Browsing by Author "Oguz, Kaya"

Now showing 1 - 7 of 7

Citation - WoS: 1
Citation - Scopus: 2
Adaptive Evolution of Finite State Machines for the Tartarus Problem
(Institute of Electrical and Electronics Engineers Inc., 2019-10) Oguz K.; Oguz, Kaya
Genetic algorithms can be used to evolve finite state machines for problems that require a large number of states and transitions. Tartarus problem is such a problem in which the purpose is to push the boxes towards the walls of a six by six grid using a bulldozer that can only sense its 8-neighbourhood. The bulldozer can rotate left, right, or move forward, each taking a single move out of its initial 80 moves. The result is scored by the number of boxes that are against a wall when the bulldozer is out of moves. Several approaches have been proposed, with genetic algorithms being the most common. We are proposing a representation of the problem using varying number of states and adaptive modification of the mutation parameter to decrease the probability of the population getting stuck at a local minima. Our results show improvement over the application of the genetic algorithm without parameter modification and dependency on the number states and the size of the population. © 2019 IEEE.
Behaviour Analysis of Izmir Residents Using Public Wi-Fi Access Point Usage
(Institute of Electrical and Electronics Engineers Inc., 2022-12-15) Dilek I.; Oguz K.; Demir A.; Dilek, Ilayda; Oguz, Kaya; Demir, Alper
The wide distribution of access points in Izmir allows the collected information to be employed in smart city algorithms. In this study, we analyze the information that has been made publicly available by Izmir Metropolitan Municipality. We first show that the data is reliable, then analyze it from the perspectives of holidays, seasonal trends, and the COVID-19 pandemic. The study also shows that the information can be used for crowd analysis and forecasting, using K-means and SARIMA algorithms, respectively. © 2022 IEEE.
Effect of Age and Gender on Facial Emotion Recognition
(Institute of Electrical and Electronics Engineers Inc., 2020-10-15) Oguz K.; Korkmaz I.; Korkmaz B.; Akkaya G.; Alici C.; Kilic E.; Kilic, Ece; Korkmaz, Beyza; Korkmaz, Ilker; Alici, Cem; Akkaya, Guliz; Oguz, Kaya
New research fields and applications on human computer interaction will emerge based on the recognition of emotions on faces. With such aim, our study evaluates the features extracted from faces to recognize emotions. To increase the success rate of these features, we have run several tests to demonstrate how age and gender affect the results. The artificial neural networks were trained by the apparent regions on the face such as eyes, eyebrows, nose, mouth, and jawline and then the networks are tested with different age and gender groups. According to the results, faces of older people have a lower performance rate of emotion recognition. Then, age and gender based groups are created manually, and we show that performance rates of facial emotion recognition have increased for the networks that are trained using these particular groups. © 2020 IEEE.
The Effects of Late-Onset Depression on Brain Activity During an Episodic Memory Task
(Turkish Neuropsychiatry Assoc-Turk Noropsikiyatri Dernegi, 2025) Gulec, Zeynep Naz; Ercan, Melis; Erdogan, Yigit; Oguz, Kaya; Uyar, Aslihan; Burhanoglu, Birce Begum; Gonul, Ali Saffet
Introduction: Late-onset depression (LOD) has been implicated in irreversible cognitive decline, potentially mirroring early Alzheimer's Disease (AD) pathology. This study aimed to investigate brain activity differences during an episodic memory (EM) task in LOD patients compared to healthy controls (HC). Methods: We recruited 15 LOD patients and 13 HC matched for age and gender. Participants completed a face-name association task during functional magnetic resonance imaging (fMRI) focusing on both the encoding and retrieval phases of EM. Results: The statistical contrast between the groups revealed that the HC group showed increased activity in the left visual association cortex (VAC) and left caudate compared to the LOD group during the encoding task. During the face recognition task, the HC group showed increased activity in the right caudate, and during the name recognition task, they showed increased activity in the right frontal eye field (FEF) compared to the LOD group. Conclusion: The differences observed between the HC and LOD groups in the VAC, caudate, and FEF suggest early changes in maintaining attention, goal-directed learning, EM formation, and coordination of information from storage to retrieval before apparent impairment develops in LOD. Although we did not find statistically significant activations in areas linked to increased vulnerability to AD, our findings of hypoactivation regions responsible for visual processing and attentional orienting in LOD patients are consistentwith hypoactivation patterns observed in AD patients in previous research. These results enhance our understanding of the neural mechanisms underlying memory impairments in LOD and their potential overlap with AD pathology.
Exploring Bio-Actors of the Cities through Serious Games
(SIGraDi 2024 Proceedings of the XXVIII Conference of the Iberoamerican Society of Digital Graphics, 2024) Ercan, İrem; Oguz, Kaya
This study focuses on the importance of biodiversity in protecting the urban ecosystem in urban planning. Considering cities as an ecosystem, city actors should communicate collaboratively within this ecosystem. Urban actors include not only humans but also other bio-based creatures. For the communication in the city through design, collecting information about bio-actors with their habitats, serious games can play an important role. Since serious games are useful for educating players, city inhabitants can be informed through these games. It was chosen as a method that provides a space to players for learning by entertaining. Therefore, the game 'My City Mate: Exploring Bio-actors of the City', developed on the Twine platform, offers players the opportunity to get to know the bio-actors of a fictional city environment with the visual, audio and text-based information it provides. Lastly, this research analyzes players' learning and interaction levels with this game through surveys.
Fmrı Deneylerinin Tasarlml, Yürütülmesi ve Analizi Design, Execution, And Analysis Of Fmrı Experiments
(Institute of Electrical and Electronics Engineers Inc., 2019-10) Oguz K.; Oguz, Kaya
Functional magnetic resonance imaging aims to correlate brain functions with the regions of the brain. To find out the region responsible for a brain function, the brain should be exposed to stimuli related to the function, and the changes in time should be monitored. To acquire images that change over time makes it more complex and difficult to extract deductions from functional images than structural images. To get the design right, it is necessary to ask the right questions, to give the correct stimuli at the right times, and to analyze the obtained data according to the design of the experiment. As a result, the design of the experiment affects the whole process. This paper presents a wide view of the complete process in the design, execution and the analysis of fMRI experiments, along with the related software and hardware requirements, as well as mentioning the challenges involved. © 2019 IEEE.
Citation - Scopus: 2
Selecting Emotion Specific Speech Features To Distinguish One Emotion From Others
(Institute of Electrical and Electronics Engineers Inc., 2021-08-25) Ozkan C.; Oguz K.; Ozkan, Cansu; Oguz, Kaya
Speech is one of the most studied modalities of emotion recognition. Most studies use one or more labeled data sets that contain multiple emotions to extract and select speech features to be trained by machine learning algorithms. Instead of this multi-class approach, our study focuses on selecting features that most distinguish an emotion from others. This requires a one-against-all (OAA) binary classification approach. The features that are extracted and selected for the multi-class case is compared to features extracted for seven one-against-all cases using a standard backpropagation feedforward neural network (BFNN). The results while OAA distinguishes some of the emotions better than the multi-class BFNN configurations, this is not true for all cases. However, when multi-class BFNN is tested with all emotions, the error rate is as high as 16.48. © 2021 IEEE.