Application of AI for Analysis of Historical Collections and Artifacts

Artificial Intelligence (AI) has become a field of great interest in recent years, with significant research growth. According to Xinping Rong et al., around 60,000 research papers on AI are published annually. A bibliometric analysis of various databases conducted by Stacey Tobin et al. revealed that a total of 26,822 papers were published in the field of AI during 2011–2021, with a significant increase in multi authored papers compared to single-authored papers. This shows that collaboration between researchers is increasing in AI research. In addition, H. Mumtaj Begum conducted a study analyzing 257,000 articles in the field of AI and highlighted the increasing academic interest in research themes such as deep learning, machine learning, and the Internet of Things. Even in a specific domain such as oncology, the use of AI has resulted in more than 6,000 scientific papers, according to Alessandra Belfiore et al. AI technology plays a crucial role in the preservation of cultural artifacts, such as the image processing application by Santos et al. (2023). One of the interesting applications of AI is in the analysis of historical collections and artifacts. Previous research has shown significant progress in the integration of AI in this field. Andhari (2024) has used AI tools for the identification and management of artifacts, while(Argentiero et al., 2022) have applied AI for artifact correction in image acquisition and reconstruction. Lind et al. (2023) have also utilized AI for noise reduction and artifact correction in wearable sensor data analysis. In a forensic context, Solanke & Biasiotti (2022) have used AI for hidden evidence detection in digital artifacts. AI applications have also made significant impacts in medical imaging, as demonstrated by Gomi et al. (2021) in reducing metal artifacts in digital tomosynthesis, and Sogani et al. (2020) in improving the quality of radiological images by minimizing artifacts. Although the application of AI in the analysis of Japanese historical artworks is still an untapped potential, as mentioned by Burgelman et al. (2019), the broader application of AI in data analysis shows promising results in accelerating the extraction of knowledge from research artifacts. This suggests that there is still significant room for further exploration in the application of AI to the analysis of historical collections and artifacts. Considering the rapid development of AI research in general, as well as the successful application of AI in various related domains, this study aims to explore the process, technology, and role of AI in identifying, classifying, and analyzing various types of historical artifacts, including their physical condition and ancient texts contained on the artifacts. The ultimate goal is to improve efficiency and accuracy in cultural heritage preservation and research

Heritage preservation. This process involves converting physical artifacts into digital formats using technologies such as 3D scanning, which allows for easier storage, analysis, and accessibility.(Wachowiak & Karas, 2009). 3D scanning plays a key role in creating high-precision digital models that accurately capture the shape, texture and color of artifacts in detail.(Surendran et al., 2009). The digitization process involves the use of specialized software and post-processing stages to produce a fully rendered 3D model. Digitization allows the preservation of fragile artifacts without the risk of physical damage, as digital models can be studied and analyzed virtually.(Todorov et al., 2013) In addition, digital models can be enlarged or reduced according to research needs, facilitating deeper analysis. Digitization also encourages collaboration between researchers from different locations, as digital artifacts can be easily shared and studied simultaneously. Technological developments in the digitization of artifacts have led to the emergence of robotic systems designed for automated 3D digitization. These systems, as described in a study by(Stefano et al., 2016), using a lightweight robotic arm and a rotary table to capture detailed 3D models, is capable of handling the uniqueness and variation in size, shape and texture of artifacts. Automation of this 3D digitization process has enabled the mass digitization of collections of three-dimensional objects, as demonstrated by the CultLab3D facility discussed in the paper by(Santos et al., 2017). This mass digitization makes the process of scanning and archiving objects on a large scale more accessible to cultural heritage institutions. With digitization, the storage and management of artifact data becomes more organized and efficient, facilitating the long-term documentation and preservation of cultural heritage. Remote Sensing Remote sensing is the technique of gathering information about artifacts without direct physical contact, often using satellite or drone technology. In the context of analyzing historical collections, remote sensing allows for the mapping of archaeological sites and the identification of hidden or hard-to-reach artifacts. Multi spectral and hyperspectral sensors mounted on drones or satellites can detect materials and structures that are invisible to the naked eye. Remote sensing is also useful in monitoring the environmental conditions around historical sites to ensure their preservation. Data collected through remote sensing is analyzed using AI algorithms to identify patterns and anomalies that indicate the presence of artifacts. This technology expands the ability of researchers to find and preserve artifacts with greater efficiency and accuracy. Remote sensing technology has been used effectively to map and identify archaeological sites, as demonstrated in research focused on prehistoric artifacts and cultural resource management on Department of Defense and Department of Energy lands.