Organizational Unit:
Department of Artificial Intelligence

Loading...
OrgUnit Logo

Date established

City

Country

ID

Publication Search Results

Now showing 1 - 5 of 5
  • Placeholder
    Master ThesisPublication
    A comprehensive human-agent negotiation framework : preferences, emotion & interaction
    Keskin, Mehmet Onur; Aydoğan, Reyhan; Aydoğan, Reyhan; Sefer, Emre; Erzin, E.; Department of Artificial Intelligence
    In today’s increasingly interconnected world, human-agent negotiation plays a pivotal role in reaching socially beneficial agreements when stakeholders need to make joint decisions. Developing intelligent agents capable of understanding not only human negotiators’ prefer ences but also attitudes is a significant prerequisite for effective human-agent interactions. Awareness of a human’s emotional state and ability to express an agent’s mood to influence the human negotiator might significantly affect the negotiation outcome. This thesis presents a comprehensive framework that revolutionizes the field of human agent negotiation, integrating two critical elements: Emotionally aware negotiation strategy and Conflict-Based Opponent Modeling (CBOM). By combining these novel approaches, the framework enhances negotiation outcomes and fosters cooperation between agents and human negotiators, ultimately leading to mutually advantageous agreements. The thesis establishes the research context and motivation, underscoring the escalating importance of human-agent negotiation in a world where collaborative decision-making is essential for addressing complex challenges. It highlights the need for advanced agents to accurately interpret human preferences and behaviors, enabling admissible settlements that serve joint interests. Shedding light on the limitations of conventional approaches that heavily rely on opponent offers and remaining time. Additionally, it explores the critical role of emotional awareness and opponent modeling strategies in human-agent negotia tion. The synthesis of existing research lays the groundwork for developing the proposed comprehensive framework. Emotional awareness takes center stage in the proposed negotiation strategy. Solver Agent: Emotional Extension of the Hybrid Agent bidding strategy is introduced. The Solver Agent considers the opponent’s emotional state during negotiation, leading to higher social welfare scores and faster agreement times. The experimental study emphasized the profound impact of emotional awareness on negotiation outcomes, particularly in human agent settings. CBOM efficiently extracts maximum information from limited interaction rounds in human-agent negotiation settings, surpassing traditional approaches in prediction performance. Experimental analyses confirmed the superiority of CBOM in human-agent and automated negotiation scenarios, even when the exploration of the outcome space is limited. The experimental findings establish CBOM as a powerful tool for modeling human behavior and preferences in negotiation. In conclusion, the comprehensive human-agent negotiation framework presented in this thesis represents a significant advancement in the field. By seamlessly combining Conflict Based Opponent Modeling and Emotional Awareness, the framework empowers intelligent agents to discern human preferences and behaviors more accurately, facilitating cooperative interactions and achieving mutually beneficial agreements. The framework’s effectiveness in human-agent and automated negotiation settings highlights its potential for designing ne gotiation agents that interact adeptly with human negotiators, fostering understanding and optimizing negotiation outcomes. The future of human-agent negotiation lies in forging a new era of cooperation, where intelligent agents serve as capable partners, promoting social welfare and driving positive change through admissible settlements that incorporate joint interests. This thesis contributes valuable insights towards realizing this vision, marking a significant step forward in the field of human-agent interaction.
  • Placeholder
    Master ThesisPublication
    Building energy performance, occupant comfort and retrofit strategies under the climate change adaptation process
    Tomrukçu, Gökçe; Aşrafi, Turaj Arda; Aşrafi, Turaj Arda; Sağlam, Neşe Ganiç; Taşçı, G. G.; Department of Artificial Intelligence
