|
| Citation | Method | Description | RQ1 | RQ2 | RQ3 |
|
| [19] | Support vector machine for classifications of biomedical signal on the platform of IoT | The authors proposed an approach for observing the signal using the digital signal processor and then measured the heart rate, blood oxygen saturation, and blood pressure. SVM is used for classification purpose, and it showed the data into unhealthy, healthy, and very unhealthy and described the accuracy of prediction classification. | | √ | √ |
|
| [20] | Treatments of hypertension based on big data using machine learning (ML) | Application of ML algorithms for big data in achieving insights into the management of hypertension disease. The decision tree and neural networks are used as ML techniques to identify the factors to contribute in hypertension drug treatment. | | √ | √ |
|
| [21] | Big data analytics and data mining for predicting the heart disease | Various technologies related to data mining for the disease of heart are discussed. These techniques can help in early prediction of heart disease. Some of these techniques are classification involving decision tree, Naïve Bayes, genetic algorithm, neural network, AI, and clustering algorithms such as support vector machine and KNN. The proposed review presents details of the available prediction models from the year 2004 to 2016 which uses data mining. | | √ | √ |
|
| [22] | Applications of the ML algorithm in cardiovascular medicine | The basic and potentiality of ML algorithms are described. The issues and assessments of the needs of ML algorithms in cardiovascular medicine are discussed. | | √ | √ |
|
| [23] | Study on comparisons of different ML classifiers on data of medical | Comparative study of different classifiers such KNN, Naïve Bayes, SVM, NN, Gaussian mixture model, and decision tree has been done in order to achieve good performance in critical prediction of cardiac arrest. This comparison was done behind the reason as a specific classifiers may or may not work very well in a particular case (dataset). | √ | √ | √ |
|
| [24] | ML for bioinformatics | Bioinformatics is classified into voluminous, incremental database, and techniques of composite data analytics. These datasets such as DNA and RNA contain huge information which is termed as big data.
Techniques of ML are used for extracting information from these datasets. | | √ | √ |
|
| [25] | Techniques of unsupervised machine learning | The data of Facebook walls of 153 different organizations were analysed to extract information about the performances and engagement of the user based on unsupervised techniques of ML | | √ | √ |
|
| [22, 26–30] | Deep learning and machine learning | The two-fold model of big data is presented for healthcare. Firstly, they presented the issues in the existing mobile healthcare system, while in the second phase mHealth 2.0, they proposed techniques of ML and deep neural networks for the processing of big data and information retrieving purpose that ensure the efficiency, time saving, data integrity, and manageable solution for making the healthcare green. The techniques have applications in the intensive care unit for essential health monitoring of the patients. | | √ | √ |
|
| [27] | Apache Spark | The authors presented the Apache Spark deployed in cloud primarily focuses on applying technique of ML for predicting health status of the patients based on the tweets | √ | √ | √ |
|
| [31] | Healthcare big data security through machine learning | The study proposed an integrated technique based on masking encryption, granular access control, activity monitoring, dynamic data encryption, and models of endpoint validation. The proposed system results by providing an efficient diagnostic system for disease in the healthcare-based big data system. | √ | √ | √ |
|
| [32] | Application of the deep learning network in left ventricular volume prediction in cardiac MRI | The authors developed left ventricular volume prediction approach without segmentation by deep learning technology and the data set form large-scale cardiac MRI from the second annual data science bowl in 2016. | | √ | √ |
|
| [33] | Applications of machine learning and analytical hierarchy process for risk assessment | The authors presented multicriteria decision methods and machine learning algorithms for assessment of risk of oil and gas pipeline defects | | √ | √ |
|
| [34] | A metaheuristic approach for developing PROAFTN with the decision tree | The authors presented an MCDA-based method called PROAFTN as a fuzzy classification method. The method used data preprocessing and genetic algorithm for extracting parameters from the data. | | √ | √ |
|
| [35] | Fuzzy set theory for active learning | The concept of fuzzy set theory is presented for learning | | √ | √ |
|
| [36] | Deep learning networks for limited data | Deep networks for limited data to calculate the uncertainty are presented | √ | √ | √ |
|
| [37] | MCDS for evaluation of RES | The authors presented an approach to cover methodology developed and the tools for processing resource data | | √ | √ |
|
| [38] | Leveraging ensemble pruning for imbalanced data classification | Integrated pruning algorithm is presented for imbalanced data | √ | | √ |
|