(Sabol et al., 2000). The use of remote sensing for archaeological exploration and mapping holds promise in identifying and interpreting archaeological sites through various data processing techniques, thereby increasing the potential for further research.(Krupochkin et al., 2019). Advances in remote sensing have enabled the documentation and analysis of archaeological elements with high precision, facilitating the discovery and study of new archaeological features and environmental resources.(Borie et al., 2019). UAV-based remote sensing equipped with a LiDAR system has proven effective in detecting and visualizing partially exposed underground structures, even in densely vegetated areas, demonstrating the potential for high-resolution geospatial data collection.(YH Shin et al., 2023). The integration of artificial intelligence with remote sensing techniques has shown significant improvements in identifying and classifying archaeological features, thereby increasing the efficiency of archaeological research.(Argyrou & Agapiou, 2022). Pattern Recognition Pattern recognition is one of the primary applications of AI in artifact analysis, enabling the identification of recurring motifs and designs in historical collections. Pattern recognition algorithms can process images and data from artifacts to find patterns that are not directly visible to humans. For example, AI can identify carved patterns on ceramic artifacts that indicate a particular manufacturing technique or geographic origin. The technology is also useful in recognizing similar signs of wear or damage on artifacts, which can provide information about the artifact’s use or storage. Pattern recognition helps researchers make more informed conclusions about artifacts, such as identifying a particular artistic style or historical period. With the ability to automatically recognize patterns, AI increases the efficiency and accuracy of analyzing historical artifacts. AI-based pattern recognition is increasingly being used to analyze images and identify patterns in artifacts, improving the accuracy of historical analysis and aiding in the identification of specific techniques and provenance.(Pieri et al., 2018). Deep learning and convolutional neural networks are used for artifact recognition, enabling the detection of subtle patterns and signs of wear on artifacts, thereby enhancing understanding of their historical use.(Shopon et al., 2017). Automated artifact detection and classification using AI in histology images demonstrates the potential of the technology to minimize human intervention, suggesting similar applications in artifact analysis. Genetic algorithms and pattern recognition techniques have been applied to match and identify patterns directly on archaeological artifacts, aiding more accurate historical interpretation.(Auwatanamongkol, 2000). The use of various procedures in pattern detection and estimation helps to identify and interpret cultural patterns represented by prehistoric artifacts, which demonstrates the superiority of AI in archaeological research.(Hietala & Stevens, 1977). Classification of Artifacts Artifact classification involves using AI algorithms to group artifacts based on certain characteristics, such as shape, material, or function. This process helps researchers organize and understand large and diverse collections of artifacts. Machine learning algorithms are used to train AI models to automatically identify and group artifacts. Not only does artifact classification make them easier to store and manage, it also helps uncover relationships between artifacts that may not have been previously apparent. For example, artifacts from different locations can be classified together if they show similarities in materials or manufacturing techniques. With AI, the classification process becomes faster and more accurate, allowing researchers to focus on in-depth analysis and interpretation of the data. Machine learning algorithms have been used to classify artifact signals in EEG, showing potential for broader applications in historical artifact classification based on various signal features.(Lawhern et al., 2012). Distance-based clustering methods have been used to detect and group artifacts in EEG signals, which can be applied to group historical artifacts based on similar features.(Gupta et al., 1995). AI algorithms designed to detect and classify artifacts in neurophysiology research show that AI can significantly improve the accuracy of artifact classification and management.