Refine
Year of publication
- 2016 (277) (remove)
Institute
- Fachbereich Medizintechnik und Technomathematik (54)
- Fachbereich Chemie und Biotechnologie (44)
- Fachbereich Bauingenieurwesen (35)
- Fachbereich Elektrotechnik und Informationstechnik (35)
- IfB - Institut für Bioengineering (35)
- Fachbereich Wirtschaftswissenschaften (31)
- Fachbereich Luft- und Raumfahrttechnik (28)
- Fachbereich Maschinenbau und Mechatronik (25)
- Fachbereich Energietechnik (17)
- INB - Institut für Nano- und Biotechnologien (15)
Document Type
- Article (116)
- Conference Proceeding (81)
- Part of a Book (27)
- Book (23)
- Other (10)
- Conference: Meeting Abstract (8)
- Report (5)
- Doctoral Thesis (3)
- Part of a Periodical (2)
- Patent (1)
Keywords
- Technical Operations Research (2)
- Additive Manufacturing (1)
- Annulus Fibrosus (1)
- Assessment (1)
- Asymptotic efficiency (1)
- Bacillus atrophaeus (1)
- Balance (1)
- Balanced hypergraph (1)
- Brandfall (1)
- Building Systems (1)
The potential of SMART climbing robot combined with a weatherproof cabin for rotor blade maintenance
(2016)
In this paper we present an extension of the action language Golog that allows for using fuzzy notions in non-deterministic argument choices and the reward function in decision-theoretic planning. Often, in decision-theoretic planning, it is cumbersome to specify the set of values to pick from in the non-deterministic-choice-of-argument statement. Also, even for domain experts, it is not always easy to specify a reward function. Instead of providing a finite domain for values in the non-deterministic-choice-of-argument statement in Golog, we now allow for stating the argument domain by simply providing a formula over linguistic terms and fuzzy uents. In Golog’s forward-search DT planning algorithm, these formulas are evaluated in order to find the agent’s optimal policy. We illustrate this in the Diner Domain where the agent needs to calculate the optimal serving order.
20 Years of RoboCup
(2016)
Characterization and evaluation of lignocellulosic biomass 130 hydrolysates for ABE fermentation
(2016)
This paper describes the development of a capacitively coupled high-pressure lamp with input power between 20 and 43 W at 2.45 GHz, using a coaxial line network. Compared with other electrodeless lamp systems, no cavity has to be used and a reduction in the input power is achieved. Therefore, this lamp is an alternative to the halogen incandescent lamp for domestic lighting. To serve the demands of domestic lighting, the filling of the lamp is optimized over all other resulting requirements, such as high efficacy at low induced powers and fast startups. A workflow to develop RF-driven plasma applications is presented, which makes use of the hot S-parameter technique. Descriptions of the fitting process inside a circuit and FEM simulator are given. Results of the combined ignition and operation network from simulations and measurements are compared. An initial prototype is built and measurements of the lamp's lighting properties are presented along with an investigation of the efficacy optimizations using large signal amplitude modulation. With this lamp, an efficacy of 135 lmW -1 is achieved.
The composition of plant biomass varies depending on the feedstock and pre-treatment conditions and influences its processing in biorefineries. In order to ensure optimal process conditions, the quantitative proportion of the main polymeric components of the pre-treated biomass has to be determined. Current standard procedures for biomass compositional analysis are complex, the measurements are afflicted with errors and therefore often not comparable. Hence, new powerful analytical methods are urgently required to characterize biomass. In this contribution, Differential Scanning Calorimetry (DSC) was applied in combination with multivariate data analysis (MVA) to detect the cellulose content of the plant biomass pretreated by Liquid Hot Water (LHW) and Organosolv processes under various conditions. Unlike conventional techniques, the developed analytic method enables the accurate quantification of monosaccharide content of the plant biomass without any previous sample preparation. It is easy to handle and avoids errors in sample preparation.
