Refine
Document Type
- Conference Proceeding (183) (remove)
Conference Type
- Konferenzartikel (183) (remove)
Is part of the Bibliography
- yes (183)
Keywords
- Machine Learning (9)
- Deep Leaning (7)
- Robustness (4)
- machine learning (4)
- Generative Adversarial Network (3)
- Radar (3)
- cryptography (3)
- neural networks (3)
- printed electronics (3)
- Computer Vision (2)
- Current measurement (2)
- Energy Flexibility (2)
- Geophysik (2)
- Kalman Filter (2)
- NB-IoT (2)
- Neural networks (2)
- Predictive Maintenance (2)
- Security (2)
- Stability (2)
- Switches (2)
- UWB radars (2)
- accountability (2)
- artificial intelligence (2)
- autoattack (2)
- catheter ablation (2)
- certificate management (2)
- convolutional neural networks (2)
- efficient training (2)
- explainability (2)
- fairness (2)
- image classification (2)
- imaging algorithms (2)
- interactive visualization (2)
- medical imaging (2)
- microwave (2)
- programming (2)
- responsibility (2)
- scattering measurements (2)
- semantics (2)
- trust (2)
- understandability (2)
- 5G (1)
- 5G mobile communication (1)
- 5G private networks (1)
- AC machines (1)
- AIN Cantilever (1)
- Additive Manufacturing (1)
- Adversarial Attacks (1)
- Adversarial Robustness (1)
- Agent based sensor (1)
- Air Pollution (1)
- Aliasing (1)
- Aluminum (1)
- Amplitude and Phase Errors (1)
- Angle of Arrival (1)
- Anti-Windup (1)
- Approximation (1)
- Artificial Intelligence (1)
- Authentication (1)
- Authorization (1)
- Automated idea generation (1)
- Automation (1)
- Automotive Radar (1)
- Battery storage (1)
- Bearings (1)
- Biomimetics (1)
- Blockchain (1)
- Blockchains (1)
- Boundary conditions (1)
- Bowtie antenna (1)
- CNN (1)
- CNNs (1)
- Calibration (1)
- Challenges in Action Recognition (1)
- Chemical engineering (1)
- Cleaning (1)
- Clustering (1)
- Collaboration of Academia and Industry (1)
- Compensation (1)
- Control Algorithms (1)
- Current Control (1)
- DC-AC converters (1)
- Data Mining (1)
- Data breech (1)
- Debinding (1)
- Deep Learning (1)
- Deep Neural Network (1)
- Demand side flexibility (1)
- Device characterization (1)
- Diagnostics (1)
- Digital Beamforming (1)
- Digital Flex Twin Optimization (1)
- Digital Twin (1)
- Digitale Turschilder (1)
- Digitalization (1)
- Drehstrom (1)
- E-Ink (1)
- E-Paper (1)
- EAP-TLS (1)
- EKF-SLAM (1)
- ETAP Simulations (1)
- Eco-inventive principles (1)
- Economics (1)
- Edge AI (1)
- Education (1)
- Eigenvalues (1)
- Embedded AI (1)
- Embedded Systems (1)
- Energiemanagement (1)
- Energy Flexibility for Companies (1)
- Energy Harvesting (1)
- Energy Management (1)
- Energy Marketing of Industrial Flexibilities (1)
- Energy management (1)
- Energy systems modeling (1)
- Environmental monitoring (1)
- Error (1)
- Estimation (1)
- FUSION (1)
- Failure analysis (1)
- Fault Classification (1)
- Featherweight Go (1)
- Federated Learning (1)
- Field Programmable Gate Array (FPGA) (1)
- Fused Filament Fabrication (1)
- GPU Computing (1)
- Gleichstrom (1)
- Handschrift (1)
- Handswritten Character Recognition (1)
- Harmonic analysis (1)
- Hochspannung (1)
- Hybrid system (1)
- IEC/IEEE 60802 security (1)
- IEEE802.15.4 (1)
- IIoT (1)
- InceptionTime (1)
- Industrial Blockchain (1)
- Inertial (1)
- Ink (1)
- Internet of Things (1)
- Inventive principles (1)
- Inventive problem solving (1)
- Inverters (1)
- IoT Security (1)
- IoT security (1)
- Künstliche Intelligenz (1)
- LPWAN (1)
- Large Grid-Connected PV Systems (1)
- Limiting (1)
- Load Flow Analysis (1)
- Logic gates (1)
