Machine learning is a subset of artificial intelligence in the field of computer science that often uses statistical techniques to give computers the ability to "learn” with data, without being explicitly programmed The processes involved in machine learning are similar to that of data mining and predictive modelling. Both require searching through data to look for patterns and adjusting program actions accordingly. Many people are familiar with machine learning from shopping on the internet and being served ads related to their purchase. This happens because recommendation engines use machine learning to personalise online ad delivery in almost real time. Beyond personalised marketing, other common machine learning use cases include fraud detection, spam filtering, network security threat detection, predictive maintenance and building news feeds.
It has been observed that the autonomous vehicles (also called self-driving car, driver less car) are attracting people in this modern world. Their demands are increasing in the area of transportation and travelling facility. This paper describes how cloud and big data technology is related with self-driving car concept. This paper also presents the solution for storage of huge amount of data that is generated by sensor network of autonomous vehicles by implementing HDFS (Hadoop Distributed File System) an efficient storage mechanism of Hadoop platform. This paper describes how Apache Spark tool of Hadoop ecosystem family is used to process algorithms and maintain software’s in self-driving car. The proposed model provides fault-tolerant, highly availability of data and widely scalable system for the self-driving car.
Streaming data analysis has attracted attention in various applications like financial records, data analysis, etc. Such type of applications require continuous storage of large amount of data in data warehouse while simultaneously providing quick response time for the queries against the data that is stored in the system. The duration of fetching data varies depending on type of data required from the system. This article presents the performance estimates in terms of MySQL Partition, Hive partition-bucketing and Apache Pig framework. In this article, big data Eco systems and comparative performance analysis of frequently used data retrieval techniques such as MySQL, Hive and Pig are described. From the work presented in the article, it is concluded that the execution time for extracting data becomes very large with growth in data size, particularly in case of MySQL. As compared to MySQL, Hive and Pig takes less time and give better results.
Sentimental analysis means to check the taste, views and interest of people regarding celebrity, politicians or some other topic. Basic thing in sentimental analysis is to classify their mood in different category like positive, negative and neutral. For example Analysis of “Our Prime Minister Sh. Modi ji” how people think about him? Whether they think positive, negative or somewhere in between them. we present a comparison between two different frameworks R and Rhadoop on the basis of architecture and performance evaluation. Rhadoop is a popular statistical programming environment with HDFS, which is a standard file system for storing large data. This article includes the methodology of sentimental data Analysis using R and Rhadoop technology.