For the successful implementation of microfluidic reaction systems, such as PCR and electrophoresis, the movement of small liquid volumes is essential. In conventional lab-on-a-chip-platforms, solvents and samples are passed through defined microfluidic channels with complex flow control installations. The droplet actuation platform presented here is a promising alternative. With it, it is possible to move a liquid drop (microreactor) on a planar surface of a reaction platform (lab-in-a-drop). The actuation of microreactors on the hydrophobic surface of the platform is based on the use of magnetic forces acting on the outer shell of the liquid drops which is made of a thin layer of superhydrophobic magnetite particles. The hydrophobic surface of the platform is needed to avoid any contact between the liquid core and the surface to allow a smooth movement of the microreactor. On the platform, one or more microreactors with volumes of 10 µL can be positioned and moved simultaneously. The platform itself consists of a 3 x 3 matrix of electrical double coils which accommodate either neodymium or iron cores. The magnetic field gradients are automatically controlled. By variation of the magnetic field gradients, the microreactors' magnetic hydrophobic shell can be manipulated automatically to move the microreactor or open the shell reversibly. Reactions of substrates and corresponding enzymes can be initiated by merging the microreactors or bringing them into contact with surface immobilized catalysts.
In the field of biotechnology and molecular biology, the use of small liquid volumes has significant advantages. In particular, screening and optimization runs with acceptable amounts of expensive and hardly available catalysts, reagents, or biomolecules are feasible with microfluidic technologies. The presented new microfluidic system is based on the inclusion of small liquid volumes by a protective shell of magnetizable microparticles. Hereby, discrete aqueous microreactor drops with volumes of 1–30 μL can be formed on a simple planar surface. A digital movement and manipulation of the microreactor is performed by overlapping magnetic forces. The magnetic forces are generated by an electrical coil matrix positioned below a glass plate. With the new platform technology, several discrete reaction compartments can be moved simultaneously on one surface. Due to the magnetic fields, the reactors can even be merged to initiate reactions by mixing or positioned above surface-immobilized catalysts and then opened by magnetic force. Comparative synthesis routes of the magnetizable shell particles and superhydrophobic glass slides including their performance and stability with the reaction platform are described. The influence of diffusive mass transport during the catalyzed reaction is discussed by evaluation finite element model of the microreactor. Furthermore, a first model dye reaction of the enzyme laccase has been established.
Evaluation of lignocellulosic material for butanol production using enzymatic hydrolysate medium
(2016)
Butanol is a promising gasoline additive and platform chemical that can be readily produced via acetone-butanolethanol (ABE) fermentation from pretreated lignocellulosic materials. This article examines lignocellulosic material from beech wood for ABE fermentation, using Clostridium acetobutylicum. First, the utilization of both C₅₋ (xylose) and C₆₋ (glucose) sugars as sole carbon source was investigated in static cultivation, using serum bottles and synthetic medium. The utilization of pentose sugar resulted in a solvent yield of 0.231 g·g_sugar⁻¹, compared to 0.262 g·g_sugar⁻¹ using hexose. Then, the Organosolv pretreated crude cellulose fibers (CF) were enzymatically decomposed, and the resulting hydrolysate medium was analyzed for inhibiting compounds (furans, organic acids, phenolics) and treated with ionexchangers for detoxification. Batch fermentation in a bioreactor using CF hydrolysate medium resulted in a total solvent yield of 0.20 gABE·g_sugar⁻¹.
The interplay of albumin (BSA) and lysozyme (LYZ) adsorbed simultaneously on titanium was analyzed by gel electrophoresis and BCA assay. It was found that BSA and lysozyme adsorb cooperatively. Additionally, the isoelectric point of the respective protein influences the adsorption. Also, the enzymatic activity of lysozyme and amylase (AMY) in mixtures with BSA was considered with respect to a possible influence of protein-protein interaction on enzyme activity. Indeed, an increase of lysozyme activity in the presence of BSA could be observed. In contrast, BSA does not influence the activity of amylase.
Schienenverkehrssysteme stehen in zunehmendem Wettbewerb, sowohl untereinander als auch mit anderen Verkehrsträgern. Als wichtiger Aspekt zur Steigerung der Kosteneffizienz wird die Digitalisierung des Betriebs und der Fahrzeuge betrachtet. Über eine Prognose der Ausfallwahrscheinlichkeit bzw. Restlebensdauer von Subsystemen können mittels Digitalisierung die Instandhaltungskosten gesenkt werden. Die geringen Fehlerraten im System Bahn machen die Nutzung besonderer Simulationstechniken notwendig. In diesem Beitrag wird gezeigt, wie sich die Subsystemverfügbarkeit aus den beobachteten Fehlerraten der Teilfunktionen vorhersagen lässt.