(Winkler et al., 2011). Motive Identification Motif identification is the process of uncovering designs and symbols engraved or painted on artifacts, which often have important cultural or historical significance. AI algorithms are used to analyze images of artifacts and identify motifs that may not be obvious to the human eye. This technique is particularly useful in studying artifacts from ancient civilizations, where motifs were often used as religious, political, or social symbols. Motif identification helps researchers understand the cultural context and purpose of an artifact. Additionally, identified motifs can be used to compare artifacts from different locations or periods, providing insight into interactions and influences between cultures. With AI, the process of motif identification becomes more efficient and accurate, paving the way for deeper historical interpretations. AI algorithms such as Geometric Hashing are used to identify structural motifs in material simulations, demonstrating the effectiveness of these algorithms in finding motifs despite different deformations and orientations (Duchstein et al., 2009). Neural network-based algorithms in artifact identification show that deep learning techniques can classify motifs with high accuracy, as used in EEG data to remove artifacts.(Hasasneh et al., 2018). Motif search techniques in biological sequence data demonstrate the ability of AI algorithms to detect significant recurring or conservative patterns, which can be similarly applied to motifs in historical artifacts (Kuksa & Pavlovic, 2010). A pattern recognition algorithm inspired by an artificial immune system is used to detect unknown motifs in time series data, which can be applied in the analysis of historical artifact motifs.(Wilson et al., 2008). Motif algorithms developed to detect important structural elements in biological data can be adapted for motif analysis in artifacts, demonstrating great potential in AI-based motif analysis (Federico & Pisanti, 2011). Machine learning Machine learning is an Artificial Intelligence (AI) technique used to analyze and predict artifact data based on patterns found in large datasets. Machine learning algorithms are trained using data collected from artifacts, allowing the model to recognize patterns and make accurate predictions (Emmitt et al., 2022). In the context of historical artifacts, machine learning can be used to identify the materials, manufacturing techniques, and even the age of an artifact based on certain characteristics. This process helps researchers make more informed conclusions and reduces human error in data analysis. Machine learning can also be used to predict the future condition of artifacts and identify potential damage. With machine learning, artifact analysis becomes more efficient, accurate, and data-driven, providing deeper insights into history and culture. In practice, machine learning uses various algorithms such as deep neural networks to accelerate progress in this field (LeCun et al., 2015). Machine learning algorithms based on neural networks, such as deep belief networks, have proven effective in handling artifacts and analyzing complex data such as EEG signals (Diachenko et al., 2022). In addition, the use of machine learning in identifying and removing artifacts from medical data, such as blood pressure data, has shown optimal results for the algorithms used (Pasma et al., 2020; Chen et al., 2016). In the specific context of identifying stone artifacts, studies have shown that machine learning, specifically deep neural networks, can distinguish processed stone artifacts from natural stones with high accuracy (Emmitt et al., 2022). The use of machine learning in the analysis of artifacts has significant implications for understanding history and culture. With the ability to accurately identify the materials, manufacturing techniques, and age of artifacts, machine learning can help researchers draw more informed conclusions about the origins and historical context of artifacts. This can provide new insights into past societies and cultures, as well as the evolution of technology and crafts over time. Additionally, the ability of machine learning to predict the future condition of artifacts and identify potential damage can help in the development of more effective conservation strategies. By identifying high-risk artifacts and taking appropriate precautions, machine learning can help in the preservation of cultural heritage for future generations. However, it is also important to consider the limitations and challenges of using machine learning in artifact analysis. The accuracy and reliability of machine learning results depend on the quality and quantity of data used to train the algorithm. Large and diverse datasets are needed to ensure accurate and generalizable results. In addition, interpreting machine learning results also requires expertise and domain knowledge from experts in the fields of archaeology, history, and conservation. Collaboration between machine learning experts and domain specialists is essential to ensure accurate and meaningful interpretation of the analysis results. Predictive Model Predictive models are AI tools used to forecast the future condition of an artifact based on historical data. These algorithms analyze patterns and trends in an artifact’s data to