Lazaros Apostolidis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lazaros Apostolidis has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Symeon Papadopoulos
Information Technologies Institute, CERTH, Thessaloniki, Greece
7 shared publications - Ioannis Kompatsiaris
Information Technologies Institute, CERTH, Thessaloniki, Greece
6 shared publications - Denis Teyssou
Agence France-Presse, Paris, France
2 shared publications - Giorgos Kordopatis-Zilos
Czech Technical University, Prague, Czech Republic
2 shared publications Killian Levacher
IBM Research, Dublin, Ireland
2 shared publications- Panagiotis Galopoulos
Information Technologies Institute - Centre of Research & Technology - Hellas, Greece
2 shared publications
Latest Publications
- Open Access
Cancer Patients’ Perspectives and Requirements of Digital Health Technologies: A Scoping Literature Review
Digital health technologies have the potential to alleviate the increasing cancer burden. Incorporating patients’ perspectives on digital health tools has been identified as a critical determinant for their successful uptake in cancer care. The main objective of this scoping review was to provide an overview of the existing evidence on cancer patients’ perspectives and requirements for patient-facing digital health technologies. Three databases (CINAHL, MEDLINE, Science Direct) were searched and 128 studies were identified as eligible for inclusion. Web-based software/platforms, mobile or smartphone devices/applications, and remote sensing/wearable technologies employed for the delivery of interventions and patient monitoring were the most frequently employed technologies in cancer care. The abilities of digital tools to enable care management, user-friendliness, and facilitate patient–clinician interactions were the technological requirements predominantly considered as important by cancer patients. The findings from this review provide evidence that could inform future research on technology-associated parameters influencing cancer patients’ decisions regarding the uptake and adoption of patient-facing digital health technologies.
Open AccessCancer Patients’ Perspectives and Requirements of Digital Health Technologies: A Scoping Literature Review
Digital health technologies have the potential to alleviate the increasing cancer burden. Incorporating patients’ perspectives on digital health tools has been identified as a critical determinant for their successful uptake in cancer care. The main objective of this scoping review was to provide an overview of the existing evidence on cancer patients’ perspectives and requirements for patient-facing digital health technologies. Three databases (CINAHL, MEDLINE, Science Direct) were searched and 128 studies were identified as eligible for inclusion. Web-based software/platforms, mobile or smartphone devices/applications, and remote sensing/wearable technologies employed for the delivery of interventions and patient monitoring were the most frequently employed technologies in cancer care. The abilities of digital tools to enable care management, user-friendliness, and facilitate patient–clinician interactions were the technological requirements predominantly considered as important by cancer patients. The findings from this review provide evidence that could inform future research on technology-associated parameters influencing cancer patients’ decisions regarding the uptake and adoption of patient-facing digital health technologies.
- Open Access
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 193-198
Online Behaviour Indicator Extraction for Enhanced Cancer Patient Management using Real-World Data
- 20 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 193-198
Open AccessOnline Behaviour Indicator Extraction for Enhanced Cancer Patient Management using Real-World Data
- Open Access
- 27 June 2022
- Published by Association for Computing Machinery (ACM)
- p. 59-68
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.
- 27 June 2022
- Published by Association for Computing Machinery (ACM)
- p. 59-68
Open AccessThe MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.
- Open Access
- 10 May 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (5) , 147
MeVer NetworkX: Network Analysis and Visualization for Tracing Disinformation
The proliferation of online news, especially during the “infodemic” that emerged along with the COVID-19 pandemic, has rapidly increased the risk of and, more importantly, the volume of online misinformation. Online Social Networks (OSNs), such as Facebook, Twitter, and YouTube, serve as fertile ground for disseminating misinformation, making the need for tools for analyzing the social web and gaining insights into communities that drive misinformation online vital. We introduce the MeVer NetworkX analysis and visualization tool, which helps users delve into social media conversations, helps users gain insights about how information propagates, and provides intuition about communities formed via interactions. The contributions of our tool lie in easy navigation through a multitude of features that provide helpful insights about the account behaviors and information propagation, provide the support of Twitter, Facebook, and Telegram graphs, and provide the modularity to integrate more platforms. The tool also provides features that highlight suspicious accounts in a graph that a user should investigate further. We collected four Twitter datasets related to COVID-19 disinformation to present the tool’s functionalities and evaluate its effectiveness.
