434 results on '"Ralf Mikut"'
Search Results
202. Takagi-Sugeno-Kang Fuzzy Classifiers for a Special Class of Time-Varying Systems.
- Author
-
Ralf Mikut, Ole Burmeister, Lutz Gröll, and Markus Reischl
- Published
- 2008
- Full Text
- View/download PDF
203. Regelungs- und Steuerungskonzepte für Neuroprothesen am Beispiel der oberen Extremitäten (Closed- and Open-Loop Control Concepts for Neuroprostheses of Upper Extremities).
- Author
-
Ralf Mikut, Thilo B. Krüger, Markus Reischl, Ole Burmeister, Rüdiger Rupp, and Thomas Stieglitz
- Published
- 2006
- Full Text
- View/download PDF
204. Zeitvariante Klassifikatoren zur Steuerung von Brain Machine Interfaces und Neuroprothesen (Time-variant Classifiers to Control Brain Machine Interfaces and Neuroprostheses).
- Author
-
Ole Burmeister, Markus Reischl, Lutz Gröll, and Ralf Mikut
- Published
- 2006
- Full Text
- View/download PDF
205. EMG-control of prostheses by switch signals: extraction and classification of features.
- Author
-
Markus Reischl, Ralf Mikut, and Lutz Gröll
- Published
- 2004
- Full Text
- View/download PDF
206. Interpretability issues in data-based learning of fuzzy systems.
- Author
-
Ralf Mikut, Jens Jäkel, and Lutz Gröll
- Published
- 2005
- Full Text
- View/download PDF
207. A hydraulically driven multifunctional prosthetic hand.
- Author
-
Stefan Schulz 0003, Christian Pylatiuk, Markus Reischl, Jan Martin, Ralf Mikut, and Georg Bretthauer
- Published
- 2005
- Full Text
- View/download PDF
208. Hardware Design and Mathematical Modeling for an Artificial Pneumatic Spine for a Biped Humanoid Robot.
- Author
-
Christian Bauer 0003, Mark Engelmann, Immanuel Gaiser, Ralf Mikut, Stefan Schulz 0003, Andreas Fischer 0003, and Thorsten Stein
- Published
- 2012
209. Rational Designed Hybrid Peptides Show up to a 6-Fold Increase in Antimicrobial Activity and Demonstrate Different Ultrastructural Changes as the Parental Peptides Measured by BioSAXS
- Author
-
Nathan Simpson, Marco Scocchi, Petar Markov, Christoph Rumancev, Jurnorain Gani, Ralf Mikut, Kai Hilpert, Vasil M. Garamus, Axel Rosenhahn, Paula Matilde Lopez-Perez, and Andreas von Gundlach
- Subjects
Drug ,antimicrobial compound ,antimicrobial peptide ,media_common.quotation_subject ,Antimicrobial peptides ,Peptide ,RM1-950 ,hybrid peptide ,mode of action ,Untreated control ,BioSAXS ,ddc:610 ,media_common ,Original Research ,chemistry.chemical_classification ,Pharmacology ,biology ,Chemistry ,biology.organism_classification ,Antimicrobial ,Resistant bacteria ,Biochemistry ,Ultrastructure ,TEM ,multi-drug resistance ,Therapeutics. Pharmacology ,ultrastructural changes ,Bacteria - Abstract
Frontiers in pharmacology 12, 769739 (2021). doi:10.3389/fphar.2021.769739, Antimicrobial peptides (AMPs) are a promising class of compounds being developed against multi-drug resistant bacteria. Hybridization has been reported to increase antimicrobial activity. Here, two proline-rich peptides (consP1: VRKPPYLPRPRPRPL-CONH2 and Bac5-v291: RWRRPIRRRPIRPPFWR-CONH2) were combined with two arginine-isoleucine-rich peptides (optP1: KIILRIRWR-CONH2 and optP7: KRRVRWIIW-CONH2). Proline-rich antimicrobial peptides (PrAMPs) are known to inhibit the bacterial ribosome, shown also for Bac5-v291, whereas it is hypothesized a “dirty drug” model for the arginine-isoleucine-rich peptides. That hypothesis was underpinned by transmission electron microscopy and biological small-angle X-ray scattering (BioSAXS). The strength of BioSAXS is the power to detect ultrastructural changes in millions of cells in a short time (seconds) in a high-throughput manner. This information can be used to classify antimicrobial compounds into groups according to the ultrastructural changes they inflict on bacteria and how the bacteria react towards that assault. Based on previous studies, this correlates very well with different modes of action. Due to the novelty of this approach direct identification of the target of the antimicrobial compound is not yet fully established, more research is needed. More research is needed to address this limitation. The hybrid peptides showed a stronger antimicrobial activity compared to the proline-rich peptides, except when compared to Bac5-v291 against E. coli. The increase in activity compared to the arginine-isoleucine-rich peptides was up to 6-fold, however, it was not a general increase but was dependent on the combination of peptides and bacteria. BioSAXS experiments revealed that proline-rich peptides and arginine-isoleucine-rich peptides induce very different ultrastructural changes in E. coli, whereas a hybrid peptide (hyP7B5GK) shows changes, different to both parental peptides and the untreated control. These different ultrastructural changes indicated that the mode of action of the parental peptides might be different from each other as well as from the hybrid peptide hyP7B5GK. All peptides showed very low haemolytic activity, some of them showed a 100-fold or larger therapeutic window, demonstrating the potential for further drug development., Published by Frontiers Media, Lausanne more...
- Published
- 2021
- Full Text
- View/download PDF
210. A Lightweight User Interface for Smart Charging of Electric Vehicles: A Real-World Application
- Author
-
Veit Hagenmeyer, Johannes Galenzowski, Karl Schwenk, Simon Waczowicz, Stefan Meisenbacher, and Ralf Mikut
- Subjects
Computer science ,business.industry ,Embedded system ,User interface ,business - Published
- 2021
- Full Text
- View/download PDF
211. Integrating a flexible anthropomorphic, robot hand into the control, system of a humanoid robot.
- Author
-
Dirk Osswald, Jan Martin, Catherina Burghart, Ralf Mikut, Heinz Wörn, and Georg Bretthauer
- Published
- 2004
- Full Text
- View/download PDF
212. Sensors, Identification, and Low Level Control of a Flexible Anthropomorphic Robot Hand.
- Author
-
Jan Martin, Sebastian Beck, Arne Lehmann, Ralf Mikut, Christian Pylatiuk, Stefan Schulz 0003, and Georg Bretthauer
- Published
- 2004
- Full Text
- View/download PDF
213. Prognose für preisbeeinflusstes Verbrauchsverhalten.
- Author
-
Stefan Klaiber, Simon Waczowicz, Irina Konotop, Dirk Westermann, Ralf Mikut, and Peter Bretschneider
- Published
- 2017
- Full Text
- View/download PDF
214. DaMoQ: Eine Open-Source-MATLAB-Toolbox zur Bewertung von Daten- und Modellqualität in Regressionen.
- Author
-
Wolfgang Doneit 0001, Ralf Mikut, Lutz Gröll, Tim Pychynski, and Markus Reischl
- Published
- 2017
- Full Text
- View/download PDF
215. Ausgewählte Beiträge aus dem GMA-Fachausschuss 5.14 'Computational Intelligence'.
- Author
-
Frank Hoffmann 0001, Andreas Kroll, and Ralf Mikut
- Published
- 2017
- Full Text
- View/download PDF
216. Real-time large-area imaging of the corneal subbasal nerve plexus
- Author
-
Stephan, Allgeier, Andreas, Bartschat, Sebastian, Bohn, Rudolf F, Guthoff, Veit, Hagenmeyer, Lukas, Kornelius, Ralf, Mikut, Klaus-Martin, Reichert, Karsten, Sperlich, Nadine, Stache, Oliver, Stachs, and Bernd, Köhler more...
