DigitalTC GrafenauZeitschriftenartikel
Ali Tehrani
The Choquet Kernel on the use of Regression Problem
Information Sciences, no. 08 December 2020
DOI: 10.1016/j.ins.2020.11.051
Abstract anzeigen
Recently, we have presented a new family of kernels on the basis of the discrete Choquet integral. While a naïve computation of this kernel has an exponential complexity in the number of features, we have proposed an efficient approach with computational complexity of 1. This kernel family is able to recognize dependencies between features and moreover it can be regularized through a proper selection of q-additivity. In fact, to reduce the effect of over-fitting there is an opportunity to restrict the flexibility of kernel to a lower degree. A key feature of the Choquet integral in a data-driven way is its monotonicity, however, this representation does not consider any monotonicity constraint; hence it is versatile for other applications, too. This issue is highlighted in the experimental study. In this regard, we apply the Choquet kernel for regression task and compare the performance of the proposed kernel versus state-of-the-art support kernel-based regression methods as well as random forest.
DigitalMobilTC FreyungBeitrag (Sammelband oder Tagungsband)
M. Novàk, J. Geyer, M. Prokýšek, M. Hais, S. Gril, M. Davidková, P. Doležal, Peter Hofmann, Rajan Paudyal
Construction of a Multisensor UAV System for Early Detection of Forest Pests
Advances in Intelligent Systems and Computing V, Cham, Switzerland, vol. 1293
ISBN: 978-3-030-63270-0
DigitalNachhaltigEuropan Campus Rottal-InnZeitschriftenartikel
Kueppers. M., C. Perau, M. Franken, H. Heger, Matthias Huber, M. Metzger, S. Niessen
Data-Driven Regionalization of Decarbonized Energy Systems for Reflecting Their Changing Topologies in Planning and Optimization
Energies, vol. 13, no. 16
DOI: 10.3390/en13164076
Abstract anzeigen
The decarbonization of energy systems has led to a fundamental change in their topology since generation is shifted to locations with favorable renewable conditions. In planning, this change is reflected by applying optimization models to regions within a country to optimize the distribution of generation units and to evaluate the resulting impact on the grid topology. This paper proposes a globally applicable framework to find a suitable regionalization for energy system models with a data-driven approach. Based on a global, spatially resolved database of demand, generation, and renewable profiles, hierarchical clustering with fine-tuning is performed. This regionalization approach is applied by modeling the resulting regions in an optimization model including a synthesized grid. In an exemplary case study, South Africa’s energy system is examined. The results show that the data-driven regionalization is beneficial compared to the common approach of using political regions. Furthermore, the results of a modeled 80% decarbonization until 2045 demonstrate that the integration of renewable energy sources fundamentally changes the role of regions within South Africa’s energy system. Thereby, the electricity exchange between regions is also impacted, leading to a different grid topology. Using clustered regions improves the understanding and analysis of regional transformations in the decarbonization process.
DigitalTC FreyungBeitrag (Sammelband oder Tagungsband)
M. K. Vichrová, P. Hájek, M. Kepka, Laura Fiegler, Mariann Juha, Wolfgang Dorner, R. Fiala
Current Digital Travel Guide of Peregrinus Silva Bohemica Project
Proceedings of the 2020 10th International Conference on Advanced Computer Information Technologies (ACIT) [September 6-8, 2020; Deggendorf]
DOI: 10.1109/ACIT49673.2020.9208922
Abstract anzeigen
Delivering a piece of proper and interesting information to tourists is always a challenge to deal with. It can be provided by many possible ways using traditional analogue materials (flyers, information table or paper maps) or using modern technologies such as web pages, mobile applications or an online multimedia tourist guide. One of online tourist guides is a travel guide created in Peregrinus Silva Bohemica project. This paper provides information about the final stage of such a guide from content and a technical point of view, to point out the complexity and usefulness of such a tool for tourists.
