Georgios Gerontakis, I. Voyiatzis, P. Yannakopoulos
The growing need to deal with modern and complex cyber threats and attacks, leads to an increase in the demand for human resources and expertise in the field of Cybersecurity, specifically in the field of monitoring and detecting these threats in the Security Operations sector. In this paper, we present already existing academic experience and literature about Cybersecurity training related topics, through attack and defense scenarios in a specially configured environment, which for the purposes of defense includes a Security Operations Center and for the purposes of the attack includes specially configured information systems which are intentionally vulnerable. Our results indicate that while there is existing literature available regarding the creation of functional SOC for educational purposes, it is not combined or used with applied attack and defense scenarios. There are also no instructions for practical use of the available information for educational purposes. We propose a theoretical structure and topology of an environment that can be used for applied training in Cybersecurity through attack scenarios using intentionally vulnerable information systems as targets and defense scenarios using a SOC to detect and respond to those attacks.
{"title":"Security Operations Center in Education: Building an Educational Environment for Attack and Defense Scenarios","authors":"Georgios Gerontakis, I. Voyiatzis, P. Yannakopoulos","doi":"10.1145/3575879.3575962","DOIUrl":"https://doi.org/10.1145/3575879.3575962","url":null,"abstract":"The growing need to deal with modern and complex cyber threats and attacks, leads to an increase in the demand for human resources and expertise in the field of Cybersecurity, specifically in the field of monitoring and detecting these threats in the Security Operations sector. In this paper, we present already existing academic experience and literature about Cybersecurity training related topics, through attack and defense scenarios in a specially configured environment, which for the purposes of defense includes a Security Operations Center and for the purposes of the attack includes specially configured information systems which are intentionally vulnerable. Our results indicate that while there is existing literature available regarding the creation of functional SOC for educational purposes, it is not combined or used with applied attack and defense scenarios. There are also no instructions for practical use of the available information for educational purposes. We propose a theoretical structure and topology of an environment that can be used for applied training in Cybersecurity through attack scenarios using intentionally vulnerable information systems as targets and defense scenarios using a SOC to detect and respond to those attacks.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130044495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohsan Ali, Maria Ioanna Maratsi, Loukis Euripidis, C. Alexopoulos, Y. Charalabidis
The plethora of digital means of expression available to the general public has provided citizens with the opportunity to share their views and opinions on government services online. Citizen (or customer) satisfaction is determined and influenced by a variety of factors, such as the municipality's environment, operations, document requirements and customer service representative behavior, among others. The main purpose of this study is to create a tool for co-creation and co-design in public service provision by using Natural Language Processing techniques to analyze all the available reviews on Greek municipalities, in order to determine the current status of service quality and customer satisfaction, while also suggesting future improvements that can be derived based on the study results. Five major topics that municipalities must focus on in order to provide services to citizens emerged: "services and processes", "response time and location of municipality", "employees", "communication channels", and "employees’ behavior". These five identified topics can be utilized to improve the service provision behind each of them, towards the end-users. In this manner, the citizens can actively participate towards the improvement of processes based on their needs, requirements and expectations.
{"title":"Analysis of Reviews on Greek Municipalities to Improve Public Service Delivery and Citizen Satisfaction: A Tool for Co-creation and Co-design","authors":"Mohsan Ali, Maria Ioanna Maratsi, Loukis Euripidis, C. Alexopoulos, Y. Charalabidis","doi":"10.1145/3575879.3576008","DOIUrl":"https://doi.org/10.1145/3575879.3576008","url":null,"abstract":"The plethora of digital means of expression available to the general public has provided citizens with the opportunity to share their views and opinions on government services online. Citizen (or customer) satisfaction is determined and influenced by a variety of factors, such as the municipality's environment, operations, document requirements and customer service representative behavior, among others. The main purpose of this study is to create a tool for co-creation and co-design in public service provision by using Natural Language Processing techniques to analyze all the available reviews on Greek municipalities, in order to determine the current status of service quality and customer satisfaction, while also suggesting future improvements that can be derived based on the study results. Five major topics that municipalities must focus on in order to provide services to citizens emerged: \"services and processes\", \"response time and location of municipality\", \"employees\", \"communication channels\", and \"employees’ behavior\". These five identified topics can be utilized to improve the service provision behind each of them, towards the end-users. In this manner, the citizens can actively participate towards the improvement of processes based on their needs, requirements and expectations.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"30 17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128883219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract: The universal daily use of the Internet and social media raises the need of privacy awareness. Using innovative technologies for educational purposes seems to be the solution to this issue. More specifically, game-based learning effectively educates users in technological fields, while offering adequate learning opportunities for a wide range of target groups. Although there are several categories of educational games and tools, virtual reality games are efficient for training on privacy issues. The present study aims to validate the adding value virtual reality games can bring to in privacy awareness status quo. In more detail, the advantages of game-based learning using cut-edge technologies, such as virtual reality, are analyzed. In order to evaluate this theory, a virtual reality escape room was designed, implemented, and navigated by 13 users that provided important feedback regarding the effectiveness of game-based learning and virtual reality in privacy Awareness.
