A Survey on Deep Learning in Big Data

By Mehdi Gheisari, Guojun Wang, Md. Zakirul Alam Bhuiyan. 22017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), 2017

531 citations recorded by the source corpus.

Big Data means extremely huge large data sets that can be analyzed to find patterns, trends. One technique that can be used for data analysis so that able to help us find abstract patterns in Big Data is Deep Learning. If we apply Deep Learning to Big Data, we can find unknown and useful patterns that were impossible so far. With the help of Deep Learning, AI is getting smart. There is a hypothesis in this regard, the more data, the more abstract knowledge. So a handy survey of Big Data, Deep Learning and its application in Big Data is necessary. In this paper, we provide a comprehensive survey on what is Big Data, comparing methods, its research problems, and trends. Then a survey of Deep Learning, its methods, comparison of frameworks, and algorithms is presented. And at last, application of Deep Learning in Big Data, its challenges, open research problems and future trends are presented.

Subfields: Information Systems and Management, Management Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/82bbf69ede840a8604d153ff23dcd95b8e5ff317

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems and Management

In Management Information Systems

In Signal Processing

Citations in the corpus

A Survey of Human-in-the-loop for Machine Learning (2021, background): “Deep learning has seen great success in a wide variety of applications, such as natural language processing, speech recognition, medical applications, computer vision, and intelligent transportation system [1, 2, 3, 4].”
Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey (2020, background): “…the difﬁcult architectural design of deep learning models, the slow convergence of backpropagation for highly complex deep architectures, their relative lack of interpretability, or the burdensome hyperparameter tuning phase required for such models to perform optimally for a given task [153].”
Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges (2019, background): “RBMs are poised to be more efficient learning algorithms [113].”
Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to? (2019, background): “higher level of abstraction is needed to describe the hidden knowledge [76].”
Deep Learning for Time Series Forecasting: A Survey (2020, unknown): “Thus, Zhang et al. 13 reviewed emerging researches of deep-learning models, including their mathematical formulation, for big data feature learning.”
A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning (2019, result): “Gheisari et al. [18] presented that the deep learning of the Big Data analysis can produce remarkable results and helped in identifying the unknown and useful patterns with high level of abstraction which were impossible to understand.”
Review of Deep Learning Algorithms and Architectures (2019, background): “Deep learning can help with semantic indexing to enable information to be more readily accessible in search engines [14], [65].”
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, background): “Indeed, there are many survey articles to discuss various aspects of big data including not only state-of-the-art technology and platforms, but also algorithms, applications and challenges [393]–[407].”
A Review of Deep Learning Models for Time Series Prediction (2019, methodology): “5) RepresentativeDeep LearningModel-Auto-Encoder: As a discriminative method for directly learning a parametric map from input to representation, Auto-Encoder (AE) is to explicitly deﬁne a feature-extracting function, i.e., the encoder f θ , in a speciﬁc parameterized closed form [107].”
A Survey on Deep Semi-Supervised Learning (2021, background): “D EEP learning has been an active research field with abundant applications in pattern recognition [1], [2], data mining [3], statistical learning [4], computer vision [5], [6], natural language processing [7], [8], etc.”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “The era of big data is triggering wide interest in deep learning across different research disciplines [28]–[31] and a growing number of surveys and tutorials are emerging (e.”
A Novel Deep-Learning Model for Automatic Detection and Classification of Breast Cancer Using the Transfer-Learning Technique (2021, methodology): “The CNN architecture is specially modiﬁed with the 2D input-image structure [76], [77].”
Predictive Maintenance and Intelligent Sensors in Smart Factory: Review (2021, background): “In addition to the mentioned Internet of Things [75], there is a significant representation of publications focused on wearable sensor-based systems [76], deep learning [77], edge technology [78], graphene-based smart materials, blockchain, smart city, and grid.”
Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “to [54]–[59] for comprehensive discussions of DNN architectures and training strategies.”
Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review (2020, background): “On the other hand, a complex set of data can be deﬁned as a big dataset, which has a large volume, wide variety, large velocity and large veracity [38].”
A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security (2018, background): “Most of the proposed DL representations are generally for high-quality data [214].”