No abstract

Unmanned Aerial Vehicles (UAVs), have intrigued different people from all walks of life, because of their pervasive computing capabilities. UAV equipped with vision techniques, could be leveraged to establish navigation autonomous control for UAV itself. Also, object detection from UAV could be used to broaden the utilization of drone to provide ubiquitous surveillance and monitoring services towards military operation, urban administration and agriculture management. As the datadriven technologies evolved, machine learning algorithm, especially the deep learning approach has been intensively utilized to solve different traditional computer vision research problems. Modern Convolutional Neural Networks based object detectors could be divided into two major categories: one-stage object detector and two-stage object detector. In this study, we utilize some representative CNN based object detectors to execute the computer vision task over Stanford Drone Dataset (SDD). State-of-the-art performance has been achieved in utilizing focal loss dense detector RetinaNet based approach for object detection from UAV in a fast and accurate manner.

Deep learning has been widely recognized as a promising approach in different computer vision applications. Specifically, one-stage object detector and two-stage object detector are regarded as the most important two groups of Convolutional Neural Network based object detection methods. One-stage object detector could usually outperform two-stage object detector in speed; However, it normally trails in detection accuracy, compared with two-stage object detectors. In this study, focal loss based RetinaNet, which works as one-stage object detector, is utilized to be able to well match the speed of regular one-stage detectors and also defeat two-stage detectors in accuracy, for vehicle detection. State-of-the-art performance result has been showed on the DETRAC vehicle dataset.

Efforts are ongoing to actively engage private and public educational administrators, community leaders, non-government agencies, state and local government leaders, and other entrepreneurial ecosystems to embrace entrepreneurship. These ecosystems are expected to provide the platform where students can develop ideas that will shape and transform their future. The goal will be to create outstanding opportunities for sustainable growth. For example, the current higher education pedagogy will require taking a closer look at the unique assets of colleges and universities in order to align curricula and institutional programs with industry needs. Engineering entrepreneurship education should focus on teaching young adults, at earlier ages, about innovation and the associated challenges. Some of these challenges include sustainability, access, safety, and lack of awareness. The paper will discuss the challenges, ideas, long-term approaches as well as general insights on how institutions can integrate core entrepreneurship values into the academic curriculum.2

Purpose – Managing product life cycle data is important for achieving design excellence, product continued operational performance, customer satisfaction and sustainment. As a result, it is important to develop a sustainment simulator to transform life cycle data into actionable design metrics. Currently, there is apparent lack of technologies and tools to synthesize product life time data. The purpose of this paper is to provide a description of how a product sustainment simulator was developed using fuzzy cognitive map (FCM). As a proof of concept, and to demonstrate the utility of the simulator, an implementation example utilizing product life time data as input was demonstrated. Design/methodology/approach – The sustainment simulator was developed using visual basic. The simulation experiment was accomplished using a FCM. The Statistical Analytical Software tool was used to run structural equation model programs that provided the initial input into the FCM and the simulator. Product life data were used as input to the simulator. Findings – There is an apparent lack of technologies and tools to synthesize product life time data. This constitutes an impediment to designing the next generation of sustainable products. Modern tools, technologies and techniques must be used if the goal of removing product design and sustainment disablers is to be achieved. Product sustainment can, therefore, be achieved using the simulator. Research limitations/implications – The sustainment simulator is a tool that demonstrates in a practical way how a product life time generated data can be transformed into actionable design parameters. This paper includes analysis of a sample generated using random numbers. The lack of actual data set is primarily due to reluctance of organizations to avail the public of actual product life time data. However, this paper provides a good demonstration of how product life time data can be transformed to ensure product sustainment. Practical implications – The technique used in this research paper would be very useful to product designers, engineers and research and development teams in developing data manipulation tools to improve product operational and sustainable life cycle performance. Sustainment conscious organizations will, no doubt, benefit from a strong comparative and competitive advantage over rivals. Originality/value – Utilizing the simulator to transform product life time data into actionable design metrics through the help of an efficient decision support tool like the FCM constitutes a step in supporting product life cycle management. The outcome of this paper alerts product designers on parameters which should be taken into account when designing a new generation of a given product(s).