints plays a major role in determining the overall accuracy. In this paper, we propose a novel fingerprint comparison method, to be used in dynamic and large-scale contexts, such as the outdoor one, based on a machine learning approach. We explore two possible machine learning solutions, that make use of decision tree ensembles and support vector machines, respectively, and carefully contrast and evaluate them against a set of well-known, state-of-the-art fingerprint comparison functions from the literature. Tests are carried out with different tracking devices and environmental settings. It turns out that the machine learning approach, especially when implemented using decision tree ensembles, provides consistently better estimations than all the other considered strategies.","PeriodicalId":44932,"journal":{"name":"Journal of Location Based Services","volume":"13 1","pages":"25 - 52"},"PeriodicalIF":1.2000,"publicationDate":"2018-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17489725.2018.1553313","citationCount":"4","resultStr":"{\"title\":\"An original approach to positioning with cellular fingerprints based on decision tree ensembles\",\"authors\":\"Andrea Viel, Andrea Brunello, A. Montanari, Federico Pittino\",\"doi\":\"10.1080/17489725.2018.1553313\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT In addition to being a fundamental infrastructure for communication, cellular networks are increasingly employed for outdoor positioning through signal fingerprinting. In this respect, the choice of the specific strategy used to obtain a position estimation from fingerprints plays a major role in determining the overall accuracy. In this paper, we propose a novel fingerprint comparison method, to be used in dynamic and large-scale contexts, such as the outdoor one, based on a machine learning approach. We explore two possible machine learning solutions, that make use of decision tree ensembles and support vector machines, respectively, and carefully contrast and evaluate them against a set of well-known, state-of-the-art fingerprint comparison functions from the literature. Tests are carried out with different tracking devices and environmental settings. It turns out that the machine learning approach, especially when implemented using decision tree ensembles, provides consistently better estimations than all the other considered strategies.\",\"PeriodicalId\":44932,\"journal\":{\"name\":\"Journal of Location Based Services\",\"volume\":\"13 1\",\"pages\":\"25 - 52\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2018-01-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1080/17489725.2018.1553313\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Location Based Services\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/17489725.2018.1553313\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"TELECOMMUNICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Location Based Services","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/17489725.2018.1553313","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
An original approach to positioning with cellular fingerprints based on decision tree ensembles
ABSTRACT In addition to being a fundamental infrastructure for communication, cellular networks are increasingly employed for outdoor positioning through signal fingerprinting. In this respect, the choice of the specific strategy used to obtain a position estimation from fingerprints plays a major role in determining the overall accuracy. In this paper, we propose a novel fingerprint comparison method, to be used in dynamic and large-scale contexts, such as the outdoor one, based on a machine learning approach. We explore two possible machine learning solutions, that make use of decision tree ensembles and support vector machines, respectively, and carefully contrast and evaluate them against a set of well-known, state-of-the-art fingerprint comparison functions from the literature. Tests are carried out with different tracking devices and environmental settings. It turns out that the machine learning approach, especially when implemented using decision tree ensembles, provides consistently better estimations than all the other considered strategies.
期刊介绍:
The aim of this interdisciplinary and international journal is to provide a forum for the exchange of original ideas, techniques, designs and experiences in the rapidly growing field of location based services on networked mobile devices. It is intended to interest those who design, implement and deliver location based services in a wide range of contexts. Published research will span the field from location based computing and next-generation interfaces through telecom location architectures to business models and the social implications of this technology. The diversity of content echoes the extended nature of the chain of players required to make location based services a reality.