7 results
Search Results
Now showing 1 - 7 of 7
Conference Object Citation - WoS: 7Citation - Scopus: 8Formation Control of a Multi-Agent System Using Decentralized Nonlinear Servomechanism(Ieee, 2003) Gazi, VIn this article we consider the formation control problem of a system of M agents with general nonlinear dynamics. We show that the problem of the agents moving in a formation along constant or periodic trajectories can be formulated as a nonlinear output regulation (servomechanism) problem and solved using known techniques. Then, we consider the example of formation control of agents with point mass dynamics and apply the procedure. Few illustrative numerical simulation examples are also provided.Conference Object Citation - WoS: 13Citation - Scopus: 34Swarm Aggregations Using Artificial Potentials and Sliding Mode Control(Ieee, 2003) Gazi, VIn this article we build on our earlier results in [1, 2] on swarm stability. In [1, 2] we had considered aggregating swarm model in n-dimensional space based on artificial potential functions for inter-individual interactions and motion along the negative gradient of the combined potential. Here we consider a general model for vehicle dynamics of each agent (swarm member) and use sliding mode control theory to force their motion to obey the dynamics of the swarm considered in [1, 2]. In this context, the results in [1, 2] serve as a "proof of concept" for swarm aggregation, whereas the present results serve as possible implementation method for engineering swarms with given vehicle dynamics. Moreover, the presented control scheme is robust with respect to disturbances and system uncertainties.Conference Object Citation - WoS: 16Target Tracking Using Artificial Potentials and Sliding Mode Control(Ieee, 2004) Gazi, V; Ordóñez, RIn this article we develop an algorithm for capturing/intercepting a moving target based on the sliding mode control method. First, we consider a "kinematic" model (in a sense) for the capture/intercept problem and develop a method for that case. Then, we build on the developed method to include general fully actuated vehicle dynamics for the pursuer agent. The algorithm is robust with respect to the system uncertainties and additive disturbances. Finally, we also provide a numerical simulation in order to illustrate the procedure.Conference Object Peer-Con: a Process Contracting Overlay(Ieee, 2008) Celebi, Remzi; Kilic, HuerevrenA peer to peer process contracting overlay what we call Peer-Con is developed. The system is an extension of Java Agent Development Framework (JADE) and uses IEEE Foundation for Intelligent Physical Agents (FIPA) Agent Communication Language (ACL) standard. Cost aware flexible representation of process capabilities; description of an operator to decide on whether given capabilities turnout to an agreement or not and self organization of peer connectivity for better contracting performance are distinguishing features of the system. The system can easily be adapted to different domains while the core functionality remains the same. Practical use of Peer-Con is shown by an application from Digital Signal Processing Module (DSPM) product planning domain.Conference Object Citation - WoS: 16KINSHIPGAN: SYNTHESIZING OF KINSHIP FACES FROM FAMILY PHOTOS BY REGULARIZING A DEEP FACE NETWORK(Ieee, 2018) Ozkan, Savas; Ozkan, AkinIn this paper, we propose a kinship generator network that can synthesize a possible child face by analyzing his/her parent's photo. For this purpose, we focus on to handle the scarcity of kinship datasets throughout the paper by proposing novel solutions in particular. To extract robust features, we integrate a pre-trained face model to the kinship face generator. Moreover, the generator network is regularized with an additional face dataset and adversarial loss to decrease the overfitting of the limited samples. Lastly, we adapt cycle-domain transformation to attain a more stable results. Experiments are conducted on Families in the Wild (FIW) dataset. The experimental results show that the contributions presented in the paper provide important performance improvements compared to the baseline architecture and our proposed method yields promising perceptual results.Conference Object A Novel Fuzzy Visual Object Classification Approach(Ieee, 2012) Altintakan, Umit Lutfu; Yazici, Adnan; Koyuncu, MuratSupport Vector Machines (SVMs) have been extensively used for visual object classification to bridge the semantic gap between the low level features and high level concepts. SVM treats each training input equally during the construction of its decision surface which results in poor learning machines if training data include outliers. In this paper, a novel fuzzy visual object classification approach utilizing Self-Organizing Maps (SOMs) in SVM is proposed. The experimental results show the effectiveness of the proposed Fuzzy SVM compared to the traditional SVM.Conference Object Citation - WoS: 1A Framework for Fuzzy Video Content Extraction, Storage and Retrieval(Ieee, 2010) Koyuncu, Murat; Yilmaz, Turgay; Yildirim, Yakup; Yazici, AdnanThis study presents a new comprehensive framework for semantic content extraction from raw video, storage of the extracted data and retrieval of the stored data. Objects, spatial relations between objects, events and temporal relations between events, which are considered as semantic contents of the video, are extracted automatically to a certain extend with the developed approach. Extraction process is supported by manual annotation when automatic extraction is not satisfactory. The extracted information is stored in an intelligent fuzzy object-oriented database in which the database is enhanced with a fuzzy knowledge-based system. Domain specific deduction rules can be defined to derive new information about semantic contents of the video. The database is also supported by an access structure to increase retrieval efficiency. The proposed framework is capable of handling uncertain data arising from annotation process or video nature.