{"title":"Virtual Reality as a mean for increasing privacy awareness: The escape room example","authors":"Sofia Niovi Maragkoudaki, Christos Kalloniatis","doi":"10.1145/3575879.3576002","DOIUrl":"https://doi.org/10.1145/3575879.3576002","url":null,"abstract":"Abstract: The universal daily use of the Internet and social media raises the need of privacy awareness. Using innovative technologies for educational purposes seems to be the solution to this issue. More specifically, game-based learning effectively educates users in technological fields, while offering adequate learning opportunities for a wide range of target groups. Although there are several categories of educational games and tools, virtual reality games are efficient for training on privacy issues. The present study aims to validate the adding value virtual reality games can bring to in privacy awareness status quo. In more detail, the advantages of game-based learning using cut-edge technologies, such as virtual reality, are analyzed. In order to evaluate this theory, a virtual reality escape room was designed, implemented, and navigated by 13 users that provided important feedback regarding the effectiveness of game-based learning and virtual reality in privacy Awareness.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121252162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maria Avramouli, I. Savvas, A. Vasilaki, G. Garani, Apostolos Xenakis
The drug discovery process is a time-consuming and quite expensive process. The predictive models of machine learning algorithms have been used efficiently for years in various stages of the drug discovery pipeline. The complexity of these algorithms increases as the size of the molecule increases, adding a single atom to a molecule increases the number of possible combinations. Quantum computers with quantum supremacy can play an important role in complex calculations. Combining the two technologies in practice is a complex endeavor that requires diverse, interdisciplinary teams of scientists working together to be able to integrate the two technologies with the goal of reducing cost and time in drug discovery.
{"title":"Quantum Machine Learning in Drug Discovery: Current State and Challenges","authors":"Maria Avramouli, I. Savvas, A. Vasilaki, G. Garani, Apostolos Xenakis","doi":"10.1145/3575879.3576024","DOIUrl":"https://doi.org/10.1145/3575879.3576024","url":null,"abstract":"The drug discovery process is a time-consuming and quite expensive process. The predictive models of machine learning algorithms have been used efficiently for years in various stages of the drug discovery pipeline. The complexity of these algorithms increases as the size of the molecule increases, adding a single atom to a molecule increases the number of possible combinations. Quantum computers with quantum supremacy can play an important role in complex calculations. Combining the two technologies in practice is a complex endeavor that requires diverse, interdisciplinary teams of scientists working together to be able to integrate the two technologies with the goal of reducing cost and time in drug discovery.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"537 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114049396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Designing in an environment of Virtual Reality is a field that gains ground. Although more and more applications are constantly released, the majority of designers have not yet been introduced into Virtual Reality. A widely used tool for designing is Rhino which has been released by McNeel and Rhino Developer encourages the users to create plug-ins for custom use of the software. In parallel, Meta's developing tools offer their users the chance to customize their own applications. Towards the direction of Virtual Reality integration, both have already released new products for their users. RhinoVR is an open source plug-in for Rhino, while at the same time Meta provides Oculus hardware and platform solutions for users to turn their concept into reality. What is yet to be developed is a model that encourages the customization of a VR design platform, focusing mainly on developing a personalized toolbox for designing.
{"title":"Customized toolbox in VR Design","authors":"Georgia Drampalou, N. Kourniatis, I. Voyiatzis","doi":"10.1145/3575879.3575960","DOIUrl":"https://doi.org/10.1145/3575879.3575960","url":null,"abstract":"Designing in an environment of Virtual Reality is a field that gains ground. Although more and more applications are constantly released, the majority of designers have not yet been introduced into Virtual Reality. A widely used tool for designing is Rhino which has been released by McNeel and Rhino Developer encourages the users to create plug-ins for custom use of the software. In parallel, Meta's developing tools offer their users the chance to customize their own applications. Towards the direction of Virtual Reality integration, both have already released new products for their users. RhinoVR is an open source plug-in for Rhino, while at the same time Meta provides Oculus hardware and platform solutions for users to turn their concept into reality. What is yet to be developed is a model that encourages the customization of a VR design platform, focusing mainly on developing a personalized toolbox for designing.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125416058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Angeliki Antoniou, A. Theodoropoulos, Jenny Rompa, Fani Giannakopoulou, G. Lepouras, Ioannis Triantafyllou
Over the last years our research group has been working with a novel concept for HCI in Cultural Informatics, that of minimum content. Responding to the cognitive overload and the museum fatigue that is well documented in the literature, the concept of minimum meaningful content was introduced and studied, with regards to the user experience, concerning possible learning benefits and overall satisfaction. The present work presents findings from different past efforts that explored the effects of minimum content on cultural heritage visitors. Minimum content was tested with visitors of different sites and lab experiment participants, focusing on augmented reality, games, and photography. The results reveal the potential of minimum content in cultural visits. The implications for HCI and future works are also discussed.
