Extending the SVM integration with case based restarting GA to predict solar flare. - In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), ISBN 978-1-5386-1645-1, (2017), S. 1994-1999
The world and human life can be had serious impact by Unusual high solar flare. In particular, serious problems may be caused by destroy satellites, damage electric power plants due to it. Therefore, it is desirable to predict sun flare peaks. However, such prediction is difficult and often inaccurate. In previous work, we used a Support Vector Machine (SVM) as a machine learning technique to predict the sun flare intensity based on data of the past. Later, we extended this SVM by a Case Based Genetic Algorithm, because such prediction turned out to be a combinatorial challenge of patterns. Since GAs are known for a tendency to fall into local optima with no further improvement, we developed a strategy of increasing the mutation rate and/or introduced restarts, whenever such stagnation occurred. The focus of the present paper is a further extension by a technology called UFCORIN along with experimental work to estimate optimal parameters.
https://doi.org/10.1109/SMC.2017.8122911
Evaluation of a classification method for MR image segmentation. - In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), ISBN 978-1-5386-1645-1, (2017), S. 1581-1586
The paper introduces a proposal for an automated magnetic resonance (MR) image segmentation called Case-Based Genetic Algorithm Location-Dependent Image Classification (CBGA-LDIC) and presents its evaluation results. This method finds an appropriate cell set towards efficient image segmentation. It uses location-dependent image classification (LDIC), which is integrated by genetic algorithm (GA) combined with case based reasoning (CB). LDIC is a local heuristic, which defines multiple location-dependent classifiers. Each classifier is trained by Gaussian mixture model. CBGA-LDIC decomposes the whole image into some cells, makes a set of cells, and then trains classifiers. The method is applied to knee bones, beca0use these bone formations are similar in their location. Therefore, good combinations of cells are useful and stored in case bases. To show, that this method produces better results that other ones and to find optimal parameters, some experiments have been performed and their results are presented in this paper.
https://doi.org/10.1109/SMC.2017.8122840
Context respectful counseling agent integrated with robot nodding for dialog promotion. - In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), ISBN 978-1-5386-1645-1, (2017), S. 1540-1545
Nowadays, a lot of IT personnel have psychological distress. Meanwhile, counselors to help them are lack in number. To solve the problem, we proposed a counseling agent (CA) called CRECA (context respectful counseling agent). CRECA listens to clients and promotes their reflection context respectfully namely in a context preserving way. This agent can be enhanced using a body language called "unazuki" in Japanese, a kind of "nodding" to greatly promote dialogue, often accompanying "un-un" (meaning "exactly") of Japanese onomatopoeia. This body language is expected to significantly help represent empathy or entire approval. In this paper, the agent is integrated with such a "unazuki" or "dialog promotion nodding" robot to continue the conversation naturally or context respectfully towards clients' further reflection. To realize such "unazuki", the robot nods twice at each end of dialog sentence input by clients. The experimental evaluation proves such nodding is effective in counseling.