- Subjects
Cornea ,Microscopy, Confocal ,Image Processing, Computer-Assisted ,Humans ,Optic Nerve - Abstract
The morphometric assessment of the corneal subbasal nerve plexus (SNP) by confocal microscopy holds great potential as a sensitive biomarker for various ocular and systemic conditions and diseases. Automated wide-field montages (or large-area mosaic images) of the SNP provide an opportunity to overcome the limited field of view of the available imaging systems without the need for manual, subjective image selection for morphometric characterization. However, current wide-field montaging solutions usually calculate the mosaic image after the examination session, without a reliable means for the clinician to predict or estimate the resulting mosaic image quality during the examination. This contribution describes a novel approach for a real-time creation and visualization of a mosaic image of the SNP that facilitates an informed evaluation of the quality of the acquired image data immediately at the time of recording. In cases of insufficient data quality, the examination can be aborted and repeated immediately, while the patient is still at the microscope. Online mosaicking also offers the chance to identify an overlap of the imaged tissue region with previous SNP mosaic images, which can be particularly advantageous for follow-up examinations. more...
- Published
- 2021
217. Machine Learning Methods for Automated Quantification of Ventricular Dimensions
- Author
-
Mark Schutera, Steffen Just, Christian Pylatiuk, Markus Reischl, Ralf Mikut, and Jakob Gierten
- Subjects
Dorsum ,animal structures ,Heart Ventricles ,Oryzias ,Danio ,Context (language use) ,Computational biology ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,medicine ,Animals ,Segmentation ,Zebrafish ,030304 developmental biology ,0303 health sciences ,biology ,fungi ,Fractional shortening ,biology.organism_classification ,medicine.anatomical_structure ,Ventricle ,embryonic structures ,Animal Science and Zoology ,030217 neurology & neurosurgery ,Developmental Biology - Abstract
Medaka (Oryzias latipes) and zebrafish (Danio rerio) contribute substantially to our understanding of the genetic and molecular etiology of human cardiovascular diseases. In this context, the quantification of important cardiac functional parameters is fundamental. We have developed a framework that segments the ventricle of a medaka hatchling from image sequences and subsequently quantifies ventricular dimensions. more...
- Published
- 2019
- Full Text
- View/download PDF
218. Digitale Bildverarbeitung und Tiefe Neuronale Netze in der Augenheilkunde – aktuelle Trends
- Author
-
Bernd Koehler, Tim Scherr, Klaus-Martin Reichert, Sebastian Bohn, Oliver Stachs, Andreas Bartschat, Stephan Allgeier, Markus Reischl, Ralf Mikut, and Denis Blessing
- Subjects
0303 health sciences ,03 medical and health sciences ,Ophthalmology ,0302 clinical medicine ,Political science ,030221 ophthalmology & optometry ,Humanities ,030304 developmental biology - Abstract
ZusammenfassungDer Einsatz von Tiefen Neuronalen Netzen (Deep Learning) eröffnet neue Möglichkeiten in der digitalen Bildverarbeitung. Auch für die Auswertung von Bilddaten in der Ophthalmologie wird diese Methode erfolgreich eingesetzt und findet weite Verbreitung. In diesem Artikel wird die methodische Vorgehensweise beim Deep Learning betrachtet und der klassischen Vorgehensweise für die Entwicklung von Methoden für die digitale Bildverarbeitung gegenübergestellt. Dabei wird auf Unterschiede eingegangen und die wichtiger werdende Rolle von Trainingsdaten für die Modellbildung erklärt. Weiterhin wird die Vorgehensweise des Transfer-Lernens (Transfer Learning) für Deep Learning am Beispiel eines Datensatzes aus der kornealen Konfokalmikroskopie vorgestellt. Dabei wird auf die Vorteile der Methode und auf Besonderheiten beim Umgang mit medizinischen Mikroskopdaten eingegangen. more...
- Published
- 2019
- Full Text
- View/download PDF
219. High accuracy beam splitting using spatial light modulator combined with machine learning algorithms
- Author
-
Ralf Mikut, Dmitriy Mikhaylov, Baifan Zhou, Andrés-Fabián Lasagni, and Thomas Kiedrowski
- Subjects
Computer science ,Holography ,Phase (waves) ,Physics::Optics ,02 engineering and technology ,Machine learning ,computer.software_genre ,01 natural sciences ,law.invention ,010309 optics ,symbols.namesake ,law ,0103 physical sciences ,Electrical and Electronic Engineering ,Ultrashort pulse laser ,Spatial light modulator ,business.industry ,Mechanical Engineering ,021001 nanoscience & nanotechnology ,Laser ,Atomic and Molecular Physics, and Optics ,Electronic, Optical and Magnetic Materials ,Power (physics) ,Fourier transform ,symbols ,Artificial intelligence ,0210 nano-technology ,business ,Algorithm ,computer ,Beam splitter - Abstract
Phase-only spatial light modulators are ideal for the generation of beam splitter profiles to parallelize a variety of laser processes. A novel approach for the calculation of phase holograms is proposed to achieve a highly accurate power distribution over all spots. The Iterative Fourier Transform Algorithm (IFTA) is extended by the use of different machine learning methods, which are trained in an open camera-feedback loop. After the training phase, improvement of the beam splitting accuracy is then validated experimentally. The advantage of the presented approach is shown by comparing it to the standard IFTA algorithm. Finally, use of the approach is demonstrated through metal marking with an ultrashort pulse laser. more...
- Published
- 2019
- Full Text
- View/download PDF
220. Automated design process for hybrid regression modeling with a one-class SVM
- Author
-
Wolfgang Doneit, Markus Reischl, Ralf Mikut, Moritz Böhland, and Lutz Gröll
- Subjects
0209 industrial biotechnology ,Class (computer programming) ,Computer science ,business.industry ,Regression analysis ,02 engineering and technology ,Machine learning ,computer.software_genre ,Model complexity ,Computer Science Applications ,Support vector machine ,020901 industrial engineering & automation ,Open source ,Control and Systems Engineering ,0202 electrical engineering, electronic engineering, information engineering ,Benchmark (computing) ,Design process ,020201 artificial intelligence & image processing ,Artificial intelligence ,Electrical and Electronic Engineering ,Matlab toolbox ,business ,computer - Abstract
The accuracy of many regression models suffers from inhomogeneous data coverage. Models loose accuracy because they are unable to locally adapt the model complexity. This article develops and evaluates an automated design process for the generation of hybrid regression models from arbitrary submodels. For the first time, these submodels are weighted by a One-Class Support Vector Machine, taking local data coverage into account. Compared to reference regression models, the newly developed hybrid models achieve significant better results in nine out of ten benchmark datasets. To enable straightforward usage in data science, an implementation is integrated in the open source MATLAB toolbox SciXMiner. more...
- Published
- 2019
- Full Text
- View/download PDF
221. Strategies for supplementing recurrent neural network training for spatio-temporal prediction
- Author
-
Stefan Elser, Markus Reischl, Ralf Mikut, Mark Schutera, and Jochen Abhau
- Subjects
Hyperparameter ,0209 industrial biotechnology ,Computer science ,business.industry ,Generalization ,02 engineering and technology ,Machine learning ,computer.software_genre ,Object (computer science) ,Automation ,Computer Science Applications ,Image (mathematics) ,020901 industrial engineering & automation ,Recurrent neural network ,Control and Systems Engineering ,0202 electrical engineering, electronic engineering, information engineering ,Trajectory ,020201 artificial intelligence & image processing ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,Generative adversarial network ,computer - Abstract
In autonomous driving, prediction tasks address complex spatio-temporal data. This article describes the examination of Recurrent Neural Networks (RNNs) for object trajectory prediction in the image space. The proposed methods enhance the performance and spatio-temporal prediction capabilities of Recurrent Neural Networks. Two different data augmentation strategies and a hyperparameter search are implemented for this purpose. A conventional data augmentation strategy and a Generative Adversarial Network (GAN) based strategy are analyzed with respect to their ability to close the generalization gap of Recurrent Neural Networks. The results are then discussed using single-object tracklets provided by the KITTI Tracking Dataset. This work demonstrates the benefits of augmenting spatio-temporal data with GANs. more...
