ARM-Based Embedded System Platform and Its Portability Research

Taking ARM as the hardware platform, the embedded system is built from both hardware and software aspects with the application as the center. In the hardware design, build the hardware platform scheme, design the schematic diagram as well as PCB, complete the hardware debugging, and ensure the system hardware platform function;in the software design, optimize the three-stage pipeline structure of ARM instruction system, design the instruction set, install the embedded system on the virtual machine, build the cross-toolchain, and set up the correct NFS network file system. Finish the design of the ARM-based embedded system platform, combined with the hardware requirements of the experimental platform, transplant the powerful Uboot as the Bootloader of the system, and further transplant the Linux-2.6. 32 kernel to the system start the operation normally, and finally, build the root file to finish the study of its portability.

Telecom-Oriented Embedded Software Support Platform

This paper presents an embedded software platform used in the telecom field.The platform consists of the Virtual Operating System (VOS)layer,core layer, protection layer and module layer.It supports and simplifies upper application software of telecom systems.In addition to basic modules and functions, its instance scheduling model and distributed process communication are detailed in the paper.

A Multilayer Security Framework for Cloud Computing in Internet of Things (IoT) Domain

Cloud computing is a type of emerging computing technology that relies on shared computing resources rather than having local servers or personal devices to handle applications. It is an emerging technology that provides services over the internet: Utilizing the online services of different software. Many works have been carried out and various security frameworks relating to the security issues of cloud computing have been proposed in numerous ways. But they do not propose a quantitative approach to analyze and evaluate privacy and security in cloud computing systems. In this research, we try to introduce top security concerns of cloud computing systems, analyze the threats and propose some countermeasures for them. We use a quantitative security risk assessment model to present a multilayer security framework for the solution of the security threats of cloud computing systems. For evaluating the performance of the proposed security framework we have utilized an Own-Cloud platform using a 64-bit quad-core processor based embedded system. Own-Cloud platform is quite literally as any analytics, machine learning algorithms or signal processing techniques can be implemented using the vast variety of Python libraries built for those purposes. In addition, we have proposed two algorithms, which have been deployed in the Own-Cloud for mitigating the attacks and threats to cloud-like reply attacks, DoS/DDoS, back door attacks, Zombie, etc. Moreover, unbalanced RSA based encryption is used to reduce the risk of authentication and authorization. This framework is able to mitigate the targeted attacks satisfactorily.

End-to-End Multiview Gesture Recognition for Autonomous Car Parking System

The use of hand gestures can be the most intuitive human-machine interaction medium.The early approaches for hand gesture recognition used device-based methods.These methods use mechanical or optical sensors attached to a glove or markers,which hinder the natural human-machine communication.On the other hand,vision-based methods are less restrictive and allow for a more spontaneous communication without the need of an intermediary between human and machine.Therefore,vision gesture recognition has been a popular area of research for the past thirty years.Hand gesture recognition finds its application in many areas,particularly the automotive industry where advanced automotive human-machine interface(HMI)designers are using gesture recognition to improve driver and vehicle safety.However,technology advances go beyond active/passive safety and into convenience and comfort.In this context,one of America’s big three automakers has partnered with the Centre of Pattern Analysis and Machine Intelligence(CPAMI)at the University of Waterloo to investigate expanding their product segment through machine learning to provide an increased driver convenience and comfort with the particular application of hand gesture recognition for autonomous car parking.The present paper leverages the state-of-the-art deep learning and optimization techniques to develop a vision-based multiview dynamic hand gesture recognizer for a self-parking system.We propose a 3D-CNN gesture model architecture that we train on a publicly available hand gesture database.We apply transfer learning methods to fine-tune the pre-trained gesture model on custom-made data,which significantly improves the proposed system performance in a real world environment.We adapt the architecture of end-to-end solution to expand the state-of-the-art video classifier from a single image as input(fed by monocular camera)to a Multiview 360 feed,offered by a six cameras module.Finally,we optimize the proposed solution to work on a limited resource embedded platform(Nvidia Jetson TX2)that is used by automakers for vehicle-based features,without sacrificing the accuracy robustness and real time functionality of the system.