LEE- Oyun ve Etkileşim Teknolojileri-Yüksek Lisans
Bu koleksiyon için kalıcı URI
Gözat
Son Başvurular
1 - 5 / 18
-
ÖgeDesign and development of audio-emotional serious games for audiology therapy(Graduate School, 2023)In recent years, with the increase in the use of technological tools, the act of playing games in people's daily lives has also started to occupy a large place. With this demand and the rapid development of the digital game industry, the digital game industry has become a major shareholder in the entertainment industry. In the digital game world, which includes a wide range of genres, the concept of serious game has emerged, which aims to provide information, education and therapy on any subject rather than just entertaining the players. The cornerstone of how people interact with their environment is communication. Communication is an indispensable phenomenon of people's daily lives. Emotions are one of the most important elements that enable effective communication. Although there are many differences between people in the world, the common concept shared by all people's emotions. Emotions are a very important building block that affects every thought or behavior in people's daily lives. It is very important for people to be able to express their emotions correctly and to understand the emotions of the others while communicating with their environment, in terms of establishing a smooth and efficient communication. At this point, especially hearing-impaired students at elementary school level, have difficulty in expressing their emotions while communicating with their peers and understanding the emotions conveyed in their dialogues with their peers. Within the scope of this thesis, two serious game projects were designed to help children who have difficulties in communicating effectively with their environment, including the mechanics of emotion analysis over voice. During the literature review, scientific studies on subjects such as emotions, expression of emotions, and serious games were examined, and many scientific research papers containing serious game projects in the field of therapy were explored. By combining the information obtained from all these scientific articles and similar studies with the principles of game design, serious games that are easy to play, enjoyable, and entertaining were developed, as indicated by the ratings provided by the participants in the experiment. The first game developed within the scope of the project is a 2D endless runner game. The first game project is called EmotiRUN. The game is designed to be as simple and easy to play as possible for the target audience of children. The main aim of the players in the game is to earn the highest score they can in a game round. The game focuses on three main emotions. These emotions are happiness, sadness and anger. These emotions are shown with animal symbols in the game. Respectively; the monkey represents happiness, the bird sadness and the snake anger. In the game, the players try to jump between the platforms and not fall into the gaps by jumping at the right time with the characters they control. At the same time, they earn points by collecting animal coins on the platforms as they progress through the game. When they collect 20 pieces of the same animal coin during the game, the players are faced with the emotion task about the related animal. Players who successfully complete this task earn extra points in the game. In the game, if the players cannot jump with their characters at the right time or if they hit into a platform and fall into the gap, the game is over. The second game developed for research is a 2.5 dimensional drag and shoot game. The name of the second game is EmotiFARM. There are many different game objects and mechanics in the game. The game consists of 10 different levels in total. There are different animals in the game levels and these animals have 3 different needs. These needs are water, food and attention. Players must select the suitable objects for these needs in the game and throw them to the right animal. If players can throw the right object to the right animal, they earn points. Players have the right to make 3 moves and choose 3 game objects