- Long Term Evolution (1)
- Low-Cost Füllstandssensor (1)
- Low-Power (1)
- MEMS (1)
- MIMO (1)
- MLOps (1)
- Machine learning (1)
- Magnetic sensors (1)
- Manufacturing automation (1)
- Manufacturing industries (1)
- Mean Square Error (1)
- Measurement (1)
- Medizintechnik (1)
- Microgrid(s) (1)
- Mode Collapse (1)
- Model Calibration (1)
- Model Predictive Control (1)
- Model Search (1)
- Monitoring (1)
- Monocular Depth Estimation (1)
- Monte-Carlo (1)
- Monte-Carlo Simulation (1)
- Monte-Carlo method (1)
- NETCONF security (1)
- NFC (1)
- Nature-inspired principles (1)
- Network Test (1)
- Netzintegration (1)
- Nyquist-Shannon (1)
- OT security (1)
- Octave Convolution (1)
- Optimization (1)
- Optimization and control (1)
- Optimization with Digital Twins (1)
- Optische Zeichenerkennung (1)
- PI control (1)
- PKI (1)
- PROFINET IO (1)
- PROFINET Security (1)
- PV System (1)
- Parallelization (1)
- Parameter Estimation (1)
- Parameter estimation (1)
- Pattern Recognition (1)
- Peak shaving (1)
- Peer to peer network (1)
- Performance (1)
- Performance evaluation (1)
- Permanent magnet machines (1)
- Physical Unclonable Functions (1)
- Physical unclonable function (1)
- Power Loss (1)
- Predictions (1)
- Predictive Models (1)
- Process design (1)
- Pulse width modulation (1)
- RFID (1)
- RUL (1)
- Radio frequency (1)
- Random call model (1)
- Real-Time Communication (1)
- Regularization (1)
- Renewable Energy Markets (1)
- Representation Learning (1)
- ResNet (1)
- Road-Quality Prediction (1)
- Roboter (1)
- Rotors (1)
- Sampling (1)
- Second-order Optimization (1)
- Self-Calibration (1)
- Semiconductor Device (1)
- Semiconductor device measurement (1)
- Sensor phenomena and characterization (1)
- Sintering (1)
- Smart Energy Metering (1)
- Smart Gardening (1)
- Smart Grids (1)
- Smart Home (1)
- Smart-UPS (1)
- SmartMAC (1)
- Software (1)
- Software algorithms (1)
- Software for measurements (1)
- Solar Radiation (1)
- Stromregelung (1)
- Stromzustandsregler (1)
- Subspace Clustering (1)
- Substrates (1)
- Sustainable technology (1)
- Synchronmaschine (1)
- Systematic innovation (1)
- TLS (1)
- TRIZ methodology (1)
- TSN security (1)
- Testbed (1)
- Time Sensitive Networking (1)
- Time Synchronization (1)
- Time series data (1)
- Time-series Classification (1)
- TinyML (1)
- Torque (1)
- Total Harmonic Distortion (1)
- Traceability (1)
- Training (1)
- Trust management (1)
- Ultra-Low Energy (1)
- Unsupervised Conditional Training (1)
- Unsupervised Learning (1)
- Variational Autoencoders (1)
- Virtual Reality (1)
- Wireless IoT (1)
- Wireless Sensor Nodes (1)
- Wärmepumpen (1)
- Yolov5 (1)
- accelerometer (1)
- adversarial (1)
- adversarial attacks (1)
- adversarial detection (1)
- attribute manipulation (1)
- autoML (1)
- autonomous systems (1)
- bearing (1)
- bench-marking (1)
- benchmarking (1)
- biocompatibility test (1)
- biodegradable (1)
- biomaterials (1)
- building management systems (1)
- camera-based navigation (1)
- cellular radio (1)
- cifar (1)
- computer network management (1)
- correlation (1)
- credentials (1)
- crossbar (1)
- curb (1)
- curriculum learning (1)
- cybersecurity (1)
- deep learning (1)
- deep reinforcement learning (1)
- defense (1)
- degradation stages (1)
- detection (1)
- dictionary passing (1)
- electrolyte-gated transistors (1)
- embedded systems (1)
- energy harvesting (1)
- face editing (1)
- face recognition (1)
- fail-operational (1)
- fingerprinting (1)
- fourier (1)
- gan (1)
- generative adversarial networks (1)