- Published
- 2019
- Full Text
- View/download PDF
222. Digital technologies in airport ground operations
- Author
-
Ivan Kovynyov and Ralf Mikut
- Subjects
Economics and Econometrics ,Service (systems architecture) ,Computer Networks and Communications ,business.industry ,Emerging technologies ,Computer science ,05 social sciences ,Big data ,Digital transformation ,Wearable computer ,Business model ,0502 economics and business ,Key (cryptography) ,Revenue ,050207 economics ,Telecommunications ,business ,050203 business & management ,Information Systems - Abstract
How have digital technologies changed airport ground operations? Although the relevant peer-reviewed literature emphasizes the role of cost savings as a key driver behind digitalization of airport ground operations, the focus is on data-driven, customer-centric innovations. This paper argues that ground handling agents are deploying new technologies mainly to boost process efficiency and to cut costs. Our research shows that ground handling agents are embracing current trends to craft new business models and develop new revenue streams. In this paper, we examine the ground handling agent’s value chain and identify areas that are strongly affected by digital technologies and those that are not. We discuss different business scenarios for digital technology and link them with relevant research, such as automated service data capturing, new digital services for passengers, big data, indoor navigation, and wearables in airport ground operations. We assess the maturity level of discussed technologies using NASA technology readiness levels. more...
- Published
- 2019
- Full Text
- View/download PDF
223. Reliable Dispatch of Renewable Generation via Charging of Time-Varying PEV Populations
- Author
-
Timm Faulwasser, Miguel Munoz-Ortiz, Veit Hagenmeyer, Ralf Mikut, Jorge Ángel González Ordiano, and Riccardo Remo Appino
- Subjects
Scheme (programming language) ,Schedule ,Computer science ,business.industry ,020209 energy ,Distributed computing ,Probabilistic logic ,Energy Engineering and Power Technology ,02 engineering and technology ,Renewable energy ,Set (abstract data type) ,Electric power system ,0202 electrical engineering, electronic engineering, information engineering ,Renewable generation ,Power output ,Electrical and Electronic Engineering ,business ,computer ,computer.programming_language - Abstract
The inherent storage of plug-in electric vehicles is likely to foster the integration of intermittent generation from renewable energy sources into existing power systems. To the end of achieving dispatchability of a system composed of plug-in electric vehicles and intermittent generation, we propose a three-stage scheme. The main difficulties in dispatching such a system are the uncertainties inherent to intermittent generation and the time-varying aggregation of vehicles. We propose to address the former by means of probabilistic forecasts, while we approach the latter with separate stage-specific models. Specifically, we first compute a dispatch schedule, using probabilistic forecasts together with an aggregated dynamic model of the system. The power output of the single devices are set subsequently using deterministic forecasts and device-specific models. We draw upon a simulation study based on real data of generation and vehicle traffic to validate our findings. more...
- Published
- 2019
- Full Text
- View/download PDF
224. On Improving an Already Competitive Segmentation Algorithm for the Cell Tracking Challenge - Lessons Learned
- Author
-
Tim Scherr, Ralf Mikut, O. Neumann, and Loeffler K
- Subjects
business.industry ,Computer science ,Deep learning ,Graph (abstract data type) ,Segmentation ,Computer vision ,Cell tracking ,Artificial intelligence ,business ,Representation (mathematics) ,Tracking (particle physics) ,Distance transform ,Task (project management) - Abstract
The virtually error-free segmentation and tracking of densely packed cells and cell nuclei is still a challenging task. Especially in low-resolution and low signal-to-noise-ratio microscopy images erroneously merged and missing cells are common segmentation errors making the subsequent cell tracking even more difficult. In 2020, we successfully participated as team KIT-Sch-GE (1) in the 5th edition of the ISBI Cell Tracking Challenge. With our deep learning-based distance map regression segmentation and our graph-based cell tracking, we achieved multiple top 3 rankings on the diverse data sets. In this manuscript, we show how our approach can be further improved by using another optimizer and by fine-tuning training data augmentation parameters, learning rate schedules, and the training data representation. The fine-tuned segmentation in combination with an improved tracking enabled to further improve our performance in the 6th edition of the Cell Tracking Challenge 2021 as team KIT-Sch-GE (2). more...
- Published
- 2021
- Full Text
- View/download PDF
225. Smart Charging of Electric Vehicles with Cloud-based Optimization and a Lightweight User Interface
- Author
-
Simon Waczowicz, Johannes Galenzowski, Karl Schwenk, Veit Hagenmeyer, Ralf Mikut, and Stefan Meisenbacher
- Subjects
Power management ,050210 logistics & transportation ,Computer science ,business.industry ,Smart Charging ,DATA processing & computer science ,05 social sciences ,Cloud computing ,010501 environmental sciences ,Grid ,Wizard ,01 natural sciences ,Charging station ,Web Applications ,Electric power system ,Battery Aging ,Embedded system ,0502 economics and business ,Web application ,ddc:004 ,User interface ,business ,Electric Vehicles ,0105 earth and related environmental sciences - Abstract
Smart Charging (SC) of Electric Vehicles (EVs) integrates them into the power system to support grid stability by power management. Large-scale adoption of SC requires a high level of EV user acceptance. Therefore, it is imperative to make the underlying charging scheme tangible for the user. We propose a web app for the user to start, adjust and monitor the charging process via a User Interface (UI). We outline the integration of this web app into an Internet of Things (IoT) architecture to establish communication with the charging station. Two scenarios demonstrate the operation of the system. Future field studies on SC should involve the EV user due to individual preferences and responses to incentive schemes. Therefore, we propose the Smart Charging Wizard with a customizable UI and optimization module for future research and collaborative development. more...
- Published
- 2021
- Full Text
- View/download PDF
226. A Comparison of Energy-Efficient Seizure Detectors for Implantable Neurostimulation Devices
- Author
-
Farrokh, Manzouri, Marc, Zöllin, Simon, Schillinger, Matthias, Dümpelmann, Ralf, Mikut, Peter, Woias, Laura Maria, Comella, and Andreas, Schulze-Bonhage
- Abstract
About 30% of epilepsy patients are resistant to treatment with antiepileptic drugs, and only a minority of these are surgical candidates. A recent therapeutic approach is the application of electrical stimulation in the early phases of a seizure to interrupt its spread across the brain. To accomplish this, energy-efficient seizure detectors are required that are able to detect a seizure in its early stages.Three patient-specific, energy-efficient seizure detectors are proposed in this study: (i) random forest (RF); (ii) long short-term memory (LSTM) recurrent neural network (RNN); and (iii) convolutional neural network (CNN). Performance evaluation was based on EEG data (The RNN seizure detector achieved a slightly better level of performance, with a median area under the precision-recall curve score of 0.49, compared to 0.47 for CNN and 0.46 for RF. In terms of energy consumption, RF was the most efficient algorithm, with a total of 67k AOs and 67k MAs per classification. This was followed by CNN (488k AOs and 963k MAs) and RNN (772k AOs and 978k MAs), whereby MAs contributed more to total energy consumption. Measurements derived from the hardware implementation of the RNN algorithm demonstrated a significant correlation between estimations and actual measurements.All three proposed seizure detection algorithms were shown to be suitable for application in implantable devices. The applied methodology for a platform-independent energy estimation was proven to be accurate by way of hardware implementation of the RNN algorithm. These findings show that seizure detection can be achieved using just a few channels with limited spatial distribution. The methodology proposed in this study can therefore be applied when designing new models for responsive neurostimulation. more...
