This study was conducted based on an assumption that Spark ML package has much better performance and accuracy than Spark MLlib package in dealing with big data. The used dataset in the comparison is for bank customers transactions. The Decision tree algorithm was used with both packages to generate a model for predicting the churn probability for bank customers depending on their transactions data. Detailed comparison results were recorded and conducted that the ML package and its new DataFrame-based APIs have betterevaluating performance and predicting accuracy.

Chronic kidney disease (CKD) has become a widespread disease among people. It is related to various serious risks like cardiovascular disease, heightened risk, and end-stage renal disease, which can be feasibly avoidable by early detection and treatment of people in danger of this disease. The machine learning algorithm is a source of significant assistance for medical scientists to diagnose the disease accurately in its outset stage. Recently, Big Data platforms are integrated with machine learning algorithms to add value to healthcare. Therefore, this paper proposes hybrid machine learning techniques that include feature selection methods and machine learning classification algorithms based on big data platforms (Apache Spark) that were used to detect chronic kidney disease (CKD). The feature selection techniques, namely, Relief-F and chi-squared feature selection method, were applied to select the important features. Six machine learning classification algorithms were used in this research: decision tree (DT), logistic regression (LR), Naive Bayes (NB), Random Forest (RF), support vector machine (SVM), and Gradient-Boosted Trees (GBT Classifier) as ensemble learning algorithms. Four methods of evaluation, namely, accuracy, precision, recall, and F1-measure, were applied to validate the results. For each algorithm, the results of cross-validation and the testing results have been computed based on full features, the features selected by Relief-F, and the features selected by chi-squared feature selection method. The results showed that SVM, DT, and GBT Classifiers with the selected features had achieved the best performance at 100% accuracy. Overall, Relief-F’s selected features are better than full features and the features selected by chi-square.

No abstract

No abstract

No abstract

No abstract

Index structures are one of the main strategies for effective data access applied for indexing data. According to expansion of data, traditional indexing strategies on big data meets several challenges that lead to weak performance; they haven't abilities to handle the rapid increase of data in terms of accurate retrieval results and processing time. So, it is necessary to substitute traditional index with another efficient index structure called learned index. Learned index goes to use machine learning models to tackle such issues and achieve more enhancements of processing time and accurate results. In this research, the authors discuss different indexing strategies on big data both traditional and learned indexes, demonstrate the main features of them, perform comparison in terms of its performance, and present big data indexing challenges and solutions. Consequently, the research suggests replacing traditional indexes by dynamic index models, which lead to less processing time and more accurate results taking into consideration specification of hardware used.

Centralized big data is an emerging field that manages information in one common repository. Currently, Internet of Things (IoT) devices are increasing massively for sensing and transmitting data to the big data environment. This information is sensitive and easily traced by attackers due to the centralized data management. To address the security and privacy issues and avoid the system in a single point of failure, in this paper the researchers proposed a new model, namely, BOBS CRABID i.e. Blockchain Based Secure Centralized Big Data model using distributed computing approach. In big data, Hadoop MapReduce is one of the distributed computing approaches which handles all information in a distributed manner. The BOBS CRABID model is designed by three ideas as Multi-Factor authentication, IoT Devices Data Collection and Processing, and Optics based MapReduce for Data Clustering. In multi-factor authentication, a lightweight camellia key generation algorithm (LCKGA) is used for their authenticating all devices based on ID, IP address, MAC and PUF. These credentials are saved in Blockchain Security Entity for authentication verification. All transactions are hashed and stored in the blockchain using Keccak hash algorithm which performs better than the traditional hashing (SHA) 2. Then the researchers conducted IoT devices data collection and pre-processing using Cross Correlation and Min-Max Normalization for redundant data pruning and normalization, respectively. Finally, clustering is performed in a distributed way for optimizing the storage and scalability performance. For that MapReduce is used in which OPTICS algorithm is applied for clustering based on the data size, type of context and nature of data (sensitive or non-sensitive). In this way, data is stored in the big data environment. Experiments were conducted for the proposed BOBS CRABID model and compared with the well-known methods using Hadoop 2.7.2. The proposed BOBS-CRABID model achieves better performance in terms of throughput (increase 1500mbps), response time (reduce 150ms), energy consumption (reduce 35%), attack detection rate (increase 30%), accuracy (increase 20%), computation overhead (300 kb), and time reduce 4s).