مقاله انگلیسی رایگان در مورد متدلوژی ID3 و k-means برای طبقه بندی دستگاههای اینترنت اشیا – IEEE 2017

IEEE

 

مشخصات مقاله
ترجمه عنوان مقاله متدلوژی ID3 و k-means برای طبقه بندی دستگاههای اینترنت اشیا
عنوان انگلیسی مقاله ID3 and k-means Based Methodology for Internet of Things Device Classification
انتشار مقاله سال ۲۰۱۷
تعداد صفحات مقاله انگلیسی ۵ صفحه
هزینه دانلود مقاله انگلیسی رایگان میباشد.
پایگاه داده نشریه IEEE
مقاله بیس این مقاله بیس نمیباشد
فرمت مقاله انگلیسی  PDF
رشته های مرتبط مهندسی فناوری اطلاعات، فناوری اطلاعات و ارتباطات
گرایش های مرتبط اینترنت و شبکه های گسترده، سامانه های شبکه ای
نوع ارائه مقاله
کنفرانس
مجله / کنفرانس کنفرانس بین المللی مهندسی مکاترونیک، الکترونیک و خودرو – International Conference on Mechatronics
دانشگاه ITAM – Mexico – Mexico City
کلمات کلیدی اینترنت اشیا، IoT، طبقه بندی، درخت تصمیم گیری، k-means، ID3
کلمات کلیدی انگلیسی Internet of Things, IoT, classification, decision tree, k-means, ID3
شناسه دیجیتال – doi
https://doi.org/10.1109/ICMEAE.2017.10
کد محصول E9938
وضعیت ترجمه مقاله  ترجمه آماده این مقاله موجود نمیباشد. میتوانید از طریق دکمه پایین سفارش دهید.
دانلود رایگان مقاله دانلود رایگان مقاله انگلیسی
سفارش ترجمه این مقاله سفارش ترجمه این مقاله

 

فهرست مطالب مقاله:
Abstract
I.INTRODUCTION
II. APPROACH PROPOSAL FOR DEVICE CLASSIFICATION
III. RESULTS
IV. FINAL REMARKS
REFERENCES

 

بخشی از متن مقاله:
Abstract

The Internet of Things (IoT) brings the issue of connecting an immense amount of diverse devices. This vast diversity will present a challenge for communications, since it is not expected that all devices will follow the same rules and standards to communicate back and forth, due to the difficulty and inefficiency of developing a unique set rules and standards for each device. A classification of devices is needed, so rules and protocols of communications could be established among the different device categories, to deal with the diversity of the things to be interconnected. In this paper, a classification methodology using a clustering algorithm like k-means is proposed; as well as, a way to establish rules of classification using a decision tree implemented with the ID3 algorithm.

INTRODUCTION

The Internet of Things (IoT) is at the core of the revolution already under way that is seeing a growing number of Internet enabled devices that communicate with each other, and with other web-enabled gadgets, creating device to device networks meant to make everyday life easier, without requiring any human direct intervention [2]. In recent years, the number of connected devices has grown dramatically, and it is expected to continue growing until the number of connected devices reaches, by the year 2020, the amount of approximately 50 billion. That is, more than six devices per person in the world. Figure 1 illustrates the expected growth according to Cisco Systems, Inc. [3] Not only the amount of connected things will increase dramatically, but also the diversity of products, services, and classes of devices, with specific features and applications. The Internet of Things (IoT) will drive an accelerated adoption rate, changing in the very near future the way technology works, and establishing absolutely new paradigms about the way that people interact with the things around them, and the way things interact among themselves [4]. In such context, it is hard to believe that the huge diversity of expected commercial devices, within the complex and rapidly changing environment of interconnected things (including devices as diverse as microwave ovens, wheelchairs, robots, phones, cars, or even intelligent key chains, to mention few) will all have the same properties, performance, types of connectivity, priorities, levels of security, standards, and/or rules of operation. Of course, it would also be very difficult (and probably inefficient too) to try to develop independent rules and stan dards for each of the thousands of products that there are expected to be. This is why it is very important to start thinking about alternatives to classify all the possible devices and other connected things that could emerge and be in operation in the near future [5]. Such classification could be determinant to understand the dynamics of the future technology; to establish the rules for the interaction and communications between connected things; and to resolve some of the many future issues that could derive from the IoT adoption. This paper proposes the use of clustering techniques to achieve automatic classification of devices, and presents the results obtained for a limited set of connected things, applying a k-means clustering technique. The used clustering approach considered the most relevant features that identify each of the considered connected devices (such as its mobility, battery capacity, bandwidth, object size, etc.), which were registered and summarized in a CSV file. An ID3 algorithm was used to generate a decision tree classification ruler that allows to classify any object, according to its own relevant features. The obtained decision tree determines the most important attributes that need to be considered for each classification category

ارسال دیدگاه

نشانی ایمیل شما منتشر نخواهد شد. بخش‌های موردنیاز علامت‌گذاری شده‌اند *