- Published
- 2021
227. Design of transformation initiatives implementing organisational agility: an empirical study
- Author
-
Ralf Mikut, Ivan Kovynyov, and Axel Buerck
- Subjects
FOS: Computer and information sciences ,Agile ,Knowledge management ,media_common.quotation_subject ,Agile transformation ,02 engineering and technology ,Organisational design ,Agile organisations ,Organisational agility ,Computer Science - Computers and Society ,Empirical research ,Perception ,Computers and Society (cs.CY) ,0502 economics and business ,0202 electrical engineering, electronic engineering, information engineering ,Human resources ,media_common ,business.industry ,DATA processing & computer science ,05 social sciences ,020207 software engineering ,Work (electrical) ,New product development ,Organizational structure ,Original Article ,Business ,ddc:004 ,050203 business & management ,Agile software development - Abstract
This study uses 125 responses from companies of all sizes predominantly headquartered in Germany, Switzerland, France and UK to reveal perceptions of the drivers of organisational agility. It further investigates current understanding of managing principles of multiple organisational dimensions such as culture, values, leadership, organisational structure, processes and others to achieve greater organisational agility. The data set is disaggregated into four major profiles of agile organisations: laggards, execution specialists, experimenters, and leaders. The approach to agile transformation is analysed by each of those profiles. While the positive effect from a more holistic approach is confirmed, leaders tend to focus more on processes and products rather than project work. Respondents perceive that IT, product development and research are most agile functions within their organisations, while human resources, finance and administration are considered being not agile. Furthermore, organisations with higher levels of organisational agility tend to use more than one agile scaling framework. Implications on theories of agile transformations and organisational design are discussed. more...
- Published
- 2021
228. A stochastic oscillator model simulates the entrainment of vertebrate cellular clocks by light
- Author
-
Daniela Vallone, Nicholas S. Foulkes, Srinivas Babu Gondi, Lennart Hilbert, Vojtěch Kumpošt, and Ralf Mikut
- Subjects
Physics ,biology ,Stochastic oscillator ,Mechanism (biology) ,Negative feedback ,Circadian clock ,Circadian rhythm ,Entrainment (chronobiology) ,biology.organism_classification ,Biological system ,Zebrafish ,Synchronization - Abstract
The circadian clock is a cellular mechanism that synchronizes various biological processes with respect to the time of the day. While much progress has been made characterizing the molecular mechanisms underlying this clock, it is less clear how external light cues influence the dynamics of the core clock mechanism and thereby entrain it with the light-dark cycle. Zebrafish-derived cell cultures possess clocks that are directly light-entrainable, thus providing an attractive laboratory model for circadian entrainment. Here, we have developed a stochastic oscillator model of the zebrafish circadian clock, which accounts for the core clock negative feedback loop, light input, and the proliferation of single-cell oscillator noise into population-level luminescence recordings. The model accurately predicts the entrainment dynamics observed in bioluminescent clock reporter assays upon exposure to a wide range of lighting conditions. Furthermore, we have applied the model to obtain refitted parameter sets for cell cultures exposed to a variety of pharmacological treatments and predict changes in single-cell oscillator parameters. Our work paves the way for model-based, large-scale screens for genetic or pharmacologically-induced modifications to the entrainment of circadian clock function.Author summaryThe circadian clock is a key, cell-autonomous timing mechanism that is encountered in most organisms. It is entrained by environmental lighting conditions and in turn temporally coordinates most aspects of physiology according to the time of day. Cell lines derived from zebrafish are attractive experimental models for studying how clocks are entrained by light since they possess clocks that respond directly to light stimuli. Here we describe a mathematical model for the behavior of the circadian clock in zebrafish cell lines during exposure to a range of lighting conditions. Using this model, we can determine how different pharmacological treatments may affect the entrainment dynamics of the clock and the degree of synchronization of individual cells’ circadian clocks in bioluminescent clock reporter assays. Our current model is mathematically simple and thus easy to apply and extend in future studies. more...
- Published
- 2021
- Full Text
- View/download PDF
229. Wide-field mosaics of the corneal subbasal nerve plexus in Parkinson’s disease using in vivo confocal microscopy
- Author
-
Fabio Scarpa, Andreas Bartschat, Reza A. Badian, Stephan Allgeier, Ralf Mikut, Neil Lagali, Marco Bellisario, Per Svenningsson, Tor Paaske Utheim, Bernd Köhler, Alessia Colonna, and Mattias Andréasson more...
- Subjects
Statistics and Probability ,Male ,medicine.medical_specialty ,Data Descriptor ,Parkinson's disease ,In vivo confocal microscopy ,Science ,Oceanografi, hydrologi och vattenresurser ,Library and Information Sciences ,Cellular level ,Predictive markers ,Education ,Cornea ,Prognostic markers ,Oceanography, Hydrology and Water Resources ,Ophthalmology ,80 and over ,Medicine ,Humans ,Small field of view ,Aged ,Aged, 80 and over ,Microscopy ,Microscopy, Confocal ,High magnification ,business.industry ,DATA processing & computer science ,Nerve plexus ,Parkinson Disease ,Middle Aged ,medicine.disease ,Wide field ,Computer Science Applications ,medicine.anatomical_structure ,Confocal ,Statistics, Probability and Uncertainty ,ddc:004 ,business ,Information Systems - Abstract
In vivo confocal microscopy (IVCM) is a non-invasive imaging technique facilitating real-time acquisition of images from the live cornea and its layers with high resolution (1–2 µm) and high magnification (600 to 800-fold). IVCM is extensively used to examine the cornea at a cellular level, including the subbasal nerve plexus (SBNP). IVCM of the cornea has thus gained intense interest for probing ophthalmic and systemic diseases affecting peripheral nerves. One of the main drawbacks, however, is the small field of view of IVCM, preventing an overview of SBNP architecture and necessitating subjective image sampling of small areas of the SBNP for analysis. Here, we provide a high-quality dataset of the corneal SBNP reconstructed by automated mosaicking, with an average mosaic image size corresponding to 48 individual IVCM fields of view. The mosaic dataset represents a group of 42 individuals with Parkinson’s disease (PD) with and without concurrent restless leg syndrome. Additionally, mosaics from a control group (n = 13) without PD are also provided, along with clinical data for all included participants., Measurement(s)Prominent corneal nerve fibers • Dendritic CellTechnology Type(s)confocal microscopyFactor Type(s)disease status • comorbiditySample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.16691452 more...