- 10 May 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (5) , 147
Open AccessMeVer NetworkX: Network Analysis and Visualization for Tracing Disinformation
The proliferation of online news, especially during the “infodemic” that emerged along with the COVID-19 pandemic, has rapidly increased the risk of and, more importantly, the volume of online misinformation. Online Social Networks (OSNs), such as Facebook, Twitter, and YouTube, serve as fertile ground for disseminating misinformation, making the need for tools for analyzing the social web and gaining insights into communities that drive misinformation online vital. We introduce the MeVer NetworkX analysis and visualization tool, which helps users delve into social media conversations, helps users gain insights about how information propagates, and provides intuition about communities formed via interactions. The contributions of our tool lie in easy navigation through a multitude of features that provide helpful insights about the account behaviors and information propagation, provide the support of Twitter, Facebook, and Telegram graphs, and provide the modularity to integrate more platforms. The tool also provides features that highlight suspicious accounts in a graph that a user should investigate further. We collected four Twitter datasets related to COVID-19 disinformation to present the tool’s functionalities and evaluate its effectiveness.
- Open Access
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.
Open AccessThe MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Enabled by recent improvements in generation methodologies, DeepFakes have become mainstream due to their increasingly better visual quality, the increase in easy-to-use generation tools and the rapid dissemination through social media. This fact poses a severe threat to our societies with the potential to erode social cohesion and influence our democracies. To mitigate the threat, numerous DeepFake detection schemes have been introduced in the literature but very few provide a web service that can be used in the wild. In this paper, we introduce the MeVer DeepFake detection service, a web service detecting deep learning manipulations in images and video. We present the design and implementation of the proposed processing pipeline that involves a model ensemble scheme, and we endow the service with a model card for transparency. Experimental results show that our service performs robustly on the three benchmark datasets while being vulnerable to Adversarial Attacks. Finally, we outline our experience and lessons learned when deploying a research system into production in the hopes that it will be useful to other academic and industry teams.
- 2 October 2020
- Published by Springer Nature
- Vol. 12250, 851-867
i-CHANGE: A Platform for Managing Dockless Bike Sharing Systems
The new generation of bike-sharing services without docking stations is spreading around large cities of the world. The paper provides a technical specification of a platform, for managing a dockless bike sharing system. The bicycles of the platform are equipped with GPS devices and GPRS cards that can transmit, over the Internet, their exact location at any time. We collect and store all events derived from a user’s interaction with the system and in addition the trajectory points of a route during a rent order. The platform aims to fulfill the requirements of bikers, administrators and the research community through the collection, analysis and exploitation of bike sharing data. In the context of the platform, an app for smart devices is implemented for citizens to access the system. A dashboard is offered to the administrator as a valuable tool to inspect, promote the system and evaluate its usage. Last, all stored anonymised data can be accessible for further analysis by the research community through a REST API. The i-CHANGE platform is currently pilot tested in the city of Thessaloniki, Greece.
- 2 October 2020
- Published by Springer Nature
- Vol. 12250, 851-867
i-CHANGE: A Platform for Managing Dockless Bike Sharing Systems
The new generation of bike-sharing services without docking stations is spreading around large cities of the world. The paper provides a technical specification of a platform, for managing a dockless bike sharing system. The bicycles of the platform are equipped with GPS devices and GPRS cards that can transmit, over the Internet, their exact location at any time. We collect and store all events derived from a user’s interaction with the system and in addition the trajectory points of a route during a rent order. The platform aims to fulfill the requirements of bikers, administrators and the research community through the collection, analysis and exploitation of bike sharing data. In the context of the platform, an app for smart devices is implemented for citizens to access the system. A dashboard is offered to the administrator as a valuable tool to inspect, promote the system and evaluate its usage. Last, all stored anonymised data can be accessible for further analysis by the research community through a REST API. The i-CHANGE platform is currently pilot tested in the city of Thessaloniki, Greece.
- Open Access
- 14 October 2019
- Published by Association for Computing Machinery (ACM)
- p. 215-222
Social media monitoring tools for air quality accounts
In recent years, social media have become a powerful medium of public discourse, and in particular microblogging services (e.g., Twitter) play a crucial role in information dissemination. Being able to efficiently monitor and glean insights from streams of social media interactions could be valuable for better mapping and engaging with a community of interest. In this paper, we focus on the domain of air quality and present the outcomes of our work in the context of a research project, called hackAIR. To fulfill the project's communication needs we provide novel tools for effectively discovering key social media accounts, keeping up-to-date with trending news in the area of air quality, and better understanding the social media audience of the project Twitter account. We showcase our tools through the use case of hackAIR's social media communication activities.
- 14 October 2019
- Published by Association for Computing Machinery (ACM)
- p. 215-222
Open AccessSocial media monitoring tools for air quality accounts
In recent years, social media have become a powerful medium of public discourse, and in particular microblogging services (e.g., Twitter) play a crucial role in information dissemination. Being able to efficiently monitor and glean insights from streams of social media interactions could be valuable for better mapping and engaging with a community of interest. In this paper, we focus on the domain of air quality and present the outcomes of our work in the context of a research project, called hackAIR. To fulfill the project's communication needs we provide novel tools for effectively discovering key social media accounts, keeping up-to-date with trending news in the area of air quality, and better understanding the social media audience of the project Twitter account. We showcase our tools through the use case of hackAIR's social media communication activities.