| [39] | MCDM approach-based framework for analytics of social media | A framework based on MCDM approach is proposed for social media analytics applied on the Twitter dataset | √ | | √ |
|
| [40] | Selecting dig data reference architecture through decision support | Methodology of design science research is used. Literature review and application of comparison of the software architecture analysis method and existing big data reference architecture are found and compared. The AHP was used, and the experiment was done through the real-world use case. | √ | | √ |
|
| [41] | Big data and visual analytics | Analytics of big data is used for solving the damages caused with alarms. The method integrates technique of interdisciplinary and accomplishing analytics with evidential inference. | √ | | √ |
|
| [42] | Video trajectory analysis using unsupervised clustering and multicriteria ranking | The unsupervised trajectory method of cluster (t-cluster) is proposed. The method creates object indexes by fusing high-level interpretable features, then the clusters are fused through MCDM, and trajectories are ranked accordingly. | √ | | √ |
|
| [43] | Visual analytics and machine learning | The authors reported the existing literature by highlighting and integrating the advances in the machine learning and visual analytics | √ | √ | √ |
|
| [44] | Applications of machine learning for early detection and treatment outcome prediction | The author presented a novel model of classification for general purpose and for launching reliable predictive rules for the applications of biology and medical | | √ | √ |
|
| [45] | Resource provisioning for applications of deep learning in smart healthcare | The authors presented a technique of proximity-based provisioning of resources for avoiding delay in achieving inference results with the mobile cloud system | | √ | √ |
|
| [46] | Outlier reduction in web mining framework | The study presented reducing outlier framework in the analysis of regression with support of ordered weighted operators as MCDM | √ | | √ |
|
| [47] | Flood susceptibility mapping of arid areas based on GIS-based MCDM, southeastern Tunisia | With the help of MCDM approach (AHP), an attempt is made to prepare flood hazard susceptibility map of the Gabes regions | √ | | √ |
|
| [48] | Healthcare management and analytics of big data | The existing literature is examined for the purpose of reviewing the existing research and to derive new agenda. | √ | | √ |
|
| [49] | The multicriteria quadratic programming model for imbalanced data | The paper presented a model of multiple criteria quadratic programming by launching the cost of misclassification to the multiple criteria quadratic programming model | √ | | √ |
|
| [50] | Clustering MCDM approach for analysis of big data for evaluation of marketing strategies | The strategy of digital bank has been recommended applying big data for the banking industry of Iran. The strategy would help the banks of Iran to distinguish and analyze the needs of the customers to offer services proportionate to their manner. | √ | | √ |
|
| [51] | Subgroup discovery in MOOCs | The paper aims to describe and categorize diverse types of learners in massive open online course by the help of the subgroup discovery method based on MapReduce | √ | | √ |
|
| [52] | Applications of machine learning algorithms in treatment of oncology big data | The study presented a decision-making systems which is a part of user-centered healthcare based on predicting cancer distribution | | √ | √ |
|
| [53] | Wireless networks and analytics of big data | A survey of the literature is presented for the analytics of big data approaches in wireless networks | √ | | √ |
|
| [54] | Open-source big data cognitive computing platform | The research has developed a platform for meeting the need of user requirement analytics for the data that are structured and unstructured | √ | | √ |
|
| [55] | Floating car data and machine learning for traffic prediction | The presented approach detects the traffics in the road networks of urban area through supervised learning approach | | √ | √ |
|
| [56] | Using clustering techniques for selection of ideal cloud services | By using the approach, the user can enter the values of his/her best service and the technique of clustering; the nearest best service is selected and returned to the user. | √ | | √ |
|
| [57] | Integrating deep learning and argumentative reasoning to analyze textual content of social media | With the help of deep learning for relation-based augment mining to derive augmentative relations of support and attack | | √ | √ |
|
| [58] | EXEHDA-RR | The paper presented machine learning in preclassification of the middleware resources of EXEHDA to reduce cost of computation by MCDA algorithms | √ | √ | √ |
|
| [59] | Social AHP | The paper presented an approach for the services of citizen-to-citizen interaction through AHP by using the identified attributes and model of decision to considering the social attributes | √ | | √ |
|
| [60] | Approaches of MCDM for big data analytics capabilities and firm performance | With the help of MCDM methodology, the abilities of big data analytics and the impact of these abilities on performance of firm are explored | √ | | √ |
|
