Universtad Autonomous de Barcelona - Prehistory / Quantitative Archaeology Lab. PhD Candidate Anatolian University - web design and coding Akdeniz University - Museum Studies - MSc Ankara University - Archaeology Antalya Anatolian High School Supervisors: Prof. Dr. Juan Antonio Barcelo Address: Antalya, Antalya, Turkey
Studies on machine learning have started to reach a level where we can save a great amount of tim... more Studies on machine learning have started to reach a level where we can save a great amount of time and labor by producing structures that can think as a human and have decisions. Deep learning, one of the methods of machine learning, is an artificial intelligence-training technique that can predict the outputs from the given dataset In this study, the use of web scraping technique was investigated to determine the potential of identifying ancient columns, which are one of the most important architectural elements of cultural heritage, by artificial intelligence. In this study, web scraping approach is presented as a digital data acquisition method for archaeology field to collect imagery datasets from web to analyze the ancient cities. For analysis, a free online, and easy-to-use tool 'Amazon Rekognation' is used for comparing the number of columns found in the scrapped images. For summarizing the research, simply, we have tried to get the answer the question from PC that 'which site has the columns most, Perge, Xanthos or Phaselis?'. With this proposed approach, the archeologists can have a primarily knowledge about the sites they will study with use of operational tools for their further comprehensive research.
Europen Journal Of Post-Classical Archaeologies (PCA), 2022
Although some of the now popular deep learning techniques and technologies have a relatively long... more Although some of the now popular deep learning techniques and technologies have a relatively long history (nearly 30 years), it has been in the last 5 years when these applications have reached mainstream Archaeology, cultural heritage and museum studies. There is a new conscience of data processing in Archaeology, although the nature of these data hardly arrives to the usual label ‘big data’, and it has opened the methodological toolbox at use, especially in domains like reconstruction, remote sensing, object recognition, typological analysis, and collection management and visitor studies. In this paper, the history and current applications of neural networks and related methods of machine learning in archaeology, cultural heritage and museum studies are investigated. The necessary theoretical background on induction and learning is provided to understand the possibilities and limitations of computational techniques. Keywords: archaeology, cultural heritage, artificial intelligence, neural networks, deep learning.
We see that the technologies developing with Industry 4.0 are rapidly spreading to our daily live... more We see that the technologies developing with Industry 4.0 are rapidly spreading to our daily lives. While new products are added to smart products every day, new developments are taking place especially on the axis of artificial intelligence even now. In recent years, breakthrough innovations have emerged as a result of the combination of machine learning and the power of deep learning algorithms with the power of embedded system GPUs with parallel processing power. It is possible to say that the developments in artificial İntelligence/deep learning in recent years have spread to Archeology, cultural and artistic life and museums naturally. The processing of big data in archeology and museums with deep learning methods making them meaningful and makes this hard work very easy, at the same time it is also used especially in object recognition and visitor studies. It also saves time and labor. In this study, both the recent developments in artificial intelligence and deep learning are examined and an evaluation of these methods in the context of archeology and museology is made. The assessment convey the current situation and provide insight into how future implementation areas could be established. Özet: Endüstri 4.0 ile birlikte gelişen teknolojilerin hızla gündelik hayatımıza sirayet ettiğini görmekteyiz. Akıllı ürünlere her geçen gün bir yenisi eklenirken, özellikle yapay zeka ekseninde her gün yeni gelişmeler olmaktadır. Son yıllarda makine öğrenmesi ve onun alt disiplini olarak son yıllarda ortaya çıkan derin öğrenme algoritmalarının gücünün, donanım alanında, paralel işlem gücüne sahip gömülü sistem GPU ların gücüyle birleşmesi sonucu çığır açan yenilikler ortaya çıkmış, başta Google ve Microsoft olmak üzere birçok teknoloji devi derin öğrenme alanında ciddi yatırımlar yaparak sadece bu alanlarda çalışmalar yapan şirketler kurmuşlardır. Son yıllarda bu alanlardaki gelişmelerin Arkeolojiye, kültür sanat hayatına ve doğal olarak müzelere sirayet ettiğini söylemek yanlış olmaz. Kültürel miras çalışmalarında ortaya çıkan ve depolanan büyük verinin derin öğrenme yöntemleri ile işlenmesi ve anlamlı bilgi haline getirilerek tasnif edilmesi bu zor işi çok kolay hale
Studies on machine learning have started to reach a level where we can save a great amount of tim... more Studies on machine learning have started to reach a level where we can save a great amount of time and labor by producing structures that can think as a human and have decisions. Deep learning, one of the methods of machine learning, is an artificial intelligence-training technique that can predict the outputs from the given dataset In this study, the use of web scraping technique was investigated to determine the potential of identifying ancient columns, which are one of the most important architectural elements of cultural heritage, by artificial intelligence. In this study, web scraping approach is presented as a digital data acquisition method for archaeology field to collect imagery datasets from web to analyze the ancient cities. For analysis, a free online, and easy-to-use tool 'Amazon Rekognation' is used for comparing the number of columns found in the scrapped images. For summarizing the research, simply, we have tried to get the answer the question from PC that 'which site has the columns most, Perge, Xanthos or Phaselis?'. With this proposed approach, the archeologists can have a primarily knowledge about the sites they will study with use of operational tools for their further comprehensive research.
