democritus university of thraceutopia.duth.gr/~kdemertz/pptx/sicaseg.pdf · 2020. 12. 15. ·...
TRANSCRIPT
-
Konstantinos Demertzis – Lazaros Iliadis
A Computational Intelligence System
for Identification Cyber-Attacks on
Smart Energy Grids
Democritus University of ThraceDep. of Forestry & Management of the
Environment & Natural ResourcesLab of Forest-Environmental Informatics
& Computational Intelligence
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Dataset
Methodologies
Results
References
5
6
Introduction1
Questions - Discussion5 7
Conclusions - Future Directions
6
5
7
3
2
1
4
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
What Is the Smart Grid?
A smart grid is an energy transmission and distributionnetwork enhanced through digital control, monitoring and
telecommunications capabilities.
It provides a real-time, two-way flow of energy andinformation to all stakeholders in the electricity chain, from
the generation plant to the commercial, industrial and
residential end user.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Architecture
Smart grid layers require a system of systems approach withdifferentiated security needs.
The smart grid includes different domains (Smart GridConceptual Model):
1. Bulk generation
2. Transmission
3. Distribution
4. Markets
5. Operations
6. Service Provider
7. Customer - Distributed energy resources - Electric Vehicles
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Conceptual Model
It relies on a multitude of stakeholders, each with its own specific role and activity within a given domain.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Conceptual Model
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Conceptual Model
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Conceptual Model
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
IT infrastructures of Smart Grid
Information and communication infrastructures will play animportant role in connecting and optimizing the available grid
layers.
Grid operation depends on control systems called SupervisoryControl and Data Acquisition (SCADA) that monitor and
control the physical infrastructure.
At the heart of these SCADA systems are specializedcomputers known as Programmable Logic Controllers (PLCs).
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Cyber Security Specificities
An important aspect of cyber security for critical infrastructureprotection focuses on a basic understanding and awareness of
real-world threats and vulnerabilities that exist within the
industrial automation and control system architectures used in
most process industries and manufacturing facilities.
As a large system of distributed and interconnected systems,the smart grid offers an exceptionally large attack surface.
Every asset of the smart grid is a potential target for a cyberattack.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Cyber Security Specificities
An attack over a critical node may jeopardize the grid securityand lead a cascade effect to a whole system blackout.
The smart grid cyber security challenge is about protecting theever-growing number of smart grid assets and their
communication channels from fast-growing and continuously
evolving cyber threats.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Cyber Security Specificities
These issues face the SCADA Systems and Distribution ControlSystems (DCS) that comprise most industrial environments,
and impact not on the common IT infrastructure like
Windows-based computers and network appliances (switches,
routers and firewalls), but also embedded "proprietary"
equipment such as programmable logic controllers (PLC),
remote terminal units (RTU), intelligent electrical device (IED),
basic process controllers (BPCS), safety instrumented systems
(SIS), operator panels, and ancillary systems that are the basis
of most integrated ICS architectures.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Cyber Security Specificities
There are destructive cyber-attacks against SCADA systems asAdvanced Persistent Threats (APT), were able to take over the
PLCs controlling the centrifuges, reprogramming them in order
to speed up the centrifuges, leading to the destruction of
many and yet displaying a normal operating speed in order to
trick the centrifuge operators and finally can not only shut
things down but can alter their function and permanently
damage industrial equipment.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
The figure shows thepower system framework
configuration used in
generating the attack
scenarios.
Mississippi State University and
Oak Ridge National Laboratory
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
In the network diagramG1 and G2 are power
generators, R1 through
R4 are Intelligent
Electronic Devices (IEDs)
that can switch the
breakers on or off.
These breakers arelabeled BR1 through
BR4.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
We also have two lines.Line One spans from
breaker one (BR1) to
breaker two (BR2) and
Line Two spans from
breaker three (BR3) to
breaker four (BR4).
Each IED automaticallycontrols one breaker. R1
controls BR1, R2 controls
BR2 and son on.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
The IEDs use a distanceprotection scheme which
trips the breaker on
detected faults whether
actually valid or faked
since they have no
internal validation to
detect the difference.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
Operators can alsomanually issue
commands to the IEDs
R1 through R4 to
manually trip the
breakers BR1 - BR4.