make accurate predictions about changes in condition or conservation needs. Predictive models help researchers and conservators plan timely care and maintenance strategies. For example, predictive models can identify artifacts that are at high risk of deterioration in the near future, so that preventive measures can be taken in advance. Additionally, these models can be used to predict environmental effects on artifacts, such as changes in temperature or humidity that could affect the artifact’s condition. By using predictive models, artifact conservation becomes more proactive and data-driven, ensuring the preservation of artifacts for future generations. Studies using multiphysics models to predict heat and moisture-induced stresses and strains in historic building materials show that these models are effective in predicting related deterioration processes, thus aiding in planning better conservation strategies.(Portal et al., 2014). Environmental monitoring-based methods and building dynamic simulations were used to assess climate control strategies in preventive conservation in historic buildings, showing that these approaches are effective in reducing the damage of hygroscopic artifacts such as cracks in valuable wooden ceilings (Frasca et al., 2019). A predictive modeling approach using machine learning to analyze historic vehicle engine health condition data can be applied in the context of artifacts to detect and classify the conservation condition of artifacts based on vibro-acoustic signals (Carrino et al., 2023). Research on predictive modeling in archaeology shows that methods such as maximum entropy are able to predict the location of archaeological sites based on historical data, providing a powerful tool for the conservation and research of historic sites (Yaworsky et al., 2020). Maintenance and Conservation Artifact preservation and conservation involves protecting and caring for artifacts to keep them in good condition. AI technology is used to monitor the condition of artifacts in real-time, providing accurate data on changes in temperature, humidity, and other environmental factors. AI algorithms can identify early signs of damage and provide recommendations for appropriate treatment actions. In addition, AI can be used to develop new, more effective and efficient conservation methods. Artifact preservation and conservation also involves analyzing the materials and structures of artifacts to determine the most appropriate treatment methods. With the help of AI, conservators can make more informed and proactive decisions about preserving artifacts. This technology allows for more effective preservation and conservation, ensuring that historical artifacts are protected for future generations. The use of AI in monitoring the condition of cultural artifacts has been proposed through the CHPC system which automatically regulates microclimate parameters based on Internet of Things (IoT) and AI technologies, assisting museum staff in selecting appropriate exhibition spaces for artifacts based on their materials.(Konev et al., 2019). Studies on the integration of information systems and digital technologies in the maintenance of artistic assets show that the combination of traditional methods with new digital technologies, such as Digital Twin, can significantly improve the maintenance and preservation of cultural heritage.(Marra et al., 2021). AI algorithms are used for predictive maintenance in various systems, as shown in a study of predictive maintenance of renewable energy systems. AI helps in detecting early signs of failure and improves the efficiency of technical inspections (W. Shin et al., 2021). Research on the application of AI to conservation challenges highlights the use of AI in automated data collection, classification, and conservation decision-making, enabling more dynamic and optimal environmental management.(Scoville et al., 2021). Quality monitoring and assessment of deep learning models in network management demonstrates the importance of regular maintenance of AI models to ensure high quality and accuracy of predictions, relevant for the maintenance of artifacts using AI (Yang & Rossi, 2021). Damage Detection Damage detection is an important process in the conservation of artifacts that aims to identify damage early and allow for immediate remedial action to prevent further damage. Artificial Intelligence (AI) technology has been widely used in the damage detection process, where AI algorithms are used to analyze images and data of artifacts, and detect signs of damage such as cracks, wear, or discoloration (Tavares et al., 2021). AI-based damage detection algorithms have the ability to process large amounts of data quickly, providing accurate and reliable results. This is critical in the conservation of artifacts, as early detection of damage allows conservators to take corrective action before the damage becomes more severe. In addition, AI can also be used to predict potential future damage based on historical data and current environmental conditions, making the conservation process more efficient and proactive, ensuring that artifacts remain in good condition for a longer period of time. The use of AI algorithms for damage detection has shown very effective