Publikationen


6718 Publikationen gefunden
    NachhaltigAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH Teisnach

    Patent

    Christian J. Trum, Sebastian Sitzberger

    Akkubetriebene Ultraschall-Handbohrmaschine sowie Verfahren zum Betreiben einer solchen Ultraschall-Handbohrmaschine

    NachhaltigAngewandte Naturwissenschaften und WirtschaftsingenieurwesenIPH Teisnach

    Patent

    Sebastian Sitzberger, Christian J. Trum, Michael Benisch

    Ultraschall-Handbohrmaschine und Verfahren zum Betreiben einer Ultraschall-Handbohrmaschine

    DigitalAngewandte Informatik

    Beitrag (Sammelband oder Tagungsband)

    Patrick Glauner, P. Valtchev, R. State

    Impact of Biases in Big Data

    Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2018) [April 27-29, 2018; Bruges, Belgium]

    Abstract anzeigen

    The underlying paradigm of big data-driven machine learning reflects the desire of deriving better conclusions from simply analyzing more data, without the necessity of looking at theory and models. Is having simply more data always helpful? In 1936, The Literary Digest collected 2.3M filled in questionnaires to predict the outcome of that year's US presidential election. The outcome of this big data prediction proved to be entirely wrong, whereas George Gallup only needed 3K handpicked people to make an accurate prediction. Generally, biases occur in machine learning whenever the distributions of training set and test set are different. In this work, we provide a review of different sorts of biases in (big) data sets in machine learning. We provide definitions and discussions of the most commonly appearing biases in machine learning: class imbalance and covariate shift. We also show how these biases can be quantified and corrected. This work is an introductory text for both researchers and practitioners to become more aware of this topic and thus to derive more reliable models for their learning problems.

    DigitalAngewandte Informatik

    Beitrag (Sammelband oder Tagungsband)

    Patrick Glauner, A. Boechat, L. Dolberg, R. State, F. Bettinger, Y. Rangoni, D. Duarte

    Large-scale detection of non-technical losses in imbalanced data sets

    Proceedings of the 2016 Seventh IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT 2016) [September 6-9, 2016; Minneapolis, MN, USA]

    DOI: 10.1109/ISGT.2016.7781159

    Abstract anzeigen

    Non-technical losses (NTL) such as electricity theft cause significant harm to our economies, as in some countries they may range up to 40% of the total electricity distributed. Detecting NTLs requires costly on-site inspections. Accurate prediction of NTLs for customers using machine learning is therefore crucial. To date, related research largely ignore that the two classes of regular and non-regular customers are highly imbalanced, that NTL proportions may change and mostly consider small data sets, often not allowing to deploy the results in production. In this paper, we present a comprehensive approach to assess three NTL detection models for different NTL proportions in large real world data sets of 100Ks of customers: Boolean rules, fuzzy logic and Support Vector Machine. This work has resulted in appreciable results that are about to be deployed in a leading industry solution. We believe that the considerations and observations made in this contribution are necessary for future smart meter research in order to report their effectiveness on imbalanced and large real world data sets.

    DigitalAngewandte Informatik

    Zeitschriftenartikel

    Patrick Glauner, J. Meira, P. Valtchev, R. State, F. Bettinger

    The Challenge of Non-Technical Loss Detection Using Artificial Intelligence: A Survey

    International Journal of Computational Intelligence Systems, vol. 10, no. 1, pp. 760-775

    DOI: 10.2991/ijcis.2017.10.1.51

    Abstract anzeigen

    Detection of non-technical losses (NTL) which include electricity theft, faulty meters or billing errors has attracted increasing attention from researchers in electrical engineering and computer science. NTLs cause significant harm to the economy, as in some countries they may range up to 40% of the total electricity distributed. The predominant research direction is employing artificial intelligence to predict whether a customer causes NTL. This paper first provides an overview of how NTLs are defined and their impact on economies, which include loss of revenue and profit of electricity providers and decrease of the stability and reliability of electrical power grids. It then surveys the state-of-the-art research efforts in a up-to-date and comprehensive review of algorithms, features and data sets used. It finally identifies the key scientific and engineering challenges in NTL detection and suggests how they could be addressed in the future.