- Published
- 2021
230. SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics
- Author
-
Arild Waaler, Yulia Svetashova, Ahmet Soylu, Evgeny Kharlamov, Ralf Mikut, Baifan Zhou, Gong Cheng, and Andre Gusmao
- Subjects
History ,Polymers and Plastics ,Computer Networks and Communications ,Computer science ,Process (engineering) ,Reuse ,Ontology (information science) ,computer.software_genre ,Semantics ,Industrial and Manufacturing Engineering ,Machine learning ,Ontologies ,Software system ,Business and International Management ,business.industry ,Software architecture ,DATA processing & computer science ,Condition monitoring ,Industry 4.0 ,Human-Computer Interaction ,Templates ,Scripting language ,Semantic technology ,Data integration ,ddc:004 ,Software engineering ,business ,computer ,Software - Abstract
Monitoring of the state, performance, quality of operations and other parameters of equipment and production processes, which is typically referred to as condition monitoring, is an important common practice in many industries including manufacturing, oil and gas, chemical and process industry. In the age of Industry 4.0, where the aim is a deep degree of production automation, unprecedented amounts of data are generated by equipment and processes, and this enables adoption of Machine Learning (ML) approaches for condition monitoring. Development of such ML models is challenging. On the one hand, it requires collaborative work of experts from different areas, including data scientists, engineers, process experts, and managers with asymmetric backgrounds. On the other hand, there is high variety and diversity of data relevant for condition monitoring. Both factors hampers ML modelling for condition monitoring. In this work, we address these challenges by empowering ML-based condition monitoring with semantic technologies. To this end we propose a software system SemML that allows to reuse and generalise ML pipelines for conditions monitoring by relying on semantics. In particular, SemML has several novel components and relies on ontologies and ontology templates for ML task negotiation and for data and ML feature annotation. SemML also allows to instantiate parametrised ML pipelines by semantic annotation of industrial data. With SemML, users do not need to dive into data and ML scripts when new datasets of a studied application scenario arrive. They only need to annotate data and then ML models will be constructed through the combination of semantic reasoning and ML modules. We demonstrate the benefits of SemML on a Bosch use-case of electric resistance welding with very promising results. This work was partially supported by SIRIUS Centre, Norwegian Research Council project number 237898. more...
- Published
- 2021
- Full Text
- View/download PDF
231. Delay-robust Estimation of the Reproduction Number and Comparative Evaluation on Generated Synthetic Data
- Author
-
Benedikt Heidrich, Tillmann Mühlpfordt, Veit Hagenmeyer, and Ralf Mikut
- Subjects
Estimation ,Ground truth ,Source code ,Computer science ,media_common.quotation_subject ,Estimator ,Asset (economics) ,Filter (signal processing) ,Algorithm ,Synthetic data ,Multiple ,media_common - Abstract
The reproduction number is an indicator of the evolution of an epidemic. Consequently, accurate estimators for this number are essential for decision making in politics. Many estimators use filtered data as input to compensate for fluctuations of reported cases. However, for daily-based estimations, this filtering leads to delays. Some approaches use small window sizes for filtering to overcome this issue. This, in turn, leads to an increased periodic behavior of estimators. To overcome these issues, in the present paper, we introduce an estimator for the reproduction number that uses an acausally filtered number of cases as input, hence avoiding both the periodic behavior and the delay. For the filter size, we suggest using a multiple of one week since reported cases often exhibit a weekly pattern. We show that this approach is more robust against periodicities, and that it does not exhibit any delays in the estimation compared to estimators with smaller filter sizes.Moreover, often it is hard to examine estimators in detail because a ground truth is missing. For analyzing different properties of the estimators, we propose a method to generate synthetic datasets that can be taken as ground truths. Importantly, the synthetic data contains all relevant real-world behavior.Finally, we apply the proposed estimator to the publicly available coronavirus disease 2019 (COVID-19) data for Germany. We compare the proposed estimator to two estimators used by the federal German Robert Koch Institut (RKI). We observe that our estimator is more stable than the benchmarks especially if the reproduction number is close to 1. Based on the observation that the proposed estimator appears more robust, it may be a useful asset when considering governmental interventions.The accompanying source code is published under the Apache-2.0 license (https://github.com/timueh/C0VID-19). more...
- Published
- 2020
- Full Text
- View/download PDF
232. Point and contextual anomaly detection in building load profiles of a university campus
- Author
-
Marian Turowski, Veit Hagenmeyer, Till Riedel, Ralf Mikut, Meng Zhang, Michael Beigl, and Long Wang
- Subjects
Electrical load ,Computer science ,020209 energy ,02 engineering and technology ,computer.software_genre ,Autoencoder ,University campus ,Smart grid ,0202 electrical engineering, electronic engineering, information engineering ,Data analysis ,020201 artificial intelligence & image processing ,Point (geometry) ,Anomaly detection ,Data mining ,Encoder ,computer - Abstract
The increasing use of smart meters enables the monitoring and diagnostics of underlying systems. The application of data analysis methods can help to automate monitoring and diagnostics such that human intervention is limited to the situations where and when it is necessary. In a smart grid, diagnostics can relate to faulty smart meters and unusual consumption, corresponding to point anomalies and contextual anomalies. This work compares a Deep Neural Network Regression, an Autoencoder with reconstruction, and the encoder of the Autoencoder as anomaly detection methods. The three models are evaluated on real-world building load profiles of a university campus containing such anomalies. The results demonstrate that the proposed models have superior detection accuracies over benchmarks and differ in their discrimination between anomalies and normal electrical load profiles. At the same time, the models correctly identify different anomalous electrical load profiles that were wrongly labeled as normal. more...
- Published
- 2020
- Full Text
- View/download PDF
233. Predicting Quality of Automated Welding with Machine Learning and Semantics
- Author
-
Yulia Svetashova, Baifan Zhou, Evgeny Kharlamov, Tim Pychynski, Seongsu Byeon, and Ralf Mikut
- Subjects
0209 industrial biotechnology ,Computer science ,business.industry ,Process (engineering) ,media_common.quotation_subject ,02 engineering and technology ,Welding ,Machine learning ,computer.software_genre ,Pipeline (software) ,law.invention ,Pipeline transport ,020901 industrial engineering & automation ,law ,Feature (computer vision) ,020204 information systems ,0202 electrical engineering, electronic engineering, information engineering ,Domain knowledge ,Quality (business) ,Artificial intelligence ,business ,Spot welding ,computer ,media_common - Abstract
Manufacturing of car bodies heavily relies on demanding welding processes of joining body parts together that introduce thousands of joining welding spots in each car. Quality monitoring for these spots impacts production efficiency and cost. In this paper we develop an ML pipeline to predict the spot quality before the actual welding happens. This pipeline is based on a Feature Engineering~(FE) approach to manually design features using domain knowledge. We evaluated the pipeline with two datasets from industrial plants, achieving very promising results with prediction errors around 2%. Then, we develop an approach to semantically enhance FE pipelines in order to automate the ML process without compromising the prediction accuracy and to facilitate generalisation and transfer of FE-based models to other datasets and processes. Our ML pipeline has been deployed offline on various Bosch manufacturing datasets in a controlled environment since early 2019 and evaluated. more...
- Published
- 2020
- Full Text
- View/download PDF
234. Author response: MondoA regulates gene expression in cholesterol biosynthesis-associated pathways required for zebrafish epiboly
- Author
-
Meltem Weger, Jonas Mertes, Andrei Yu Kobitski, Thomas Dickmeis, Philipp Gut, Uwe Strähle, Gerd Ulrich Nienhaus, Nils Krone, Benjamin D. Weger, Masanari Takamiya, Cédric Gobet, Alice Parisi, Andrea Schink, Johannes Stegmaier, Ralf Mikut, and Frédéric Gachon more...
- Subjects
biology ,Gene expression ,Epiboly ,biology.organism_classification ,Zebrafish ,Cholesterol biosynthesis ,Cell biology - Published
- 2020
- Full Text
- View/download PDF
235. Forecasting energy time series with profile neural networks
- Author
-
Marian Turowski, Benedikt Heidrich, Nicole Ludwig, Veit Hagenmeyer, and Ralf Mikut
- Subjects
Artificial neural network ,Computer science ,business.industry ,020209 energy ,Deep learning ,05 social sciences ,02 engineering and technology ,Grid ,Machine learning ,computer.software_genre ,Load profile ,Convolutional neural network ,0502 economics and business ,0202 electrical engineering, electronic engineering, information engineering ,Benchmark (computing) ,Noise (video) ,Artificial intelligence ,business ,computer ,Energy (signal processing) ,050205 econometrics - Abstract
Forecasting the energy demand is essential for network operators to balance the grid, in particular with the increasing share of renewable energy sources. Neural networks, especially deep neural networks, have shown promising results in recent forecasting tasks. However, they often struggle learning periodicities in time series efficiently. In line with the finding that deep learning can be improved with statistical information, we introduce profile neural networks based on the fast and promising convolutional neural networks. The underlying idea of profile neural networks is that decomposing periodic energy time series into a standard load profile, a trend, and a colorful noise module improves the forecasting accuracy. The proposed deep neural network architecture is applied to real-world electricity data from buildings on a university campus, more specifically of one building with strong seasonal variation and one building with weak seasonal variation. The new architecture outperforms current state-of-the-art deep learning benchmark models regarding the forecasting accuracy on forecast horizons of one day and one week-ahead, improving the mean absolute scaled error by up to 25%, as well as regarding the trade-off between training time and accuracy. more...
