Michalis Kanetidis
Michalis Kanetidis (Area: Computational Physics), Physics Department, A.U.Th.
E-mail: mkanetid@auth.gr
Michalis (Michael) Kanetidis is a dedicated researcher and Ph.D. candidate in the Physics Department at A.U.Th. With an extensive academic background and research expertise, he actively contributes to the field of Computational Physics, focusing on nanostructures, complex networks, data analysis, and artificial intelligence, including deep learning and graph neural networks.
He obtained his Bachelor’s degree in Physics from A.U.Th. in 2003. Building on this foundation, he pursued an MSc in Computational Physics from the same university (2017 – 2019).
Michalis Kanetidis has made significant contributions to the scientific community through selected publications. Notable among them is the paper titled “Au Nanobead Chains with Tunable Plasmon Resonance and Intense Optical Scattering,” published in 2021, where he employed Monte Carlo simulations to study properties of Au Nano-chains. Additionally, he contributed to research on the role of local interactions in the global networking of multinational firms, using an SIR model applied to partial-multiplex directed networks. In 2018, he presented work on IPC class-level correlations of patent citations time-series at the Conference on Complex Systems.
Role in GRADIENCE: Michalis Kanetidis is engaged in the Part-of-Speech (PoS) annotation of HelexKids and the extraction of noun stress frequences, contributes to the development of the Wordlist tool tailored for educators, and actively contributes to the development and testing of both the Machine Learning (ML) and Gradient Harmonic Grammar (GHG) algorithms. He also participates in the publication process of the anticipated research outcomes.