George  Giakos

Dr. George Giakos

Department of Electrical and Computer Engineering, Manhattan College, Riverdale, NY, USA

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2022 in Future Internet
Verified
Journal Article
Open access
PDF file
JZJason Zheng
Jason Zheng
CDChidinma Dike
Chidinma Dike
SPStefan Pancari
Stefan Pancari
YWYi Wang
Yi Wang
George  GiakosGeorge Giakos
George Giakos
BWBingyang Wei
Bingyang Wei
Simulating blockchain technology within the IoT has never been as important. Along with this comes the need to find suitable blockchain simulators capable of simulating blockchain networks within an IoT environment. Despite there being a wide variety of blockchain simulators, not all are capable of simulating within an IoT environment and not all are suitable for every IoT environment. This article will review previously published works and present a list of suitable blockchain simulators as well as a few untested simulators that have the potential to simulate blockchain networks within an IoT environment. A total of 18 blockchain simulators are presented and discussed in this paper. In addition, a comprehensive list of the advantages and limitations of each simulator is presented to demonstrate the best situation in which simulators should be used. Finally, recommendations are made on when each simulator should be used and in what situation it should be avoided.

1 February 2018 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
SSSuman Shrestha
Suman Shrestha
ADAditi Deshpande
Aditi Deshpande
TFTannaz Farrahi
Tannaz Farrahi
TCThomas Cambria
Thomas Cambria
TQTri Quang
Tri Quang
George  GiakosGeorge Giakos
George Giakos

5 July 2023
Verified
Conference Paper
Open access
Fotios Κ. KonstantinidisFotios Κ. Konstantinidis
Fotios Κ. Konstantinidis
VBVasiliki Balaska
Vasiliki Balaska
SSSymeon Symeonidis
Symeon Symeonidis
Foivos PsarommatisFoivos Psarommatis
Foivos Psarommatis
APAthanasios Psomoulis
Athanasios Psomoulis
Antonios GasteratosAntonios Gasteratos
Antonios Gasteratos

19 May 2025 in Energies
Verified
Journal Article
Open access
PDF file
DNDowens Nicolas
Dowens Nicolas
KOKevin Orozco
Kevin Orozco
SMSteve Mathew
Steve Mathew
YWYi Wang
Yi Wang
WEWafa Elmannai
Wafa Elmannai
George  GiakosGeorge Giakos
George Giakos
Advanced as they are, DL models in cyber-physical systems remain vulnerable to attacks like the Fast Gradient Sign Method, DeepFool, and Jacobian-Based Saliency Map Attacks, rendering system trustworthiness impeccable in applications with high stakes like power systems. In power grids, DL models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are commonly utilized for tasks like state estimation, load forecasting, and fault detection, depending on their ability to learn complex, non-linear patterns in high-dimensional data such as voltage, current, and frequency measurements. Nevertheless, these models are susceptible to adversarial attacks, which could lead to inaccurate predictions and system failure. In this paper, the impact of these attacks on DL models is analyzed by employing the use of defensive countermeasures such as Adversarial Training, Gaussian Augmentation, and Feature Squeezing, to investigate vulnerabilities in industrial control systems with potentially disastrous real-world impacts. Emphasizing the inherent requirement of robust defense, this initiative lays the groundwork for follow-on initiatives to incorporate security and resilience into ML and DL algorithms and ensure mission-critical AI system dependability.

21 June 2020 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
OIOgbonna Michael Igwe
Ogbonna Michael Igwe
YWYi Wang
Yi Wang
George  GiakosGeorge Giakos
George Giakos
JFJoel Fu
Joel Fu

8 July 2021 in Electronics Letters
Verified
Journal Article
Open access
PDF file
MNMartin Nowak
Martin Nowak
ABAnthony Beninati
Anthony Beninati
NDNicolas Douard
Nicolas Douard
APAlec Puran
Alec Puran
CBCharles Barnes
Charles Barnes
George  GiakosGeorge Giakos
George Giakos
The purpose of this study is to introduce efficient bio‐inspired vision architectures, integrating human cognition capabilities, such as computation and memory emulating neurons and synapses, together with polarization of light properties, that would ultimately revolutionize and give rise to the next‐generation highly efficient augmented intelligence vision systems. The system consists of a polarimetric dynamic vision sensor) and a spinning wheel, whose motion is externally modulated and controlled by means of a signal generator, varying its motion pattern and speed, respectively. A neural network has been designed to classify different object speeds and motion patterns. The neural network utilizes a limited number of events within a given time window, instead of full‐frame images; as well as two classifiers, which practically take a single input and independently classify both its speed and motion pattern. As a result, both high computational efficiency and motion classification accuracy are achieved.