DigitalTC FreyungBeitrag (Sammelband oder Tagungsband)
M. Novàk, M. Prokýšek, P. Doležal, M. Hais, S. Gril, M. Davídková, J. Geyer, Peter Hofmann, Rajan Paudyal
Multisensor UAV System for the Forest Monitoring
Proceedings of the 2020 10th International Conference on Advanced Computer Information Technologies (ACIT) [September 6-8, 2020; Deggendorf]
DOI: 10.1109/ACIT49673.2020.9208993
Abstract anzeigen
In recent years, unmanned aerial vehicles (UAV) of various shapes, sizes and functions have been increasingly used for civilian applications in a wide range of fields. UAVs are flexible, inexpensive, with the ability to carry high resolution sensing systems. UAVs fill the gap between manned aircraft and satellite remote sensing systems. When searching for new methodologies, especially in forestry research, UAVs are a unique platform. Remote forest sensing, forest mapping, forest precise measurement, forest fire monitoring and support for intensive forest management are areas in which remote sensing is fully utilized. The advantages of remote sensing are mainly low material and operating costs, flexible space and time deployment, and high intensity data collection. In order to move remote sensing applications from the experimental phase into real deployment, it is necessary to come up with new methodologies that can be determined using UAVs.
DigitalGesundAngewandte GesundheitswissenschaftenTC FreyungBeitrag (Sammelband oder Tagungsband)
Ludwig Schiller, Manuela Wühr, Rainer Pöschl, Wolfgang Dorner
Concept for the Large Scale Deployment of Ambient Assisted Living Systems
Proceedings of the 2020 10th International Conference on Advanced Computer Information Technologies (ACIT) [September 6-8, 2020; Deggendorf]
DOI: 10.1109/ACIT49673.2020.9208911
Abstract anzeigen
This paper deals with the problem of equipping 100 households in Lower Bavarian with sensors using different interfaces and protocols. This sensor set in the households is used in the context of the research project DeinHaus 4.0 of Deggendorf Institute of Technology. This project focuses on supporting technologies to enable elderly people to live as long as possible in their own house or apartment. Therefore, a set of sensors and Ambient Assisted Living (AAL) technologies are used to build a supporting system. Furthermore, the system collects, anonymizes and stores the sensor data for further technical and social analysis.
DigitalTC GrafenauBeitrag (Sammelband oder Tagungsband)
Sebastian Wilhelm
Exploiting Home Infrastructure Data for the good: Emergency Detection by reusing existing Data Sources
[Accepted for publication]
Advances in Intelligent Systems and Computing
Abstract anzeigen
Monitoring people within their residence can enable elderly to live a self-determined life in their own home environment for a longer period of time. Therefore commonly activity profiles of the residents are created using various sensors in the house. Deviations from the typical activity profile may indicate an emergency situation. An alternative approach for monitoring people within their residence we investigates within our research is reusing existing data sources instead of installing additional sensors. In private households there are already numerous data sources such as smart meters weather station routers or voice assistants available. Intelligent algorithms can be used to evaluate this data and conclude on personal activities. This in turn allows the creation of activity profiles of the residents without using external sensor technology.This work outlines the research gap in reusing existing data sources for Human Activity Recognition (HAR) and emergency detection which we intend to fill with our further work.
DigitalTC GrafenauBeitrag (Sammelband oder Tagungsband)
Dietmar Jakob
Acceptance and Practically of Voice Assistance Systems in the everyday life of seniors: A study design
[Accepted for publication]
Advances in Intelligent Systems and Computing
Abstract anzeigen
Voice assistance systems (VAs) are becoming more popular. For Digital Natives these systems are almost part of everyday life. Does this technology also have the potential to facilitate access to digital services for persons aged 55+? Using the example of Amazon's "Echo" devices our research intends to provide a survey of the extent to which VAs are known to the target group how many elderly people own these systems and whether there are any reservations. In addition test persons will be investigated which form of interaction seems easiest for the solution of the tasks and how the operation of VAs differs from the operation of mobile devices to be learned and applied. The evaluation will include statements on socio-demographic and ethnographic aspects. Various Amazon Echo devices are installed in 20 senior households (and additionally in their family households) in order to test user acceptance and its benefits under real-world conditions.