    DigitalAngewandte Informatik

    Beitrag (Sammelband oder Tagungsband)

    Patrick Glauner, N. Dahringer, O. Puhachov, J. Meira, P. Valtchev, R. State, D. Duarte

    Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations

    Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW 2017) [November 18-21, 2017; New Orleans, LA, USA]

    DOI: 10.1109/ICDMW.2017.40

    Abstract anzeigen

    Power grids are critical infrastructure assets that face non-technical losses (NTL) such as electricity theft or faulty meters. NTL may range up to 40% of the total electricity distributed in emerging countries. Industrial NTL detection systems are still largely based on expert knowledge when deciding whether to carry out costly on-site inspections of customers. Electricity providers are reluctant to move to large-scale deployments of automated systems that learn NTL profiles from data due to the latter's propensity to suggest a large number of unnecessary inspections. In this paper, we propose a novel system that combines automated statistical decision making with expert knowledge. First, we propose a machine learning framework that classifies customers into NTL or non-NTL using a variety of features derived from the customers' consumption data. The methodology used is specifically tailored to the level of noise in the data. Second, in order to allow human experts to feed their knowledge in the decision loop, we propose a method for visualizing prediction results at various granularity levels in a spatial hologram. Our approach allows domain experts to put the classification results into the context of the data and to incorporate their knowledge for making the final decisions of which customers to inspect. This work has resulted in appreciable results on a real-world data set of 3.6M customers. Our system is being deployed in a commercial NTL detection software.

    NachhaltigElektrotechnik und MedientechnikIQMA

    Zeitschriftenartikel

    H. Fan, Y. Zhang, D. Liu, C. Niu, L. Liu, W. Ni, Y. Xia, Z. Bi, Günther Benstetter, G. Lei

    Tensile stress-driven cracking of W fuzz over W crystal under fusion-relevant He ion irradiations

    Nuclear Fusion, vol. 60, no. 4

    DOI: 10.1088/1741-4326/ab71bb

    Abstract anzeigen

    Although W fuzz is formed in the divertor region of the fusion reactor, no theory may clearly explain the W fuzz growth mechanism. In this study, we observe the growth process of W fuzz over W crystal under ITER-relevant He ion irradiations. We propose the tensile stress-driven cracking of nano-structured fuzz during the initial growth of W fuzz. We demonstrate that the existence of tensile stress is due to the swelling of He nano-bubbles in the fuzz. After this cracking, the W fuzz breaks away from the planar network and grows over the W surface, where the micro-stress in the W surface layer acts as the driving force.

    DigitalAngewandte InformatikTC Plattling MoMo

    Zeitschriftenartikel

    T. Hammer, Berthold Bäuml

    The Communication Layer of the aRDx Software Framework: Highly Performant and Realtime Deterministic

    Journal of Intelligent & Robotic Systems, vol. 77, pp. 171-185

    DOI: 10.1007/s10846-014-0095-9

    Abstract anzeigen

    Communication between software components is one of the most important functionalities a software framework for modern complex robotic systems has to provide. Here, we present the highly performant realtime communication layer of our new robotic software framework aRDx (agile robot development – next generation), with, e.g., zero-copy semantics, realtime determinism and detailed control of the QoS (quality of service). In addition, we give an in- depth performance comparison to other popular robotic frameworks, namely ROS, YARP, Orocos and aRD.

