Browsing Bildiri Koleksiyonu by Author "Germen, Emin"
Now showing items 1-11 of 11
-
Autopilot Project with Unmanned Robot
Seckin, Bilgin; Ayan, Tuna; Germen, Emin (Elsevier Science BV, 2012)Mobile robot is an important figure during the search and rescue application after the natural diseases such as earthquakes, fire, flooding. In the disaster areas, searching the sign of living bodies or investigating the ... -
Discrimination of faulty compressors and healthy one using Kohonen maps [Kohonen hari·ta kullanarak hatali ve saglikli kompresörleri·n ayriştirilmasi]
Germen, Emin; Kaya, A.; Ünlü, Ü. (2011)Kohonen's Self Organizing Map (SOM) is a very usable method for the classification problems. In this work SOM is used to classify the possible faults of Hermetic Compressors which are used in the refrigerators. In refrigerators ... -
Identification of acoustic spectra for fault detection in induction motors
Akçay, Hüseyin; Germen, Emin (IEEE, 2013)In this paper, we study fault detection problem for induction motors by using a recently developed cross-power spectral density estimation algorithm from sound measurements. In a test rig, from multiple experiments the ... -
Improving the resultant quality of Kohonen's self organizing map using stiffness factor
Germen, Emin (2005)The performance of Self Organizing Map (SOM) is always influenced by learn methods. The resultant quality of the topological formation of the SOM is also highly dependent onto the learning rate and the neighborhood function. ... -
Increasing the topological quality of Kohonen's self organising map by using a hit term
Germen, Emin (Institute of Electrical and Electronics Engineers Inc., 2002)The quality of the topology obtained at the end of the training period of Kohonen's self organizing map (SOM) is highly dependent on the learning rate and neighborhood function that are chosen at the beginning. The ... -
Increasing the topological quality of Kohonen's self-organising map by using a hit term
Germen, Emin (Nanyang Technological University, 2002)The quality of the topology obtained at the end of the training period of Kohonen's Self Organizing Map (SOM) is highly dependent on the learning rate and neighborhood function that are chosen at the beginning. The ... -
Induction Motor Identification from Acoustic Noise Spectrum by a Covariance Subspace Algorithm
Akçay, Hüseyin; Germen, Emin; Türkay, Semiha (IEEE Computer Society, 2018)In this paper, we study identification of induction motors by using a recently developed covariance-based subspace algorithm from sound measurements. The sound data are collected by an array of five-microphones placed ... -
A new approach to estimate red parameters using global congestion notification
Yelbaşi, Ö.; Germen, Emin (2011)In communication networks, congestion avoidance in routers is one of the hottest topics. In this work, a new queue management approach is proposed on the RED (Random Early Detection) algorithm by monitoring the global ... -
A new approach to mathematical water quality modeling in reservoirs: Neural networks
Karul, C; Soyupak, S; Germen, Emin (Wiley-V C H Verlag GMBH, 1998)Neural Networks are becoming more and more valuable tools for system modeling and function approximation as computing power of microcomputers increase. Modeling of complex ecological systems such as reservoir limnology is ... -
Self Organizing Map (SOM) approach for classification of mechanical faults in induction motors
Germen, Emin; Ece, D. Gökhan; Gerek, Ömer Nezih (Springer-Verlag Berlin, 2007)In this work, Self Organizing Map (SOM) is used in order to detect and classify the broken rotor bars and misalignment type mechanical faults that often occur in induction motors which are widely used in industry. The ... -
A statistical approach to determine the neighborhood function and learning rate in Self-Organizing Maps
Germen, Emin; Bilgen, S (Springer-Verlag Singapore Pte LTD, 1998)The problem of choosing the neighborhood function and learning rate in Kohonen's Self-Organizing Map (SOM) is generally application dependent, empirical and difficult to analyze. In this paper, a new approach based on the ...