{"title":"Effects of minimum content in cultural informatics","authors":"Angeliki Antoniou, A. Theodoropoulos, Jenny Rompa, Fani Giannakopoulou, G. Lepouras, Ioannis Triantafyllou","doi":"10.1145/3575879.3575996","DOIUrl":"https://doi.org/10.1145/3575879.3575996","url":null,"abstract":"Over the last years our research group has been working with a novel concept for HCI in Cultural Informatics, that of minimum content. Responding to the cognitive overload and the museum fatigue that is well documented in the literature, the concept of minimum meaningful content was introduced and studied, with regards to the user experience, concerning possible learning benefits and overall satisfaction. The present work presents findings from different past efforts that explored the effects of minimum content on cultural heritage visitors. Minimum content was tested with visitors of different sites and lab experiment participants, focusing on augmented reality, games, and photography. The results reveal the potential of minimum content in cultural visits. The implications for HCI and future works are also discussed.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"373 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125567668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aristeidis Karras, Christos N. Karras, Agorakis Bompotas, P. Bouras, Leonidas Theodorakopoulos, S. Sioutas
Visualization is a critical component across every software as it enables users to familiarize themselves with the environment and perform certain tasks with ease. Therefore, straightforward yet interactive and easy-to-understand tools let users’ complex demands be satisfied within minutes. The objective of this work is to give an optimized graphical user interface for the Apache Spark MLlib library to apply machine learning algorithms quickly, conveniently, and effectively. We introduce SparkReact, a responsive graphical user interface that allows users to apply clustering, classification, and regression techniques within just a few mouse clicks by implementing and evaluating a certain algorithm and pre-building the code ready for import to Spark. To evaluate the usefulness of our tool we performed crowdsourcing to two categories, computer experts and ordinary users. The results indicate that both populations were satisfied with the tool at a surprising 98 percent. As per the time required to construct and evaluate a machine learning model, it took approximately 4 minutes using SparkReact while with ordinary methods it took almost 4 times longer. Ultimately, future extensions will seek to provide more algorithmic choices.
{"title":"SparkReact: A Novel and User-friendly Graphical Interface for the Apache Spark MLlib Library","authors":"Aristeidis Karras, Christos N. Karras, Agorakis Bompotas, P. Bouras, Leonidas Theodorakopoulos, S. Sioutas","doi":"10.1145/3575879.3575998","DOIUrl":"https://doi.org/10.1145/3575879.3575998","url":null,"abstract":"Visualization is a critical component across every software as it enables users to familiarize themselves with the environment and perform certain tasks with ease. Therefore, straightforward yet interactive and easy-to-understand tools let users’ complex demands be satisfied within minutes. The objective of this work is to give an optimized graphical user interface for the Apache Spark MLlib library to apply machine learning algorithms quickly, conveniently, and effectively. We introduce SparkReact, a responsive graphical user interface that allows users to apply clustering, classification, and regression techniques within just a few mouse clicks by implementing and evaluating a certain algorithm and pre-building the code ready for import to Spark. To evaluate the usefulness of our tool we performed crowdsourcing to two categories, computer experts and ordinary users. The results indicate that both populations were satisfied with the tool at a surprising 98 percent. As per the time required to construct and evaluate a machine learning model, it took approximately 4 minutes using SparkReact while with ordinary methods it took almost 4 times longer. Ultimately, future extensions will seek to provide more algorithmic choices.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125782814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid development of cloud computing environments has resulted in various advances and personalized services for users, raising thus several privacy issues. Towards this, research focused on privacy safeguard in the cloud, indicating solutions on the area of self-adaptive privacy. A detailed review is produced to bring forward the carried out work and to analyze it in terms of privacy interdisciplinary standards. In this regard, our work presents the existing self-adaptive privacy approaches and identifies the context for which they have been developed. Moreover, a corresponding classification scheme is provided. The findings give also insights on the proposed tools, which were critically analyzed. This review aims at indicating the developments and limitations of the area, providing potentials of future work in less discussed aspects of the self-adaptive privacy in cloud under an interdisciplinary point of view.