The manual override isused when performing
maintenance on the lines
or other system
components.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
The dataset comprised of 128 independent variables and 3classes - markers (No Events, Normal Events, Attack).
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
128 features are extracted there are 116 measurements from phasor measurement
units (PMU). A PMU or synchrophasor is a device which
measures the electrical waves on an electricity grid,
using a common time source for synchronization.
4 features for control panel logs 4 features for relay logs 4 features for Snort alerts logs
Marker
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
Types of Scenarios (classes - markers): No Events Short-circuit fault (Normal Events) – this is a short in a power
line and can occur in various locations along the line, the
location is indicated by the percentage range.
Line maintenance (Normal Events) – one or more relays aredisabled on a specific line to do maintenance for that line.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
Types of Scenarios: Remote tripping command injection (Attack) – this is an
attack that sends a command to a relay which causes a
breaker to open. It can only be done once.
Relay setting change (Attack) – relays are configured with adistance protection scheme and the attacker changes the
setting to disable the relay function such that relay will not
trip for a valid fault or a valid command.
Data Injection (Attack) – here we imitate a valid fault bychanging values to parameters such as current, voltage,
sequence components etc. This attack aims to blind the
operator and causes a black out.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
Preprocessing Dataset is determined and normalized to the interval
[-1,1] in order to phase the problem of prevalence of
features with wider range over the ones with a
narrower range, without being more important.
The outliers and the extreme values spotted wereremoved based on the Inter Quartile Range technique.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
Inter Quartile Range technique
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Smart Grid Attack Dataset
The final dataset containing 159,045 patterns: 48,455 No Events, 54,927 Natural and 55,663 Attack
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Methodologies
Extreme Learning Machines (ELM) an emerging learning technique provides efficient unified
solutions to generalized feed-forward networks,
theories show that hidden neurons are important but can berandomly generated, independent from applications and that
ELMs have both universal approximation and classification
capabilities, build a direct link between theories namely:
ridge regression (for non-linear least squares problems), ANN generalization performance, linear system stability and matrix theory,
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Methodologies
Extreme Learning Machines (ELM) works for the “generalized” Single-hidden Layer feedforward
Networks (SLFNs) but the hidden layer (or called feature
mapping) need not be tuned,
learning theory shows that the hidden nodes/neurons ofgeneralized feedforward networks needn’t be tuned andthese hidden nodes/neurons can be randomly generated,
all the hidden node parameters are independent from thetarget functions or the training datasets,
the hidden node/neuron parameters are not onlyindependent of the training data but also of each other,
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Methodologies
Extreme Learning Machines (ELM) can handle non-differentiable activation functions, and do
not have issues such as finding a suitable stopping criterion,
learning rate, and learning epochs.
Advantages: ease of use, faster learning speed, higher generalization
performance,
suitable for many nonlinear activation function or kernelfunctions
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Methodologies
Extreme Learning Machines (ELM)
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
SICASEG
A Computational Intelligence System for Identification Cyber-Attacks on Smart Energy Grids
we propose a novel system that use a Self-adaptiveEvolutionary Extreme Learning Machine (SaE-ELM).
In SaE-ELM, the hidden node learning parameters areoptimized by the Self-adaptive Differential Evolution
Algorithm (SaDEA), whose trial vector generation strategies
and their associated control parameters are self-adapted in a
strategy pool by learning from their previous experiences in
generating promising solutions, and the network output
weights are calculated using the Moore–Penrose (MP)generalized inverse.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Results
To identify the integrity of SICASEG we have compared the SaE-ELMwith other neural network methods such as:
Radial Basis Function (RBF) ANN, Group Methods of Data Handling (GMDH) Polynomial ANN (PANN) and Feed Forward Neural Networks (FNN) trained under Genetic
Algorithm (GA)
The results showed that the SaE-ELM has much faster learningspeed (run thousands times faster than conventional methods) and
has much better generalization performance and more accurate and
reliable classification results.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Results
Confusion Matrix:
No Events Natural Attack
48318 98 39 No Events
74 52645 2208 Natural
118 2950 52595 Attack
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Results
The performance comparisons of algorithms:
ClassifierClassification Accuracy & Performance Metrics
ACC RMSE Precision Recall F-Score ROC Area Validation
SaE-ELM 96.55% 0.1637 0.966% 0.966 0.965% 0.996 10-fcv
RBF ANN 90.60% 0.2463 0,909% 0.907 0.907% 0.905 10-fcv
GMDH 92.66% 0.1828 0.927% 0.927 0.927% 0.980 10-fcv
PANN 91.34% 0.2162 0.914% 0.913 0.914% 0.961 10-fcv
FNN-GA 94.71% 0.2054 0.947% 0.947 0.947% 0.969 10-fcv
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Future Directions
feature minimization using Principal Component Analysis (PCA) orother existing approaches,
additional computational intelligence methods such as SpikingNeural Networks could be explored and compared on the same
security task and
scalability of ELM with Hadoop Distributed File System (HDFS).