    Increasing energy consumption in our developing and changing world, which has become a critical risk, is among the main reasons for climate change. Buildings are among the high priority sectors in climate change due to their high CO2 emissions, significant energy consumption and increasing comfort demands of building occupants. Therefore, integrating buildings with climate-resistant strategies and energy-efficient parameters in the adaptation process to climate change is of great importance for sustainable development. The necessity of taking measures to adapt buildings to climate change in the future and the importance of reducing the effects of climate change is obvious. Therefore, a comprehensive and quantitative assessment of how climate change will affect future building energy performance is essential for designing climate-resilient structures and making long-term strategic decisions. It is predicted that this change may affect each region in different ways and degrees. It is therefore critical to evaluate different climatic zones and different emission scenarios. The thesis aims to investigate how buildings and their energy performance will be affected by climate change in the future. In the reports announced by the IPCC, two different emission scenarios, RCP 4.5 and 8.5, were considered. The housing type, which constitutes a major part of the building stock, has been selected and analyzed comparatively with two different climatic regions, Istanbul, and Izmir. Future climate data of different climatic regions were obtained using the morphing method. Different scenarios have been developed to improve building energy and thermal comfort during the climate adaptation process. In this context, it aims to explore approaches to improve v the climate resilience of residential buildings by using energy efficient integrated building design criteria. According to the results obtained, it has been proven that climate change affects each region differently. According to the RCP 8.5 scenario, the temperature increased by +4.3 °C in Istanbul and +5 °C in Izmir. Especially in Izmir, overheating has increased during the summer months. Within the scope of improvement strategies, a decrease in overheating rates was observed remarkably. Another critical outcome is that the integration of renewable energy sources into the building is of critical importance in the adaptation process to the climate. In addition, the selection of appropriate insulation thicknesses has resulted in significant energy savings in both climate zones. Although it changes according to emission scenarios compared to the current situation, approximately 65-70% of energy improvement was achieved in Istanbul, while 60-65% of energy savings were achieved in Izmir. On the other hand, in terms of thermal comfort values, significant decreases were calculated in both provinces in the suggested most efficient scenarios. In this direction, the thesis emphasizes the importance of reducing the adverse effects of climate change and aims to increase awareness of the importance of using future climate scenarios in building energy efficiency analysis and design.
  • Placeholder
    Master ThesisPublication
    Illumination-guided inverse rendering benchmark : learning real objects with few cameras
    Yılmaz, Doğa; Kıraç, Mustafa Furkan; Kıraç, Mustafa Furkan; Aydoğan, Reyhan; Gökberk, B.; Department of Artificial Intelligence
    The field of 3D computer vision and graphics has seen a rapid expansion of late, making the development of realistic virtual environments and digital representations of real-world objects possible. Fundamental to this development are 3D reconstruction techniques that enable the transition of physical objects’ form, color, and surface particulars to the virtual domain. Current approaches mainly rely on neural scene representations, which, despite being effective, face challenges such as the need for a large quantity of captured images and the complexity associated with converting these representations into explicit geometric forms. An alternative strategy that has gained traction is the deployment of methods such as physically-based differentiable rendering (PBDR) and inverse rendering. These approaches require fewer viewpoints, yield explicit format results, and ensure a smoother transition to other representation methods. However, in order to effectively assess the performance of the available methods in 3D reconstruction, it is imperative to utilize standard benchmark scenes for comparison. Although there are standard objects and scenes available in existing research, there is a noticeable deficiency of real-world benchmark data that simultaneously captures camera, lighting, and scene parameters — all of which are essential for high-quality 3D reconstructions using methods based on PBDR and inverse rendering. In this study, we present a method for capturing real-world scenes as virtual environments, incorporating lighting parameters along with camera and scene parameters to enhance the veracity of virtual representations. In addition, we provide a set of ten realworld scenes, each with its corresponding virtual counterparts, purposely designed as benchmarks. These benchmarks cover a basic assortment of geometric structures, such as convex, concave, flat, and composite surfaces. Furthermore, we showcase the 3D reconstruction results of cutting-edge 3D reconstruction techniques using PBDR in real-world scenes, using both established methodologies and our proposed one.
