Development Of Deep Learning Based Recommendation Engine For Embedded Programmer

Author

Yu Zhou, Prairie View A&M University

Date of Award

12-2019

Document Type

Dissertation - Campus Access Only

Degree Name

Doctor of Philosophy (PhD)

Degree Discipline

Electrical Engineering

Abstract

Microcontroller based embedded devices have been widely used in the Internet of Things (IoT). In the IoT, the embedded based microcontroller unit (MCU) plays an irreplaceable role because of its advantages of real-time processing and low power consumption. Many successful embedded Integrated circuits (IC) designs are still being utilized and updated at a very fast speed, which brings big trouble and challenge to the coder. In this design, a smart embedded code recommendation system is developed to assist embedded programmers to quickly search high quality embedded code segments with precise tags.

In the beginning, a largescale embedded code database was built and reorganized as a code description dataset and code content dataset. In addition, a tag correlated machine-learning-based auto code classifier was implemented to label the embedded code with precise tags. Finally, the Modular Hierarchical Convolution Neural Network (MHCNN) deep learning model was presented to achieve the dynamic recommendation level by level. The detail design of the system included the code database structure, the classifier enhancement, and the promising performances of the MHCNN model were provided. The experimental results demonstrated that the proposed dataset structure outperformed the traditional dataset; the proposed tag correlated classifier could enhance the precision of labeling, and the MHCNN model showed performance that is more promising in embedded code recommendation.

Committee Chair/Advisor

Suxia Cui

Committee Co-Chair:

Yonghui Wang

Committee Member

Richard T. Wilkins

Committee Member

Matthew O. Sadiku

Committee Member

Cajetan M. Akujuobi

Publisher

Prairie View A&M University

Rights

© 2021 Prairie View A & M University

Date of Digitization

11/25/2024

Contributing Institution

John B Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Recommended Citation

Zhou, Y. (2019). Development Of Deep Learning Based Recommendation Engine For Embedded Programmer. Retrieved from https://digitalcommons.pvamu.edu/pvamu-dissertations/68