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
Conclusions An innovative Computational Intelligence System for
Identification Cyber-Attacks on SEGs has been introduced.
It performs classification by using a Self-adaptiveEvolutionary ELM, a very fast approach to properly classify
cyber attacks with high accuracy and generalization with
minimum computational power and resources.
This is done to enhance the energetic security and themechanisms of reaction of the general system, without
special requirements.
In this way it adds a higher degree of integrity to the rest ofthe security infrastructure of SEGs.
-
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
References[1] Chi Cheng, Wee Peng Tay, Guang-Bin Huang, Extreme learning machines for
intrusion detection, Neural Networks (IJCNN), International Joint Conference, DOI:
10.1109/IJCNN.2012.6252449, 2012.
[2] Erik Cambria, Guang-Bin Huang, Extreme Learning Machines, IEEE InTeLLIGenT
SYSTemS, 541-1672/13, 2013.
[3] Jiuwen Cao, Zhiping Lin, Guang-Bin Huang, Self-Adaptive Evolutionary Extreme
Learning Machine, Neural Process Lett (2012) 36:285–305, DOI 10.1007/s11063-012-9236-y.
[4] Yves Aillerie, Said Kayal, Jean-Pierre Mennella, Raj Samani, Sylvain Sauty, Laurent
Schmitt, Smart Grid Deployment Requires a New End-to-End Security Approach, White
Paper - Cyber Security, Intel Corp, 2015.
[5] Mete Ozay, Inaki Esnaola, Fatos T. Yarman Vural, Sanjeev R. Kulkarni, H. Vincent
Poor, Machine Learning Methods for Attack Detection in the Smart Grid, IEEE
Transactions on Neural Networks and Learning Systems, 2015, DOI:
10.1109/TNNLS.2015.2404803.
-
http://utopia.duth.gr/~kdemertz/
3rd CryCybIW26th – 27th May 2016Hellenic Military Academy
Athens, Greece
mailto:[email protected]
-
My Publications
Cyber Security informatics
Journals
1. Demertzis, K., and L. Iliadis. Cognitive Web Application Firewall to Critical Infrastructures Protection from Phishing Attacks, Journal of Computations &
Modelling, vol.9, no.2, 2019, 1-26, ISSN: 1792-7625 (print), 1792-8850 (online),
Scienpress Ltd, 2019.
2. Xing, L., K. Demertzis, and J. Yang. Identify Data Streams Anomalies by Evolving
Spiking Restricted Boltzmann Machines. Neural Computing & Application, Springer,
2019. doi:10.1007/s00521-019-04288-5.
3. Demertzis, K., L. Iliadis, and I. Bougoudis. Gryphon: A semi-supervised anomaly
detection system based on one-class evolving spiking neural network. Neural
Computing & Application, Springer, 2019. doi:10.1007/s00521-019-04363-x.
4. Demertzis, K., and L. Iliadis. 2017. Computational intelligence anti-malware
framework for android OS. Vietnam Journal of Computer Science vol. 4, 245–259. https://doi.org/10/gdp86x doi:10.1007/s40595-017-0095-3.
5. Demertzis, Konstantinos. Iliadis, L.S., Anezakis, V.-D., 2018. An innovative soft computing system for smart energy grids cybersecurity. Advances in Building Energy
Research 12, 3–24. https://doi.org/10/gdp862 6. Demertzis, Konstantinos. Kikiras, P., Tziritas, N., Sanchez, S.L., Iliadis, L., 2018. The
Next Generation Cognitive Security Operations Center: Network Flow Forensics
Using Cybersecurity Intelligence. Big Data and Cognitive Computing 2,
35. https://doi.org/10/gfkhpp
7. Demertzis, Konstantinos. Iliadis, L.S., 2016. Ladon: A Cyber Threat Bio-Inspired Intelligence Management System. Journal of Applied Mathematics & Bioinformatics,
vol.6, no.3, 2016, 45-64, ISSN: 1792-6602 (print), 1792-6939 (online), Scienpress Ltd,
2016.