and efficient results in various applications. In a study conducted by Tavares et al. (2021), AI algorithms were used to detect damage in lightweight structures through vibration processing and local resonance analysis. The results showed that the AI algorithm was able to detect defects with high accuracy. In addition, a study conducted by Chartier & Mita (2009) used an artificial immune system-based damage detection algorithm implemented on acceleration data. The results showed high effectiveness in identifying changes in modal properties and structural damage. Another study conducted by Agarwal, Xu, & Gopi (2016) used an automatic damage detection algorithm in mouse brain slice images with a geometric approach. The results showed a high ability to automatically detect tissue damage, which is relevant for the analysis of historical artifact damage. Restoration Recommendations Restoration recommendations are one of the important applications of Artificial Intelligence (AI) in the field of artifact conservation. AI is used to provide advice on the most effective methods and materials for repairing and restoring damaged artifacts. AI algorithms analyze data about the condition of the artifact and its damage history, then identify the most appropriate restoration solution (Lee, 2022). These recommendations can include repair techniques, restoration materials, and necessary maintenance steps. AI technology can also simulate the results of various restoration methods to select the most effective and safe approach. With AI-based restoration recommendations, conservators can make more informed and accurate decisions in repairing artifacts. This process not only improves the quality of restoration but also speeds up repair time and reduces the risk of further damage. Several studies have demonstrated the effectiveness of using AI in the restoration of cultural artifacts. A study by Lee (2022) demonstrated the use of artificial neural networks to mimic human visual styles in sound and images, and repair damaged parts using generative adversarial networks (GANs). 3D modeling and digital printing techniques have also been used to restore cultural artifacts, where these technologies can minimize direct contact with the artifact and facilitate modification of the restored part.(Hong et al., 2018). In addition, a framework integrating machine learning and pattern recognition for damage identification and artifact restoration has shown effectiveness in dealing with noisy and incomplete signals (Salehi et al., 2019). The use of virtual imaging technology for artifact restoration has also shown that this method can achieve fully reversible in situ restoration and provide a better visiting experience (Qiao et al., 2020). Accurate, data-driven restoration recommendations ensure that historical artifacts can be restored in the most effective and sustainable manner. By leveraging AI’s ability to analyze data, simulate outcomes, and provide precise recommendations, the process of restoring artifacts becomes more efficient, accurate, and safe. This allows conservators to better preserve cultural heritage and ensure that historical artifacts can be enjoyed by future generations. Accessibility Improvements Increasing the accessibility of artifacts by leveraging Artificial Intelligence (AI) technology is an important step in making artifact collections more accessible to the wider community. Through digitization and AI analysis, artifacts can be studied and appreciated without having to physically see them (Pisoni et al., 2021). AI-powered online platforms and mobile applications can provide detailed information about artifacts, including descriptions, 3D images, and historical context. The technology also allows visitors to virtually explore museums and historical sites, enhancing educational experiences and public engagement. Additionally, AI can be used to create more inclusive content, such as audio and text descriptions for individuals with special needs. With AI-powered accessibility enhancements, artifact collections become more open and accessible to a wider audience, strengthening appreciation for cultural and historical heritage. Research shows that AI can be used to create and deliver more accessible museum experiences, using technologies designed for more inclusive and participatory interactions (Pisoni et al., 2021). Studies on the digitization of biological collections also show that collaboration between humans and AI can improve data curation and management, and accelerate global access to important datasets.