Deep learning for intelligent IoT: Opportunities, challenges and solutions

Abstract Next-generation wireless networks have to be robust and self-sustained. Internet of things (IoT) is reshaping the technological adaptation in the daily life of human beings. IoT applications are highly diverse, and they range from critical applications like smart city, health-based industries, to industrial IoT. Machine learning (ML) techniques are integrated into IoT to make the network efficient and autonomous. Deep learning (DL) is one of the types of ML, and it is computationally complex and expensive. One of the challenges is to merge deep learning methods with IoT to overall improve the efficiency of the IoT applications. An amalgamation of these techniques, maintaining a balance between computational cost and efficiency is crucial for next-generation IoT networks. In consideration of the requirements of ML and IoT and seamless integration demands overhauling the whole communication stack from physical layer to application layer. Hence, the applications build on top of modified stack will be significantly benefited, and It also makes it easy to widely deploy the network.

[1]  Wazir Zada Khan,et al.  A deep neural networks based model for uninterrupted marine environment monitoring , 2020, Comput. Commun..

[2]  Xiaojiang Du,et al.  The enhancement of catenary image with low visibility based on multi-feature fusion network in railway industry , 2020, Comput. Commun..

[3]  Fadi Al-Turjman,et al.  Intelligence in the Internet of Medical Things era: A systematic review of current and future trends , 2020, Comput. Commun..

[4]  Byung-Seo Kim,et al.  (ReLBT): A Reinforcement learning-enabled listen before talk mechanism for LTE-LAA and Wi-Fi coexistence in IoT , 2020, Comput. Commun..

[5]  Byung-Seo Kim,et al.  Performance optimization of QoS-supported dense WLANs using machine-learning-enabled enhanced distributed channel access (MEDCA) mechanism , 2019, Neural Computing and Applications.

[6]  Yousaf Bin Zikria,et al.  Intelligent learning automata-based objective function in RPL for IoT , 2020 .

[7]  Sami Ahmed Haider,et al.  Optimization of secure wireless communications for IoT networks in the presence of eavesdroppers , 2020, Comput. Commun..

[8]  Fadi Al-Turjman,et al.  SAHCI: Scheduling Approach for Heterogeneous Content-Centric IoT Applications , 2019, IEEE Access.

[9]  Joel J. P. C. Rodrigues,et al.  Cascading handcrafted features and Convolutional Neural Network for IoT-enabled brain tumor segmentation , 2020, Comput. Commun..

[10]  Ali Kashif Bashir,et al.  Performance optimization of IoT based biological systems using deep learning , 2020, Comput. Commun..

[11]  Yousaf Bin Zikria,et al.  Data-driven intelligence in wireless networks: Issues, challenges, and solution , 2019, Trans. Emerg. Telecommun. Technol..

[12]  Muhammad Imran,et al.  Deep learning and big data technologies for IoT security , 2020, Comput. Commun..

[13]  M. Shamim Hossain,et al.  Deep learning-based intelligent face recognition in IoT-cloud environment , 2020, Comput. Commun..