8. Demertzis, K., N. Tziritas, P. Kikiras, S. L. Sanchez, and L. Iliadis. The Next Generation Cognitive Security Operations Center: Adaptive Analytic Lambda Architecture for
Efficient Defense against Adversarial Attacks. Big Data Cognitive Computing 3, no. 1
(2019): 6. doi:10.3390/bdcc3010006.
9. Demertzis, K.; Rantos, K.; Drosatos, G. A Dynamic Intelligent Policies Analysis Mechanism for Personal Data Processing in the IoT Ecosystem . Big Data Cogn.
Comput. 2020, 4, 9.
Book Chapters
10. Demertzis, K., and L. Iliadis. A Bio-Inspired Hybrid Artificial Intelligence Framework
for Cyber Security. In Computation, Cryptography, and Network Security. Edited by
N. J. Daras and M. T. Rassias, 161–93. Cham: Springer International Publishing, 2015. doi:10.1007/978-3-319-18275-9_7.
11. Demertzis, Konstantinos. Iliadis, L.S., 2018. Real-time Computational Intelligence Protection Framework Against Advanced Persistent Threats.
Book entitled Cyber-Security and Information Warfare, Series: Cybercrime and
Cybersecurity Research, NOVA science publishers, ISBN: 978-1-53614-385-0,
Chapter 5.
https://doi.org/10/gdp86xhttps://doi.org/10.1007/s40595-017-0095-3https://doi.org/10/gdp862https://doi.org/10/gfkhpphttps://doi.org/10.3390/bdcc3010006https://doi.org/10.1007/978-3-319-18275-9_7
-
12. Demertzis, K., and L. Iliadis. A Computational Intelligence System Identifying Cyber-
Attacks on Smart Energy Grids. In Modern Discrete Mathematics and Analysis: With
Applications in Cryptography, Information Systems and Modeling, Springer
Optimization and Its Applications. Edited by N. J. Daras and T. M. Rassias, 97–116. Cham: Springer International Publishing, 2018. doi:10.1007/978-3-319-74325-7_5.
Conferences
13. Demertzis, K., L. Iliadis, P. Kikiras, and N. Tziritas. Cyber-Typhon: An Online Multi-task Anomaly Detection Framework. In Artificial Intelligence Applications and
Innovations. AIAI 2019. IFIP Advances in Information and Communication Technology,
Vol. 559. Edited by J. MacIntyre, I. Maglogiannis, L. Iliadis, and E. Pimenidis. Cham:
Springer, 2019. doi:10.1007/978-3-030-19823-7_2.
14. Demertzis, K., and L. Iliadis. Bio-inspired Hybrid Intelligent Method for Detecting
Android Malware. In Knowledge, Information and Creativity Support Systems,
Advances in Intelligent Systems and Computing. Edited by S. Kunifuji, G. A.
Papadopoulos, A. M. J. Skulimowski, and J. Kacprzyk, 289–304. Springer International Publishing, 2016. doi:10.1007/978-3-319-27478-2_20.
15. Demertzis, K., and L. Iliadis. Evolving Smart URL Filter in a Zone-Based Policy Firewall
for Detecting Algorithmically Generated Malicious Domains . In Statistical Learning
and Data Sciences. Edited by A. Gammerman, V. Vovk, and H. Papadopoulos, 223–33. Lecture Notes in Computer Science. Springer International Publishing,
2015. doi:10.1007/978-3-319-17091-6_17.
16. Demertzis, K., and L. Iliadis. SAME: An Intelligent Anti-malware Extension for Android
ART Virtual Machine. In Computational Collective Intelligence. Edited by M. Núñez, N. T. Nguyen, D. Camacho, and B. Trawiński, 235–45. Lecture Notes in Computer Science. Springer International Publishing, 2015. doi:10.1007/978-3-319-24306-1_23.