This work presents a methodology for automated
damage-sensitive feature extraction and anomaly
detection under multivariate operational variability
for in-flight assessment of wings. The
method uses a passive excitation approach, i. e.
without the need for artificial actuation. The
modal system properties (natural frequencies and
damping ratios) are used as damage-sensitive
features. Special emphasis is placed on the use
of Fiber Bragg Grating (FBG) sensing technology
and the consideration of Operational and
Environmental Variability (OEV). Measurements
from a wind tunnel investigation with a composite
cantilever equipped with FBG and piezoelectric
sensors are used to successfully detect an impact
damage. In addition, the feasibility of damage
localisation and severity estimation is evaluated
based on the coupling found between damageand
OEV-induced feature changes.
The main objective of the BATIMASS project was to address how the energy balance in relatively lightweight steel buildings can be improved by building in ‘active thermal mass’ (ATM) into the building fabric. This was achieved through concept design, dynamic thermal modelling and testing of a number of potentially viable systems and concepts. A significant programme of thermal simulation modelling was undertaken utilising the thermally equivalent slab (TES) concept to model the passive thermal capacity effect of profiled, composite metal floor decks. It is apparent from the modelling results that thermal mass is a highly complex phenomenon which is highly dependent upon building type, occupancy patterns, climate and many other aspects of the building design and servicing strategy. The ATM systems developed, both conceptually and for prototype testing, focussed on water-cooled composite slabs, the Cofradal floor system and the phase change material (PCM) Energain. In addition to laboratory testing of prototypes, whole building monitoring was undertaken at the Kubik building in Spain and the RWTH test building in Germany. Advanced thermal modelling was also undertaken to estimate the likely benefits of the ATM concept designs developed and for comparison with the test results. In addition to thermal testing, structural tests were conducted on composite floor specimens incorporating embedded water pipes. This Final Report presents the results of the activities carried out under this RFCS contract RFSR CT 2012 00033. The work carried out is reported in six major sections corresponding to the technical Work Packages of the project. Only summaries of the work carried out are provided in this report; all work undertaken is fully reported in the formal project deliverables.
Purpose
To assess the feasibility of prostate ¹H MR spectroscopic imaging (MRSI) using low-power spectral-spatial (SPSP) pulses at 7T, exploiting accurate spectral selection and spatial selectivity simultaneously.
Methods
A double spin-echo sequence was equipped with SPSP refocusing pulses with a spectral selectivity of 1 ppm. Three-dimensional prostate ¹H-MRSI at 7T was performed with the SPSP-MRSI sequence using an 8-channel transmit array coil and an endorectal receive coil in three patients with prostate cancer and in one healthy subject. No additional water or lipid suppression pulses were used.
Results
Prostate ¹H-MRSI could be obtained well within specific absorption rate (SAR) limits in a clinically feasible time (10 min). Next to the common citrate signals, the prostate spectra exhibited high spermine signals concealing creatine and sometimes also choline. Residual lipid signals were observed at the edges of the prostate because of limitations in spectral and spatial selectivity.
Conclusion
It is possible to perform prostate ¹H-MRSI at 7T with a SPSP-MRSI sequence while using separate transmit and receive coils. This low-SAR MRSI concept provides the opportunity to increase spatial resolution of MRSI within reasonable scan times.
Compared to peripheral pain, trigeminal pain elicits higher levels of fear, which is assumed to enhance the interruptive effects of pain on concomitant cognitive processes. In this fMRI study we examined the behavioral and neural effects of trigeminal (forehead) and peripheral (hand) pain on visual processing and memory encoding. Cerebral activity was measured in 23 healthy subjects performing a visual categorization task that was immediately followed by a surprise recognition task. During the categorization task subjects received concomitant noxious electrical stimulation on the forehead or hand. Our data show that fear ratings were significantly higher for trigeminal pain. Categorization and recognition performance did not differ between pictures that were presented with trigeminal and peripheral pain. However, object categorization in the presence of trigeminal pain was associated with stronger activity in task-relevant visual areas (lateral occipital complex, LOC), memory encoding areas (hippocampus and parahippocampus) and areas implicated in emotional processing (amygdala) compared to peripheral pain. Further, individual differences in neural activation between the trigeminal and the peripheral condition were positively related to differences in fear ratings between both conditions. Functional connectivity between amygdala and LOC was increased during trigeminal compared to peripheral painful stimulation. Fear-driven compensatory resource activation seems to be enhanced for trigeminal stimuli, presumably due to their exceptional biological relevance.
