Browsing by Author "Ayrulu, Birsel"

Now showing 1 - 6 of 6

Open Access
Classification of target primitives with sonar using two non-parametric data fusion methods
(1996) Ayrulu, Birsel
In this study, physical models are used to model reflections from target primitives commordy encountered in a mobile robot’s environment. These tcirgets are differentiated by employing a multi-transducer pulse/echo system which relies on both cimplitude and time-of-flight (TOP) data in the feature fusion process, cillowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused for multiple logical soncirs at different geographical sites. Feature data from multiple logical sensors are fused with Dernpster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Using three sensing nodes, improvement in differentiation is 20% without false decision, however, at the cost of additional computation. Simulation results are verified by experiments with real sonar systems. As an alternative method, neural networks are used for incorporating lecirning of identifying pcirameter relations of target primitives. Amplitude and time-of-flight measurements of .‘]1 sensor pairs cire fused with these neural networks. Improvement in differentiation is 72% with 28% false decision at the cost of elapsed time until the network learns these patterns. These two approaches help to overcome the vulnerability of echo amplitude to noise and enable the modeling of non-parametric uncertainty.
Open Access
Comparative analysis of different approaches to target classification and localization with sonar
(IEEE, 2001-08) Ayrulu, Birsel; Barshan, Billur
The comparison of different classification and fusion techniques was done for target classification and localization with sonar. Target localization performance of artificial neural networks (ANN) was found to be better than the target differentiation algorithm (TDA) and fusion techniques. The target classification performance of non-parametric approaches was better than that of parameterized density estimator (PDE) using homoscedastic and heteroscedastic NM for statistical pattern recognition techniques.
Open Access
Evidential logical sensing using multiple sonars for the identification of target primitives in a mobile robot's environment
(IEEE, 1996) Ayrulu, Birsel; Barshan, Billur; Erkmen, İ.; Erkmen, A.
Physical models are used to model reflections from target primitives commonly encountered in mobile robot applications. These targets are differentiated by employing a multi-transducer pulse/echo system which relies on both amplitude and time-of-flight (TOF) data in the feature fusion process, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused for multiple logical sonars at different geographical sites. This evidential approach helps to overcome the vulnerability of echo amplitude to noise and enables the modeling of non-parametric uncertainty. Feature data from multiple logical sensors are fused with Dempster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Using three sensing nodes, improvement in differentiation is between 20-40% without false decision, at the cost of additional computation. Simulation results are verified by experiments with a real sonar system. This evidential approach helps to overcome the vulnerability of the echo amplitude to noise and enables the modeling of non-parametric uncertainty in real time.
Open Access
Fractional fourier transform pre-processing for neural networks and its application to object recognition
(Elsevier, 2002-01) Barshan, Billur; Ayrulu, Birsel
This study investigates fractional Fourier transform pre-processing of input signals to neural networks. The fractional Fourier transform is a generalization of the ordinary Fourier transform with an order parameter a. Judicious choice of this parameter can lead to overall improvement of the neural network performance. As an illustrative example, we consider recognition and position estimation of different types of objects based on their sonar returns. Raw amplitude and time-of-flight patterns acquired from a real sonar system are processed, demonstrating reduced error in both recognition and position estimation of objects. (C) 2002 Elsevier Science Ltd. All rights reserved.
Open Access
Target identification with multiple logical sonars using evidential reasoning and simple majority voting
(IEEE, 1997) Ayrulu, Birsel; Barshan, Billur; Utete, S. W.
In this study, physical models are used to model reflections from target primitives commonly encountered in a mobile robot's environment. These targets are differentiated by employing a multi-transducer pulse/echo system which relies on both amplitude and time-of-flight data, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused by employing multiple logical sonars at different geographical sites. Feature data from multiple logical sensors are fused with Dempster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Dempster-Shafer fusion results are contrasted with the results of combination of sensor beliefs through simple majority vote. The method is verified by experiments with a real sonar system. The evidential approach employed here helps to overcome the vulnerability of the echo amplitude to noise and enables the modeling of non-parametric uncertainty in real time.
Open Access
Transform pre-processing for neural networks for object recognition and localization with sonar
(SPIE, 2003) Barshan, Billur; Ayrulu, Birsel
We investigate the pre-processing of sonar signals prior to using neural networks for robust differentiation of commonly encountered features in indoor environments. Amplitude and time-of-flight measurement patterns acquired from a real sonar system are pre-processed using various techniques including wavelet transforms, Fourier and fractional Fourier transforms, and Kohonen's self-organizing feature map. Modular and non-modular neural network structures trained with the back-propagation and generating-shrinking algorithms are used to incorporate learning in the identification of parameter relations for target primitives. Networks trained with the generating-shrinking algorithm demonstrate better generalization and interpolation capability and faster convergence rate. The use of neural networks trained with the back-propagation algorithm, usually with fractional Fourier transform or wavelet pre-processing results in near perfect differentiation, around 85% correct range estimation and around 95% correct azimuth estimation, which would be satisfactory in a wide range of applications. Neural networks can differentiate more targets, employing only a single sensor node, with a higher correct differentiation percentage than achieved with previously reported methods employing multiple sensor nodes. The success of the neural network approach shows that the sonar signals do contain sufficient information to differentiate a considerable number of target types, but the previously reported methods are unable to resolve this identifying information. This work can find application in areas where recognition of patterns hidden in sonar signals is required. Some examples are system control based on acoustic signal detection and identification, map building, navigation, obstacle avoidance, and target-tracking applications for mobile robots and other intelligent systems.