{"title":"An Analysis on Deep Learning Approach Performance in Classifying Big Data Set","authors":"Masurah Mohamad, A. Selamat, K. Salleh","doi":"10.1109/AiDAS47888.2019.8970980","DOIUrl":null,"url":null,"abstract":"Big data sets are mainly derived from social media as well as stock market exchange. It is commonly described according to its main characteristics the 3Vs, which refers to Volume, Velocity and Variety. Big data sets often contributed to difficulties faced by the back end groups such as data analyst, system developer, programmer, and network analyst due to its complexity issue. To overcome this issue, many researchers and professionals have proposed and initiated various solutions, for instance; algorithm, software, hardware and framework related to big data. One beneficial and popularly known approach in dealing with big data is deep learning. It is an extension of neural network that is able to analyze huge data sets without assistance from any parameterization methods. To make use of this advantage, this paper aimed to evaluate the capability of deep learning in analyzing big data sets. Several data sets were selected and support vector machine (SVM) was chosen as a benchmark method for the experimental work. The results obtained revealed that deep learning has outperformed SVM in classifying big data set. As a conclusion, deep learning can be categorized as one of the best machine learning approaches to be used in decision analysis process. It can also be used as an alternative approach to other traditional approaches such as Naive Bayes or SVM which require more data processing phases.","PeriodicalId":227508,"journal":{"name":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AiDAS47888.2019.8970980","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Big data sets are mainly derived from social media as well as stock market exchange. It is commonly described according to its main characteristics the 3Vs, which refers to Volume, Velocity and Variety. Big data sets often contributed to difficulties faced by the back end groups such as data analyst, system developer, programmer, and network analyst due to its complexity issue. To overcome this issue, many researchers and professionals have proposed and initiated various solutions, for instance; algorithm, software, hardware and framework related to big data. One beneficial and popularly known approach in dealing with big data is deep learning. It is an extension of neural network that is able to analyze huge data sets without assistance from any parameterization methods. To make use of this advantage, this paper aimed to evaluate the capability of deep learning in analyzing big data sets. Several data sets were selected and support vector machine (SVM) was chosen as a benchmark method for the experimental work. The results obtained revealed that deep learning has outperformed SVM in classifying big data set. As a conclusion, deep learning can be categorized as one of the best machine learning approaches to be used in decision analysis process. It can also be used as an alternative approach to other traditional approaches such as Naive Bayes or SVM which require more data processing phases.