    DigitalAngewandte InformatikTC Plattling MoMo

    Zeitschriftenartikel

    O. Birbach, U. Frese, Berthold Bäuml

    Rapid calibration of a multi-sensorial humanoid’s upper body: An automatic and self-contained approach

    The International Journal of Robotics Research, vol. 34, no. 4-5, pp. 420-436

    DOI: 10.1177/0278364914548201

    Abstract anzeigen

    This paper addresses the problem of calibrating a pair of cameras, a Microsoft Kinect sensor and an inertial measurement unit (IMU) mounted at the head of a humanoid robot with respect to its kinematic chain. As complex manipulation tasks require an accurate interplay of all involved sensors, the quality of calibration is crucial for the outcome of the intended tasks. Typical procedures for calibrating are often time-consuming, involve multiple people overseeing a series of subsequent calibration steps and require external tools. We therefore propose to auto-calibrate all sensors in a single, completely automatic and self-contained procedure, i.e. without a calibration plate. By automatically detecting a single point feature on each wrist while moving the robot’s head, the stereo cameras’, the Kinect’s infrared camera’s intrinsic and extrinsic and an IMU’s extrinsic parameters are calibrated while considering the arm joint elasticities and joint angle offsets. All parameters are obtained by formulating the calibration problem as a single least-squares batch-optimization problem. The procedure is integrated on DLR’s humanoid robot Agile Justin allowing to obtain an accurate calibration in around 5 minutes by simply “pushing a button”. The proposed approach is experimentally validated by means of standard metrics of the calibration errors.

    DigitalAngewandte InformatikTC Plattling MoMo

    Beitrag (Sammelband oder Tagungsband)

    S. Baishya, Berthold Bäuml

    Robust material classification with a tactile skin using deep learning

    Proceedings of the 2016 IEEE International Workshop on Intelligent Robots and Systems (IROS) [October 9-14, 2016; Daejeon, South Korea]

    DOI: 10.1109/IROS.2016.7758088

    Abstract anzeigen

    Attaching a flexible tactile skin to an existing robotic system is relatively easy compared to integrating most other tactile sensor designs. In this paper we show that material classification purely based on the spatio-temporal signal of a flexible tactile skin can be robustly performed in a real world setting. We compare different classification algorithms and feature sets, including features adopted and extended from previous works in tactile material classification and that are based on the signal's Fourier spectrum. Our convolutional deep learning network architecture, which we also present here, is directly fed with the raw 24000 dimensional sensor signal and performs best by a large margin, reaching a classification accuracy of up to 97.3%.

    DigitalAngewandte InformatikTC Plattling MoMo

    Beitrag (Sammelband oder Tagungsband)

    R. Wagner, U. Frese, Berthold Bäuml

    Unified treatment of sparse and dense data in graph-based least squares

    Proceedings of the 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids 2016) [November 15-17, 2016; Cancún, Mexico]

    DOI: 10.1109/HUMANOIDS.2016.7803393

    Abstract anzeigen

    In this paper, we present a novel method of incorporating dense (e.g., depth, RGB-D) data in a general purpose least-squares graph optimization framework. Rather than employing a loosely coupled, layered design where dense data is first used to estimate a compact SE(3) transform which then forms a link in the optimization graph as in previous approaches [28, 10, 26], we use a tightly coupled approach that jointly optimizes over each individual (i.e. per-pixel) dense measurement (on the GPU) and all other traditional sparse measurements (on the CPU). Concretely, we use Kinect depth data and KinectFusion-style point-to-plane ICP measurements. In particular, this allows our approach to handle cases where neither dense, nor sparse measurements separately define all degrees of freedom (DoF) while taken together they complement each other and yield the overall maximum likelihood solution. Nowadays it is common practice to flexibly model various sensors, measurements and to be estimated variables in least-squares frameworks. Our intention is to extend this flexibility to applications with dense data. Computationally, the key is to combine the many dense measurements on the GPU efficiently and communicate only the results to the sparse framework on the CPU in a way that is mathematically equivalent to the full least-squares system. This results in <;20 ms for a full optimization run. We evaluate our approach on a humanoid robot, where in a first experiment we fuse Kinect data and odometry in a laboratory setting, and in a second experiment we fuse with an unusual “sensor”: using the embodiedness of the robot we estimate elasticities in the kinematic chain modeled as unknown, time-varying joint offsets while it moves its arms in front of a tabletop manipulation workspace. In both experiments only tightly coupled optimization will localize the robot correctly.

