• Vanitha
• Nagaraj R

Nowadays, accurate and intelligent resource management by Artificial Intelligence (AI) has become the center of attention particularly in industrial applications. With the organization of AI at the edge will outstandingly enhance the computational speed and range of Internet of Things (IoT) based devices in industries. However, there is main challenge is the short battery lifetime and power hungry. A Forward Central Dynamic and Available Approach (FCDAA) was proposed for power saving and battery lifetime saving of IoT based devices in industries by adopting the running time of sensing and transmission processes in IoT-based portable devices. Moreover, a system level battery model and data reliability model were proposed for edge based IoT devices. In this paper, the FCDAA is improved by proposing Machine Learning-based Self-adaptive Joint wireless Power Transfer, Modulation and Coding technique (MLSJPTMC). In a deep learning technique called Deep Neural Network (DNN) is introduced to learn the duty-cycle and energy consumption of IoT-based portable devices. DNN consists of single input layer, multiple hidden layers, and single output layer. Finally DNN returns duty-cycle and energy consumption of IoT-based portable devices with mining error. The learned duty-cycle and energy consumption of IoT-based portable devices are used in FCDAA which enhance the performance of power and battery lifetime-aware communication in AI-based IoT devices in industrial application. The experimental results prove that the proposed MLSJPTMC technique has better performance in terms of energy consumption and energy dissipation.

Artificial Intelligence, Edge Computing, Forward Central Dynamic and Available Approach, Internet of Things, Machine Learning-based Self-adaptive Joint wireless Power Transfer, Modulation and Coding technique.

"Artificial Driven Mechanism for Edge Computing with Deep Neural Network based Industrial Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.22-28, June 2019, Available :http://www.jetir.org/papers/JETIR1907I04.pdf

"Artificial Driven Mechanism for Edge Computing with Deep Neural Network based Industrial Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp22-28, June 2019, Available at : http://www.jetir.org/papers/JETIR1907I04.pdf