| 1. |
- Axelsson, Jakob, et al.
(författare)
-
MOPED : A Mobile Open Platform for Experimental Design of Cyber-Physical Systems
- 2014
-
Ingår i: The 40th Euromicro Conference on Software Engineering and Advanced Applications SEAA 2014. - 9781479957941 ; , s. 423-430
-
Konferensbidrag (refereegranskat)abstract
- Due to the increasing importance of cyber-physical and embedded systems in industry, there is a strong demand for engineers with an updated knowledge on contemporary technology and methods in the area. This is a challenge for educators, in particular when it comes to creating hands-on experiences of real systems, due to their complexity and the fact that they are usually proprietary. Therefore, a laboratory environment that is representative of the industrial solutions is needed, with a focus on software and systems engineering issues. This paper describes such an environment, called the Mobile Open Platform for Experimental Design (MOPED). It consists of a model car chassis, equipped with a network of three control units based on standard hardware, and running the automotive software standard AUTOSAR, which consists of operating system, middleware, and application software structures. It is equipped with various sensors and actuators, and is open to extensions both in hardware and software. It also contains elements of future systems, since it allows connectivity to cloud services, development of federated embedded systems, and continuous deployment of new functionality. In this way, the platform provides a very relevant learning environment for cyber-physical systems, today and in the future.
|
|
| 2. |
- Ni, Ze, et al.
(författare)
-
Design and Implementation of a Dynamic Component Model for Federated AUTOSAR Systems
- 2014
-
Ingår i: Proceedings - Design Automation Conference, 2014. - New York, NY, USA : ACM. - 9781479930173 ; , s. Article number 2593121-
-
Konferensbidrag (refereegranskat)abstract
- The automotive industry has recently agreed upon the embedded software standard AUTOSAR, which structures an application into reusable components that can be deployed using a configuration scheme. However, this configuration takes place at design time, with no provision for dynamically installing components to reconfigure the system. In this paper, we present the design and implementation of a dynamic component model that extends AUTOSAR with the possibility to add plug-in components at runtime. This opens up for shorter deployment time for new functions; opportunities for vehicles to participate in federated embedded systems; and involvement of third-party software developers.
|
|
| 3. |
- Zhou, Guang-Quan, et al.
(författare)
-
A Single-Shot Region-Adaptive Network for Myotendinous Junction Segmentation in Muscular Ultrasound Images
- 2020
-
Ingår i: IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control. - : Institute of Electrical and Electronics Engineers (IEEE). - 0885-3010 .- 1525-8955. ; 67:12, s. 2531-2542
-
Tidskriftsartikel (refereegranskat)abstract
- Tracking the myotendinous junction (MTJ) in consecutive ultrasound images is crucial for understanding the mechanics and pathological conditions of the muscletendon unit. However, the lack of reliable and efficient identification of MTJ due to poor image quality and boundary ambiguity restricts its application in motion analysis. In recent years, with the rapid development of deep learning, the region-based convolution neural network (RCNN) has shown great potential in the field of simultaneous objection detection and instance segmentation in medical images. This article proposes a region-adaptive network (RAN) to localize MTJ region and to segment it in a single shot. Our model learns about the salient information of MTJ with the help of a composite architecture. Herein, a region-based multitask learning network explores the region containing MTJ, while a parallel end-to-end U-shaped path extracts the MTJ structure from the adaptively selected region for combating data imbalance and boundary ambiguity. By demonstrating the ultrasound images of the gastrocnemius, we showed that the RAN achieves superior segmentation performance when compared with the state-of-the-art Mask RCNN method with an average Dice score of 80.1. Our proposed method is robust and reliable for advanced muscle and tendon function examinations obtained by ultrasound imaging.
|
|