17. Demertzis, K., and L. Iliadis. A Hybrid Network Anomaly and Intrusion Detection
Approach Based on Evolving Spiking Neural Network Classification . In E-Democracy,
Security, Privacy and Trust in a Digital World, Communications in Computer and
Information Science. Edited by A. B. Sideridis, Z. Kardasiadou, C. P. Yialouris, and V.
Zorkadis, 11–23. Springer International Publishing, 2014. doi:10.1007/978-3-319-11710-2_2.
18. Demertzis, K., and L. Iliadis. Evolving Computational Intelligence System for Malware
Detection. In Advanced Information Systems Engineering Workshops, Lecture Notes
in Business Information Processing. Edited by L. Iliadis, M. Papazoglou, and K. Pohl,
322–34. Springer International Publishing, 2014. doi:10.1007/978-3-319-07869-4_30. 19. Demertzis, K., L. Iliadis, and V. Anezakis. 2018. MOLESTRA: A Multi-Task Learning
Approach for Real-Time Big Data Analytics, in: 2018 Innovations in Intelligent
Systems and Applications (INISTA). Presented at the 2018 Innovations in Intelligent
Systems and Applications (INISTA), pp. 1–8. doi:10.1109/INISTA.2018.8466306. 20. Demertzis, Konstantinos. Iliadis, L., Anezakis, V.-D., 2018. A Dynamic Ensemble
Learning Framework for Data Stream Analysis and Real-Time Threat Detection, in:
Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2018, Lecture Notes in Computer Science. Springer International Publishing, pp. 669–681.
21. Demertzis, Konstantinos. Iliadis, L., Spartalis, S., 2017. A Spiking One-Class Anomaly Detection Framework for Cyber-Security on Industrial Control Systems, in: Boracchi,
https://doi.org/10.1007/978-3-030-19823-7_2https://doi.org/10.1007/978-3-319-27478-2_20https://doi.org/10.1007/978-3-319-17091-6_17https://doi.org/10.1007/978-3-319-24306-1_23https://doi.org/10.1007/978-3-319-11710-2_2https://doi.org/10.1007/978-3-319-11710-2_2https://doi.org/10.1007/978-3-319-07869-4_30https://doi.org/10.1109/INISTA.2018.8466306
-
G., Iliadis, L., Jayne, C., Likas, A. (Eds.), Engineering Applications of Neural Networks,
Communications in Computer and Information Science. Springer International
Publishing, pp. 122–134. 22. Rantos, K., G. Drosatos, K. Demertzis, C. Ilioudis, and A. Papanikolaou. 2018.
Blockchain-based Consents Management for Personal Data Processing in the IoT
Ecosystem. Presented at the International Conference on Security and Cryptography,
pp. 572–577. doi:10.5220/0006911005720577. 23. Rantos, K., G. Drosatos, K. Demertzis, C. Ilioudis, A. Papanikolaou, and A. Kritsas.
ADvoCATE: A Consent Management Platform for Personal Data Processing in the IoT
Using Blockchain Technology. In Innovative Security Solutions for Information
Technology and Communications. SECITC 2018, Vol. 11359. Edited by J. L. Lanet and
C. Toma. Lecture Notes in Computer Science. Cham: Springer, 2019. doi:10.1007/978-
3-030-12942-2_23.
24. Demertzis, K.; Rantos, K.; Drosatos, G. A Dynamic Intelligent Policies Analysis Mechanism for Personal Data Processing in the IoT Ecosystem . Big Data Cogn.
Comput. 2020, 4, 9.
Environmental informatics
Journals
25. Demertzis, K.; Iliadis, L. GeoAI: A Model-Agnostic Meta-Ensemble Zero-Shot Learning
Method for Hyperspectral Image Analysis and Classification . Algorithms 2020, 13, 61
26. Anezakis, V.-D., K. Demertzis, L. Iliadis, and S. Spartalis. Hybrid intelligent modeling
of wild fires risk. Evolving Systems, no. 4 (2018): 267–83. https://doi.org/10/gdp863 doi:10.1007/s12530-017-9196-6.
27. Bougoudis, I., K. Demertzis, L. Iliadis, V.-D. Anezakis, and A. Papaleonidas. 2018.
FuSSFFra, a fuzzy semi-supervised forecasting framework: the case of the air
pollution in Athens. Neural Computing & Application, Springer, vol. 29, 375–388. https://doi.org/10/gc9bbf doi:10.1007/s00521-017-3125-2.