    DigitalAngewandte InformatikTC Plattling MoMo

    Beitrag (Sammelband oder Tagungsband)

    A. Tulbure, Berthold Bäuml

    Superhuman Performance in Tactile Material Classification and Differentiation with a Flexible Pressure-Sensitive Skin

    Proceedings of the 2018 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2018) [November 6-9, 2018; Beijing China]

    DOI: 10.1109/HUMANOIDS.2018.8624987

    Abstract anzeigen

    In this paper, we show that a robot equipped with a flexible and commercially available tactile skin can exceed human performance in the challenging tasks of material classification, i.e., uniquely identifying a given material by touch alone, and of material differentiation, i.e., deciding if the materials in a given pair of materials are the same or different. For processing the high dimensional spatio-temporal tactile signal, we use a new tactile deep learning network architecture TactNet-II which is based on TactNet [1] and is significantly extended with recently described architectural enhancements and training methods. TactN et- Iireaches an accuracy for the material classification task as high as 95.0 %. For the material differentiation a new Siamese network based architecture is presented which reaches an accuracy as high as 95.4 %. All the results have been achieved on a new challenging dataset of 36 everyday household materials. In a thorough human performance experiment with 15 subjects we show that the human performance is significantly lower than the robot's performance for both tactile tasks.

    NachhaltigTC Hutthurm

    Zeitschriftenartikel

    Sebastian Kölbl, J. Leßlhumer, A. Haider, O. Brüggemann, W. Buchberger

    Oxidationsinduktionszeit - dass passende Qualitätskriterium für WPC-Terrassendielen?

    holztechnologie, vol. 58, no. 2, pp. 38-45

    Abstract anzeigen

    Over the last years the popularity and approval of wood-polymer composites (WPC) are growing. Particularly in the field of terrace deckings the produced amounts have increased considerably. Outdoor applications lead to the questions of durability of these bio-composites. Therefore, in this work the determination of the oxidation induction time (OIT) as a possible quality criterion for WPC was evaluated. For this purpose, WPC-profiles were produced via direct-extrusion, with different amounts of additives. The produced profiles were treated by artificial weathering and examined continuously. In the course of the work, numerous influencing factors on the measurement were revealed and it was shown that an initial high OIT-value is no warranty for a long-lasting product. Parallelly conducted high-performance liquid chromatography (HPLC) measurements revealed what kind of additive has the biggest influence on the oxidation induction time and to what extent the amount of additives in the bio-composite is decreased by artificial weathering. In den letzten Jahren erfreut sich der Werkstoff WPC zunehmender Beliebtheit und Akzeptanz. Vor allem im Bereich der Terrassendielen (sogenannte "Deckings") sind die produzierten Mengen deutlich angestiegen. Die Anwendung im Außenbereich wirft aber auch die Frage der Dauerhaftigkeit dieser Bio-Composite auf. In der vorliegenden Arbeit wurde daher die Bestimmung der Oxidationsinduktionszeit als ein mögliches Qualitätskriterium für WPC unter die Lupe genommen. Dazu wurden WPC-Profile ohne und mit Additiven mittels Direktextrusion hergestellt, künstlich bewittert und fortlaufend untersucht. Dabei wurden zahlreiche Einflussfaktoren auf die OIT-Messung aufgezeigt sowie dargestellt, dass ein anfänglich hoher OIT-Wert keine Garantie für ein langlebiges Produkt ist. Durch HPLC-Messungen wurde des Weiteren nachgewiesen, welche Additive großen Einfluss auf die Oxidationsinduktionszeit haben und in welchem Maße diese durch UV-Bestrahlung und Beregnung abgebaut werden. Schlüsselwörter: Dauerhaftigkeit, Antioxidationsmittel, UV-Stabilisierung, Oxidationsinduktionszeit, Hochleistungsflüssigchromatographie