in each level. If the players run out of these rights, they are faced with the emotion mission panel. On this screen, if the players can successfully complete the task, they gain in game moves or in game objects. The level ends when all the needs and tasks in a level are completed. Players who successfully complete 10 levels in total are finished the game. Both projects were developed using the Unity game engine. While designing the games, cartoonish graphics, cute objects and sounds were used to attract children's attention. During the design process, the design of the levels and the user interface design were designed to be simple, aesthetic, easy to understand and comfortable to use. Confusing and complex design is avoided as children can be easily distracted. A product called entertAIn play was used to analyze emotions from the voice in games. entertAIn play is a plugin powered by devAIce developed by the company named audEERING GmbH that can analyze emotions from voice with artificial intelligence. Within the scope of the research, the company was contacted and they agreed to support this project through their free academic license. Using this tech, the emotions of happiness, sadness and anger from the voices of the players in the games were detected in real time on the device without sending the data to any cloud server. Within the scope of the research, game experiments were conducted with 11 participants. While the target audience is especially hearing impaired children, the games in the research were tested on hearing impaired, autistic, dyslexic and normally developing children. 5 of the participants are hearing impaired, 1 has autism, 1 is dyslexia and 4 is typically developed children. 4 of the participants are female and 7 are male and their ages are between 10 and 16. Within the scope of the study, the first game was tested 5 times, and the second game was tested for a maximum of 30 minutes over 10 levels. At the end of the experimental sessions, the opinions of the participants about the features of the games were recorded using a 5-point Likert-type scale consisting of 14 items under 7 main headings. No additional explanation was given to any participant during the experiment, and they were expected to solve and play the games on their own. It was observed that the participants participating in the experiment played both games with great interest, fun and enthusiasm during the game testing process. When the test results were examined, it was seen that normally developed children, regardless of the type and complexity of the game, were able to express their emotions better with voice than other participants. Although hearing impaired participants achieved better results than dyslexic participant, it was observed that the success rates in expressing emotion over voice were very close to each other. The autistic participant was the participant with the lowest percentage of success in expressing emotion with voice in both games. Among the hearing impaired participants, the participants who had previously received speech therapy were more successful in both games than those who did not receive speech therapy. When the attitudes of the participants towards the game features were examined, it was determined that the first game with simpler mechanics was found to be easier to understand, fun and easy to play by the hearing impaired, dyslexic and autistic participants than the other game. In contrast, typically developed participants found the second game with complex mechanics and different levels more enjoyable. Apart from these, the second game, which has 2.5 dimensional graphics and contains many various game objects, was generally found more attractive among the participants in terms of gameplay and visually. Within the scope of this thesis study, when the feedback of the participants participating in the experiment were examined, it was seen that they had a pleasant time while playing the games and they had fun while playing the games, even though they were serious games. The mechanics of emotion analysis over sound have been successfully integrated into the games and can be used without disrupting the flow of gameplay. It has been seen that serious games can