Search

Fog computing is defined as the distribution of computing resources between the data devices and the cloud or any other data centre in a distributed computing infrastructure or process. This paper briefly reviews the various definitions, applications, architecture and fog simulators proposed by researchers over the years. In this paper, a comparison table is presented which highlights the key features of simulators available like FogtorchII, iFogSim, Fogbus, MyiFogSim etc. [ABSTRACT FROM AUTHOR]

The purpose of this study is to understand public awareness of cybersecurity-related issues and discussions during the COVID-19 pandemic. Employees and confidential organizational data are vulnerable to cyber-attacks as a result of the pandemic, which has raised concerns about cyber security about the new normal of working from home. The public's main sentiments and aspects related to cyber security concerns have been mined from tweets on the microblogging social media website Twitter. Sentiment Analysis and Topic Modeling techniques have been applied to understand the perspectives, emotions, and themes discussed by people. The analysis reveals people are becoming more aware of cybercrime-related concerns and are more positive than negative in combating the challenge of cybercrime. The paper also highlights the main themes revealed by Topic Modeling. [ABSTRACT FROM AUTHOR]

Data analysis and processing is playing an important role because of the large amount of data generated through various sources of big data. It is an important component in big data-based applications. Data qualities are the main concern in the data acquisition, transformation and data pre-processing under big data applications. Data pre-processing is required because of inconsistent, noisy and incomplete data generation in big data applications. Data analysis basically encompasses different methods and a function applicable to data's to detect characteristics such as data type, size, format, patterns and so on. Based on data format, it's easy to identify data qualities for further use in various applications. Moreover, data analysis and processing includes various steps such as data qualities identification, statistical analysis of data, defining modeling, and hypothetical testing of model and result from analysis. Raw data is unused data and required analysis, filtering, and processing in any system. This paper deals with the analysis and processing aspects of raw data and cleaned data in big data applications. This paper also deals with data cleaning and its implementation concepts. [ABSTRACT FROM AUTHOR]

Big Data Analytics is considered to be the key disruptive technology of the decade, and is revolutionizing the industries like never before with its ubiquitous applicability. Though the term "Big Data" gained more traction since 2011 after the McKinsey Report [1], some business models have been generating huge volumes of data for several decades. Some prominent examples include the Government [2] and Private [3] Meteorological Departments forecasting weather on the basis of Satellite Imagery [4] and the Logistics industry working with Geospatial Data [5]. There has been a significant boost to the efficiency of operations and the accuracy of results in both sectors after the advent of Big Data Analytics. This paper examined the Geolocation Data provided by Google based on the Location Service API [6], and suggested different ways to preprocess and visualize the data for a business analysis later. The data had been taken from the operational fleet of a leading logistics service provider in India and a small subset has been analyzed to assess the suitability of the application of this paper in a general purpose manner. This study is a part of research[7] on applications of IoT and Big Data Analytics in the supply chain management being conducted by the authors, but can be used independently in other applications as well. [ABSTRACT FROM AUTHOR]

According to problems existing in the process of university audit informatization, the internal audit framework based on big data is analyzed in this paper. Audit data processing and analysis technology of government procurement in universities based on big data are elaborated. Analysis models of the government procurement audit that highlight the association analysis are established, and through the government procurement audit data, the validity of the models is verified. The researches in the paper can provide an important reference for auditing department, and also can promote the improvement of government procurement system and the level of management authority. [ABSTRACT FROM AUTHOR]

In today's age, where data is of prime importance and rate at which data generated and sources of data generation is quite huge. The attacks on the data have increased manifold due to which its security is of prime importance. The traditional defense mechanisms are proving to be inadequate. In this paper, a new method to analyses network logs using R and Big data technologies is introduced. The approach detects fraudulent ip address in the network logs based on a set of conditions using pig scripting language. The results of using this method to detect the attack on the dataset is also presented. [ABSTRACT FROM AUTHOR]

With the increasing importance of the internet and computers in the modern world, the task of its maintenance and protection from the threats posed by malicious software has become incredibly important. Malwares interfere with the regular working operations of other files and are responsible for corruption and leakage of private data to the outside world. The overall purpose of this research was to handle this exponentially growing threat to information technology and find a robust machine learning model required for the correct detection of malware. A more efficient and real-time working model is required for detection. The aim of this paper is to provide a concise analysis of malware detection methods using machine learning (ML) models having high detection rates, that have been proposed for the past few years. As the result of our analysis we found that the detection techniques can be divided into three sections on the basis of analysis carried out for feature study viz. Static, Dynamic and Hybrid. Classification algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Trees (DT), Naïve Bayes (NB), Neural Networks (NN), and many others were used for classification purpose. Some of the ML models have also combined big data, data mining and deep learning algorithms to achieve high accuracy rates. We concluded that ML methods have proven to give better results than the old signature-based or heuristics-based detection techniques and have high possibilities of further development. [ABSTRACT FROM AUTHOR]