Objective
This study assesses and quantifies impairment of postoperative magnetic resonance imaging (MRI) at 7 Tesla (T) after implantation of titanium cranial fixation plates (CFPs) for neurosurgical bone flap fixation.
Materials and methods
The study group comprised five patients who were intra-individually examined with 3 and 7 T MRI preoperatively and postoperatively (within 72 h/3 months) after implantation of CFPs. Acquired sequences included T₁-weighted magnetization-prepared rapid-acquisition gradient-echo (MPRAGE), T₂-weighted turbo-spin-echo (TSE) imaging, and susceptibility-weighted imaging (SWI). Two experienced neurosurgeons and a neuroradiologist rated image quality and the presence of artifacts in consensus reading.
Results
Minor artifacts occurred around the CFPs in MPRAGE and T2 TSE at both field strengths, with no significant differences between 3 and 7 T. In SWI, artifacts were accentuated in the early postoperative scans at both field strengths due to intracranial air and hemorrhagic remnants. After resorption, the brain tissue directly adjacent to skull bone could still be assessed. Image quality after 3 months was equal to the preoperative examinations at 3 and 7 T.
Conclusion
Image quality after CFP implantation was not significantly impaired in 7 T MRI, and artifacts were comparable to those in 3 T MRI.
Purpose
To calculate local specific absorption rate (SAR) correctly, both the amplitude and phase of the signal in each transmit channel have to be known. In this work, we propose a method to derive a conservative upper bound for the local SAR, with a reasonable safety margin without knowledge of the transmit phases of the channels.
Methods
The proposed method uses virtual observation points (VOPs). Correction factors are calculated for each set of VOPs that prevent underestimation of local SAR when the VOPs are applied with the correct amplitudes but fixed phases.
Results
The proposed method proved to be superior to the worst-case calculation based on the maximum eigenvalue of the VOPs. The mean overestimation for six coil setups could be reduced, whereas no underestimation of the maximum local SAR occurred. In the best investigated case, the overestimation could be reduced from a factor of 3.3 to a factor of 1.7.
Conclusion
The upper bound for the local SAR calculated with the proposed method allows a fast estimation of the local SAR based on power measurements in the transmit channels and facilitates SAR monitoring in systems that do not have the capability to monitor transmit phases
Zum Zweck der Kapitalanlage beteiligte sich der Bekl. an einer Publikumsgesellschaft. Diese war als (mehrgliedrige) atypische stille Gesellschaft organisiert (vgl. a. BGHZ 199, 104 = DNotZ 2014, 374 = NZG 2013, 1422 = DStR 2014, 45 Rn. 18). Der Gesellschaftsvertrag („GV“) sah für diejenigen Gesellschafter, die wie der Bekl. ihre Einlage in Form einer Einmaleinlage erbracht hatten, eine jährliche gewinnunabhängige Ausschüttung vor. Es sollte sich dabei ausdrücklich nicht um eine Garantieverzinsung handeln. Ende 2009 wurde die stille Gesellschaft durch Mehrheitsbeschluss der Stillen aufgelöst. Nach dem GV waren die Stillen im Falle ihres Ausscheidens sowie bei „Liquidation des Unternehmens“ des Geschäftsinhabers verhältnismäßig an dem jeweils seit ihrem Beitritt gebildeten Vermögen einschließlich der stillen Reserven sowie eines evtl. Geschäftswerts zu beteiligen (Auseinandersetzungswert). Den sich hiernach für den Bekl. auf seinem Kapitalkonto ergebenden Negativsaldo sollte dieser durch Erstattung der von ihm erhaltenen gewinnunabhängigen Auszahlungen ausgleichen. Anders als das LG als Berufungsinstanz bejahte der BGH auf Grundlage des GV einen Rückerstattungsanspruch der klagenden Geschäftsinhaberin.
