This paper presents the development of a scalable hydro- ponics monitoring system and data processing through wireless sensor networks. We implement novel hardware and virtual sensors through ab- straction in an IoT management platform. We introduce the concept of collaborative machine learning from multiple sites to improve prediction and discuss related project challenges

Komninos, A., Georgiadis G., Koskeris A., & Garofalakis J. (2019).  Internet of things applications on monitoring hydroponics through wireless sensor networks. 10th International Conference on Information, Intelligence, Systems and Applications (IISA'19). ., Springer.

Internet of Things is the cornerstone of most of the modern technological achievements and one of the biggest sources of data. The millions of Mbytes generated by telemetry sensors are already used for statistical analysis or the creation of prediction models used in various applications in the area of smart cities, smart building, smart health, smart energy, etc. From the other hand, the expansion of IoT forced the need of more standardized approaches such the ones used in industrial automation. The Industrial Internet of Things, as part of Industry 4.0 concept, promotes the cyber physical systems (CPS) as sensors and actuators that will build the modern automation world in and out of the factories. This article studies the IIoT reference architectures and the existing open source IoT platforms for proposing an integrated architecture for installing IIoT infrastructure that can collect and analyze big volume of data, easy and with low cost. The approach is evaluated in a smart building scenario.

Alexakos, C., Komninos A., Anagnostopoulos C., Kalogeras G., Savvopoulos A., & Kalogeras A. (In Press).  Building an Industrial IoT Infrastructure with open Source Software for Smart Energy. First International Conference on Societal Automation. Krakow, Poland, IEEE.

In this paper, we discuss the main challenges for human monitoring of complex cyberphysical systems, with the use of mobile technology such as smartphones, tablets and head- mounted augmented (or virtual) reality headsets. We discuss the limitations of human cognition in terms of attention management, and provide an overview of the state of the art in mobile notification systems. Concluding, we describe the role of machine learning and artificial intelligence in the assistance of mobile CPS monitoring engineers.

Komninos, A.. (In Press).  Challenges in multimodal notifications for monitoring cyberphysical systems. First International Conference on Societal Automation. Krakow, Poland, IEEE.

Cyber Physical Systems (CPS) combine computational and physical components enabling real world interaction. Digitization, decentralization and high connectivity as well as incorporation of various enabling technologies raise various security issues. These security concerns may affect safety, endangering as- sets and even human lives. This is especially true for CPS utilization in different sectors of great significance, including manufacturing or critical infrastructures, creating a need for efficiently handling relevant security issues. Including security as part of a software intensive technical system (i.e the CPS) that can be distribut- ed and highly resilient highlights the need for appropriate security methodologies to be applied on the CPS from the engineering stage during CPS design. The effi- cient security related processes that are implemented at design time, have an im- pact on security monitoring during the CPS operational phase (at run time). Effi- cient and accurate security monitoring that follows security-by-design principles can be a potent tool in the hands of the CPS manager for detecting and mitigating cyber threats. Monitoring traffic and activity at the system boundaries, detecting changes to device status and configuration, detecting suspicious activity indicating attacks, detecting unauthorized activity that is suspicious or violates security poli- cies, timely responding to security incidents and recovering from them, are issues that need to be efficiently tackled with by security monitoring. In the present chap- ter, we are exploring the various CPS cybersecurity threats and discus how adding security as a parameter at the CPS design phase can provide a well-structured and efficient approach on providing strong security CPS foundations. New technolo- gies on CPS security Design are presented and emerging security directions are discussed. Furthermore, in the chapter, the different aspects of security monitoring are presented with a special emphasis on CPSs, discussing the various existing monitoring approaches that are followed in order to detect security issues at run time. Specific use-cases of CPSs in the manufacturing domain and with reference to critical infrastructures are also detailed and security requirements like confiden- tiality, integrity and availability are discussed

Fournaris, A., Komninos A., Lalos A., Kalogeras A. P., Koulamas C., & Serpanos D. (In Press).  Design and Run-time aspects of Secure Cyber Physical Systems. Security and Quality in Cyber-Physical Systems Engineering (Biffl S., Eckhart M., Lüder A. & Weippl E. eds.). ., Springer International Publishing.

Social media and microblogs have become an integral part of everyday life. People use microblogs to communicate with each other, express their opinion about a wide range of topics and inform themselves about issues they are interested in. The increasing volume of information generated in microblogs has led to the need of automatically determining the sentiment expressed in microblog comments. Researchers have worked in systematically analyzing microblog comments in order to identify the sentiment expressed in them. Most work in sentiment analysis of microblog comments has been focused on comments written in the English language, whereas fewer efforts have been made in predicting the sentiment of Greek microblog comments. In this paper, we propose a lexicon-based sentiment analysis algorithm for the sentiment classification of both Greek and English microblog comments. The proposed method uses a unified approach for determining the sentiment of comments written in both languages and incorporates techniques that exploit the distinctive features of the language used in microblogs in order to accurately predict the sentiment expressed in microblog comments. Our approach achieves promising results for the sentiment classification of microblog comments into positive, negative or neutral.

Tsamis, K., Komninos A., & Garofalakis J. (2019).  Leveraging Social Media Linguistic Features for Bilingual Microblog Sentiment Classification. 10th International Conference on Information, Intelligence, Systems and Applications (IISA'19). Patras, Greece, IEEE.