(Stenhouse et al., 2023). This shows the potential of AI in increasing accessibility and dissemination of information about artifacts to the wider community. In addition, AI algorithms such as NeRF used in photogrammetry enable artifact processing using mobile devices, reducing hardware requirements and facilitating augmented reality visualization of museum artifacts (Green, 2023). This technology opens up new opportunities in expanding access and interaction with artifacts digitally. AI-driven accessibility improvements not only benefit the general public, but also have important implications for education and research. With easier access to information and visualization of artifacts, researchers and students can conduct more in-depth studies of related history, culture, and science. This can enrich our understanding of the past and provide new insights into our cultural heritage. Additionally, increased accessibility can also encourage greater public engagement in the preservation and appreciation of artifacts, as well as raise awareness of the importance of preserving cultural heritage for future generations. Virtual Reality Virtual Reality (VR) is a technology that creates an immersive virtual environment, allowing users to interact with artifacts in three-dimensional space. In the context of artifact analysis, VR allows researchers and the public to view and manipulate digital models of artifacts as if they were in front of them (Wang, 2013). This technology provides an immersive and realistic experience, enriching the understanding of the artifact and its historical context. VR is also used in education, allowing students to learn about history and culture through engaging, hands-on experiences. Studies have shown that VR can increase student engagement and learning outcomes by allowing for 3D object manipulation and manual simulation in a virtual environment rich in experimental stimulation (Wang, 2013). Additionally, VR can be used to reconstruct archaeological sites and museum exhibits, providing deeper insight into how artifacts were used and displayed during their time. The use of VR is not limited to the field of artifact analysis alone, but also in various other educational fields. Studies on the use of VR in educating health professionals have shown that VR can improve cognitive skills and post-intervention knowledge better than traditional learning (Kyaw et al., 2019). The implementation of VR in academic libraries has also shown that VR can provide a richer and more intuitive learning environment by allowing students to interact with models of rare, fragile, or hard-to-reach artifacts and spaces (Lischer-Katz et al., 2018). In the field of art history, the use of VR has been shown to promote more active and interactive learning through the use of gamification techniques in a virtual museum environment (Huaman et al., 2019). With VR, the study and appreciation of artifacts becomes more interactive and immersive, opening up new ways to understand and appreciate cultural heritage. The technology allows users to explore artifacts and historical sites in a more immersive and personal way, providing a richer and more meaningful experience. In addition, VR can also expand access to artifacts and sites that may be physically difficult to reach, allowing more people to enjoy and learn about cultural heritage. As VR technology continues to develop, its potential uses in artifact analysis and education will expand, providing new opportunities to preserve and disseminate knowledge about our past. A digital database is a system for storing and managing information about artifacts in digital format that allows fast and efficient access to the data needed. Artificial Intelligence (AI) technology is used to organize and manage these databases, ensuring that artifact data is stored securely and easily found (Deutsch et al., 2014). Digital databases contain detailed information about each artifact, including images, descriptions, history, and analyses that have been performed. This system allows researchers to easily search and analyze data, identifying patterns and relationships between artifacts. In addition, digital databases allow collaboration between researchers from different locations, because data can be accessed online. With digital databases, the management and analysis of artifacts becomes more organized and efficient, opening up new opportunities for more in-depth research and conservation. The integration of AI in digital database management has shown promising results in various applications. An automated verification system for database-based systems shows that the integration of AI techniques with model verification systems can improve the accuracy and efficiency of complex database management, including in business applications and web services.(Deutsch et al., 2014). Studies on AI integration in big database management also show that collaboration between AI and database technology can improve information processing, supporting intelligent information systems based on distributed tasks (Wang, Zhang, & Yang, 2021). In the context of artifact management, dataspace-based artifact management systems show that the characteristics of dataspaces greatly support the life cycle of software artifacts, enabling automatic or semi-automatic traceability recovery and maintenance (Ying et al., 2009). The use of digital databases with AI integration in artifact management has significant implications for cultural heritage preservation and research. With the ability to efficiently store, organize, and analyze artifact data, digital databases allow researchers to access relevant information quickly and easily. This can speed up the research process and facilitate new discoveries in understanding artifacts and their historical context. In addition, digital databases also allow for better collaboration between researchers from different disciplines and geographic locations, allowing for a broader exchange of knowledge and insights. As AI and digital database technologies continue to advance, their potential use in artifact management and research will expand, providing new opportunities to better preserve and understand our cultural heritage. Collaboration and Publication Collaboration and publication are important aspects of artifact research, where Artificial Intelligence (AI) technology is used to facilitate collaboration between researchers and publish findings. AI-based collaboration platforms allow researchers to share data, ideas, and analysis results in real-time, accelerating the research process.