© TUHH, Martin Kunze

Forschung

Themen & Anwendungen

LGSC: Lernendes Galley-Catering-System

Entwurf eines selbstlernenden Galley-Catering-Systems (LGCS), das für Bordvorräte innerhalb der Kette Caterer, Fluggesellschaft, Kabinenbesatzung und Passagier pro Flugroute Daten erzeugt und kommuniziert, daraus lernt und aktiv Entscheidungen trifft

Machine Learning für die Detektion von “weak-bonds” in Klebeverbindungen von Faserverbunden

Auswertung von Messdaten für die Detektion von Klebefehlern in Strukturbauteilen mit Neuralen Netzen

Machine Learning für Automobil-Bremsen und deren Emissionen

Im Rahmen dieses Projekts werden modernste Machine Learning (ML) und Deep Learning Methoden angewandt, um die Emissionen von Bremsstaub und Bremsgeräuschen zu verstehen (Entstehungsmechanismen, Sensitivitäten). Feinste Bremsstäube tragen in urbanen maßgeblich zur gesundheitsschädlichen Belastung der Umwelt bei, während Bremsgeräusche, wie z.

Sustainable & Cost Efficient High Performance Composite Structures - SuCoHS

Künstliche neuronale Netze zur effizienten Quantifizierung von Unsicherheiten in der Analyse von Faserverbundstrukturen

Anomaliedetektion in eingebetteten Systeme

Detektion von unerwartetem Verhalten in eingebetten Systemen - zum Beispiel durch Fehler zur Laufzeit. Maschinelles Lernen dient zunächst dazu, das nominale Verhalten automatisch zu bestimmen.

Zuverlässigkeit von Systemen beim Einsatz von Machine Learning

Wird Machine Learning in der Praxis eingesetzt, können Fehlfunktionen in der zugrunde liegenden Recheninfrastruktur die Korrektheit gefährden. Im Projekt wird dieser Zusammenhang analysiert.

Entwicklung datengetriebener Modelle zur Identifikation umweltfreundlicher Degradationsmodulatoren

Anwendung von Methoden des maschinellen Lernens zur Vorhersage des Einflusses kleiner organischer Additive auf das Degradationsverhalten von Magnesium

Bestärktes Lernen im industriellen Internet der Dinge

Anwendung von Techniken des bestärkten Lernens im MAC-Protkoll IEEE 802.15.4 DSME

Business Analytics in der Maritimen Logistik

Optimierungspotenziale und strategische Risiken für maritime logistische Systeme

Modellierung von Schwingungssystemen mit Machine Learning Unterstützung

Neuronale Netze zur Zeitreihenprädiktion in Bezug auf mechanische Schwingungssysteme

Machine Learning for Online Monitoring of Electric Power System Stability

Due to an ever increasing penetration of the electrical power system with power electronics coupled generation and transmission devices as well as loads, their dynamic behaviour will dominate the overall system dynamics in the future.

Maschinelles Lernen für die Elektromagnetische Verträglichkeit

Anwendung maschinelles Lernen im Ingenieursbereich der Elektromagnetischen Verträglichkeit

Machine Learning für ressourcenbeschränkte eingebettete Systeme

Künstliche neuronale Netze auf kleinen Microcontrollern zur Gestenerkennung.

Business Analytics

Optimierungspotenziale und strategische Risiken für maritime logistische Systeme

Publikationen

Suchen Sie in unseren Publikationen mit der Filterfunktion.

Global predictions of primary soil salinization under changing climate in the 21st century

Soil salinization has become one of the major environmental and socioeconomic issues globally and this is expected to be exacerbated …

Time- and Frequency-Domain Dynamic Spectrum Access: Learning Cyclic Medium Access Patterns in Partially Observable Environments

Upcoming communication systems increasingly often tackle the spectrum scarcity problem through the coexistence with legacy systems in …

bSTAB: an open-source software for computing the basin stability of multi-stable dynamical systems

The pervasiveness of multi-stability in nonlinear dynamical systems calls for novel concepts of stability and a consistent …

Data-Driven Radar Processing Using a Parametric Convolutional Neural Network for Human Activity Classification

The paper proposes a data-driven pre-processing optimization for radar data using a parametric convolutional neural network. The …

Neural network surgery: Combining training with topology optimization

With ever increasing computational capacities, neural networks become more and more proficient at solving complex tasks. However, …

Explainable machine learning: A case study on impedance tube measurements

Machine learning (ML) techniques allow for finding hidden patterns and signatures in data. Currently, these methods are gaining …

QMA: A Resource-efficient, Q-learning-based Multiple Access Scheme for the IIoT

Many MAC protocols for the Industrial Internet of Things, such as IEEE 802.15.4 and its extensions, require contention-based channel …

Exploring the application of reinforcement learning to wind farm control

Optimal control of wind farms to maximize power is a challenging task since the wake interaction between the turbines is a highly …

Weak adhesion detection – Enhancing the analysis of vibroacoustic modulation by machine learning

Adhesive bonding is a well-established technique for composite materials. Despite advanced surface treatments and preparations, surface …

Hybrid Modelling by Machine Learning Corrections of Analytical Model Predictions towards High-Fidelity Simulation Solutions

Within the fields of materials mechanics, the consideration of physical laws in machine learning predictions besides the use of data …

