Navigationsweiche Anfang

Navigationsweiche Ende

Lehrstuhl für Allgemeine Elektrotechnik und Theoretische Nachrichtentechnik

Prof. Dr.- Ing. Anton Kummert

Prof. Dr.-Ing. Anton Kummert


Raum: FE 1.01
Telefon: +49 (0)202 439 1961
E-Mail: kummert{at}





J. Cao; H. Dai; B. Lei; C. Yin; H. Zeng; A. Kummert
Maximum Correntropy Criterion-Based Hierarchical One-Class Classification
IEEE Transactions on Neural Networks and Learning Systems, :1-7
ISSN: 2162-2388

Schlüsselwörter: Hierarchical structure;maximum correntropy criterion (MCC);one-class classification;outlier/anomaly detection.

Zusammenfassung: Due to the effectiveness of anomaly/outlier detection, one-class algorithms have been extensively studied in the past. The representatives include the shallow-structure methods and deep networks, such as the one-class support vector machine (OC-SVM), one-class extreme learning machine (OC-ELM), deep support vector data description (Deep SVDD), and multilayer OC-ELM (ML-OCELM/MK-OCELM). However, existing algorithms are generally built on the minimum mean-square-error (mse) criterion, which is robust to the Gaussian noises but less effective in dealing with large outliers. To alleviate this deficiency, a robust maximum correntropy criterion (MCC)-based OC-ELM (MC-OCELM) is first proposed and then further extended to a hierarchical network to enhance its capability in characterizing complex and large data (named HC-OCELM). The gradient derivation combining with a fixed-point iterative updation scheme is adopted for the output weight optimization. Experiments on many benchmark data sets are conducted for effectiveness validation. Comparisons to many state-of-the-art approaches are provided for the superiority demonstration.

Jessica Malerczyk; Sabine Lerch; Bernd Tibken; Anton Kummert
Impact of intelligent agents on the avoidance of spontaneous traffic jams on two-lane motorways
MATEC Web of Conferences Band 308 , Seite 05003.
EDP Sciences
Jan-Christoph Schmitz; Stephan Tilgner; Kathrin Kalischewski; Daniel Wagner; Anton Kummert
Hands on Wheel Classification Based on Depth Images and Neural Networks
MATEC Web of Conferences Band 308 , Seite 06003.
EDP Sciences
L. Kolonko; J. Velten; A. Kummert
Optimization of Artificial Port Reflectances for Wave Digital Filters with Topology-Related Delay-Free Loops
2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS) , Seite 170-173.

Schlüsselwörter: Wave Digital Filter;Automatic Differentiation;Delay-Free Loop;Multi-Dimensional;Bridged-T Model

Zusammenfassung: In this paper, a generic method for fast determination of all involved optimal artificial port resistances is presented for the realization of Wave Digital Filters (WDFs) containing noncomputable, delay-free loops. Therefore, the concept of Automatic Differentiating WDFs (ADWDFs) is applied to obtain said resistances by minimizing the associated artificial reflectances, which performs significantly faster than empirical approaches, as will be shown in an example. This way, the resulting Wave Digital structure remains completely modular under fixed point iteration schemes achieving optimal convergence speeds. Additionally, contractivity of WDFs is exploited to obtain an optimal operating point from a different perspective.


L. Kolonko; J. Velten; A. Kummert
An Improved Multi-Dimensional Approach to Wave Digital Filters with Topology-Related Delay-Free Loops using Automatic Differentiation
2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS) , Seite 1163-1166.
August 2019

Schlüsselwörter: Digital filters;Delays;Topology;Linear systems;Mathematical model;Numerical models;Jacobian matrices;Wave Digital Filter;Automatic Differentiation;Delay-Free Loop;Multi-Dimensional;Contractivity;Bridged-T Model

Lukas Hahn; Lutz Roese-Koerner; Klaus Friedrichs; Anton Kummert
Fast and Reliable Architecture Selection for Convolutional Neural Networks Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pages 179-184, Bruges 2019
ArXiv, abs/1905.01924

Schlüsselwörter: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Zusammenfassung: The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example. Especially in smaller networks and applications with limited computational resources, optimisation is key. We present a fast and efficient approach for CNN architecture selection. Taking into account time consumption, precision and robustness, we develop a heuristic to quickly and reliably assess a network's performance. In combination with Bayesian optimisation (BO), to effectively cover the vast parameter space, our contribution offers a plain and powerful architecture search for this machine learning technique.

T. Schwerdtfeger; A. Kummert
Nonlinear Circuit Simulation by Means of Alfred Fettweis' Wave Digital Principles
IEEE Circuits and Systems Magazine, 19(1):55-C3
ISSN: 1531-636X

Schlüsselwörter: circuit simulation;nonlinear network analysis;wave digital filters;Alfred Fettweis wave digital principles;general circuit simulation strategy;digital filter design;analogue reference circuits;accurate digital model;WDFs;Wave Digital Filters;commercial circuit design;dependable circuit simulation;nonlinear circuit simulation;Digital filters;Circuit simulation;Circuit synthesis;Finite element analysis;Nonlinear circuits;SPICE

J. Cao; J. Zhu; W. Hu; A. Kummert
Epileptic Signal Classification with Deep EEG Features by Stacked CNNs
IEEE Transactions on Cognitive and Developmental Systems, :1
ISSN: 2379-8920

Schlüsselwörter: Electroencephalogram, Epilepsy, Seizure detection, Preictal state classification, Stacked CNNs.

Matthias Buß; Stephan Benen; D Kraus; Anton Kummert
False Alarm Reduction for Active Sonars using Deep Learning Architectures
2019 UDT, Stockholm
K. Kalischewski; D. Wagner; J. Velten; A. Kummert
Spoken Letter Recognition using Deep Convolutional Neural Networks on Sparse and Dissimilar Data
2019 IEEE International Symposium on Circuits and Systems (ISCAS) , Seite 1-5.

Schlüsselwörter: Training;Task analysis;Visualization;Spectrogram;Convolutional neural networks;Image recognition

D. Wagner; K. Kalischewski; S. Tilgner; J. Velten; A. Kummert
Automatic Labeling of Industrial Images by using Generative Adversarial Networks
2019 IEEE International Symposium on Circuits and Systems (ISCAS) , Seite 1-5.

Schlüsselwörter: Kernel;Generative adversarial networks;Training;Decoding;Generators;Loss measurement;Mutual information

L. Kolonko; J. Velten; A. Kummert
Live Demonstration: A Raspberry Pi Based Video Pipeline for 2-D Wave Digital Filters on Low-Cost FPGA Hardware
2019 IEEE International Symposium on Circuits and Systems (ISCAS) , Seite 1-1.

Schlüsselwörter: Field programmable gate arrays;Economic indicators;Liquid crystal displays;Pipeline processing;Digital filters;Hardware;Universal Serial Bus;Wave Digital Filter;Video Pipeline;FPGA;Raspberry Pi

Zurück | 1, 2, 3, 4, 5, 6, ... , 29 | Weiter