Deep Learning for IoT Big Data and Streaming Analytics: A Survey

Mohammadi, Mehdi; Al-Fuqaha, Ala; Sorour, Sameh; Guizani, Mohsen

doi:10.1109/comst.2018.2844341

Cited by 1,137 publications

(580 citation statements)

References 156 publications

Supporting

Mentioning

565

Contrasting

Unclassified

Order By: Relevance

“…The ideas of online DNNs have started to attract research attention [9]. In [10], online incremental feature learning is proposed using a denoising autoencoder (DAE) [11].…”

Section: Related Workmentioning

confidence: 99%

DEVDAN: Deep evolving denoising autoencoder

et al. 2020

View full text Add to dashboard Cite

The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.

show abstract

“…The ideas of online DNNs have started to attract research attention [9]. In [10], online incremental feature learning is proposed using a denoising autoencoder (DAE) [11].…”

Section: Related Workmentioning

confidence: 99%

DEVDAN: Deep evolving denoising autoencoder

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The IoT devices are connected usually by wireless networks to an access point (AP) such as a mobile base station (BS), which acts as a gateway to the Internet where cloud servers are deployed. Moreover, edge/fog servers with limited data processing and storage capabilities as compared to the cloud servers may be deployed at the APs [3]. After the IoT devices acquire data from sensors that represent full or partial status of physical system, they need to process the data and generate control decisions for the actuators to react.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we will review the state-of-art research, and identify the model and challenges for the application of DRL in AIoT. Although there are currently several recent articles discussing on the application of machine learning in general IoT systems [3], [6], this paper focuses on a specific type of machine learning -reinforcement learning, and its application on a promising type of IoT system -AIoT.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges

Lei

Tan

Zheng

et al. 2020

IEEE Commun. Surv. Tutorials

225

View full text Add to dashboard Cite

The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices around the world, which collect and share information to reflect the status of physical world. The Autonomous Control System (ACS), on the other hand, performs control functions on the physical systems without external intervention over an extended period of time. The integration of IoT and ACS results in a new concept -autonomous IoT (AIoT). The sensors collect information on the system status, based on which intelligent agents in IoT devices as well as Edge/Fog/Cloud servers make control decisions for the actuators to react. In order to achieve autonomy, a promising method is for the intelligent agents to leverage the techniques in the field of artificial intelligence, especially reinforcement learning (RL) and deep reinforcement learning (DRL) for decision making. In this paper, we first provide comprehensive survey of the state-of-art research, and then propose a general model for the applications of RL/DRL in AIoT. Finally, the challenges and open issues for future research are identified.

show abstract

“…Some examples of these applications are mobile asset tracking, micro-location, secure communication, and environment sensing [3,4,5]. With the emergence of IoT development, large volumes of data are being generated by IoT devices every day [6]. This growth shows the need for dedicated storage and more processing capacity, which resulted in the introduction of cloud computing.…”

Section: Introductionmentioning

confidence: 99%

A scalable IoT-fog framework for urban sound sensing

Baucas

Spachos

2020

Computer Communications

View full text Add to dashboard Cite

Internet of Things (IoT) is a system of interrelated devices that can be used to allow large-scale collection and analysis of data. However, as it grew, IoT networks were not capable of managing the data from these services. As a result, cloud computing was introduced to address the need for datacentres for IoT networks. As the technology evolved, the demand for a proper means of supporting and managing crowdsensing and real-time data increased, and cloud servers could no longer keep up with the large volumes of incoming data. This demand brought rise to fog computing. It became an extension to the cloud and allowed resources to be allocated around the network effectively. Its integration to IoT reduced the strain towards the cloud servers. However, issues in high power consumption at the end device and data management constraints surfaced. This paper proposes two approaches to alleviate these issues to keep fog computing remain as a reliable option for IoT-related applications. We created an IoT-based sensing framework that used an urban sound classification model. Through active low and high power states and resource reallocation, we created a network configuration. We tested this configuration against IoT frameworks that use the default fog and cloud setups. The results improved the framework's end device power consumption and server latency. Overall, with the proposed framework, fog computing was proven to be capable of supporting a scalable IoT framework for urban sound sensing.

show abstract

Deep Learning for IoT Big Data and Streaming Analytics: A Survey

Cited by 1,137 publications

References 156 publications

DEVDAN: Deep evolving denoising autoencoder

DEVDAN: Deep evolving denoising autoencoder

Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges

A scalable IoT-fog framework for urban sound sensing

Contact Info

Product

Resources

About