    NachhaltigTC Teisnach 2 Sensorik

    Patent

    Günther Ruhl, K. Pruegl

    Method for processing a carrier

    NachhaltigTC Teisnach 2 Sensorik

    Patent

    R. Berger, W. Lehnert, G. Metzger-Brueckl, Günther Ruhl, R. Rupp

    Wafer composite and method for producing semiconductor components

    NachhaltigTC Teisnach 2 Sensorik

    Patent

    R. Rupp, Günther Ruhl, H.-J. Schulze

    Silicon carbide semiconductor device and a method for forming a silicon carbide semiconductor device

    Elektrotechnik und Medientechnik

    Zeitschriftenartikel

    H. Heckelmüller, F. Kendl, Gerhard Krump

    TDR Einzahlwert zur Charakterisierung der dynamischen Oberbausteifigkeit

    ZEVrail - Zeitschrift für das gesamte System Bahn, vol. 144, no. Mai, pp. 190-194

    Abstract anzeigen

    Der Schallmesswagen (SMW) der DB Systemtechnik prüft den akustischen Zustand des Oberbaus und wird vor allem zur Überprüfung von Streckenabschnitten mit der Maßnahme „Besonders überwachtes Gleis“ (BüG) verwendet. Zusätzlich wird der SMW zur Qualitätskontrolle und Abnahme des akustischen Schienenschleifens eingesetzt. Falls ein BüG-Abschnitt nicht vom SMW befahren werden kann, gilt seit 2001 die Ersatzmaßnahme RMF-BüG. Dieses Verfahren soll die Messaufgaben des SMW durch kontinuierliche Rauheitsmessungen beider Schienen ersatzweise übernehmen können. Beim RMF-BüG-Verfahren wurde zur Berechnung des SMW-Pegels ausschließlich die Schienenrauheit berücksichtigt. Anhand einer Vielzahl von Messungen konnte gezeigt werden, dass das Rollgeräusch des SMW signifikant ebenfalls von der Gleisabklingrate (Track Decay Rate TDR) abhängig ist. Das vorgestellte Verfahren zeigt die Verwendung des Einzahlwertes der Schienenrauheit LλCA und des Einzahlwertes der TDR L TDR zur Bestimmung des SMW-Pegels.

    GesundEuropan Campus Rottal-Inn

    Zeitschriftenartikel

    T. Lorenz, Vlaskamp, B. N. S., Anna-Maria Kasparbauer, A. Mörtl, S. Hirche

    Dyadic Movement Synchronization While Performing Incongruent Trajectories Requires Mutual Adaptation

    Frontiers in Human Neuroscience, no. June

    DOI: 10.3389/fnhum.2014.00461

    Abstract anzeigen

    Unintentional movement synchronization is often emerging between interacting humans. In the present study, we investigate the extent to which the incongruence of movement trajectories has an influence on unintentional dyadic movement synchronization. During a target-directed tapping task, a participant repetitively moved between two targets in front of another participant who performed the same task in parallel but independently. When the movement path of one participant was changed by placing an obstacle between the targets, the degree of their unintentional movement synchronization was measured. Movement synchronization was observed despite of their substantially different movement trajectories. A deeper investigation of the participant's unintentional behavior shows, that although the actor who cleared the obstacle puts unintentional effort in establishing synchrony by increasing movement velocity—the other actor also unintentionally adjusted his/her behavior by increasing dwell times. Results are discussed in the light of joint action, movement interference and obstacle avoidance behavior.