  • Placeholder
    Master ThesisPublication
    Graph neural networks-based primal heuristics for combinatorial optimization
    Cantürk, Furkan; Aydoğan, Reyhan; Aydoğan, Reyhan; Sefer, Emre; Özener, Okan Örsan; Özer, A. H.; Toğçuoğlu, H.; Department of Artificial Intelligence
    By examining the patterns of solutions obtained for varying instances, one can gain insights into the structure and behavior of combinatorial optimization (CO) problems and develop efficient algorithms for solving them. Machine learning techniques, especially Graph Neural Networks (GNNs), have shown promise in parametrizing and automating this laborious design process. The inductive bias of GNNs allows for learning solutions to mixed-integer programming (MIP) formulations of constrained CO problems with a relational representation of decision variables and constraints. The trained GNNs can be leveraged with primal heuristics to construct high-quality feasible solutions to CO problems quickly. However, current GNN-based end-to-end learning approaches have limitations for scalable training and generalization on larger-scale instances; therefore, they have been mostly evaluated over small-scale instances. Addressing this issue, our study builds on end-to-end learning of optimal solutions to the downscaled instances of given large-scale CO problems. We introduce several improvements on a recent GNN model for CO to generalize on instances of a larger scale than those used in the training. We also propose a two-stage primal heuristic strategy based on uncertainty-quantification to automatically configure how solution search relies on the predicted decision values. Our models can generalize on 16x upscaled instances of commonly benchmarked five CO problems. Unlike the regressive performance of existing GNN-based CO approaches as the scale of problems increases, the CO pipelines using our models offer an incremental performance improvement relative to a state-of-the-art MIP solver CPLEX. The proposed uncertainty-based primal heuristics provide 6-75% better optimality gap values and 45-99% better primal gap values for the 16x upscaled instances and brings immense speedup to obtain high-quality solutions. All these gains are achieved in a computationally efficient modeling approach without sacrificing solution quality.
  • Placeholder
    Master ThesisPublication
    Joint analysis of SQTL and HI-C reveals spatial proximity between SQTLS and target genes across multiple tissues
    Eralp, Batuhan; Sefer, Emre; Sefer, Emre; Fındıkçı, İlknur Eruçar; Okan, Ö. T.; Department of Artificial Intelligence
    Gene expression and regulation with or without alternative splicing are crucial for tissues and cells to properly function. They have been studied from three almost independent perspectives at the genome level: 1- Recognition of splicing quantitative trait loci (sQTLs), 2- Expression quantitative trait loci (eQTLs) recognition, and 3- Recognition of longer-range physical chromatin interactions between genome segments which model 3D dynamics of cells and tissues. Even though the associations between eQTLs and longer range chromatin interactions have been previously studied, similar relationship between sQTLs and chromatin interactions has not been previously analyzed. In this case, it is crucial to analyze whether sQTLs control the alternative splicing of their target genes mRNA via physically-interacting genome segments. Even though chromatin interactions are part of the principal processes governing eQTLs functioning, similar analysis is missing from sQTLs perspective. We have jointly analyzed high-throughput chromatin conformation capture (HiC) and sQTL datasets over 8 different human cancer tissues. We have discovered the existence of positive association between the number of genes having sQTLs and chromatin interaction frequency. Such positive association still exists when we also control for eQTLs. Additionally, sQTLs and their target genes generally exist inside identical topologically associating domain (TAD). Those findings are observed over the whole set of analyzed cancer types and over different functional subsets of sQTL dataset such as survival-related sQTLs. Furthermore, tissue-specific sQTLs are statistically enriched in tissue-specific frequently interacting regions (FIREs) in 6 out of 8 human cancer tissues (Chronic Myeloid Leukemia, Colon Adenocarcinoma, Acute Myeloid Leukemia, Lung Adenocarcinoma, Prostate Cancer, Sarcoma). iv Our sQTL and Hi-C datasets have shown the existence of closer spatial distance between sQTLs and their target genes with possible alternative splicing across a number of different cancer types in human. Such closer spatial distance also exists independent of whether we integrate eQTLs into the analysis. We found that sQTLs regulate the alternative splicing through chromatin interactions.