Since their introduction, FPGAs can be seen in more and more different fields of applications. The key advantage is the combination of software-like flexibility with the performance otherwise common to hardware. Nevertheless, every application field introduces special requirements to the used computational architecture. This paper provides an overview of the different topics FPGAs have been used for in the last 15 years of research and why they have been chosen over other processing units like e.g. CPUs.

Survey of FPGA applications in the period 2000 – 2015 (Technical Report)

Convenience has become an important indicator of e-commerce systems success. Based on the information systems management and marketing literature, this study explores how customer convenience in using functions and services affects e-commerce systems success. It proposes and analyzes a re-specified ecommerce system model based on the updated DeLone and McLean Information Systems Success Model with a new variable, e-commerce/electronic service convenience. The proposed model re-specifies and validates e-commerce systems success where continuance intention is proposed as a dependent variable and its relationship with independent variables such as information quality, system quality, e-service convenience, perceived usefulness and satisfaction are discussed. Partial least squares structural equation modeling technique is employed to analyze data collected by 210 users of business-to-consumer e-commerce systems in Taiwan. Findings indicate that continuance intention was found to be influenced by both satisfaction and perceived usefulness, which were found to be significant precursors of information quality, system quality, and e-service convenience. These results strongly support our contention that e-service convenience is an important factor affecting e-commerce systems success. They also offer practitioners and managers deeper insights into successful e-commerce systems implementation as well as aid researchers interested in testing related theories.

E-SERVCON and E-Commerce Success: Applying the DeLone & McLean Model

Cloud Computing is an increasingly important worldwide development in business service provision. The business benefits of Cloud Computing usage include reduced IT overhead costs, greater flexibility of services, reduced TCO (Total Cost of Ownership), on-demand services, and improved productivity. As a result, Small and Medium-Sized Enterprises (SMEs) are increasingly adopting Cloud Computing technology because of these perceived benefits. The most economical deployment model in Cloud Computing is called the Public Cloud, which is especially suitable for SMEs because it provides almost immediate access to hardware resources and reduces their need to purchase an array of advanced hardware and software applications. The changes experienced in Cloud Computing adoption over the past decade are unprecedented and have raised important issues with regard to privacy, security, trust, and reliability. This chapter presents a conceptual model for Cloud Computing adoption by SMEs in Australia.

/pdf/a-conceptual-model-for-cloud-computing-adoption-by-smes-in-587yj6cved.pdf

A Conceptual Model for Cloud Computing Adoption by SMEs in Australia

Precise classification and detection of (distorted and normal) traffic signs in real-time is one of the non-trivial requirements for safe autonomous driving. The state-of-the-art convolutional neural networks (CNNs) for traffic sign detection though accurate are resource-hungry due to their inherent structure with massive networks with millions of full-precision parameters making them infeasible for low-end FPGA platforms leading to higher implementation costs. The existing works employing low-precision bits and similar techniques though hardware friendly leads to degradation in accuracy. In this work, we propose a resource-efficient CNN (ResCoNN) architecture with a small number of weights (only 60,000 compared to a few million in state-of-the-art CNNs) and employ for traffic sign detection and classification. For increased efficiency, the network takes advantage of binary weights and integer activations, rather than employing complex computations like Batch Normalization and Exponential Linear Units. ResCoNN achieves a classification accuracy of > 96% on real-world images at a framerate of 36fps on a Zynq SoC (xc7z020clg484-1) with 90% reduced weights compared to state-of-the-art CNNs.

ResCoNN: Resource-Efficient FPGA-Accelerated CNN for Traffic Sign Classification

This chapter brings the reader’s attention to understanding how technologies are aiding education with a focus on mobile technologies. In the early sections of this chapter, mobile technologies are explained briefly along with their significance to education. Implications for all involved in the education process using these technologies are then discussed. A pedagogical framework for mobile learning is then introduced along with standard theories commonly used, such as the transactional distance theory. Technological limitations and considerations are discussed to highlight future measures when designing these technologies specifically for educational purposes. Examples of mobile technology implementations in current education stages are then presented, such as mobile technology uses in higher education along with technologies used for early learners. Finally, the main objective of this chapter is presented to discuss the future of mobile technologies thoroughly, including assumptions of how these technologies will be part of everyday life for future learners.

Mobile Wireless Technologies Application in Education

This paper describes an efficient FPGA based hardware design for different image processing, enhancement, and filtering algorithms. FPGAs are often used as implementation platforms for real-time image processing applications because their structure is able to exploit spatial and temporal parallelism. The approach used is a windowing operator technique to traverse the pixels of an image, and apply the filters to them. As image sizes bit depth grow larger, software becomes less useful and real-time hardware systems are needed to take their place. The results are obtained for image size of 585×450, but the approach discussed can be used for images of any size, as long as the FPGA memory will hold it. The implementation was created with the Xilinx Spartan-6 FPGA on a Nexys3 board in mind.

Implementing image processing algorithms in FPGA hardware

This paper presents efficient low-power compact hardware designs for common image processing functions including the median filter, smoothing filter, motion blurring, emboss filter, sharpening, Sobel, Roberts, and Canny edge detection. The designs were described in Verilog HDL. Xilinx ISE design suite was used for code simulation, synthesis, implementation, and chip programming. The designs were all evaluated in terms of speed, area number of LUTs and registers, and power consumption. Post placement and routing Post-PAR results show that they need very small area and consume very little power while achieving good frame per second rate even for HDTV high resolution frames. This makes them suitable for real-time applications with stringent area and power budgets.

Mohammad I. Alali

Papers

Implementing image processing algorithms in FPGA hardware

Efficient Low-Power Compact Hardware Units for Real-Time Image Processing