Auflistung nach Schlagwort "Organic Computing"
1 - 8 von 8
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAdapting Organic Computing Architectures to an Automotive Environment to Increase Safety & Security(Automotive - Safety & Security 2017 - Sicherheit und Zuverlässigkeit für automobile Informationstechnik, 2017) Lamshöft, Kevin; Altschaffel, Robert; Dittmann, JanaModern cars are very complex systems operating in a diverse environment. Today they incorporate an internal network connecting an array of actuators and sensors to ECUs (Electronic Control Units) which implement basic functions and advanced driver assistance systems. Opening these networks to outside communication channels (like Car-to-X-communication) new possibilities but also new attack vectors arise. Recent work has shown that it is possible for an attacker to infiltrate the ECU network insides a vehicle using these external communication channels. Any attack on the security of a vehicle comes implies an impact on the safety of road traffic. This paper discusses the possibilities of using architectures suggested by Organic Computing to reduce these arising security risks and therefore improve safety. A proposed architecture is implemented in a demonstrator and evaluated using different attack scenarios.
- KonferenzbeitragAveraging rewards as a first approach towards Interpolated Experience Replay(INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge), 2019) Pilar von Pilchau, WenzelReinforcement learning and especially deep reinforcement learning are research areas which are getting more and more attention. The mathematical method of interpolation is used to get information of data points in an area where only neighboring samples are known and thus seems like a good expansion for the experience replay which is a major component of a variety of deep reinforcement learning methods. Interpolated experiences stored in the experience replay could speed up learning in the early phase and reduce the overall amount of exploration needed. A first approach of averaging rewards in a setting with unstable transition function and very low exploration is implemented and shows promising results that encourage further investigation.
- KonferenzbeitragDealing with Hardware-related Disturbances in Organic Computing Systems(INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge), 2019) Görlich-Bucher, MarkusThe ability to withstand disturbances while remaining functioning in a desired way is regarded as a crucial element in the field of Organic Computing. However, current approaches to self-healing and robustness fail in considering hardware-related breakdowns. These disturbances differ from software-sided disturbances in various aspects: They persist until being repaired, therefore their removal necessitates maintenance actions performed by human repair workers. Furthermore, they may be predicted to a certain degree. In this article, we formulate a problem statement and various requirements an OC system must fulfil in order to increase its robustness against hardware-related disturbances. Furthermore, we present a working plan for a PhD project concerning the investigation of several aspects of the previously motivated problem statement.
- TextdokumentDevelopment of a Vehicle Simulator for the Evaluation of a Novel Organic Control Unit Concept(INFORMATIK 2020, 2021) Brinkschulte, MelanieNew challenges in the field of automotive systems (e.g. autonomous driving) require innovative and highly robust vehicle architectures. These are intended to increase the reliability and fault tolerance of the system and therefore realize the transition from Fail-Save to Fail-Operational behavior. Organic computing is a possible approach to achieve these goals. Based on an artificial hormone system and an artificial DNA, a novel organic control unit concept exists. In this paper we introduce an evaluation tool for this novel concept. Therefore, a simulator physically models the longitudinal and lateral dynamics of a vehicle. For an easy handling, visualization and reproducibility of experiments, an user interface and a scripting language are designed. In extensive evaluation runs the usability of the vehicle simulator is tested. Hereby, real vehicle data is used.
- TextdokumentEnhancing Resilience in IoT Networks using Organic Computing(INFORMATIK 2020, 2021) Weikert, Dominik; Steup, Christoph; Mostaghim, SanazIn this paper we present and analyse the requirements and challenges of the Task Allocation Problem for Internet-of-Things (IoT) Networks, especially Wireless Sensor Networks (WSNs). As IoT is comprised of a variety of heterogeneous devices and network configuration may change regularly due to low-power nodes failing or communication disruptions, a static allocation of tasks to individual nodes cannot be assumed. Therefore, task allocation has to be carried out and managed for every dynamic change in the network along the lifetime of the network. In dynamic task allocation, a NP-hard problem, the calculation of a new optimal allocation could quickly become a bottleneck for network performance, giving rise to the need of organic computing solutions to provide self-organised task allocation solutions for such networks.
- KonferenzbeitragKnowledge Self-Adaptive Multi-Agent Learning(INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge), 2019) Reichhuber, SimonIn this paper concepts of a starting Doctoral Dissertation are presented, discussing the question how agents constructed according to Organic Computing methodologies can autonomously identify Knowledge Sources and adapt them to their learning procedure. Achieving this, the fields of Multi-Agent Learning, Organic Computing, Transfer Learning, and Online Learning are combined to an unified architecture. The focus of the work is on the real-time evaluation of knowledge sources. In order to show the practical use case of such systems, the author presents two scenarios. The first, collaborative crawling, is an information retrieval task, hence it deals with knowledge distributed over multiple websites. Whereas the latter is designed to run in a virtual space, the second, denoted as machine park collaboration, can be implemented in industrial 4.0 fields of the real world.
- KonferenzbeitragOrganic Computing Doctoral Dissertation Colloquium 2019(INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge), 2019) Krupitzer, Christian; Tomforde, Sven
- KonferenzbeitragThe Organic Computing Doctoral Dissertation Colloquium: Status and Overview in 2019(INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge), 2019) Krupitzer, Christian; Tomforde, SvenToday, people are surrounded by smart and connected devices. Gartner Inc. estimated that 8.4 billion devices were connected in the Internet-of-Things worldwide in 2017, reaching 20.4 billion by 2020. The growing number of mobile and embedded devices in combination with the omnipresence of (wireless) network connections facilitates new applications, such as autonomous driving, ambient assisted living / smart home, or Industry 4.0. However, it requires integration of all available, highly specialised, and heterogeneous devices, ranging from embedded sensor nodes to servers in the cloud. Further, the inclusion of data streams with sensor data and web data leads to an increasing complexity in system development. Additionally, as these systems are mobile, changing environmental conditions increase the complexity even further. Organic Computing systems are able to deal with such systems and lower the complexity for their development by introducing methods for integrating adaptiveness and intelligence to computing systems. This workshops brings together PhD students from different research streams related to Organic Computing with the objective to represent the wide field of research in the domain of adaptive and intelligence systems.