be used in the field of audiological therapy and it has been determined in general terms what features should be included in a therapy oriented serious game project whose target audience is children. In terms of areas that can be improved within the scope of the project, new levels, scenarios, mechanics, objects and emotion types can be added for future studies to increase the replayability of the games developed in this study and for a deeper therapy game experience. By increasing the number of children with hearing impairment, autism and other communication difficulties participating in the experiments, the data group can be expanded and more and reliable feedback can be collected in terms of game designs. In addition, the long term effectiveness of the use of serious games in therapy can be determined by extending the experimental periods of the games over a longer period. It is believed that the serious game projects presented within the scope of this thesis study, along with future developments and research, will provide inspiring information on how to design and develop a serious game project in the most effective way for audiological audio-emotion therapy, how serious games can help people to overcome their deficiencies in certain points and how serious game projects can contribute to keeping individuals motivated during the rehabilitation process and play an important role in having an enjoyable and effective therapy experience.
-
ÖgeOyunlaştırılmış artırılmış gerçeklik ile müze deneyimini geliştirme: İstanbul Oyuncak Müzesi(Lisansüstü Eğitim Enstitüsü, 2025-04-11)Geleneksel müze sergileri, her ne kadar ziyaretçilerle iletişim kurmak ve sergi nesneleri ile ilgili bilgi aktarımını sağlamak için uzun zamandır duvara monte paneller ve multimedya ekranlar gibi statik bilgi araçlarını kullanmakta olsa da bu yöntemler ziyaretçilerin aktif katılımını ve sergi içeriğinin incelenebilmesini teşvik etmede yetersiz kalmaktadır. Hızlı teknolojik gelişmelerle birlikte geleneksel yöntemlere olan ilginin azalmasıyla, müze ziyaretçilerinin beklentileri de değişmiştir. Bu süreçte ziyaretçiler kendilerini pasivize eden müzecilik yöntemlerine kıyasla daha aktif olarak rol aldıkları sergileme yöntemlerini tercihleri haline getirmişlerdir. Bu değişen beklentileri karşılamak için sergi mekanlarını daha etkileşimli alanlara dönüştürmek amacıyla dijitalleştirme unsurları ve oyunlaştırmalar benimsenmeye başlanmıştır. Ziyaretçilerin bu taleplerine paralel olarak müzelerde kullanılan artırılmış gerçeklik (AG) teknolojisi ve oyunlaştırma unsurları müze ve ziyaretçi arasındaki etkileşimi artırarak önemli bir rol üstlenmiştir. Dijital unsurları gerçekliğin üzerine yansıtan AG'nin müze sergilerine entegre edilmesi ile bilgi aktarımı daha güçlü bir hale getirilmektedir. Ziyaretçiler AG ile geleneksel sergileme yöntemlerinde erişemedikleri bilgilere kolaylıkla erişebilmekte ve bu sayede deneyimlerini zenginleştirebilmektedirler. Öte yandan oyunlaştırma, içinde barındırdıkları ilgi çekici görevler ile katılımı artıran bir yaklaşımdır. Sergi nesneleri özelinde hazırlanmış olan bulmacaları ve etkileşimli hikaye anlatımlarını içeren oyunlaştırmaların müzelere entegre edilmesi, ziyaretçilerin müzeye olan ilgisini artırmakta ve karmaşık bilgilerin ziyaretçiler tarafından daha kolay anlaşılmasını sağlamaktadır. Bu unsurlar öğrenmeyi daha eğlenceli bir hale getirmektedirler. Bu tez çalışması, bir müze ortamında ziyaretçi etkileşimini geliştirmek için oyunlaştırma ve AG'nin birleşik kullanımını incelemeyi amaçlamaktadır. Tez çalışması kapsamında AG teknolojisi ile hazırlanmış olan oyunlaştırmalar ile müzelerin görsel olarak geliştirilmesi; bu öğeler vasıtasıyla tecrübe etmiş oldukları müze deneyimlerinde ziyaretçilere sergi nesnelerini daha derinlemesine inceleme ve müze ile olan etkileşimlerini artırma fırsatı sunulması hedeflenmektedir. Dünya genelinde müzelerde dijitalleşme çalışmaları mevcut olsa da oyunlaştırma unsurları ile AG teknolojisi ayrı ayrı kullanılmaktadır. Bu tez çalışmasında ise bu iki ögenin birlikte kullanımı çalışmayı mevcut dönemde yapılmış olan çalışmalardan ayırmakta ve daha özgün kılmaktadır. Bu sebeple tez çalışması kapsamında dünya ve Türkiye'deki AG ve oyunlaştırma uygulamaları