Serafim Bakalis

Serafim Bakalis

Auto-generated profile, based on publicly available information

Serafim Bakalis

Department of Food Science, University of Copenhagen 1 , Copenhagen

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
1 December 2024 in Physics of Fluids
Verified
Journal Article
Closed access
SCSatyasaran Changdar
Satyasaran Changdar
BBBivas Bhaumik
Bivas Bhaumik
NSNabanita Sadhukhan
Nabanita Sadhukhan
SPSumit Pandey
Sumit Pandey
SMSabyasachi Mukhopadhyay
Sabyasachi Mukhopadhyay
SBSerafim Bakalis
Serafim Bakalis
This study explores a hybrid framework integrating machine learning techniques and symbolic regression via genetic programing for analyzing the nonlinear propagation of waves in arterial blood flow. We employ a mathematical framework to simulate viscoelastic arterial flow, incorporating assumptions of long wavelength and large Reynolds numbers. We used a fifth-order nonlinear evolutionary equation using reductive perturbation to represent the behavior of nonlinear waves in a viscoelastic tube, considering the tube wall's bending. We obtain solutions through physics-informed neural networks (PINNs) that optimizes via Bayesian hyperparameter optimization across three distinct initial conditions. We found that PINN-based models are proficient at predicting the solutions of higher-order nonlinear partial differential equations in the spatial-temporal domain [−1,1]×[0,2]. This is evidenced by graphical results and a residual validation showing a mean absolute residue error of O(10−3). We thoroughly examine the impacts of various initial conditions. Furthermore, the three solutions are combined into a single model using the random forest machine learning algorithm, achieving an impressive accuracy of 99% on the testing dataset and compared with another model using an artificial neural network. Finally, the analytical form of the solutions is estimated using symbolic regression that provides interpretable models with mean square error of O(10−3). These insights contribute to the interpretation of cardiovascular parameters, potentially advancing machine learning applications within the medical domain.

14 December 2015 in RSC Advances
Verified
Journal Article
Closed access
PDF file
HKHani El Kadri
Hani El Kadri
TOTim Overton
Tim Overton
SBSerafim Bakalis
Serafim Bakalis
KGKonstantinos Gkatzionis
Konstantinos Gkatzionis
The results suggest that release of bacteria from W1/O/W2emulsion can be controlled by varying the formulation. Release occurs due to oil globule bursting independent to diffusion.

1 October 2009 in Innovative Food Science & Emerging Technologies
Verified
Journal Article
Closed access
KMK. Mehauden
K. Mehauden
PCP.W. Cox
P.W. Cox
SBS. Bakalis
S. Bakalis
PFPeter J. Fryer
Peter J. Fryer
Xianfeng FanXianfeng Fan
Xianfeng Fan
MSMark John Simmons
Mark John Simmons


31 July 2024 in Particuology
Verified
Journal Article
Open access
MMMohamed S. Manga
Mohamed S. Manga
Dimitrios KontziampasisDimitrios Kontziampasis
Dimitrios Kontziampasis
MAMustafa Al-Maqdad
Mustafa Al-Maqdad
SCSean Clifford
Sean Clifford
SBSerafim Bakalis
Serafim Bakalis
DYDavid W. York
David W. York

1 January 2016
Verified
Book Chapter
Closed access
TMT.E. Moxon
T.E. Moxon
SBS. Bakalis
S. Bakalis