Explainable machine learning determines effects on the sound absorption coefficient measured in the impedance tube

Measurements of acoustic properties of sound absorbing materials in impedance tubes show poor reproducibility, which was demonstrated …

Deep learning for brake squeal: Brake noise detection, characterization and prediction

Despite significant advances in modeling of friction-induced vibrations and brake squeal, the majority of industrial research and …

Integrated Simulation-Based Optimization of Operational Decisions at Container Terminals

At container terminals, many cargo handling processes are interconnected and occur in parallel. Within short time windows, many …

Exploring structure-property relationships in magnesium dissolution modulators

Small organic molecules that modulate the degradation behavior of Mg constitute benign and useful materials to modify the service …

Artificial Neural Networks for Sensor Data Classification on Small Embedded Systems

In this paper we investigate the usage of machine learning for interpreting measured sensor values in sensor modules. In particular we …

Predicting long-term dynamics of soil salinity and sodicity on a global scale

Knowledge of spatiotemporal distribution and likelihood of (re)occurrence of salt-affected soils is crucial to our understanding of …

Industrial Federated Learning – Requirements and System Design

Federated Learning (FL) is a very promising approach for improving decentralized Machine Learning (ML) models by exchanging knowledge …

ANN Performance for the Prediction of High-Speed Digital Interconnects over Multiple PCBs

In this paper the performance and the accuracy of artificial neural networks for the prediction of high-speed digital interconnects up …

JavaScript malware detection using locality sensitive hashing

In this paper, we explore the idea of using locality sensitive hashes as input features to a feed-forward neural network with the goal …

Comparison of Collaborative versus Extended Artificial Neural Networks for PDN Design

Currently machine learning tools are not capable to provide analysis solutions for complex printed circuit boards. It is unknown how to …

Mechanical Performance Prediction for Friction Riveting Joints of Dissimilar Materials via Machine Learning

Solid-state joining techniques have become increasingly attractive for joining similar and dissimilar materials because it enables …

Towards Delay-Minimal Scheduling through Reinforcement Learning in IEEE 802.15.4 DSME

The rise of wireless sensor networks (WSNs) inindustrial applications imposes novel demands on existing wireless protocols. The …

Parareal with a Learned Coarse Model for Robotic Manipulation

A key component of many robotics model-based planning and control algorithms is physics predictions, that is, forecasting a sequence of …

A Deep Learning Approach for Pose Estimation from Volumetric OCT Data

Tracking the pose of instruments is a central problem in image-guided surgery. For microscopic scenarios, optical coherence tomography …

Melanoma detection with electrical impedance spectroscopy and dermoscopy using joint deep learning models

The initial assessment of skin lesions is typically based on dermoscopic images. As this is a difficult and time-consuming task, …

Left Ventricle Quantification Using Direct Regression with Segmentation Regularization and Ensembles of Pretrained 2D and 3D CNNs

Cardiac left ventricle (LV) quantification provides a tool for diagnosing cardiac diseases. Automatic calculation of all relevant LV …

Joint Learning of Geometric and Probabilistic Constellation Shaping

The choice of constellations largely affects the performance of communication systems. When designing constellations, both the …

A machine learning-based method for simulation of ship speed profile in a complex ice field

Computational methods for predicting ship speed profile in a complex ice field have traditionally relied on mechanistic simulations. …

Trainable Communication Systems: Concepts and Prototype

We consider a trainable point-to-point communication system, where both transmitter and receiver are implemented as neural networks …

Local monitoring of embedded applications and devices using artificial neural networks

Reliability, security, and safety become even more challenging in times of the Internet of Things (IoT). Devices operate jointly in …

Evaluation of Neural Networks to Predict Target Impedance Violations of Power Delivery Networks

An artificial neural network approach is presented to predict whether a power delivery network setup violates the target impedance. …

Online Monitoring of Power System Small Signal Stability Using Artificial Neural Networks

Shifting paradigms in electrical power generation, transmission and consumption will affect system dynamics and may negatively …

The 'Dark Side' of Big Data Analytics - Uncovering Path Dependency Risks of BDA-Investments

Recently, information systems (IS) literature has shown an increasing interest in Big Data and Analytics (BDA) to gain competitive …

A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics

Machine learning tools represent key enablers for empowering material scientists andengineers to accelerate the development of novel …

Data Science Based Mg Corrosion Engineering

Magnesium exhibits a high potential for a variety of applications in areas such as transport, energy and medicine. However, untreated …

Force Estimation from OCT Volumes using 3D CNNs

Purpose: Estimating the interaction forces of instruments and tissue is of interest, particularly to provide haptic feedback during …

The Effect of Dimensionality Reduction on Software Vulnerability Prediction Models

Statistical prediction models can be an effective technique to identify vulnerable components in large software projects. Two aspects …

Is Newer Always Better? The Case of Vulnerability Prediction Models

Finding security vulnerabilities in the source code as early as possible is becoming more and more essential. In this respect, …

Predicting Vulnerable Components: Software Metrics vs Text Mining

Building secure software is difficult, time-consuming, and expensive. Prediction models that identify vulnerability prone software …

Predicting Vulnerable Software Components via Text Mining

This paper presents an approach based on machine learning to predict which components of a software application contain security …