LEE- Oyun ve Etkileşim Teknolojileri-Yüksek Lisans
Bu koleksiyon için kalıcı URI
Gözat
Son Başvurular
1 - 5 / 17
-
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.
-
ÖgeGame-based learning in architecture education: Consolidating visual design principles in freshmen(Graduate School, 2023-07-21)Using games to teach people concepts has always been an attention-catching topic in the area of education. That is the main premise of game-based learning. Providing the players with manipulation tools such as the ability to change scale etc. to change the game environment by giving them more flexible options further facilitates their learning through trial and error, and encourages more involvement. With this aim, it was decided to create an artificial intelligence (AI) evaluated free creation video game aimed to consolidate visual design principle (VDP) knowledge in freshmen architecture students. VDPs are the underlying patterns that are present in designs people usually find appealing. The artificial intelligence that was used in the game was trained to detect some of these principles. There are more than only three main elements, however the artificial intelligence is trained on 3 main principles and their derivatives, which end up making up 9 sub VDPs. These VDPs are emphasis (color, isolation, shape), balance (symmetric, asymmetric, crystallographic), rhythm (regular, progressive, flowing). Artificial intelligence was decided to be used in the game because it can detect the trained VDP with success, as well as create a reliable checkpoint before students present their ideas to their instructors, which is time-consuming and might induce stress on some students. The usage of AI aims to eliminate some of that stress and the gaming nature of game-based learning is expected to motivate students further. The game welcomed the players with a menu screen in which they could choose to learn about VDPs with several example pictures and explanations. Following that, they could play a quiz mini-game where they were asked to choose a picture out of three pictures that held the VDP that was asked from them. All 9 sub VDPs, derived out of 3 main design principles, the artificial intelligence can detect were asked in order. Once they were done with the quiz, the game moved on to the "creation" section where the players were given an objective to create a composition with an emphasis on a specific VDP. The composition was managed by placing and manipulating design elements (basic shapes such as square, triangle, hexagon etc. or object textures) on a canvas with a grid. The design elements could snap onto the grid so that it would be easier to create more calculated compositions. When the players were happy with their composition, they submitted their compositions to the application in the background where artificial intelligence resides and that artificial intelligence evaluated that composition, giving a score to the player. The score showed the top 3 VDPs the composition had and the percentages of how much they governed the composition. Once players were done playing and creating their compositions, they were asked to fill out a questionnaire. Players' experiences about the game were obtained via the questionnaire, which based its scientific validity on the research named "Assessing the Core Elements of Gaming Experience (CEGE)". The questionnaire consisted of 24 statements in which students were asked to grade their level of agreement to using a 5-point Likert scale. 43 students participated in the questionnaire and all 43 of them answered every question. There was only one group and no control group. Following the questionnaire, a follow-up survey was given to 10 students. The follow-up survey consisted of 7 open-ended questions aimed to further understand what elements of the game were liked or disliked. According to the results gathered through that questionnaire, the majority of players stated that playing the game helped them consolidate their VDP knowledge, that they would want to see the game used in VDP education, and that they would want serious games to be used in education more. In addition, the results of the follow-up survey were helpful to see what was done right in the serious game, and what else could have been added to improve the game. This result points to the need for further research on game-based learning in architecture and shows some students' wish for more game-based learning in architecture education.