Browsing by Subject "Embedded systems"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Compressed convolutional neural network for autonomous systems
    (2018-12) Pathak, Durvesh; El-Sharkawy, Mohamed; Rizkalla, Maher; King, Brian
    The word “Perception” seems to be intuitive and maybe the most straightforward problem for the human brain because as a child we have been trained to classify images, detect objects, but for computers, it can be a daunting task. Giving intuition and reasoning to a computer which has mere capabilities to accept commands and process those commands is a big challenge. However, recent leaps in hardware development, sophisticated software frameworks, and mathematical techniques have made it a little less daunting if not easy. There are various applications built around to the concept of “Perception”. These applications require substantial computational resources, expensive hardware, and some sophisticated software frameworks. Building an application for perception for the embedded system is an entirely different ballgame. Embedded system is a culmination of hardware, software and peripherals developed for specific tasks with imposed constraints on memory and power. Therefore, the applications developed should keep in mind the memory and power constraints imposed due to the nature of these systems. Before 2012, the problems related to “Perception” such as classification, object detection were solved using algorithms with manually engineered features. However, in recent years, instead of manually engineering the features, these features are learned through learning algorithms. The game-changing architecture of Convolution Neural Networks proposed in 2012 by Alex K [1], provided a tremendous momentum in the direction of pushing Neural networks for perception. This thesis is an attempt to develop a convolution neural network architecture for embedded systems, i.e. an architecture that has a small model size and competitive accuracy. Recreate state-of-the-art architectures using fire module’s concept to reduce the model size of the architecture. The proposed compact models are feasible for deployment on embedded devices such as the Bluebox 2.0. Furthermore, attempts are made to integrate the compact Convolution Neural Network with object detection pipelines.
  • Thumbnail Image
    Item
    Curriculum innovations through advancement of MEMS/NEMS and wearable devices technologies
    (2017) Shayesteh, S.; Rizkalla, M.E.; El-Sharkawy, M.; Electrical and Computer Engineering, School of Engineering and Technology
    State of the art technologies using both micro- and nano-electromechanical systems (MEMS and NEMS) and wearable and Internet of Things (IoT) devices have impacted our daily lives in applications including wearable devices and sensor technology as applied to renewable energies and health sciences, among others. Several examples are device implants, optical devices, micro and nanomachining, embedded systems and integrated nano sensor systems. The recent Electrical and Computer Engineering (ECE) and Mechanical Engineering (ME) curricula lacked inclusion of these elements within their programs. Close scrutiny to the need of local industry from engineering graduates has emphasized the motivation to develop these materials into the engineering curricula. Within the ECE curriculum, a new senior course was developed to cover MEMS/NEMS devices as well as wearable and IoT devices with Bluetooth and wireless features. The MEMS/NEMS module of the new course integrates software CAD tools and hardware implementations. It is a project-based course where students learn software for the device process, then fabricate the device in the school laboratories. The wearable and IoT devices module introduces the students to Wearable and Internet of Things systems. It covers sensors and sensor fusion, embedded processors, tools for wearable and IoT applications, and design using Bluetooth and wireless IoT systems. The new course development objectives are hands-on practice, and preparation of senior students for industrial and research careers. In addition, an introductory MEMS topic section is added in the sophomore level electrical engineering course offered to mechanical engineering students. It introduces MEMS devices employed as energy conversion devices. Based on our recent feedback, the students have favorably accepted this MEMS addition to the course. This paper details the software and hardware development elements of the new course. It also presents the assessment data for students' satisfaction for both the electrical and computer engineering (ECE), and mechanical engineering (ME) students. © American Society for Engineering Education, 2017.