ayrı ayrı incelenmiş, yerel ve evrensel çalışmalar üzerinde gerçekleştirilmiş olan incelemeler müzeciliğin gelecekte nasıl geliştirilebileceğine dair tespitler yapılmasına imkan tanımıştır. Bu metodoloji ile günümüzde ziyaretçilerin müzelerden beklentilerinin ve bu beklentiler doğrultusunda gerçekleştirilen müzelerdeki dijitalleşmenin müze deneyimleri üzerindeki etkilerine dair bulgulara ulaşılmış olup, bu husus araştırmanın temel amaç ve konusunu oluşturmaktadır. Bu amaçlar doğrultusunda İstanbul Oyuncak Müzesi'nde yapılan çalışmada, ziyaretçilerin sergi nesneleri olan oyuncaklarla etkileşim kurmak istedikleri ancak bu beklentilerinin aksine oyuncaklar ile etkileşimin, cam vitrinler ile sınırlandırıldığı gözlemlenmiş ve müzenin kapsamlı oyuncak koleksiyonuna sahip olması sebebi ile de vaka çalışması alanı olarak İstanbul Oyuncak Müzesi seçilmiştir. Bu geliştirmeyi keşfetmek ve değerlendirmek için oyunlaştırılmış bir AG arayüzü geliştirilmiştir. Çalışma yöntemi dokuz aşamadan oluşmaktadır: i. Müze nesneleri olarak oyuncaklar araştırma için seçilmiştir. ii. AG arayüzü ile yapılacak olan oyunlaştırmalarda kullanımı uygun olanlar belirlenmiştir. iii. Oyuncaklara ilişkin senaryoların ve müze deneyim rotalarının belirlenmesi amacıyla oyuncakların tarihi, sosyo-kültürel ve fiziki özellikleri araştırılmıştır. iv. Oyuncaklar fotogrametri ve lidar olmak üzere birden çok yöntemle taranmıştır. v. Taramalar neticesinde en iyi sonuç alınan nesneler ile hikaye anlatımının da katkısıyla bir müze deneyim rotası oluşturulmuş ve beş belirli oyuncağa odaklanılmıştır. vi. Bu metodolojiden elde edilen veriler, ilk olarak uzman testleri ile değerlendirilmiştir. vii. Geleneksel müzeciliğin deneyimlerinin araştırılması amacıyla müze deneyimini daha yakından keşfetmek, değerlendirmek ve müze deneyiminin bilgi aktarımını ölçmek için sergi nesneleri olan oyuncakların bilgilerinin yer aldığı bir müze broşürü tasarlanmıştır. viii. Oyunlaştırılmış AG uygulaması ile müzeyi deneyimlemek üzere 30 ziyaretçi, müze broşürü ile müzeyi deneyimlemek üzere 30 ziyaretçi olmak üzere proje kapsamında oluşturulan deneyimler, toplamda 60 katılımcı ile gerçekleştirilmiştir. Deneyimler sırasında katılımcıların video kayıtları alınmış ve fotoğrafları çekilmiştir. Deneyimler sonrasında ise katılımcılara anketler yapılmış ve katılımcıların deneyimleri ile ilgili görüşleri alınmıştır. ix. Uzman testleri ve ziyaretçi deneyimleri sonucunda toplanan verilerin analizleri yapılmıştır. Bu tez çalışması kapsamında yapılan analizler sonucunda katılımcılarla gerçekleştirilen röportajlar neticesinde; oyunlaştırılmış AG uygulamaları ile müze deneyiminin daha ilgi çekici olduğu, öğrenme sürecinin geleneksel yöntemlere kıyasla daha akılda kalıcı ve eğlenceli olduğu gözlemlenmiştir. Ayrıca analizler, deneyim sonrası yapılan ankette oyunlaştırılmış AG uygulaması ile müzeyi deneyimleyen katılımcılar tarafından bilgi sorularının %84 oranında doğru cevaplandığı, müze broşürüyle müzeyi deneyimleyen katılımcıların cevaplarında ise bu oranın %59'da kaldığı görülmüştür. Bu sonuç, AG ve oyunlaştırma ögelerinin birlikte kullanılmasıyla oluşturulan oyunlaştırılmış AG uygulamaları ile gerçekleştirilen deneyimlerin bilgi aktarımı ve bilgilerin akılda kalıcılığı üzerindeki etkinliğini açıkça ortaya koymaktadır. Bu çalışma, İstanbul Oyuncak Müzesi'nde sergilenen uluslararası oyuncakların, hikaye anlatımı yoluyla kültürel değişime katkıda bulunma potansiyellerinin vurgulanmasıyla, bu oyuncakların farklı kitleler arasında kültürel anlatıları paylaşmanın bir aracı olarak nasıl hizmet edebileceğini göstermiştir. Çalışmada AG'nin potansiyeli değerlendirilmiş ve gelecekteki müze uygulamaları için AG uygulama senaryoları tanımlanmıştır. Ayrıca dijital unsurlar ile oyunlaştırmaların birleşik kullanımı ile özgün bir yaklaşım sergileyen çalışma kapsamında, müzeciliğe farklı bir perspektif oluşturulmuştur. Çalışma sonucu elde edilen bulgular, araştırmacıları ve tasarımcıları dijital bir öğrenme deneyimine teşvik ederek oyunlaştırılmış AG uygulamaları geliştirmeye yönlendirecektir. Kullanılan metodolojiden elde edilen veriler ve sonuçlar, müzelerin ziyaretçilere daha ilgi çekici ve eğitici deneyimler sunmasına yardımcı olacak önerilere yol haritası sağlayacaktır.
