Presentation/Event

P. Fountas, K. Kolomvatsos, 'Ensemble based Data Imputation at the Edge', in 32th International Conference on Tools with Artificial Intelligence (ICTAI), November 09-11, 2020. [Best Student Paper Award] link

T. Tziouvaras, K. Kolomvatsos, 'Intelligent Monitoring of Virtualized Services', in8th European Conference on Service-Oriented and Cloud Computing, Sept. 2020. link

A. Karanika. P. Oikonomou, K. Kolomvatsos, C. Anagnostopoulos, 'An Ensemble Interpretable Machine Learning Scheme for Securing Data Quality at the Edge', in International IFIP Cross Domain (CD) Conference for Machine Learning & Knowledge Extraction (MAKE) - CD-MAKE 2020, August 25-28, 2020. link

P. Fountas, K. Kolomvatsos, 'A Continuous Data Imputation Mechanism based on Streams Correlation', in 10th Workshop on Management of Cloud and Smart City Systems, in conjunction with IEEE Symposium on Computers and Communications (ISCC), 2020. link

Karanika, A., Oikonomou, P., Kolomvatsos, K., Loukopoulos, T., 'A Demand-driven, Proactive Tasks Management Model at the Edge', in IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE World Congress on Computational Intelligence (WCCI), Glasgow, UK, 2020. link

Karanika, A., Soula, M., Anagnostopoulos, C., Kolomvatsos, K., Stamoulis, G., 'Optimized Analytics Query Allocation at the Edge of the Network', in 12th International Conference on Internet and Distributed Computing Systems, Naples, Italy, Oct. 10-12, 2019. link

Datasets/Code

A Dataset produced by Dht11 sensors using them inside a minature Greenhouse. Fault values have been removed. Every tuple represents measurements for air Temperature, humitidy, soil temperature retrieved every 3 minutes in a real environment. The physical location of the GreenHouse was in an open space with good airflow and sunlight. The project was performed in partial fulfillment of the requirements for the BSc Thesis of Mr Achilleas Matsoukas. The dataset can be found here

Datasets and code for a simple simulator that applies Fuzzy Logic System combined with a Support Vector Machine (SVM) model to handle the uncertainty in deciding the allocation of queries to a set of processing nodes link