Robotergestütztes System für ein verbessertes neuromuskuläres Aufbautraining der Beinstrecker
(2016)
Neuromuskuläres Aufbautraining der Beinstrecker ist ein wichtiger Bestandteil in der Rehabilitation und Prävention von Muskel-Skelett-Erkrankungen. Effektives Training erfordert hohe Muskelkräfte, die gleichzeitig hohe Belastungen von bereits geschädigten Strukturen bedeuten. Um trainingsinduzierte Schädigungen zu vermeiden, müssen diese Kräfte kontrolliert werden. Mit heutigen Trainingsgeräten können diese Ziele allerdings nicht erreicht werden. Für ein sicheres und effektives Training sollen durch den Einsatz der Robotik, Sensorik, eines Regelkreises sowie Muskel-Skelett-Modellen Belastungen am Zielgewebe direkt berechnet und kontrolliert werden. Auf Basis zweier Vorstudien zu möglichen Stellgrößen wird der Aufbau eines robotischen Systems vorgestellt, das sowohl für Forschungszwecke als auch zur Entwicklung neuartiger Trainingsgeräte verwendet werden kann.
Für die Verarbeitung von natürlicher Sprache ist ein wichtiger Zwischenschritt das Parsing, bei dem für Sätze der natürlichen Sprache Ableitungsbäume bestimmt werden. Dieses Verfahren ist vergleichbar zum Parsen formaler Sprachen, wie z. B. das Parsen eines Quelltextes. Die Parsing-Methoden der formalen Sprachen, z. B. Bottom-up-Parser, können nicht auf das Parsen der natürlichen Sprache übertragen werden, da keine Formalisierung der natürlichen Sprachen existiert [3, 12, 23, 30].
In den ersten Programmen, die natürliche Sprache verarbeiten [32, 41], wurde versucht die natürliche Sprache mit festen Regelmengen zu verarbeiten. Dieser Ansatz stieß jedoch schnell an seine Grenzen, da die Regelmenge nicht vollständig sowie nicht minimal ist und wegen der benötigten Menge an Regeln schwer zu verwalten ist. Die Korpuslinguistik [22] bot die Möglichkeit, die Regelmenge durch Supervised-Machine-Learning-Verfahren [2] abzulösen.
Teil der Korpuslinguistik ist es, große Textkorpora zu erstellen und diese mit sprachlichen Strukturen zu annotieren. Zu diesen Strukturen gehören sowohl die Wortarten als auch die Ableitungsbäume der Sätze. Vorteil dieser Methodik ist es, dass repräsentative Daten zur Verfügung stehen. Diese Daten werden genutzt, um mit Supervised-Machine-Learning-Verfahren die Gesetzmäßigkeiten der natürliche Sprachen zu erlernen.
Das Maximum-Entropie-Verfahren ist ein Supervised-Machine-Learning-Verfahren, das genutzt wird, um natürliche Sprache zu erlernen. Ratnaparkhi [25] nutzt Maximum-Entropie, um Ableitungsbäume für Sätze der natürlichen Sprache zu erlernen. Dieses Verfahren macht es möglich, die natürliche Sprache (abgebildet als Σ∗) trotz einer fehlenden formalen Grammatik zu parsen.
This summer, RoboCup competitions were held for the 20th time in Leipzig, Germany. It was the second time that RoboCup took place in Germany, 10 years after the 2006 RoboCup in Bremen. In this article, we give an overview on the latest developments of RoboCup and what happened in the different leagues over the last decade. With its 20th edition, RoboCup clearly is a success story and a role model for robotics competitions. From our personal view point, we acknowledge this by giving a retrospection about what makes RoboCup such a success.
Mit steigenden Dämmstandards und höheren Komfortanforderungen der Nutzer gerät die Problematik der sommerlichen Überhitzung zunehmend in den Fokus. Um die Überhitzung möglichst gering zu halten, sind Maßnahmen und Lösungen zu entwickeln, die den potenziellen Kühlbedarf eines Gebäudes vermeiden sowie reduzieren. Im Rahmen des europäischen Forschungsprojektes BATIMASS wurden Techniken untersucht, die die sommerliche Raumtemperatur ohne zusätzliche Kühlung (passiv) oder aber mit energieeffizienter wasserbasierter Flächenkühlung (aktiv) reduzieren und die besonders für Gebäude in Stahl(leicht)bauweise geeignet sind. Dafür wurde die Methodik der thermisch äquivalenten Decke weiterentwickelt, um das thermische Verhalten von Profilblechdecken in Gebäuden für beide Lösungsansätze analysieren zu können. Darüber hinaus wurde der Einsatz von Phasenwechselmaterial (PCM) zur Steigerung der Speicherfähigkeit von leichten Decken mit besonders geringer thermischer Masse in Simulationen sowie im Labor untersucht und bewertet.