-
ÖgeDeep learning for game genre classification from game posters(Graduate School, 2024-12-06)This thesis aims to classify the genres of video games using a deep learning based model. The models, which were developed based on the ResNet50V2 and InceptionV3 architectures in the Keras library, were trained with game capsule images taken from the Steam platform and genre labels determined by game publishers. In addition, an online survey was conducted in which a group of participants classified games according to their genres. The results were used to comparatively evaluate the ability of both human participants and deep learning models to infer genres from the image content. The survey participants performed this task with more success than the ResNet50V2 model. Among the genres analyzed, it was observed that the prediction scores of the "indie" and "action" genres were higher than the "RPG" and "strategy" genres. This difference was also observed when the survey results were compared with the performance of the model using ResNet50V2. While the predictions made by survey participants show less variation between genres, the low performance of the ResNet50V2 model can be attributed to the different proportions of genres in the dataset. Therefore, it is recommended that the study be repeated with a more extensive data set, especially for these species. The variation in the survey results may be due to the ambiguity in the definition of RPG and strategy games or, in other words, the broader definition of these genres. The discrepancy in the ResNet50V2 model could be caused by the problem's structure or dataset size. Consequently, we trained two more models with the same number of data for every genre and one genre for every game. Again the ResNet50V2-based model performed poorly across most genres, and changing the dataset and issue format had no considerable effect on performance. Nonetheless, the model constructed using InceptionV3 demonstrated noteworthy advancements, especially with an RPG success rate of 82\% and an overall accuracy of 52\%. These findings imply that InceptionV3 outperforms ResNet50V2 in this challenge, suggesting that it is a more effective design. When the games that the ResNet50V2 model and the survey participants performed well and poorly were divided into two groups, it was observed that action, adventure, indie and casual game genres were more prominent in the well-performed group. It was stated that the images in the poorly performed group usually consisted of only the game name written on a simple background and that the common opinion that these images were incomprehensible was a positive result for the "providing design feedback" use case of the model. Likewise, the occurrence of cases where the model and survey participants marked the same genres but did not match the game genres on the Steam platform indicates that the model can be used for the "genre validation" use case. A noteworthy point between this study and previous studies is that there is no fixed standard for determining game genres. To overcome this problem and to find hidden relationships between games, unsupervised classification studies can be carried out in the future, and genres can be grouped into clusters without naming them, and the consistency of these clusters can be examined. Based on the responses from survey participants, the game images were reclassified, and new models capable of generating genre-specific game images were created using the stable diffusion 1.0 model. Subsequently, these models were employed to generate sample images for imaginary games, and a new survey was conducted. In this survey, the same pool of participants was asked to match the images with the corresponding genres. Unlike the initial survey, the independent game genre, which defines the organizational structure of the game developer team, and the casual game genre, which describes the complexity of the game, were excluded from this study based on the feedback received. The results of the second survey were similar to those of the first survey. When compared to the base model, the genre-specific image generation model produced images with higher genre predictability. As a result, using a deep learning models in recommendation systems based on game genres will improve the performance of the recommendation system and genre-specific image generation model has potential to assist designers. This thesis study contributes to game development and marketing processes by revealing the power of game images to reflect genres and the difficulties in accurately determining genres.
-
ÖgeDynamic difficulty adjustment by changing enemy behavior using reinforcement learning(Graduate School, 2024-07-25)Dynamic difficulty adjustment (DDA) systems are essential in modern gaming to provide to the diverse skill levels of players. These systems ensure that games remain challenging yet enjoyable by automatically adjusting the difficulty based on the player's performance. Traditional fixed difficulty settings often fail to provide an optimal experience for all players, leading to frustration for less skilled players and boredom for more skilled ones. Implementing DDA systems aims to enhance player engagement and satisfaction by maintaining an appropriate level of challenge throughout the game. Various techniques have been explored to implement DDA systems. One common approach is dynamic scripting, which involves adjusting the game's rules and parameters in real-time based on the player's actions. This technique allows for a more responsive and adaptable gaming experience. Other methods include player modeling, which uses data from the player's performance to predict their future behavior and adjust the difficulty accordingly, and machine learning algorithms that continuously learn and adapt to the player's skill level over time. Reinforcement learning (RL) has emerged as a powerful tool for developing DDA systems. In this approach, Artificial Intelligence (AI) agents are trained to play the game and learn optimal strategies to maximize their rewards. These agents can then dynamically adjust the game's difficulty by modifying the behavior of non-player characters (NPCs) or the game's mechanics based on the player's performance. This method allows for a more nuanced and effective DDA system that can adapt to the player's