    GesundEuropan Campus Rottal-Inn

    Zeitschriftenartikel

    T. Talanow, Anna-Maria Kasparbauer, J. Lippold, B. Weber, U. Ettinger

    Neural Correlates of Proactive and Reactive Inhibition of Saccadic Eye Movements

    Brain Imaging and Behavior, vol. 14, pp. 72-88

    DOI: 10.1007/s11682-018-9972-3

    Abstract anzeigen

    Although research on goal-directed, proactive inhibitory control (IC) and stimulus-driven, reactive IC is growing, no previous study has compared proactive IC in conditions of uncertainty with regard to upcoming inhibition to conditions of certain upcoming IC. Therefore, we investigated effects of certainty and uncertainty on behavior and blood oxygen level dependent (BOLD) signal in proactive and reactive IC. In two studies, healthy adults performed saccadic go/no-go and prosaccade/antisaccade tasks. The certainty manipulation had a highly significant behavioral effect in both studies, with inhibitory control being more successful under certain than uncertain conditions on both tasks (p ≤ 0.001). Saccadic go responses were significantly less efficient under conditions of uncertainty than certain responding (p < 0.001). Event-related functional magnetic resonance imaging (fMRI) (one study) revealed a dissociation of certainty- and uncertainty-related proactive inhibitory neural correlates in the go/no-go task, with lateral and medial prefrontal and occipital cortex showing stronger deactivations during uncertainty than during certain upcoming inhibition, and lateral parietal cortex being activated more strongly during certain upcoming inhibition than uncertainty or certain upcoming responding. In the antisaccade task, proactive BOLD effects arose due to stronger deactivations in uncertain response conditions of both tasks and before certain prosaccades than antisaccades. Reactive inhibition-related BOLD increases occurred in inferior parietal cortex and supramarginal gyrus (SMG) in the go/no-go task only. Proactive IC may imply focusing attention on the external environment for encoding salient or alerting events as well as inhibitory mechanisms that reduce potentially distracting neural processes. SMG and inferior parietal cortex may play an important role in both proactive and reactive IC of saccades.

    GesundEuropan Campus Rottal-Inn

    Zeitschriftenartikel

    Anna-Maria Kasparbauer, D. Rujescu, M. Riedel, O. Pogarell, A. Costa, T. Meindl, C. La Fougère, U. Ettinger

    Methylphenidate Effects on Brain Activity as a Function of SLC6A3 Genotype and Striatal Dopamine Transporter Availability

    Neuropsychopharmacology, vol. 40, pp. 736-745

    DOI: 10.1038/npp.2014.240

    Abstract anzeigen

    We pharmacologically challenged catecholamine reuptake, using methylphenidate, to investigate its effects on brain activity during a motor response inhibition task as a function of the 3′-UTR variable number of tandem repeats (VNTR) polymorphism of the dopamine transporter (DAT) gene (SLC6A3) and the availability of DATs in the striatum. We measured the cerebral hemodynamic response of 50 healthy males during a Go/No-Go task, a measure of cognitive control, under the influence of 40 mg methylphenidate and placebo using 3T functional magnetic resonance imaging. Subjects were grouped into 9-repeat (9R) carriers and 10/10 homozygotes on the basis of the SLC6A3 VNTR. During successful no-go trials compared with oddball trials, methylphenidate induced an increase of blood oxygen level-dependent (BOLD) signal for carriers of the SLC6A3 9R allele but a decrease in 10/10 homozygotes in a thalamocortical network. The same pattern was observed in caudate and inferior frontal gyrus when successful no-go trials were compared with successful go trials. We additionally investigated in a subset of 35 participants whether baseline striatal DAT availability, ascertained with 123I-FP-CIT single photon emission computed tomography, predicted the amount of methylphenidate-induced change in hemodynamic response or behavior. Striatal DAT availability was nominally greater in 9R carriers compared with 10/10 homozygotes (d=0.40), in line with meta-analyses, but did not predict BOLD or behavioral changes following MPH administration. We conclude that the effects of acute MPH administration on brain activation are dependent on DAT genotype, with 9R carriers showing enhanced BOLD following administration of a prodopaminergic compound.