- Published
- 2020
- Full Text
- View/download PDF
236. BeadNet: deep learning-based bead detection and counting in low-resolution microscopy images
- Author
-
Johannes Stegmaier, Andreas Bartschat, Tim Scherr, Ralf Mikut, Véronique Orian-Rousseau, Markus Reischl, Karolin Streule, and Moritz Böhland
- Subjects
Statistics and Probability ,AcademicSubjects/SCI01060 ,Computer science ,Bead ,Biochemistry ,03 medical and health sciences ,Deep Learning ,ddc:570 ,Microscopy ,Code (cryptography) ,Image Processing, Computer-Assisted ,Molecular Biology ,030304 developmental biology ,0303 health sciences ,business.industry ,Low resolution ,Deep learning ,DATA processing & computer science ,030302 biochemistry & molecular biology ,Process (computing) ,Pattern recognition ,Applications Notes ,Computer Science Applications ,Computational Mathematics ,Computational Theory and Mathematics ,visual_art ,visual_art.visual_art_medium ,Artificial intelligence ,ddc:004 ,business ,Bioimage Informatics ,Algorithms ,Software - Abstract
Bioinformatics 36(17), 4668-4670 (2020). doi:10.1093/bioinformatics/btaa594, Published by Oxford Univ. Press, Oxford
- Published
- 2020
- Full Text
- View/download PDF
237. Ontology-Enhanced Machine Learning: A Bosch Use Case of Welding Quality Monitoring
- Author
-
Stefan Schmidt, Ralf Mikut, Tim Pychynski, Yulia Svetashova, York Sure-Vetter, Baifan Zhou, and Evgeny Kharlamov
- Subjects
Computer science ,business.industry ,Process (engineering) ,010401 analytical chemistry ,Automotive industry ,020207 software engineering ,02 engineering and technology ,Ontology (information science) ,Machine learning ,computer.software_genre ,Electric resistance welding ,01 natural sciences ,Pipeline (software) ,0104 chemical sciences ,Variety (cybernetics) ,Task (project management) ,0202 electrical engineering, electronic engineering, information engineering ,Semantic technology ,Artificial intelligence ,business ,computer - Abstract
In the automotive industry, welding is a critical process of automated manufacturing and its quality monitoring is important. IoT technologies behind automated factories enable adoption of Machine Learning (ML) approaches for quality monitoring. Development of such ML models requires collaborative work of experts from different areas, including data scientists, engineers, process experts, and managers. The asymmetry of their backgrounds, the high variety and diversity of data relevant for quality monitoring pose significant challenges for ML modeling. In this work, we address these challenges by empowering ML-based quality monitoring methods with semantic technologies. We propose a system, called SemML, for ontology-enhanced ML pipeline development. It has several novel components and relies on ontologies and ontology templates for task negotiation and for data and ML feature annotation. We evaluated SemML on the Bosch use-case of electric resistance welding with very promising results. more...
- Published
- 2020
- Full Text
- View/download PDF
238. Evaluation of semi-supervised learning using sparse labeling to segment cell nuclei
- Author
-
Roman Bruch, Rüdiger Rudolf, Markus Reischl, and Ralf Mikut
- Subjects
semi-supervised learning ,sparse labeling ,iterative training ,Computer science ,business.industry ,DATA processing & computer science ,education ,Biomedical Engineering ,deep learning ,Pattern recognition ,Semi-supervised learning ,semantic segmentation ,Medicine ,Artificial intelligence ,ddc:004 ,business - Abstract
The analysis of microscopic images from cell cultures plays an important role in the development of drugs. The segmentation of such images is a basic step to extract the viable information on which further evaluation steps are build. Classical image processing pipelines often fail under heterogeneous conditions. In the recent years deep neuronal networks gained attention due to their great potentials in image segmentation. One main pitfall of deep learning is often seen in the amount of labeled data required for training such models. Especially for 3D images the process to generate such data is tedious and time consuming and thus seen as a possible reason for the lack of establishment of deep learning models for 3D data. Efforts have been made to minimize the time needed to create labeled training data or to reduce the amount of labels needed for training. In this paper we present a new semisupervised training method for image segmentation of microscopic cell recordings based on an iterative approach utilizing unlabeled data during training. This method helps to further reduce the amount of labels required to effectively train deep learning models for image segmentation. By labeling less than one percent of the training data, a performance of 90% compared to a full annotation with 342 nuclei can be achieved. more...
- Published
- 2020
- Full Text
- View/download PDF
239. Microscopic & non Invasive Imaging
- Author
-
Klaus-Martin Reichert, Andreas Bartschat, Bernd Köhler, Stephan Allgeier, Ralf Mikut, Karsten Sperlich, Sebastian Bohn, and Oliver Stachs
- Subjects
Focus (computing) ,Materials science ,In vivo ,Confocal microscopy ,law ,Biomedical Engineering ,Biomedical engineering ,law.invention - Published
- 2018
- Full Text
- View/download PDF
240. On the use of probabilistic forecasts in scheduling of renewable energy sources coupled to storages
- Author
-
Jorge Ángel González Ordiano, Veit Hagenmeyer, Ralf Mikut, Riccardo Remo Appino, and Timm Faulwasser
- Subjects
Mathematical optimization ,Optimization problem ,business.industry ,020209 energy ,Mechanical Engineering ,020208 electrical & electronic engineering ,Probabilistic logic ,Economic dispatch ,02 engineering and technology ,Building and Construction ,Management, Monitoring, Policy and Law ,Energy storage ,Renewable energy ,Electric power system ,Model predictive control ,General Energy ,0202 electrical engineering, electronic engineering, information engineering ,Economics ,Probabilistic forecasting ,business - Abstract
Electric energy generation from renewable energy sources is generally non-dispatchable due to its intrinsic volatility. Therefore, its integration into electricity markets and in power system operation is often based on volatility-compensating energy storage systems. Scheduling and control of this kind of coupled systems is usually based on hierarchical control and optimization. On the upper level, one solves an optimization problem to compute a dispatch schedule and a coherent allocation of energy reserves. On the lower level, one performs online adjustments of the dispatch schedule using, for example, model predictive control. In the present paper, we propose a formulation of the upper level optimization based on data-driven probabilistic forecasts of the power and energy output of the uncontrollable loads and generators dependent on renewable energy sources. Specifically, relying on probabilistic forecasts of both power and energy profiles of the uncertain demand/generation, we propose a novel framework to ensure the online feasibility of the dispatch schedule with a given security level. The efficacy of the proposed scheme is illustrated by simulations based on real household production and consumption data. more...