skill level in real-time. In this thesis, a DDA framework was created to be used in various gaming environments. Three different game scenarios were developed to demonstrate its effectiveness: a basic shooter, a basic action game, and a complex action game. Each of these scenarios provided a unique set of challenges and complexities, allowing for a thorough evaluation of the framework's adaptability and performance. The developed framework is capable of analyzing the performance of AI agents against human players and suggesting new difficulty levels accordingly. All parameters for these difficulty adjustments can be modified in the editor, providing game developers and designers with the flexibility to tweak the system to suit their specific needs. This capability ensures that the DDA system remains effective and relevant across different games and player demographics. The BrainBox plugin, developed for Unreal Engine, is a versatile tool designed to facilitate the creation of environments for DDA systems. It seamlessly communicates with a Python backend, managing the complex interplay between game environments and AI training processes. The plugin efficiently handles the creation and management of game environments, executes player and agent actions, calculates rewards, and xxii implements difficulty change procedures. This integration ensures that game developers can easily implement and tweak DDA systems, enhancing the gaming experience by maintaining an optimal level of challenge. A Python backend was created for training and evaluating the RL models. This backend communicates with the game environments created in Unreal Engine using Transmission Control Protocol (TCP), facilitating seamless integration between the training process and the game. The backend is responsible for managing the training data, running simulations, and updating the models based on the results, ensuring a robust and efficient training process. In the complex action game scenario, models were trained and evaluated to determine their effectiveness. The models were ordered by their median rewards across 20 episodes and mapped into difficulty levels. This process allowed for a detailed analysis of the models' performance and provided insights into their learning capabilities and adaptability to different levels of game complexity. A test case was conducted with 20 participants of varying game experience and skill levels. In this test case, the DDA was benchmarked with multiple testers. All sessions were logged, and a comprehensive analysis was performed on the collected data. This analysis provided valuable feedback on the system's performance and effectiveness in real-world scenarios, highlighting areas for improvement and potential future developments. In conclusion, the DDA demonstrated a robust capability in tailoring game difficulty to individual player needs. Its ability to adapt in real-time, guided by both player performance and feedback, highlights its potential to enhance gaming experiences significantly. The findings suggest that the DDA system not only improves player engagement and satisfaction but also offers a scalable solution for balancing difficulty in a wide array of games. Future implementations could benefit from refining this system to further optimize player retention and enjoyment, ensuring the game remains accessible and rewarding for all players regardless of their initial skill level.
-
ÖgeReinforcement learning in fighting games(Graduate School, 2022)Reinforcement learning is one of the most popular learning methods used on games because of its similar nature to competitive play. Winning the game and the means to win the game can be used as rewards easily, which enables us to create a reasonable benchmark. The field has many algorithms and approaches that can solve simple Atari games and robotic problems, however, it still has many unexplored areas with difficult problems to solve. After the introduction of Deep Q-Learning (DQN) by DeepMind, learning from pixel data become popular and applied to many other games. Agents could reach and exceed human level play in simple games. But for more complex games like Montezuma's Revenge, different approaches such as hierarchical DQN is needed to search the huge search space of the game. Furthermore, the classical +1 reward for win, -1 reward for lose strategy is not always enough for complex games. As the complexity increases, the algorithm and model should change and adapt. Even though Atari games look simple, they are hard problems to solve for an AI agent. The most recent work on Atari games published in 2020, claims to outperform humans on all Gym Atari games. However, there are still many difficult games to solve that requires novel approaches. The work on this thesis focuses on reaching a human-like play at the end stage boss fight in the game called Megaman X. Existing RL algorithms have been tested with different replay buffer types, parameters and exploration strategies and their performances were compared. To make a better comparison of the algorithms, a simple game called Super Mario World and a fighting game with similar characteristics to the main game called Ultimate Mortal Kombat has been tested as well. We proposed new game specific methods to make the agent play better, including reward shaping and feature extraction methods. This thesis shows the all the results of those trainings and analyses the results. In order to get better results from the trainings, reward shaping and feature extraction methods have been suggested and tested. For feature extraction, CNN based methods and auto-encoder frameworks have been tested and in addition to that, direct data read from the RAM such as character and enemy positions. Reward shaping is applied for the main focus on this thesis, the game Megaman X. Variables such as the charge status of the weapon, distance between the enemy and the agent, health and time are used as reward shaping parameters. Both Q-learning and policy gradient methods are tested. In addition, the latest exploration focused methods and hierarchical methods, which are said to be enhancing exploration, are tested. Also, human players who are familiar with platform games are also played the game and their experiences are recorded in a survey. In this thesis, all those methods and results are analysed.