دانلود رایگان مقاله انگلیسی یادگیری ماشینی برای تجزیه و تحلیل اطلاعات اینترنت اشیا: یک تحقیق - الزویر 2017

Abstract

Rapid developments in hardware, software, and communication technologies have allowed the emergence of Internet-connected sensory devices that provide observation and data measurement from the physical world. By 2020, it is estimated that the total number of Internet-connected devices being used will be between 25-50 billion. As the numbers grow and technologies become more mature, the volume of data published will increase. Internet-connected devices technology, referred to as Internet of Things (IoT), continues to extend the current Internet by providing connectivity and interaction between the physical and cyber worlds. In addition to increased volume, the IoT generates Big Data characterized by velocity in terms of time and location dependency, with a variety of multiple modalities and varying data quality. Intelligent processing and analysis of this Big Data is the key to developing smart IoT applications. This article assesses the different machine learning methods that deal with the challenges in IoT data by considering smart cities as the main use case. The key contribution of this study is presentation of a taxonomy of machine learning algorithms explaining how different techniques are applied to the data in order to extract higher level information. The potential and challenges of machine learning for IoT data analytics will also be discussed. A use case of applying Support Vector Machine (SVM) on Aarhus Smart City traffic data is presented for a more detailed exploration.

8. Conclusions

IoT consists of a vast number of devices with varieties that are connected to 845 each other and transmit huge amounts of data. The Smart City is one of the most important applications of IoT and provides different services in domains like energy, mobility, and urban planning. These services can be enhanced and optimized by analyzing the smart data collected from these areas. In order to extract knowledge from collected data, many data analytic algorithms can be 850 applied. Choosing a proper algorithm for specific IoT and Smart City application is an important issue. In this article, many IoT data analytic studies are reviewed to address this issue. Here three facts should be considered in applying data analytic algorithms to smart data. The first fact is that different applications in IoT and smart cities have their characteristics as the number of devices 855 and types of the data that they generate; the second fact is that the generated data have specific features that should be realized. The third fact is that the taxonomy of the algorithms is another important point in applying data analysis to smart data. The findings in this article make the choice of proper algorithm for a particular problem easy. The analytic algorithms are of eight categories, 860 described in detail. This is followed by reviewing application specifics of Smart City use cases. The data characteristics and quality of smart data are described in detail. In the discussion section, how the data characteristics and application specifics can lead to choosing a proper data analytic algorithms is reviewed. In the future trend section the recent issues and the future path for research in the 865 field of smart data analytics are discussed.