DigitalTC GrafenauBeitrag (Sammelband oder Tagungsband)
Sebastian Wilhelm
Activity-Monitoring in Private Households for Emergency Detection: A Survey of Common Methods and Existing Disaggregable Data Sources
[Accepted for publication]
Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies
Abstract anzeigen
Ambient-Assisted Living (AAL) technologies can enable the elderly people to live a self-determined life in their own home environment instead of hospitals and retirement homes for a longer period of time. Hence AAL systems are not only used for everyday support but also for the detection of potential emergency situ- ations and for triggering notification chains. For this purpose the people are usually continuously monitored within their residents by ambient or wearable sensors to detect deviations in their daily behavior.This work surveys common used technologies for Human Activity Recognition (HAR) / Human Presence De- tection (HPD) which is the basis for emergency detection. Furthermore by examining various home automa- tion software existing data sources from the residential infrastructure are identified that would be suitable for detecting personal activities.
DigitalTC GrafenauBeitrag (Sammelband oder Tagungsband)
Sebastian Wilhelm, Dietmar Jakob, Jakob Kasbauer, Diane Ahrens
GeLaP: German Labeled Dataset for Power Consumption
[Accepted for publication]
Proceedings of the 6th International Congress on Information and Communication Technology
Abstract anzeigen
Due to the increasing spread of smart meters numerous researchers are currently working on disaggregating the power consumption data. This procedure is commonly known as Non-Intrusive Load Monitoring (NILM). However most approaches to energy disaggregation first require a labeled dataset to train these algorithms.In this paper we present a new labeled power consumption dataset that was collected in 20 private households in Germany between September 2019 and July 2020. For this purpose the total power consumption of each household was measured with a commercial available smart meter and the individual consumption data of 10 selected household appliances were collected.
DigitalAngewandte InformatikBeitrag (Sammelband oder Tagungsband)
Heribert Popp, Monica I. Ciolacu, Leon Binder
Education 4.0: IoT- und CoP-unterstützte Smarte E-Learning Prozesse
Tagungsband zum 19. E-Learning-Tag der FH JOANNEUM: Innovation & Reflexion – Henne oder Ei?
, vol. 130
Abstract anzeigen
Studierende erleben im Lernmanagementsystem (LMS) „Moodle“ smarte E-Learning Prozesse in Mathematik- und Wissensmanagement-Kursen. „Smartes E-Learning“ besteht in Anlehnung an „smarte Produkte“ aus einer physischen, einer intelligenten und einer Vernetzungs-Komponente. Vernetzt sind die StudentInnen mit dem LMS einerseits in „Communities of Practice“ (CoP) zur Reflexion und andererseits über die Sensoren ihrer Smartphones oder Smartwatches (physische Komponente). Damit lässt sich dieses Lernumfeld der Kategorie “Internet of Things” (IoT) zuordnen. Im Lernprozess können die eingebetteten Sensoren mit den Biosignalen „Puls“ (HR) und „Herzfrequenzvariabilität“ (HRV) zur Selbstreflexion der Lernenden, zur Steuerung des Lernsystems und zur Personalisierung des Nutzungserlebnisses dienen. Erste Tests fanden u.a. Korrelationen zwischen erreichten Punkten in den Kontrollfragen und den Werten der Biosignale. Als intelligente Komponenten sind BenutzerInnenmodellierung, Chatbot, maschinelles Lernen usw. bei „Education 4.0“ im Einsatz.