https://doi.org/10.1109/SMC.2017.8122833
Sex mediates the effects of high-definition transcranial direct current stimulation on "Mind-Reading". - In: Neuroscience, ISSN 1873-7544, Bd. 366 (2017), S. 84-94
https://doi.org/10.1016/j.neuroscience.2017.10.005
Prospects for constructing remote laboratories for the study of cognitive systems. - In: The crossing point of intelligent data aquisition & advanced computing systems and east & west scientists, ISBN 978-1-5386-0697-1, (2017), S. 965-968
https://doi.org/10.1109/IDAACS.2017.8095230
Privacy-preserving spatiotemporal multicast for mobile information services. - Ilmenau : Universitätsbibliothek, 2017. - 1 Online-Ressource (233 Seiten)
Technische Universität Ilmenau, Dissertation 2017
Mobilgeräte bilden heute die Grundlage allgegenwärtiger Informationsdienste. Während der sogenannte geografische Multicast (Geocast) hier bereits ausführlich erforscht worden ist, so bezieht sich dieser nur auf Geräte, welche sich aktuell innerhalb einer geografischen Zielregion befinden. Diese Arbeit erweitert dieses Konzept durch einen räumlich-zeitlichen Multicast, welcher sich informell als "Geocast in die Vergangenheit" beschreiben lässt. Dabei wird die Zustellung einer Nachricht an alle Nutzer betrachtet, die sich in der Vergangenheit an einem bestimmten Ort aufgehalten haben. Während eine Vielzahl von Anwendungen für dieses Konzept denkbar ist, so ergeben sich hier mehrere Herausforderungen. Um Nachrichten an ehemalige Besucher eines Ortes senden zu können, müsste ein räumlich-zeitlicher Multicast-Dienst die Bewegungen aller Nutzer vollständig erfassen. Aus Gründen des Datenschutzes ist das zentralisierte Sammeln solch sensibler personenbezogener Daten jedoch nicht wünschenswert. Diese Arbeit befasst sich daher insbesondere mit dem Schutz der Privatsphäre von Nutzern eines solchen Dienstes. Zur Entwicklung eines räumlich-zeitlichen Multicast-Dienstes erörtert diese Arbeit zunächst mögliche Anwendungen. Darauf aufbauend werden funktionale, nicht-funktionale, sowie Sicherheits- und Privatsphäre-relevante Anforderungen definiert. Diese bilden die Grundlage einer umfangreichen Literaturrecherche relevanter Realisierungstechniken. Der vielversprechendste Ansatz basiert hierbei auf der Hinterlegung von Nachrichten in sogenannten Rendezvous Points. Vereinfacht betrachtet stellen diese "anonyme Briefkästen" für bestimmte räumlich-zeitliche Regionen dar. Nachrichten werden in diesen so hinterlegt, dass legitime Empfänger sie dort später abholen können. Der Schutz der Nutzer-Privatsphäre entspricht dann der Verschleierung der Zuständigkeiten von Rendezvous Points für verschiedene räumlich-zeitliche Regionen. Diese Arbeit schlägt zwei Ansätze vor: CSTM, welches kryptografische Hashfunktionen nutzt, sowie OSTM, welches ordnungserhaltende Verschlüsselung in einem CAN Overlay einsetzt. Beide Optionen werden detailliert analytisch sowie empirisch bezüglich ihrer Diensteigenschaften untersucht und verglichen. Dabei zeigt sich, dass OSTM vorteilhaftere Leistungseigenschaften besitzt, während CSTM einen besseren Schutz der Nutzer-Privatsphäre bietet.
http://nbn-resolving.de/urn:nbn:de:gbv:ilm1-2017000497
An fUML extension simplifying executable UML models implemented for a C++ execution engine. - In: International Symposium on Model-driven Approaches for Simulation Engineering (Mod4Sim'17), ISBN 978-1-5108-3826-0, (2017), S. 46-56
Deriving architecture design variants for system optimization from design space descriptions expressed using a UML profile. - In: International Symposium on Model-driven Approaches for Simulation Engineering (Mod4Sim'17), ISBN 978-1-5108-3826-0, (2017), S. 34-45
Crack detection with an interactive and adaptive video inspection system. - In: Arbeitsgruppentagung Infrastrukturmanagement, ISBN 978-3-86446-176-7, (2017), insges. 10 S.
Improving the optical inspection of through hole resistors with additional spectral illuminations. - In: 2017 8th IEEE Annual Information, Technology, Electronics and Mobile Communication Conference (IEMCON), ISBN 978-1-5386-3371-7, (2017), S. 273-277
Through hole technology is still playing an important role in the manufacturing of electronics. Thus, there is the need for reliable and contemporary automatic optical inspection of such components. The resistor as one of the most common parts challenges the optical inspection with its colored rings encoding its resistance value. The current approach to inspecting these components is discussed and its drawbacks are shown. A new approach is presented using the comprehensive illumination options available to modern automatic optical inspection machines. To test the new method a dataset of real inspection data was collected. The applicability of the new approach is shown by training a neural classifier with the data and comparing it to the formerly used method.
https://doi.org/10.1109/IEMCON.2017.8117218