28. Bougoudis, I., K. Demertzis, and L. Iliadis. 2016. HISYCOL a hybrid computational
intelligence system for combined machine learning: the case of air pollution
modeling in Athens. Neural Computing & Application, Springer, vol. 27, 1191–1206. https://doi.org/10/f8r7vf doi:10.1007/s00521-015-1927-7.
29. Anezakis, V.-D., L. Iliadis, K. Demertzis, and G. Mallinis. Hybrid Soft Computing
Analytics of Cardiorespiratory Morbidity and Mortality Risk Due to Air Pollution .
In Information Systems for Crisis Response and Management in Mediterranean
Countries, Lecture Notes in Business Information Processing. Edited by I. M. Dokas, N.
Bellamine-Ben Saoud, J. Dugdale, and P. Díaz, 87–105. Springer International Publishing, 2017. doi:10.1007/978-3-319-67633-3_8.
30. Bougoudis, I., K. Demertzis, and L. Iliadis. Fast and low cost prediction of extreme air
pollution values with hybrid unsupervised learning. Integrated Computer-Aided
Engineering 23, no. 2 (2016): 115–27. https://doi.org/10/f8dt4t doi:10.3233/ICA-150505.
31. Demertzis, K., and L. Iliadis. 2017. Detecting invasive species with a bio-inspired
semi-supervised neurocomputing approach: the case of Lagocephalus sceleratus .
Neural Computing & Application, Springer, vol. 28 pp. 1225–1234. https://doi.org/10/gbkgb7 doi:10.1007/s00521-016-2591-2.
32. Demertzis, Konstantinos. Iliadis, L., Anezakis, V.-D., 2017. Commentary: Aedes
albopictus and Aedes japonicus—two invasive mosquito species with different
https://doi.org/10.5220/0006911005720577https://doi.org/10.1007/978-3-030-12942-2_23https://doi.org/10.1007/978-3-030-12942-2_23
-
temperature niches in Europe. Frontiers Environmental Science
5. https://doi.org/10/gdp865
33. Demertzis, K., L. Iliadis, S. Avramidis, and Y. A. El-Kassaby. 2017. Machine learning use
in predicting interior spruce wood density utilizing progeny test information. Neural
Computing & Application, Springer, vol. 28, 505–519. https://doi.org/10/gdp86z doi:10.1007/s00521-015-2075-9.
34. Demertzis, Konstantinos. Iliadis, L.S., Anezakis, V.-D., 2018. Extreme deep learning in
biosecurity: the case of machine hearing for marine species identification . Journal
of Information and Telecommunication 2, 492–510. https://doi.org/10/gdwszn 35. Dimou, V., V.-D. Anezakis, K. Demertzis, and L. Iliadis. Comparative analysis of
exhaust emissions caused by chainsaws with soft computing and statistical
approaches. International Journal of Environmental Science and Technology 15, no. 7
(2018): 1597–608. https://doi.org/10/gdp864 doi:10.1007/s13762-017-1555-0. 36. Iliadis, L., V.-D. Anezakis, K. Demertzis, and G. Mallinis. 2017. Hybrid Unsupervised
Modeling of Air Pollution Impact to Cardiovascular and Respiratory Diseases .
IJISCRAM 9, 13–35. https://doi.org/10/gfkhpm doi:10.4018/IJISCRAM.2017070102.
Conferences
37. Demertzis, K., L. Iliadis, and V. D. Anezakis. A Machine Hearing Framework for Real-
Time Streaming Analytics Using Lambda Architecture. In Engineering Applications of
Neural Networks. EANN 2019. Communications in Computer and Information Science,
Vol. 1000. Edited by J. Macintyre, L. Iliadis, I. Maglogiannis, and C. Jayne. Cham:
Springer, 2019. doi:10.1007/978-3-030-20257-6_21.
38. Anezakis, V., G. Mallinis, L. Iliadis, and K. Demertzis. 2018. Soft computing forecasting
of cardiovascular and respiratory incidents based on climate change scenarios , in:
2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS). Presented
at the 2018 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), pp.
