Browsing by Subject "Artificial intelligence."

Now showing 1 - 7 of 7

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
Classification with overlapping feature intervals
(1995) Koç, Hakime Ünsal
This thesis presents a new form of exemplar-based learning method, based on overlapping feature intervals. Classification with Overlapping Feature Intervals (COFI) is the particular implementation of this technique. In this incremental, inductive and supervised learning method, the basic unit of the representation is an interval. The COFI algorithm learns the projections of the intervals in each class dimension for each feature. An interval is initially a point on a class dimension, then it can be expanded through generalization. No specialization of intervals is done on class dimensions by this algorithm. Classification in the COFI algorithm is based on a majority voting among the local predictions that are made individually by each feature.
Open Access
A comparison of different approaches to target differentiation with sonar
(2001) Ayrulu (Erdem), Birsel
This study compares the performances of di erent classication schemes and fusion techniques for target di erentiation and localization of commonly encountered features in indoor robot environments using sonar sensing Di erentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identication map building navigation obstacle avoidance and target tracking The classication schemes employed include the target di erentiation algorithm developed by Ayrulu and Barshan statistical pattern recognition techniques fuzzy c means clustering algorithm and articial neural networks The fusion techniques used are Dempster Shafer evidential reasoning and di erent voting schemes To solve the consistency problem arising in simple ma jority voting di erent voting schemes including preference ordering and reliability measures are proposed and veried experimentally To improve the performance of neural network classiers di erent input signal representations two di erent training algorithms and both modular and non modular network structures are considered The best classication and localization scheme is found to be the neural network classier trained with the wavelet transform of the sonar signals This method is applied to map building in mobile robot environments Physically di erent sensors such as infrared sensors and structured light systems besides sonar sensors are also considered to improve the performance in target classication and localization.
Open Access
Distributed scheduling
(1999) Toptal, Ayşegül
Distributed Scheduling (DS) is a new paradigm that enables the local decisionmakers make their own schedules by considering local objectives and constraints within the boundaries and the overall objective of the whole system. Local schedules from different parts of the system are then combined together to form a final schedule. Since each local decision-maker acts independently from each other, the communication system in a distributed architecture should be carefully designed to achieve better overall system performance. These systems are preferred over the traditional systems due to the ability to update the schedule, flexibility, reactivity and shorter lead times. In this thesis, we review the existing work on DS and propose a new classification framework. We also develop a number of bidding based DS algorithms. These algorithms are tested under various manufacturing environments.
Open Access
Fire and flame detection methods in images and videos
(2010) Habiboğlu, Yusuf Hakan
In this thesis, automatic fire detection methods are studied in color domain, spatial domain and temporal domain. We first investigated fire and flame colors of pixels. Chromatic Model, Fisher’s linear discriminant, Gaussian mixture color model and artificial neural networks are implemented and tested for flame color modeling. For images a system that extracts patches and classifies them using textural features is proposed. Performance of this system is given according to different thresholds and different features. A real-time detection system that uses information in color, spatial and temporal domains is proposed for videos. This system, which is develop by modifying previously implemented systems, divides video into spatiotemporal blocks and uses features extracted from these blocks to detect fire.
Open Access
A general purpose rotation, scaling, and translation invariant pattern classification system
(1992) Yüceer, Cem
Artificial neural networks have recently been used for pattern classification purposes. In this work, a general purpose pattern classification system which is rotation, scaling, and, translation invariant is introduced. The system has three main blocks; a Karhunen-Loeve transformation based preprocessor, an artificial neural network based classifier, and an interpreter. Through experimentation on the English alphabet, the Japanese Katakana alphabet, and some geometric symbols the power of the system in maintaining invariancies and performing pattern classification has been shown.
Open Access
Utilization of the MVL system in qualitative reasoning about the physical world
(1993) Şencan, Mine Ülkü
An experimental progra.m, QRM, has been implemented using the inference mechanism of the Multivalued Logics (MVL) Theorem Proving System of Matthew Ginsberg. QRM has suitable facilities to reason about dynamical systems in qualitative terms. It uses Kenneth Forbus’s Qualitative Process Theory (QPT) to describe a physical system and constructs the envisionment tree for a given initial situation. In this thesis, we concentrate on knowledge representation issues, and basic qualitative reasoning tasks based on QPT. We offer some insights about what MVL can provide for writing Qualitative Physics programs.