- ground penetrating radar (1)
- hair (1)
- heat pump (1)
- height estimation (1)
- home automation (1)
- hybrid systems (1)
- identification (1)
- image color analysis (1)
- imagenet (1)
- industrial Ethernet (1)
- industrial IoT (1)
- industrial communication (1)
- irrigation (1)
- lid (1)
- machine-to-machine communication (1)
- mahalanobis (1)
- metal oxide transistor (1)
- millimeter-wave (1)
- model-predictive control (1)
- molybdenum (1)
- multipath (1)
- mutual authentication (1)
- natürliche Leistung (1)
- neural architecture search (1)
- noise measurement (1)
- nose (1)
- parking (1)
- pattern recognition (1)
- perception (1)
- performance (1)
- physical unclonable function (1)
- physically unclonable function (PUF) (1)
- predictive maintenance (1)
- primary authentication (1)
- printed Antennas (1)
- programming languages (1)
- pruning (1)
- radio networks (1)
- rekeying (1)
- resource efficiency (1)
- secure communication (1)
- security (1)
- skin cancer (1)
- skin cancer detection (1)
- software defined radio (1)
- solar module (1)
- sparse backpropagation (1)
- spectral defense (1)
- spectraldefense (1)
- statistical methods, ROS (1)
- stochastic computing (1)
- style (1)
- style transfer (1)
- system authenticity (1)
- telecommunication equipment testing (1)
- temperature sensor (1)
- thinned ASIC in foil (1)
- transmit beamforming (1)
- wide area networks (1)
- wireless sensor networks (1)
- übertragbare Wirkleistung (1)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (183) (remove)
Open Access
- Closed Access (79)
- Closed (53)
- Open Access (50)
- Bronze (11)
- Diamond (9)
- Grün (3)
- Gold (1)
Generative convolutional deep neural networks, e.g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences. In this paper, we show that common up-sampling methods, i.e. known as up-convolution or transposed convolution, are causing the inability of such models to reproduce spectral distributions of natural training data correctly. This effect is independent of the underlying architecture and we show that it can be used to easily detect generated data like deepfakes with up to 100% accuracy on public benchmarks. To overcome this drawback of current generative models, we propose to add a novel spectral regularization term to the training optimization objective. We show that this approach not only allows to train spectral consistent GANs that are avoiding high frequency errors. Also, we show that a correct approximation of the frequency spectrum has positive effects on the training stability and output quality of generative networks.
Mit der Implementierung sowie einer anschließenden aussagekräftigen Evaluierung, soll das, visuelle-inertiale Kartierungs- und Lokalisierungssystem maplab analysiert werden. Hierbei basiert die Kartierung bzw. Lokalisierung auf der Detektion von Umgebungsmerkmalen. Neben der Möglichkeit der Kartenerstellung besteht ferner die Option, mehrere Karten zu fusionieren und somit weitreichende Gebiete zu kartieren sowie für weitere Datenauswertungen zu nutzen. Aufgrund der Durchführung und Bewertung der Ergebnisse in unterschiedlichen Anwendungsszenarien zeigt sich, dass maplab besonders zur Kartierung von Räumen bzw. kleinen Gebäudekomplexen geeignet ist. Die Möglichkeit der Kartenfusionierung bietet weiterhin die Option, den Informationsgehalt von Karten zu erhöhen, welches die Effektivität für eine anschließende Lokalisierung steigert. Bei wachsender Kartierungsgröße hingegen zeigt sich jedoch eine Vergrößerung geometrischer Inkonsistenzen.