Europen Journal Of Post-Classical Archaeologies (PCA), 2022
Although some of the now popular deep learning techniques and technologies have a relatively long... more Although some of the now popular deep learning techniques and technologies have a relatively long history (nearly 30 years), it has been in the last 5 years when these applications have reached mainstream Archaeology, cultural heritage and museum studies. There is a new conscience of data processing in Archaeology, although the nature of these data hardly arrives to the usual label ‘big data’, and it has opened the methodological toolbox at use, especially in domains like reconstruction, remote sensing, object recognition, typological analysis, and collection management and visitor studies. In this paper, the history and current applications of neural networks and related methods of machine learning in archaeology, cultural heritage and museum studies are investigated. The necessary theoretical background on induction and learning is provided to understand the possibilities and limitations of computational techniques. Keywords: archaeology, cultural heritage, artificial intelligence, neural networks, deep learning.
We see that the technologies developing with Industry 4.0 are rapidly spreading to our daily live... more We see that the technologies developing with Industry 4.0 are rapidly spreading to our daily lives. While new products are added to smart products every day, new developments are taking place especially on the axis of artificial intelligence even now. In recent years, breakthrough innovations have emerged as a result of the combination of machine learning and the power of deep learning algorithms with the power of embedded system GPUs with parallel processing power. It is possible to say that the developments in artificial İntelligence/deep learning in recent years have spread to Archeology, cultural and artistic life and museums naturally. The processing of big data in archeology and museums with deep learning methods making them meaningful and makes this hard work very easy, at the same time it is also used especially in object recognition and visitor studies. It also saves time and labor. In this study, both the recent developments in artificial intelligence and deep learning are examined and an evaluation of these methods in the context of archeology and museology is made. The assessment convey the current situation and provide insight into how future implementation areas could be established. Özet: Endüstri 4.0 ile birlikte gelişen teknolojilerin hızla gündelik hayatımıza sirayet ettiğini görmekteyiz. Akıllı ürünlere her geçen gün bir yenisi eklenirken, özellikle yapay zeka ekseninde her gün yeni gelişmeler olmaktadır. Son yıllarda makine öğrenmesi ve onun alt disiplini olarak son yıllarda ortaya çıkan derin öğrenme algoritmalarının gücünün, donanım alanında, paralel işlem gücüne sahip gömülü sistem GPU ların gücüyle birleşmesi sonucu çığır açan yenilikler ortaya çıkmış, başta Google ve Microsoft olmak üzere birçok teknoloji devi derin öğrenme alanında ciddi yatırımlar yaparak sadece bu alanlarda çalışmalar yapan şirketler kurmuşlardır. Son yıllarda bu alanlardaki gelişmelerin Arkeolojiye, kültür sanat hayatına ve doğal olarak müzelere sirayet ettiğini söylemek yanlış olmaz. Kültürel miras çalışmalarında ortaya çıkan ve depolanan büyük verinin derin öğrenme yöntemleri ile işlenmesi ve anlamlı bilgi haline getirilerek tasnif edilmesi bu zor işi çok kolay hale
Uploads
Papers by Deniz Kayikci
Keywords: archaeology, cultural heritage, artificial intelligence, neural networks, deep learning.
Keywords: archaeology, cultural heritage, artificial intelligence, neural networks, deep learning.