Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
6 results
Search Results
Conference Object Collabpersona: A Framework for Collaborative Decision Analysis in Persona Driven LLM-Based Multi-Agent Systems(IEEE Computer Society, 2025) Tamer, O.A.; Gumus, A.Large Language Model (LLM) agents have recently demonstrated impressive capabilities in single agent and adversarial settings, but their ability to collaborate effectively with minimal communication remains uncertain. We introduce CollabPersona, a simulation framework that combines persona-grounded memory with one-shot feedback to study team-based reasoning among LLM agents. In a multi-round variant of the Guess 0.8 of the Average game, agents reason entirely through structured prompts without fine-tuning. Our results show that minimal feedback significantly improves intra-team coordination and stabilizes strategic behavior, while cognitive style remains a primary driver of competitive outcomes. These findings suggest that lightweight scaffolding can elicit emergent collaboration in LLM agents and provide a flexible platform for studying cooperative intelligence. © 2025 IEEE.Conference Object Citation - Scopus: 2Enhancing Multiview 3d Reconstruction Using Polarization Imaging(IEEE Computer Society, 2014) Ozan, S.; Gumustekin, S.Performance of stereo imaging methods, which are used to find depth information of a scene, can be adversely affected by surface reflection properties of subjects in the scene and possible change in relative camera and light source positions. In this study a catadioptric multiview imaging system, which is constructed by using planar mirrors, is proposed. Stereo matching problems which are caused by the specular reflections in the scene are highlighted and it is shown that those problems can be significantly alleviated by using polarization images. © 2014 IEEE.Editorial Message From the Mvv Workshop Chairs(IEEE Computer Society, 2012) Tuglular,T.; Linschulte,M.[No abstract available]Article Citation - WoS: 6Citation - Scopus: 8Software Size Measurement: Bridging Research and Practice(IEEE Computer Society, 2024) Hacaloglu,T.; Unlu,H.; Yildiz,A.; Demirors,O.Despite the availability of software size measures with proven effectiveness, structured characteristics, and reliability, practitioners often favor subjective estimation approaches like story points due to perceived ease and flexibility. Amid ongoing industry transformations driven by artificial intelligence, distributed architectures, and agile practices, innovative approaches to software size measurement are crucial to aligning research solutions with evolving industry demands. This study investigates the limited adoption of functional size measurement methods in the software development industry despite their research-backed success. By gathering insights from firms experienced in size measurement, the research aims to uncover industry expectations and facilitate the translation of theoretical methodologies into practical applications. This effort seeks to overcome barriers and promote the integration of novel concepts into the software development landscape. IEEEArticle Citation - WoS: 4Citation - Scopus: 7Adaptive Reduced Feedback Links for Distributed Power Allocation in Multicell Miso-Ofdma Networks(IEEE Computer Society, 2014) Özbek, Berna; Le Ruyet, Didier; Pischella, MyleneFor multi-antenna Orthogonal Frequency-Division Multiple Access (OFDMA) based multicell networks, the channel state information (CSI) of all users is required to share among base stations in order to perform distributed power allocation. However, the amount of feedback increases with the number of users, base stations, subcarriers and antennas. Therefore, it is important to perform a selection at the user side to reduce the feedback load and the complexity of resource allocation. In this letter, we propose adaptive reduced feedback links by choosing the users based on their approximate signal to interference noise ratio (SINR) and their locations in the cell to satisfy users' rate constraints. We illustrate the performance results of reduced feedback links by employing distributed resource allocation with link adaptation.Conference Object Citation - Scopus: 3Taylor Series Approximation for Low Complexity Semi-Blind Best Linear Unbiased Channel Estimates for the General Linear Model With Applications To Dtv(IEEE Computer Society, 2004) Pladdy, Christopher; Nerayanuru, Sreenivasa M.; Fimoff, Mark; Özen, Serdar; Zoltowski, MichaelWe present a low complexity approximate method for semi-blind best linear unbiased estimation (BLUE) of a channel impulse response vector (CIR) for a communication system which utilizes a periodically transmitted training sequence, within a continuous stream of information symbols. The algorithm achieves slightly degraded results at a much lower complexity than directly computing the BLUE CIR estimate. In addition, the inverse matrix required to invert the weighted normal equations to solve the general least squares problem may be precomputed and stored at the receiver. The BLUE estimate is obtained by solving the general linear model, y = Ah + w + n, for h, where w is correlated noise and the vector n is an AWGN process, which is uncorrelated with w. The solution is given by the Gauss-Markoff Theorem as h = (A TC(h) -1A) -1 A TC(h) -1y. In the present work we propose a Taylor series approximation for the function F(h) = (A TC(h) -1A) -1 A TC(h) -1y where, F: R L → R L for each fixed vector of received symbols, y, and each fixed convolution matrix of known transmitted training symbols, A. We describe the full Taylor formula for this function, F (h) = F (h id + ∑ |α|≥1(h - h id) α (∂/∂h) α F(h id) and describe algorithms using, respectively, first, second and third order approximations. The algorithms give better performance than correlation channel estimates and previous approximations used at only a slight increase in complexity. The linearization procedure used is similar to that used in the linearization to obtain the extended Kalman filter, and the higher order approximations are similar to those used in obtaining higher order Kalman filter approximations,