This article discusses the contrast between the information transportation companies provide to travellers and that of their brand messaging. Companies’ brand messaging often portrays the service they provide as pleasant, stress free and perfect. Customers and users of the service, on the other hand, often describe their experience of the service as a negative one. This article suggests that the brand value would be greater if transportation companies paid more attention to the users’ experience when designing their information systems, particularly in worst case scenarios.
The enormous diversity of seed traits is an intriguing feature and critical for the overwhelming success of higher plants. In particular, seed mass is generally regarded to be key for seedling development but is mostly approximated by using scanning methods delivering only two-dimensional data, often termed seed size. However, three-dimensional traits, such as the volume or mass of single seeds, are very rarely determined in routine measurements. Here, we introduce a device named phenoSeeder, which enables the handling and phenotyping of individual seeds of very different sizes. The system consists of a pick-and-place robot and a modular setup of sensors that can be versatilely extended. Basic biometric traits detected for individual seeds are two-dimensional data from projections, three-dimensional data from volumetric measures, and mass, from which seed density is also calculated. Each seed is tracked by an identifier and, after phenotyping, can be planted, sorted, or individually stored for further evaluation or processing (e.g. in routine seed-to-plant tracking pipelines). By investigating seeds of Arabidopsis (Arabidopsis thaliana), rapeseed (Brassica napus), and barley (Hordeum vulgare), we observed that, even for apparently round-shaped seeds of rapeseed, correlations between the projected area and the mass of seeds were much weaker than between volume and mass. This indicates that simple projections may not deliver good proxies for seed mass. Although throughput is limited, we expect that automated seed phenotyping on a single-seed basis can contribute valuable information for applications in a wide range of wild or crop species, including seed classification, seed sorting, and assessment of seed quality.
Wind-induced operational variability is one of the major challenges for structural health monitoring of slender engineering structures like aircraft wings or wind turbine blades. Damage sensitive features often show an even bigger sensitivity to operational variability. In this study a composite cantilever was subjected to multiple mass configurations, velocities and angles of attack in a controlled wind tunnel environment. A small-scale impact damage was introduced to the specimen and the structural response measurements were repeated. The proposed damage detection methodology is based on automated operational modal analysis. A novel baseline preparation procedure is described that reduces the amount of user interaction to the provision of a single consistency threshold. The procedure starts with an indeterminate number of operational modal analysis identifications from a large number of datasets and returns a complete baseline matrix of natural frequencies and damping ratios that is suitable for subsequent anomaly detection. Mahalanobis distance-based anomaly detection is then applied to successfully detect the damage under varying severities of operational variability and with various degrees of knowledge about the present operational conditions. The damage detection capabilities of the proposed methodology were found to be excellent under varying velocities and angles of attack. Damage detection was less successful under joint mass and wind variability but could be significantly improved through the provision of the currently encountered operational conditions.
Label-free Electrostatic Detection of DNA Amplification by PCR Using Capacitive Field-effect Devices
(2016)
A capacitive field-effect EIS (electrolyte-insulator-semiconductor) sensor modified with a positively charged weak polyelectrolyte of poly(allylamine hydrochloride) (PAH)/single-stranded probe DNA (ssDNA) bilayer has been used for a label-free electrostatic detection of pathogen-specific DNA amplification via polymerase chain reaction (PCR). The sensor is able to distinguish between positive and negative PCR solutions, to detect the existence of target DNA amplicons in PCR samples and thus, can be used as tool for a quick verification of DNA amplification and the successful PCR process.
A New Class of Biosensors Based on Tobacco Mosaic Virus and Coat Proteins as Enzyme Nanocarrier
(2016)
Air-water flows can be found in different engineering applications: from nuclear engineering to huge hydraulic structures. In this paper, a single tip fibre optical probe has been used to record high frequency (over 1 MHz) phase functions at different locations of a stepped spillway. These phase functions have been related to the interfacial velocities by means of Artificial Neural Networks (ANN) and the measurements of a classical double tip conductivity probe. Special attention has been put to the input selection and the ANN dimensions. Finally, ANN have shown to be able to link the signal rising times and plateau shapes to the air-water interfacial velocity.