Die Positionierung mobiler Systeme mit hoher Genauigkeit ist eine Voraussetzung für intelligentes autonomes Verhalten, sowohl in der Feldrobotik als auch in industriellen Umgebungen. Dieser Beitrag beschreibt den Aufbau einer Roboterplattform und ihre Verwendung für den Test und die Bewertung von Kalman-Filter-Konfigurationen. Der Aufbau wurde mit einem mobilen Roboter Husky A200 und einem LiDAR-Sensor (Light Detection and Ranging) realisiert. Zur Verifizierung des vorgeschlagenen Aufbaus wurden fünf verschiedene Szenarien ausgearbeitet. Mit denen wurden die Filter auf ihre Leistungsfähigkeit hinsichtlich der Genauigkeit der Positionsbestimmung getestet.
A method for evaluating skin cancer detection based on millimeter-wave technologies is presented. For this purpose, the relative permittivities are calculated using the effective medium theory for the benign and cancerous lesion, considering the change in water content between them. These calculated relative permittivities are further used for the simulation and evaluation of skin cancer detection using a substrate-integrated waveguide probe. A difference in the simulated scattering parameters S 11 of up to 13dB between healthy and cancerous skin can be determined in the best-case.
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small “detector” is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks’ local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant m argin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
In this study, an approach to a microwave-based radar system for the localization of objects has been proposed. This could be particularly useful in microwave imaging applications such as cardiac catheter detection. An experimental system is defined and realized with the selection of an appropriate antenna design. Hardware control functions and different imaging algorithms are implemented as well. The functionality of this measurement setup has been analyzed considering multiple testscenarios and it is proved to be capable of locating multiple objects as well as expanded objects.
As industrial networks continue to expand and connect more devices and users, they face growing security challenges such as unauthorized access and data breaches. This paper delves into the crucial role of security and trust in industrial networks and how trust management systems (TMS) can mitigate malicious access to these networks.The TMS presented in this paper leverages distributed ledger technology (blockchain) to evaluate the trustworthiness of blockchain nodes, including devices and users, and make access decisions accordingly. While this approach is applicable to blockchain, it can also be extended to other areas. This approach can help prevent malicious actors from penetrating industrial networks and causing harm. The paper also presents the results of a simulation to demonstrate the behavior of the TMS and provide insights into its effectiveness.
Towards a Formal Verification of Seamless Cryptographic Rekeying in Real-Time Communication Systems
(2022)
This paper makes two contributions to the verification of communication protocols by transition systems. Firstly, the paper presents a modeling of a cyclic communication protocol using a synchronized network of transition systems. This protocol enables seamless cryptographic rekeying embedded into cyclic messages. Secondly, we test the protocol using the model checking verification technique.
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller units (MCUs). Sparse backpropagation algorithms try to reduce the computational load of on-device learning by training only a subset of the weights and biases. Existing approaches use a static number of weights to train. A poor choice of this so-called backpropagation ratio limits either the computational gain or can lead to severe accuracy losses. In this paper we present TinyProp, the first sparse backpropagation method that dynamically adapts the back-propagation ratio during on-device training for each training step. TinyProp induces a small calculation overhead to sort the elements of the gradient, which does not significantly impact the computational gains. TinyProp works particularly well on fine-tuning trained networks on MCUs, which is a typical use case for embedded applications. For typical datasets from three datasets MNIST, DCASE2020 and CIFAR10, we are 5 times faster compared to non-sparse training with an accuracy loss of on average 1%. On average, TinyProp is 2.9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.