Today we are living with the extensive volume of information which is developing at a very fast pace. Clustering is the process of group similar kinds of information. The serial k-means clustering method takes a large amount of computational time when it is applied to enormous data sets which are large in size of tera and petabyte. In this paper, we evaluated the performance of the K-means algorithm in different ways like K-mean simple (using java codes on MapReduce), K-means (using java codes on MapReduce) with IEC (Initial Equidistant Centres), K-mean on Mahout (using Machine learning library) and K-mean on Spark (Machine learning library) on static IP address data sets over the MapReduce framework. In addition to this we also compare the K-mean simple and K-mean (IEC) on different iteration level. Outcome shows on the better performance on the basis of time on different infrastructure and it also defines the behaviour of K-means algorithms on the basis of centroids and different iteration levels. [ABSTRACT FROM AUTHOR]

In cloud environment, big data analytics is a very innovative idea;Big data is defined as a very huge quantity of data. To extract meaning full value from it we need different technologies for analysis of the data. Big data Analytic is used to study pattern of historical data and the effect of changes of different parameters. Rainfall Forecasting has been a standout amongst the most intriguing and captivating space and it assumes a noteworthy part in meteorology and daily human life. Rainfall forecasting is used to estimate the probability of whether it will rain or not. Rainfall situation is the state of atmosphere at a given time in terms of different parameter like temperature, humidity and wind speed. Forecasting of rainfall is important to facilitate preparing for the finest and the nastiest of the climate. India is agrarian country so it is essential to know in advance about climate. This paper presents big data analytics for Rainfall forecasting and studies the advantage of using it. The algorithm which is used in this project is Time Series. The intention of time series analysis is generally in two ways, one is to recognize or representation the stochastic mechanisms that gives rise to an observed series and second is to predict or forecast the future value of an arrangement in light of the historical backdrop of that arrangement. Forecasts are prepared for new data when the actual result may not be known until some future date. What's to come is being anticipated, yet all earlier perceptions are quite often treated similarly. [ABSTRACT FROM AUTHOR]

Storage density of the traditional cloud storage system is not big and the comprehensive storage efficiency is low. When the large amount of data increases dramatically, the storage efficiency of the system would be decreased seriously. Therefore, with the development of cloud storage technology, an application of Markov Decision Process in Scheduling Strategy on cloud storage (MDPSS) is proposed in this paper. MDPSS can predict periodically in stages by using the steady Markov decision process and select the optimal storage node easily. By scheduling the data to the optimal node in real time, MDPSS can enhance the flexibility of the data storage and reduce the storage cost. Simulation results show that MDPSS has the ability to predict accurately when the size of the data is different. [ABSTRACT FROM AUTHOR]

Aiming at the limitation of incremental learning for the imbalanced massive data streams, this paper proposes the approach of the cost-sensitive incremental classification under the MapReduce framework for imbalanced massive data streams (CILCIDS). Firstly, this paper gives cost-sensitive concept drift detection for massive data stream under the MapReduce framework by counting the recession numbers of the pure and tolerance clusters. Secondly, we give Cost-sensitive SVM algorithm based on incremental learning. The new incremental samples can be divided into two parts, and only the samples against KKT conditions are used for the incremental learning. At last, the imbalanced massive data streams are divided under the MapReduce framework and are processed in parallel. The cost-sensitive incremental learning classification based on cloud computing platform is developed, and the weighted cost-sensitive ensemble classifier is constructed. The experiments show that the proposed incremental learning algorithm under the MapReduce framework is feasible and correct. CILCIDS has high performance by comparing to the other classification algorithms for imbalanced data streams, and can be effective to deal with unbalanced data stream with concept drift. [ABSTRACT FROM PUBLISHER]

The paper puts forward employing open source software and open standards on the cloud, and lists candidate tools and technology for collecting, analyzing and visualizing big traffic data customized as R. Finally, it designs an integrated platform as Business Intelligence (BI) and illustrates the whole idea with a prototype R and Shiny system. [ABSTRACT FROM AUTHOR]

Large-scale distributed database includes a large number of redundant data, which will lead to low correlation between the data, resulting in lower network efficiency. This paper proposes a method for optimizing redundant data classification in distributed databases. Firstly, the redundant data attributes are extracted to provide the accurate data base for the classification of redundant data. Then the optimal classification threshold is obtained according to the weight probability theory, and the redundant data classification is realized. The experimental results show that the algorithm can improve the accuracy of classification and achieve satisfactory results. [ABSTRACT FROM AUTHOR]

The current method of data mining has the problem of low accuracy. Therefore, this paper proposes a fuzzy clustering algorithm based on chaotic and dynamic variation shuffled frog leaping algorithm (SFLA). Firstly, the data association feature is denoised, and then the correlation feature is extracted by combining the denoising data. By using the fuzzy clustering algorithm based on chaotic and dynamic variation SFLA, the data are clustered to complete association feature mining of Web accessing data. Experimental results show that the algorithm can effectively improve the accuracy of data mining. [ABSTRACT FROM AUTHOR]