| [61] | Profitability performance in project tendering with big data and deep learning for benchmarking | The study developed a benchmark system for the evaluation of tender using big data | | √ | √ |
|
| [62] | Big data and machine learning for game-predicting | The research has developed ranking for teams and players and designed a system for the answers of managerial questions regarding the game of hockey. With the help of 18 performance measure, the player rating is done. The game of hockey is predicted using big data and machine leaning. | | √ | √ |
|
| [63] | Image classification through multicriteria active deep learning | The study proposed multicriteria active deep learning for learning strategy for deep neural networks in the classification of image | | √ | √ |
|
| [64] | Classification of multiattribute inventory through an integrated decision analytic framework of machine learning with multicriteria decision-making | Multicriteria inventory classification approach was presented through the integration of machine learning with multicriteria decision-making | | √ | √ |
|
| [65] | Decisions for marketing, supplying, and purchasing | With the help of online review, a decision support system is presented for measuring the stratification of the customer | √ | | √ |
|
| [66] | Deep learning with GIS data for prediction of automobile maintenance | The research presented an approach of GIS data into modelling of TBF, and it researched the impact on automobile TBF with the help of deep learning | | √ | √ |
|
| [67] | Deep learning and data warehouse for depth prediction of urban flood | Deep learning and data warehouse were considered for assessing the flood risk in urban areas | | √ | √ |
|
| [68] | Selecting cloud service through a hybrid multicriteria decision | MCDM approach was developed for the selection of cloud services | √ | | √ |
|
| [69] | Machine learning-based traffic offloading in fog networks | The study presented an offloading solution and shows different profiles for different proposes such as to get maximum data rate, save battery, and so on | | √ | √ |
|
| [70] | Framework of IT for identifying high-quality physicians using big data analytics | With the help of signalling theory, high-quality doctors are identifying based on the four-level model | √ | | √ |
|
| [71] | Analysis of microarray leukemia data using an efficient MapReduce-based KNN | The study presented an approach by using framework of Hadoop for classification of microarray data. The KNN classifier was used for the classification purpose of data. | | √ | √ |
|
| [72] | Combining CNN streams of RGB-D and skeletal data for recognition of human activity | Convolution neural network-based approach is proposed for the recognition of human activity | | √ | √ |
|
| [73] | Applying machine learning to the AHP multicriteria decision-making method to asset prioritization in the context of industrial maintenance 4.0 | With the help of machine learning algorithms and relevance analysis of attribute to process the event log failure of components of industrial machine | √ | | √ |
|
| [74] | Amended fused TOPSIS-VIKOR for classification | The study presented a novel classification ATOVIC based on fused VIKOR and TOPSIS | √ | | √ |
|
| [75] | Machine learning models, epistemic set-valued data, and generalized loss functions | The research aim is to study the problem where the goal is to identify optimal model to specific criteria in supervised and regression classification problems | | √ | √ |
|
| [76] | Framework for modelling of drug electrochemical removal from wastewater based on data mining algorithms, scatter interpolation method, and multicriteria decision analysis | The study presented a framework for modelling of removal of drug from wastewater. With the help of data mining algorithms, ciprofloxacin electrochemical removal modelling is done and MCDA is developed for ranking the algorithm of data mining. | √ | | √ |
|
| [77] | Feature selection based on multicriteria on cost-sensitive data with missing values | An evaluation system based on multicriteria is proposed for evaluating features from diverse viewpoints | √ | | √ |
|
| [78] | Frameworks of ML and data mining for prediction of drug response in cancer | The study gives an overview of the supervised and unsupervised algorithms used in the prediction of drug response, the strategies applied for designing these algorithms into functional models, data resources for feeding to frameworks, and challenges for maximizing the performance of the models | | √ | √ |
|
| [79] | Data fusion and machine learning for industrial prognosis | The study overviewed the literature in data fusion and analysis for industrial prognosis | | √ | √ |
|
| [80] | A supervised machine learning approach to data-driven simulation | With the help of data analytics, the risk profiles of supplier performance based on uncertainty are analysed | | √ | √ |
|
| [81] | Machine learning model-based favourite data to analyze asymmetric competition | The study presented an approach for analysis of asymmetric competition based on favourite data with the help of machine learning algorithms | | √ | √ |
|
| [82] | Machine learning powered software for accurate prediction of biogas production | The study presented machine learning approaches for biogas production data from projects of China | | √ | √ |
|