- Published
- 2018
- Full Text
- View/download PDF
241. Data processing of high-rate low-voltage distribution grid recordings for smart grid monitoring and analysis.
- Author
-
Heiko Maaß, Hüseyin Kemâl çakmak, Felix Bach, Ralf Mikut, Aymen Harrabi, Wolfgang Süß, Wilfried Jakob, Karl-Uwe Stucky, Uwe G. Kühnapfel, and Veit Hagenmeyer
- Published
- 2015
- Full Text
- View/download PDF
242. Probabilistic forecasts of the distribution grid state using data-driven forecasts and probabilistic power flow
- Author
-
Timm Faulwasser, Jianlei Liu, Tillmann Mühlpfordt, Veit Hagenmeyer, Uwe Kuhnapfel, Simon Waczowicz, Ralf Mikut, Clemens Düpmeier, Eric Braun, Riccardo Remo Appino, Huseyin K. Cakmak, and Jorge Angel Gonzalez-Ordiano more...
- Subjects
Mathematical optimization ,business.industry ,Computer science ,Mechanical Engineering ,Computation ,DATA processing & computer science ,Probabilistic logic ,Building and Construction ,Management, Monitoring, Policy and Law ,Grid ,Data-driven ,Renewable energy ,General Energy ,State (computer science) ,ddc:004 ,business ,Energy (signal processing) ,Quantile - Abstract
The uncertainty associated with renewable energies creates challenges in the operation of distribution grids. One way for Distribution System Operators to deal with this is the computation of probabilistic forecasts of the full state of the grid. Recently, probabilistic forecasts have seen increased interest for quantifying the uncertainty of renewable generation and load. However, individual probabilistic forecasts of the state defining variables do not allow the prediction of the probability of joint events, for instance, the probability of two line flows exceeding their limits simultaneously. To overcome the issue of estimating the probability of joint events, we present an approach that combines data-driven probabilistic forecasts (obtained more specifically with quantile regressions) and probabilistic power flow. Moreover, we test the presented method using data from a real-world distribution grid that is part of the Energy Lab 2.0 of the Karlsruhe Institute of Technology and we implement it within a state-of-the-art computational framework. more...
- Published
- 2021
- Full Text
- View/download PDF
243. Charakterisierung der Fahrbahnbeschaffenheit durch Data Mining von gemessenen kinematischen Fahrzeuggrößen
- Author
-
Frank Gauterin, Markus Reischl, Guillaume Levasseur, Michael Frey, Ralf Mikut, and Johannes Masino
- Subjects
050210 logistics & transportation ,Control and Systems Engineering ,Computer science ,020209 energy ,0502 economics and business ,05 social sciences ,0202 electrical engineering, electronic engineering, information engineering ,02 engineering and technology ,Electrical and Electronic Engineering ,Computer Science Applications - Abstract
Zusammenfassung Die Arbeit beschreibt eine Untersuchung von Data-Mining-Ansätzen zur Klassifikation der Fahrbahnbeschaffenheit mittels einfacher Beschleunigungssensoren und Gyroskope. Ziel ist sowohl die Klassifikation des Fahrbahnmaterials als auch das Erkennen von Unregelmäßigkeiten wie z. B. Schlaglöcher oder Bahnübergänge. Aus den Sensorsignalen werden frequenzbasierte Merkmale extrahiert, automatisch bewertet und diskutiert. Die besten Merkmale kommen beim Entwurf verschiedener Klassifikationsverfahren zum Einsatz. Die verwendeten Verfahren werden schließlich in einer MATLAB-Toolbox implementiert, die Klassifikationsergebnisse auf Karten ausgibt, so dass eine manuelle Prüfung der Ergebnisse möglich wird. Anhand eines umfangreichen exemplarischen Datensatzes werden die Ergebnisse diskutiert. more...
- Published
- 2017
- Full Text
- View/download PDF
244. Data-driven analysis of interactions between people with dementia and a tablet device
- Author
-
Wolfgang Doneit, Tanja Schultz, Timo Schulze, Tobias Gehrig, Felix Putze, Kristina Glesing, Ingo Franz, Philipp Gaerte, Anamaria Depner, Andreas Kruse, Christof Ziegler, Ralf Mikut, Monika Fischer, Marc Aurel Engels, Keni Bernardin, Joachim Herzig, Michael Ricken, Todor Dimitrov, Clarissa Simon, Dietmar Bothe, Jana Lohse, and Irene Maucher more...
- Subjects
030214 geriatrics ,Computer science ,DATA processing & computer science ,lcsh:R ,Biomedical Engineering ,tablet device ,lcsh:Medicine ,data mining ,medicine.disease ,Data-driven ,03 medical and health sciences ,0302 clinical medicine ,Human–computer interaction ,medicine ,Dementia ,030212 general & internal medicine ,ddc:004 ,events ,dementia - Abstract
In the project I-CARE a technical system for tablet devices is developed that captures the personal needs and skills of people with dementia. The system provides activation content such as music videos, biographical photographs and quizzes on various topics of interest to people with dementia, their families and professional caregivers. To adapt the system, the activation content is adjusted to the daily condition of individual users. For this purpose, emotions are automatically detected through facial expressions, motion, and voice. The daily interactions of the users with the tablet devices are documented in log files which can be merged into an event list. In this paper, we propose an advanced format for event lists and a data analysis strategy. A transformation scheme is developed in order to obtain datasets with features and time series for popular methods of data mining. The proposed methods are applied to analysing the interactions of people with dementia with the I-CARE tablet device. We show how the new format of event lists and the innovative transformation scheme can be used to compress the stored data, to identify groups of users, and to model changes of user behaviour. As the I-CARE user studies are still ongoing, simulated benchmark log files are applied to illustrate the data mining strategy. We discuss possible solutions to challenges that appear in the context of I-CARE and that are relevant to a broad range of applications. more...
- Published
- 2017
- Full Text
- View/download PDF
245. In-vivo-Bildgebung des kornealen Nervenplexus
- Author
-
Klaus-Martin Reichert, Stephan Allgeier, Ralf Mikut, Sebastian Bohn, Andreas Bartschat, Rainer Guthoff, Oliver Stachs, Bernd Köhler, and Karsten Winter
- Subjects
Gynecology ,03 medical and health sciences ,Ophthalmology ,medicine.medical_specialty ,0302 clinical medicine ,business.industry ,030221 ophthalmology & optometry ,medicine ,030209 endocrinology & metabolism ,business - Abstract
Der subbasale Nervenplexus (SNP) der Kornea bietet die Moglichkeit, periphere Nervenstrukturen nichtinvasiv in vivo mithilfe der Konfokalmikroskopie (CCM) zu untersuchen. Morphologische Veranderungen des SNP konnen so unmittelbar detektiert und quantitativ charakterisiert werden. Aufgrund der inhomogenen Verteilung der Nervenfasern reicht eine einzelne CCM-Aufnahme fur eine valide Diagnose nicht aus. Gesucht werden daher Verfahren zur grosflachigen Erfassung des SNP. Dieser Beitrag gibt einen Uberblick uber publizierte Ansatze zur Losung dieses Problems. Aktuelle Entwicklungsarbeiten am Karlsruher Institut fur Technologie und der Universitatsaugenklinik in Rostock lassen zukunftig eine vereinfachte Handhabung der Technologie und eine weitere Verbesserung der Bildqualitat erwarten. more...