1–8doi:10.1109/EAIS.2018.8397174. 39. Anezakis, V.-D., K. Demertzis, and L. Iliadis. 2018. Classifying with fuzzy chi-square
test: The case of invasive species. AIP Conference Proceedings 1978,
290003. https://doi.org/10/gdtm5q
40. Anezakis, V.-D., K. Demertzis, L. Iliadis, and S. Spartalis. A Hybrid Soft Computing
Approach Producing Robust Forest Fire Risk Indices. In Artificial Intelligence
Applications and Innovations, IFIP Advances in Information and Communication
Technology. Edited by L. Iliadis and I. Maglogiannis, 191–203. Springer International Publishing, 2016. doi:10.1007/978-3-319-44944-9_17.
41. Anezakis, V.-D., K. Dermetzis, L. Iliadis, and S. Spartalis. Fuzzy Cognitive Maps for
Long-Term Prognosis of the Evolution of Atmospheric Pollution, Based on Climate
Change Scenarios: The Case of Athens. In Computational Collective Intelligence.
Edited by N.-T. Nguyen, L. Iliadis, Y. Manolopoulos, and B. Trawiński, 175–86. Lecture Notes in Computer Science. Springer International Publishing, 2016. doi:10.1007/978-
3-319-45243-2_16.
42. Bougoudis, I., K. Demertzis, L. Iliadis, V.-D. Anezakis, and A. Papaleonidas. Semi-
supervised Hybrid Modeling of Atmospheric Pollution in Urban Centers .
In Engineering Applications of Neural Networks, Communications in Computer and
Information Science. Edited by C. Jayne and L. Iliadis, 51–63. Springer International Publishing, 2016. doi:10.1007/978-3-319-44188-7_4.
-
43. Demertzis, Konstantinos. Anezakis, V.-D., Iliadis, L., Spartalis, S., 2018. Temporal
Modeling of Invasive Species’ Migration in Greece from Neighboring Countries Using Fuzzy Cognitive Maps, in: Iliadis, L., Maglogiannis, I., Plagianakos, V. (Eds.), Artificial
Intelligence Applications and Innovations, IFIP Advances in Information and
Communication Technology. Springer International Publishing, pp. 592–605. 44. Demertzis, K., and L. Iliadis. Adaptive Elitist Differential Evolution Extreme Learning
Machines on Big Data: Intelligent Recognition of Invasive Species . In Advances in Big
Data, Advances in Intelligent Systems and Computing. Edited by P. Angelov, Y.
Manolopoulos, L. Iliadis, A. Roy, and M. Vellasco, 333–45. Springer International Publishing, 2017. doi:10.1007/978-3-319-47898-2_34.
45. Demertzis, K., and L. Iliadis. Intelligent Bio-Inspired Detection of Food Borne
Pathogen by DNA Barcodes: The Case of Invasive Fish Species Lagocephalus
Sceleratus. In Engineering Applications of Neural Networks, Communications in
Computer and Information Science. Edited by L. Iliadis and C. Jayne, 89–99. Springer International Publishing, 2015. doi:10.1007/978-3-319-23983-5_9.
46. Demertzis, K., L. Iliadis, and V. Anezakis. 2017. A deep spiking machine-hearing
system for the case of invasive fish species, in: 2017 IEEE International Conference
on INnovations in Intelligent SysTems and Applications (INISTA). Presented at the
2017 IEEE International Conference on INnovations in Intelligent SysTems and
Applications (INISTA), pp. 23–28doi:10.1109/INISTA.2017.8001126. 47. Iliadis, L., V.-D. Anezakis, K. Demertzis, and S. Spartalis. Hybrid Soft Computing for
Atmospheric Pollution-Climate Change Data Mining. In Transactions on
Computational Collective Intelligence XXX. Edited by N. Thanh Nguyen and R.
Kowalczyk, 152–77. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018. doi:10.1007/978-3-319-99810-7_8.
Book Chapters
48. K. Demertzis, Bougoudis, I., L. Iliadis, Geospatial Big Data Analytics: Air Quality and
Pollution Forecasting Using AI and GIS, MACHINE LEARNING PARADIGMS – Advances in Data Analytics, Springer, INTELLIGENT SYSTEMS REFERENCE LIBRARY bookseries (in
press)
49. Demertzis, K., and L. Iliadis. 2018. The Impact of Climate Change on Biodiversity: The
Ecological Consequences of Invasive Species in Greece , in: Leal Filho, W., Manolas,
E., Azul, A.M., Azeiteiro, U.M., McGhie, H. (Eds.), Handbook of Climate Change
Communication: Vol. 1: Theory of Climate Change Communication, Climate Change
Management. Springer International Publishing, Cham, pp. 15–38. https://doi.org/doi:10.1007/978-3-319-69838-0_2.
