مقاله انگلیسی رایگان در مورد اصلاح خطای سنسور کلان داده در شبکه حسگر بی سیم – اسپرینگر 2018

 

مشخصات مقاله
انتشار مقاله سال 2018
تعداد صفحات مقاله انگلیسی 10 صفحه
هزینه دانلود مقاله انگلیسی رایگان میباشد.
منتشر شده در نشریه اسپرینگر
نوع مقاله ISI
عنوان انگلیسی مقاله WFCM based big sensor data error detection and correction in wireless sensor network
ترجمه عنوان مقاله شناسایی و اصلاح خطای سنسور کلان داده در شبکه حسگر بی سیم مبتنی بر WFCM
فرمت مقاله انگلیسی  PDF
رشته های مرتبط مهندسی فناوری اطلاعات
گرایش های مرتبط شبکه های کامپیوتری
مجله محاسبه خوشه ای – Cluster Computing
دانشگاه Department of ECE – PSN College of Engineering and Technology – India
کلمات کلیدی نقشه خرد، خوشه بندی C-means فازی وزنی، تشخیص خطا، محلی سازی خطا، کرنل SVM
کلمات کلیدی انگلیسی Map reduce, Weighted fuzzy C-means clustering, Error detection, Error localization, Kernel SVM
کد محصول E7621
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

 

بخشی از متن مقاله:
1 Introduction

The wireless sensor networks (WSN) has several independent wireless sensor nodes connected with each other to form a network. Each and every individual sensor node is capable of sensing and processing information [1]. The WSN monitors and interacts with people’s physical environment [2] and the collected data is hopped to the requested node through the gateway. With the tremendous improvement in technology where daily life starts with sharing of data, the data collected from the Sensor nodes collectively form the Big Data. Big data is a term for data sets that are so large or complex that traditional data processing application software is inadequate to deal. WSN consist of a large numbers of wireless sensor nodes dispersed in one or more base stations, where big sensor data is collected. While transforming the information in sensor network, loss of big sensor data or error may be spotted in the received data [14]. Big data challenges include capturing data, data storage, data analysis, search, sharing, transfer, visualization, querying, error detection and correction, updating and information privacy. Big sensor data has five characteristics such as volume, variety, veracity, velocity and value which are known as 5 V’s of big data. The big data is collected from several areas such as meteorology, connectomics, complex physics simulations, genomics, biological study, gene analysis and environmental research [4]. These collections can start from complex framework structures such as boundless scale sensor frameworks and relational association [9]. The big data collected from the Wireless Sensor Network is called as the big sensor data. The big sensor data can be easily corrupted and lost, due to the presence of hardware faults and inaccuracies in nodes which may occur naturally or by intrusion [6, 12]. In real time network application, the collected big data can be abnormal and errors might occur [15]. Specifically numerical data errors are set down and introduced in big data [7] But the big sensor data collected from WSN has to be clean, accurate, error free and of less loss for an efficient decision making [3]. Therefore, Big sensor data error has to be detected and corrected in an efficient way which is a challenging one [5]. For the error detection process, initially the errors are identified by error classification method. Classification can be done using several algorithms for numerical errors [13]. In Big Sensor Data, error detection often requires real time processing and storage for massive sensor data which uses the complex error model to detect the event of abnormality [10]. It deals with context of using inherently complex error models to spot and locate events of abnormalities [11]. The map reduce error detection approach is usually used in big sensor data for finding errors in data sets [8]. The defined error model will trigger the error detection process, compares the result with the previous error detection methods of sensor network systems.