DigitalAngewandte InformatikBeitrag (Sammelband oder Tagungsband)
Monica I. Ciolacu, Ali Fallah Tehrani, P. M. Svasta, I. Tache, D. Stoichescu
Education 4.0: An Adaptive Framework with Artificial Intelligence, Raspberry Pi and Wearables- Innovation for Creating Value
Proceedings of the 2020 IEEE 26th International Symposium for Design and Technology in Electronic Packaging (SIITME)
DOI: 10.1109/SIITME50350.2020.9292148
Abstract anzeigen
The Education 4.0 process can be used to foster students' performance, to motivate them by means of adaptive and personalized learning, to automate answering routine questions and to improve the quality of online examinations. It releases teachers from routine tasks, and it enables them to be more involved in the individualization of the educational process and in innovation. We apply artificial intelligence methodology to motivate students to improve their performance, and to identify early in course which students are at-risk of dropping out. In the adaptive Education 4.0 loT framework, the environmental and embedded sensors from wearables examine biosignals with biofeedback, such as pulse (HR) and heart rate variability (HRV), thereby increasing students' self-reflection, and allowing for a more personalized learning experience. The first experiments corroborate meaningful correlations between the data-points reached in the self-assessments, and values of the biosignals.
DigitalAngewandte InformatikBeitrag (Sammelband oder Tagungsband)
Monica I. Ciolacu, P. M. Svasta, D. Hartl, S. Görzen
Education 4.0: Smart Blended Learning assisted by Artificial Intelligence, Biofeedback and Sensors
Proceedings of the 2020 IEEE 14th International Symposium on Electronics and Telecommunications (ISETC2020)
DOI: 10.1109/ISETC50328.2020.9301034
Abstract anzeigen
The paper presents smart blended learning for fostering students’ performance. It uses models of student activity and detects causes of a possible drop out, using learning analytics and real-time data. Taking advantage of embedded sensors (non-invasive, low-cost, flexible and distraction free) built into wearable devices real-time data can be used to support students’ success, well-being and health. In our contribution to the research topic we evaluate the students' experience with smart blended learning using biofeedback methods, sensor data extracted from wearables for five specific lectures, during study periods and in examinations. The preliminary results indicate a correlation between the physiological signals and the grades in examination.
DigitalAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH TeisnachBuch (Monographie)
Franz Xaver Röhrl
Ein flexibles Leiterplatten-Technologiekonzept für Anwendungen im Millimeterwellenbereich
Dissertationsschrift
Elektrotechnik, München
ISBN: 978-3-8439-4537-0
Abstract anzeigen
Die vorliegende Arbeit beschreibt ein Konzept zum Betrieb von millimeterwellentauglichen Schaltungen auf konventionellen Leiterplatten. Dazu werden neben den technologischen Grundlagen und neuen Leiterplattentechnologien auch konkrete Realisierungen von Schaltungen vorgestellt. Der Fokus liegt dabei auf einer toleranzarmen, fertigungstechnisch prozesssicheren Umsetzung. Die entwickelten Fertigungsverfahren und Optimierungen erlauben die Herstellung von bisher nicht realisierbaren Feinstleiter-Strukturen auf Außenlagen und ermöglichen dadurch auch eine breitbandige dämpfungsarme Signalführung. Ein großer Vorteil der hier vorgestellten Umsetzung ist, dass die Verfahren zum Großteil mit konventionellen Leiterplattenprozessen umgesetzt werden können und auch eine beliebige Kombination mit bestehenden Leiterplattenprozessen zulässig ist. Es wird versucht möglichst viele Funktionen und Herausforderungen direkt auf der kostengünstigen Leiterplatte zu lösen. Das Konzept beinhaltet zudem eine breite Auswahl an Möglichkeiten zur reflexionsarmen Kontaktierung der Leiterplatte von Signalen im Millimeterwellenbereich. Außerdem wird die Anbindung von aktiven Bausteinen und anderen Schaltungsträgern detailliert behandelt. Die Ergebnisse werden sowohl mit dem aktuellen Stand der Leiterplattentechnologie als auch mit alternativen Fertigungstechnologien verglichen und bewertet.
DigitalAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH TeisnachZeitschriftenartikel
Felix Sepaintner, Andreas Scharl, Franz Xaver Röhrl, Werner Bogner, Stefan Zorn
Characterization and Production of PCB Structures With Increased Ratio of Electromagnetic Field in Air
IEEE Transactions on Microwave Theory and Techniques, vol. 68, no. 6, pp. 2134-2143
DOI: 10.1109/TMTT.2020.2983934
Abstract anzeigen
Producing passive printed circuit board (PCB) structures in the millimeter-wave range includes some fundamental challenges, such as low manufacturing costs and high fabrication accuracy. These aspects, in general, have to be combined with low signal attenuation, precise simulation models, and a reliable producibility. This article shows a new method to manufacture different kinds of passive RF waveguides with reduced attenuation and decreased electrical length on low-cost PCB substrates. First, the complex material parameters of the used substrate and the used copper foil are extracted from 10 to 100 GHz to have accurate simulation models in CST Microwave Studio. This is necessary because the parameters provided by the manufacturer are often no longer generally valid in this frequency range. In addition, PCB materials have a significantly higher surface roughness compared with conventional materials for millimeter-wave applications. Therefore, the correct determination and the correct modeling of surface roughness is particularly important. Next, laminate is removed partially on the outer layer of the PCB to increase the electromagnetic field ratio in air. The undesired substrate is removed by a CO2 laser drilling machine by setting narrow drills sequentially. The RF performance of these waveguides is compared with those manufactured in conventional PCB technology according to attenuation and producibility.
DigitalAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH TeisnachZeitschriftenartikel
E. Hassan, B. Scheiner, F. Michler, M. Berggren, E. Wadbro, Franz Xaver Röhrl, Stefan Zorn, R. Weigel, F. Lurz
Multi-Layer Topology Optimization of Wideband SIW-to-Waveguide Transitions
IEEE Transactions on Microwave Theory and Techniques, vol. 68, no. 4, pp. 1326-1339
DOI: 10.1109/TMTT.2019.2959759
Abstract anzeigen
This article utilizes a topology optimization approach to design planar multilayer transitions between substrate integrated waveguides (SIWs) and rectangular waveguides (RWGs). The optimization problem is formulated based on the modal field analyses and Maxwell's equations in the time domain solved by the finite-difference time-domain (FDTD) method. We present a time-domain boundary condition based on the Klein-Gordon equation to split traveling waves at homogeneous waveguide ports. We employ the boundary condition to compute portal quantities and to devise an adjoint-field system that enabled an efficient computation of the objective function gradient. We solve design problems that include more than 105 000 design variables by using less than 400 solutions of Maxwell's equations. Moreover, a new formulation that effectively combats the development of in-band resonances in the design is presented. The transition configuration allows the direct mount of conventional RWG sections on the circuit board and aims to cover the entire K-band. The guiding structure of the optimized transition requires blind vias, which is realized by a simple and cost-efficient technique. In addition, the transition is optimized for three different setups that can be used to provide different field polarizations. The proposed transitions show less than 1-dB insertion loss and around 15-dB return loss over the frequency interval 18-28 GHz. Several prototypes are fabricated with an excellent match between the simulation and measurement results.
DigitalAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH TeisnachBeitrag (Sammelband oder Tagungsband)
Felix Sepaintner, Andreas Scharl, Franz Xaver Röhrl, Werner Bogner, Stefan Zorn
Extracting Complex PCB Substrate Permittivity from a Transmission Line using the Finite Difference Integral Method from 10 GHz - 100 GHz
[Invited Talk]
Proceedings of the 2020 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)
DOI: 10.1109/IMWS-AMP49156.2020.9199738
Abstract anzeigen
This paper presents a new numerical method to deduce the complex permittivity εr of PCB (printed circuit board) substrates. First, the attenuation and phase of an on board transmission line are measured with a vector network analyzer (VNA). The transmission line is then simulated with the finite difference integral method (FDI) with the substrate substituted by air. The measured and simulated phases are used, to calculate the effective permittivity and the real part of the complex permittivity εr ' . With known εr ' , the electromagnetic field distribution can be calculated, which is necessary to deduce the imaginary part of the permittivity. The shown algorithms can be used for frequencies up to 100 GHz and without any iterative processes.
Version: 2.1.2-qf2