(Seeber et al., 2020). The technology also makes it easier to compile and edit scientific publications, with automated tools that assist in referencing and error checking. AI is also used to analyze previously published data, identifying research trends and knowledge gaps that new research can fill. With AI-powered collaboration and publishing, researchers can work more efficiently and productively, disseminating knowledge more quickly and widely. The technology strengthens global research networks, enriching the study of artifacts with diverse and in-depth perspectives. Research on the use of AutoML in human-machine collaboration suggests that this technology can lower the barriers to data work, but still requires human intervention to be functional (Rogers & Crisan, 2023). This study develops a taxonomy of data work artifacts that captures the collaborative processes of humans and machines. Additionally, the study of machines as teammates in collaboration develops a research agenda to explore the potential risks and benefits of machines as teammates, with a focus on collaborative artifacts, collaboration, and institutions (Seeber et al., 2020). In the context of language learning, research on the use of social technologies suggests that these technologies can support collaboration in the construction of artifacts that can be shared by groups of learners, enhancing student understanding and engagement (Parmaxi, Zaphiris, & Ioannou, 2016). The use of AI in collaboration and publication of artifact research has significant implications for the advancement of knowledge and understanding of cultural heritage. By facilitating more efficient and productive collaboration between researchers from different disciplines and geographic locations, AI technology can accelerate new discoveries and broaden the scope of research. AI-based collaboration platforms enable researchers to share resources, expertise, and insights more easily, encouraging the exchange of ideas and innovation. In addition, AI-based publishing tools can help researchers compile and disseminate their findings more effectively, increasing the visibility and impact of artifact research. As AI technology continues to advance in collaboration and publication, the potential to advance our understanding of artifacts and cultural heritage will only grow, opening up new opportunities for more collaborative, interdisciplinary, and impactful research. Research Platform An Artificial Intelligence (AI)-based research platform is a tool that integrates various functions to support the analysis and conservation of artifacts. This platform provides access to digital databases, analysis tools, and collaboration facilities, allowing researchers to work efficiently and in an organized manner (Daniaty et al., 2022). AI technology in this platform helps in data management, pattern analysis, and prediction of artifact conditions. In addition, the research platform can be used to design and test hypotheses, develop predictive models, and compile research reports. With an AI-based research platform, the research process becomes more integrated and systematic, allowing researchers to focus on data analysis and interpretation. This technology improves the quality and productivity of research, paving the way for new di

This study aims to explore the technological process and role of AI in identifying, classifying, and analyzing various types of historical artifacts, including their physical condition and ancient texts. The study found that the Naga Community has a very rich knowledge of bamboo diversity and traditional management practices that are important for bamboo conservation and sustainable livelihoods. The study underlines the importance of supporting the Naga Community's efforts in preserving their cultural heritage and traditional knowledge and recommends the government and stakeholders to provide access to modern technology and resources to support bamboo conservation. In addition, this study demonstrates the great potential of AI in the analysis of historical collections and artifacts. With AI's ability to efficiently store, organize, and analyze artifact data, digital databases enable researchers to access relevant information quickly and easily, speeding up the research process, and facilitating new discoveries in understanding artifacts and their historical context. The use of AI technology in artifact research collaboration and publication also strengthens global research networks, enriching artifact studies with diverse and in-depth perspectives, and opening up new opportunities for better preservation and understanding of cultural heritage.