Other
50. Demertzis K, Tsiotas D, Magafas L. Modeling and forecasting the COVID-19 temporal
spread in Greece: an exploratory approach based on complex network defined
splines. arXiv:200501163 [physics] [Internet]. 2020 May 3 [cited 2020 May 5];
Available from: http://arxiv.org/abs/2005.01163.
-
Panhellenic Conferences
51. Aνεζάκης, Bαρδής-Δημήτριος, Kωνσταντίνος Δεμερτζής, Λάζαρος Hλιάδης, (2017) Πρόβλεψη Xαλαζοπτώσεων Mέσω Mηχανικής Mάθησης. 3o Πανελλήνιο Συνέδριο Πολιτικής Προστασίας SafeEvros 2016: Oι νέες τεχνολογίες στην υπηρεσία της Πολιτικής Προστασίας, Proceedings, ISBN : 978-960-89345-7-3, Iούνιος 2017, Eκδοτικός Oίκος: ∆ημοκρίτειο Πανεπιστήμιο Θράκης.
52. Kωνσταντίνος Δεμερτζής, Λάζαρος Hλιάδης, 2019, H Αξιοποίηση των Συγχρόνων Τεχνολογιών Πληροφορικής και Επικοινωνιών στην Μουσειοπαιδαγωγική: Η Περίπτωση του Λαογραφικού Μουσείου Νέας Ορεστιάδας και Περιφέρειας , Πρακτικά 2ου Πανελλήνιου Συνεδρίου Ιστορίας και Πολιτισμού της Ορεστιάδας Πολιτιστική Κληρονομιά και Τοπική Ανάπτυξη, Έκδοση Σχολής Επιστημών Γεωπονίας και Δασολογίας Δημοκρίτειου Πανεπιστημίου Θράκης και Δήμου Ορεστιάδας, ISBN: 978-618-00-1152-4, Απρίλιος 2019, Επιμέλεια: Ευάγγελος Μανωλάς.
Greek Books Chapters
53. Κωνσταντίνος Δεμερτζής, 2018, Ενίσχυση της Διοικητικής Ικανότητας των Δήμων Μέσω της Ηλεκτρονικής Διακυβέρνησης: Η Στρατηγική των Έξυπνων Πόλεων με Σκοπό την Αειφόρο Ανάπτυξη, Θέματα Δασολογίας και Διαχείρισης Περιβάλλοντος και Φυσικών Πόρων, 10ος Τόμος: Περιβαλλοντική Πολιτική: Καλές Πρακτικές, Προβλήματα και Προοπτικές, σελ. 84 - 100, ISSN: 1791-7824, ISBN: 978-960-9698-14-6, Νοέμβριος 2018, Eκδοτικός Oίκος: Δημοκρίτειο Πανεπιστήμιο Θράκης.
54. Kωνσταντίνος Δεμερτζής, Λάζαρος Hλιάδης, 2015, Γενετική Tαυτοποίηση Xωροκατακτητικών Eιδών με Eξελιγμένες Mεθόδους Tεχνητής Nοημοσύνης: H Περίπτωση του Aσιατικού Kουνουπιού Tίγρης (Aedes Albopictus) . Θέματα Δασολογίας & Διαχείρισης Περιβάλλοντος & Φυσικών Πόρων, 7ος τόμος, Kλιματική Aλλαγή: Διεπιστημονικές Προσεγγίσεις, ISSN: 1791-7824, ISBN: 978-960-9698-11-5, Eκδοτικός Oίκος: Δημοκρίτειο Πανεπιστήμιο Θράκης.
http://utopia.duth.gr/~kdemertz/papers/HESADM.pdfhttp://utopia.duth.gr/~kdemertz/papers/HESADM.pdf
C:\Users\user\Desktop\SICASEG.compress.pdfC:\Users\user\Desktop\SICASEG.pdfC:\Users\user\Desktop\My Publications_2.pdf
C:\Users\user\Desktop\My Publications_2.pdf