- Published
- 2017
- Full Text
- View/download PDF
246. Aus der Arbeit des GMA-FA 5.14 'Computational Intelligence'.
- Author
-
Ralf Mikut
- Published
- 2009
- Full Text
- View/download PDF
247. [Digital Image Processing and Deep Neural Networks in Ophthalmology - Current Trends]
- Author
-
Andreas, Bartschat, Stephan, Allgeier, Sebastian, Bohn, Tim, Scherr, Denis, Blessing, Klaus-Martin, Reichert, Markus, Reischl, Oliver, Stachs, Bernd, Koehler, and Ralf, Mikut
- Subjects
Ophthalmology ,Deep Learning ,Microscopy, Confocal ,Image Processing, Computer-Assisted ,Neural Networks, Computer - Abstract
The use of deep neural networks ("deep learning") creates new possibilities in digital image processing. This approach has been widely applied and successfully used for the evaluation of image data in ophthalmology. In this article, the methodological approach of deep learning is examined and compared to the classical approach for digital image processing. The differences between the approaches are discussed and the increasingly important role of training data for model generation is explained. Furthermore, the approach of transfer learning for deep learning is presented with a representative data set from the field of corneal confocal microscopy. In this context, the advantages of the method and the specific problems when dealing with medical microscope data will be discussed.Der Einsatz von Tiefen Neuronalen Netzen (Deep Learning) eröffnet neue Möglichkeiten in der digitalen Bildverarbeitung. Auch für die Auswertung von Bilddaten in der Ophthalmologie wird diese Methode erfolgreich eingesetzt und findet weite Verbreitung. In diesem Artikel wird die methodische Vorgehensweise beim Deep Learning betrachtet und der klassischen Vorgehensweise für die Entwicklung von Methoden für die digitale Bildverarbeitung gegenübergestellt. Dabei wird auf Unterschiede eingegangen und die wichtiger werdende Rolle von Trainingsdaten für die Modellbildung erklärt. Weiterhin wird die Vorgehensweise des Transfer-Lernens (Transfer Learning) für Deep Learning am Beispiel eines Datensatzes aus der kornealen Konfokalmikroskopie vorgestellt. Dabei wird auf die Vorteile der Methode und auf Besonderheiten beim Umgang mit medizinischen Mikroskopdaten eingegangen. more...
- Published
- 2019
248. The effect of lipidation and glycosylation on short cationic antimicrobial peptides
- Author
-
Elizabeth M Grimsey, Ralf Mikut, Dominic W. P. Collis, and Kai Hilpert
- Subjects
0301 basic medicine ,Methicillin-Resistant Staphylococcus aureus ,Glycosylation ,medicine.drug_class ,Polymyxin ,Antimicrobial peptides ,Antibiotics ,Biophysics ,Microbial Sensitivity Tests ,01 natural sciences ,Biochemistry ,Microbiology ,Vancomycin-Resistant Enterococci ,03 medical and health sciences ,chemistry.chemical_compound ,Structure-Activity Relationship ,Anti-Infective Agents ,Drug Resistance, Multiple, Bacterial ,medicine ,Humans ,chemistry.chemical_classification ,010405 organic chemistry ,Fatty acid ,Cell Biology ,Antimicrobial ,Lipid Metabolism ,Glycopeptide ,0104 chemical sciences ,Anti-Bacterial Agents ,030104 developmental biology ,chemistry ,PEGylation ,Antimicrobial Cationic Peptides - Abstract
The global health threat surrounding bacterial resistance has resulted in antibiotic researchers shifting their focus away from 'traditional' antibiotics and concentrating on other antimicrobial agents, including antimicrobial peptides. These low molecular weight "mini-proteins" exhibit broad-spectrum activity against bacteria, including multi-drug resistant strains, viruses, fungi and protozoa and constitute a major element of the innate-immune system of many multicellular organisms. Some naturally occurring antimicrobial peptides are lipidated and/or glycosylated and almost all antimicrobial peptides in clinical use are either lipopeptides (Daptomycin and Polymyxin E and B) or glycopeptides (Vancomycin). Lipidation, glycosylation and PEGylation are an option for improving stability and activity in serum and for reducing the rapid clearing via the kidneys and liver. Two broad-spectrum antimicrobial peptides NH2-RIRIRWIIR-CONH2 (A1) and NH2-KRRVRWIIW-CONH2 (B1) were conjugated via a linker, producing A2 and B2, to individual fatty acids of C8, C10, C12 and C14 and in addition, A2 was conjugated to either glucose, N-acetyl glucosamine, galactose, mannose, lactose or polyethylene glycol (PEG). Antimicrobial activity against two Gram-positive strains (methicillin resistant Staphylococcus aureus (MRSA) and vancomycin resistant Enterococcus faecalis (VRE)) and three Gram-negative strains (Salmonella typhimurium, E. coli and Pseudomonas aeruginosa) were determined. Activity patterns for the lipidated versions are very complex, dependent on sequence, bacteria and fatty acid. Two reciprocal effects were measured; compared to the parental peptides, some combinations led to a 16-fold improvement whereas other combinations let to a 32-fold reduction in antimicrobial activity. Glycosylation decreased antimicrobial activity by 2 to 16-fold in comparison to A1, respectively on the sugar-peptide combination. PEGylation rendered the peptide inactive. Antimicrobial activity in the presence of 25% human serum of A1 and B1 was reduced 32-fold and 8-fold, respectively. The longer chain fatty acids almost completely restored this activity; however, these fatty acids increased hemolytic activity. B1 modified with C8 increased the therapeutic index by 2-fold for four bacterial strains. Our results suggest that finding the right lipid-peptide combination can lead to improved activity in the presence of serum and potentially more effective drug candidates for animal studies. Glycosylation with the optimal sugar and numbers of sugars at the right peptide position could be an alternative route or could be used in addition to lipidation to counteract solubility and toxicity issues. more...
- Published
- 2019
249. Feature Space Exploration for Motion Classification Based on Multi-Modal Sensor Data for Lower Limb Exoskeletons
- Author
-
Isabel Patzer, Tilman Daab, Ralf Mikut, and Tamim Asfour
- Subjects
030506 rehabilitation ,Computer science ,business.industry ,Dimensionality reduction ,Feature vector ,Pattern recognition ,02 engineering and technology ,Exoskeleton ,Reduction (complexity) ,03 medical and health sciences ,Modal ,Feature (computer vision) ,Inertial measurement unit ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,0305 other medical science ,Hidden Markov model ,business - Abstract
In this paper, we address the problem of finding a minimal multi-modal sensor setup for motion classification in lower limb exoskeleton applications while maintaining the classification performance. We present an approach for a systematic exploration of the feature space and feature space dimensionality reduction for motion recognition using Hidden Markov Models (HMMs). We evaluated our approach using IMU and force sensor data with 10 subjects performing 14 different daily activities. We perform a dimensionality reduction on sensor feature level with single- and multi-subjects and we explore the feature space using fine-grained features such as the force value of a single direction. Additionally, we investigate the influence of physical characteristics on the classification quality. Our results show that a subject specific and general reduction of the sensors is possible while still achieving the same classification performance. more...
- Published
- 2019
- Full Text
- View/download PDF
250. On Calendar-Based Scheduling for User-Friendly Charging of Plug-In Electric Vehicles
- Author
-
Riccardo Remo Appino, Karl Schwenk, Veit Hagenmeyer, Ralf Mikut, and Manuel Faix
- Subjects
Cost reduction ,User Friendly ,Test case ,Operations research ,Robustness (computer science) ,Computer science ,Individual mobility ,Plug-in ,Directed graph ,computer.software_genre ,computer ,Scheduling (computing) - Abstract
Users of Plug-in Electric Vehicles (PEVs) struggle to decide when, where and how much to charge their vehicles - a user acceptance issue inadequately dealt with in the literature. Careless choices may endanger individual mobility, and discourage users from using this technology. Here, we propose a calendar-based charging strategy for PEVs that targets the requirements of their users. The proposed scheme aims at maximizing the charging convenience in terms of cost and comfort. In addition, it guarantees the mobility service on any occasion despite the uncertainty affecting users' future behavior. The scheme is based on a receding horizon stochastic algorithm that utilizes scenarios representing possible user behavior as input. We generate these scenarios via a digital user calendar, modeled with directed graphs. To validate the proposed scheduling scheme we simulate the evolution of the stored energy in realistic test cases. For comparison, we simulate the effect of naive charging strategies. The results indicate significant benefits compared with intuitive charging strategies, both in terms of cost reduction and robustness against uncertainty. more...
- Published
- 2019
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.