{"title":"Self-Adaptive Privacy in Cloud Computing: An overview under an interdisciplinary spectrum","authors":"Angeliki Kitsiou, Michail Pantelelis, Aikaterini-Georgia Mavroeidi, Maria Sideri, Stavros Simou, Aikaterini Vgena, Eleni Tzortzaki, Christos Kalloniatis","doi":"10.1145/3575879.3575968","DOIUrl":"https://doi.org/10.1145/3575879.3575968","url":null,"abstract":"The rapid development of cloud computing environments has resulted in various advances and personalized services for users, raising thus several privacy issues. Towards this, research focused on privacy safeguard in the cloud, indicating solutions on the area of self-adaptive privacy. A detailed review is produced to bring forward the carried out work and to analyze it in terms of privacy interdisciplinary standards. In this regard, our work presents the existing self-adaptive privacy approaches and identifies the context for which they have been developed. Moreover, a corresponding classification scheme is provided. The findings give also insights on the proposed tools, which were critically analyzed. This review aims at indicating the developments and limitations of the area, providing potentials of future work in less discussed aspects of the self-adaptive privacy in cloud under an interdisciplinary point of view.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127156192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tiny Machine Learning (TinyML) and Transfer Learning (TL) are two widespread methods of successfully deploying ML models to resource-starving devices. Tiny ML provides compact models, that can run on resource-constrained environments, while TL contributes to the performance of the model by using pre-existing knowledge. So, in this work we propose a simple but efficient TL method, applied to three types of Convolutional Neural Networks (CNN), by retraining more than the last fully connected layer of a CNN in the target device, and specifically one or more of the last convolutional layers. Our results shown that our proposed method (FxC1) achieves about increase in accuracy and increase in convergence speed, while it incurs a bit larger energy consumption overhead, compared to two baseline techniques, namely one that retrains the last fully connected layer, and another that retrains the whole network.
{"title":"Transfer Learning for Convolutional Neural Networks in Tiny Deep Learning Environments","authors":"E. Fragkou, Vasileios Lygnos, Dimitrios Katsaros","doi":"10.1145/3575879.3575984","DOIUrl":"https://doi.org/10.1145/3575879.3575984","url":null,"abstract":"Tiny Machine Learning (TinyML) and Transfer Learning (TL) are two widespread methods of successfully deploying ML models to resource-starving devices. Tiny ML provides compact models, that can run on resource-constrained environments, while TL contributes to the performance of the model by using pre-existing knowledge. So, in this work we propose a simple but efficient TL method, applied to three types of Convolutional Neural Networks (CNN), by retraining more than the last fully connected layer of a CNN in the target device, and specifically one or more of the last convolutional layers. Our results shown that our proposed method (FxC1) achieves about increase in accuracy and increase in convergence speed, while it incurs a bit larger energy consumption overhead, compared to two baseline techniques, namely one that retrains the last fully connected layer, and another that retrains the whole network.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127467790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ioannis Stoitsis, P. Amanatidis, T. Lagkas, D. Karampatzakis
This paper aims to present a hands-on short course for Edge AI to university students of Computer Science and Engineering departments. Edge Computing is a modern, distributed computing architecture that brings data storage and computation closer to the source of data generation instead of being sent to the Cloud. This approach provides several benefits to a modern IoT network such as bandwidth savings and improved response time. We propose an Edge Computing short course that includes theoretical knowledge reinforced with hands-on laboratory exercises. Our course syllabus combines different cutting edge technologies like Embedded systems, Artificial Intelligence and Machine Learning. For the implementation of the Edge Computing laboratory exercises we selected the Raspberry Pi Single Board Computer (SBC) to inference ML workloads applying different configurations. The proposed short course provides students the opportunity to develop expertise in Edge Computing and enforce skill development to manage projects that may encounter in a professional carrier.
{"title":"A Hands-on University Short Course for Edge AI","authors":"Ioannis Stoitsis, P. Amanatidis, T. Lagkas, D. Karampatzakis","doi":"10.1145/3575879.3575971","DOIUrl":"https://doi.org/10.1145/3575879.3575971","url":null,"abstract":"This paper aims to present a hands-on short course for Edge AI to university students of Computer Science and Engineering departments. Edge Computing is a modern, distributed computing architecture that brings data storage and computation closer to the source of data generation instead of being sent to the Cloud. This approach provides several benefits to a modern IoT network such as bandwidth savings and improved response time. We propose an Edge Computing short course that includes theoretical knowledge reinforced with hands-on laboratory exercises. Our course syllabus combines different cutting edge technologies like Embedded systems, Artificial Intelligence and Machine Learning. For the implementation of the Edge Computing laboratory exercises we selected the Raspberry Pi Single Board Computer (SBC) to inference ML workloads applying different configurations. The proposed short course provides students the opportunity to develop expertise in Edge Computing and enforce skill development to manage projects that may encounter in a professional carrier.","PeriodicalId":164036,"journal":{"name":"Proceedings of the 26th Pan-Hellenic Conference on Informatics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125323659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：