Fabio C. Zegarra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fabio C. Zegarra has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Alberto M. Coronado
Laboratorio de Sistemas Inteligentes, EPIME, Universidad Nacional Tecnológica de Lima Sur (UNTELS), Lima, Peru
5 shared publications - Juan Vargas-Machuca
Laboratorio de Sistemas Inteligentes, EPIME, Universidad Nacional Tecnológica de Lima Sur (UNTELS), Lima, Peru
4 shared publications Andrei G. Gasic
Department of Physics , University of Houston , Houston 77204 , United States
2 shared publicationsDirar Homouz
Department of Physics , University of Houston , Houston 77204 , United States
2 shared publications- Margaret Shun Cheung
Department of Physics University of Washington Seattle Washington USA
2 shared publications - Avid Roman-Gonzalez
Aerospace Sciences & Health Research Laboratory (INCAS-Lab), Universidad Nacional Tecnológica de Lima Sur, Villa el Salvador, Peru
1 shared publication
Latest Publications
- 18 October 2023
- Published by Wroclaw Board of Scientific Technical Societies Federation NOT in Journal of Machine Engineering
A Comparative Study of CNN, LSTM, BiLSTM, and GRU Architectures for Tool Wear Prediction in Milling Processes
Accurately predicting machine tool wear requires models capable of capturing complex, nonlinear interactions in multivariate time series inputs. Recurrent neural networks (RNNs) are well-suited to this task, owing to their memory mechanisms and capacity to construct highly complex models. In...
- 18 October 2023
- Published by Wroclaw Board of Scientific Technical Societies Federation NOT in Journal of Machine Engineering
A Comparative Study of CNN, LSTM, BiLSTM, and GRU Architectures for Tool Wear Prediction in Milling Processes
Accurately predicting machine tool wear requires models capable of capturing complex, nonlinear interactions in multivariate time series inputs. Recurrent neural networks (RNNs) are well-suited to this task, owing to their memory mechanisms and capacity to construct highly complex models. In...
- 25 August 2023
- Published by Wroclaw Board of Scientific Technical Societies Federation NOT in Journal of Machine Engineering
Unsupervised and Supervised Machine Learning Methods for Cutting Tool Path Clustering and RUL Estimation in Manufacturing
Machine learning has been widely used in manufacturing, leading to significant advances in diverse problems, including the prediction of wear and remaining useful life (RUL) of machine tools. However, the data used in many cases correspond to simple and stable processes that differ from practical...
- 25 August 2023
- Published by Wroclaw Board of Scientific Technical Societies Federation NOT in Journal of Machine Engineering
Unsupervised and Supervised Machine Learning Methods for Cutting Tool Path Clustering and RUL Estimation in Manufacturing
Machine learning has been widely used in manufacturing, leading to significant advances in diverse problems, including the prediction of wear and remaining useful life (RUL) of machine tools. However, the data used in many cases correspond to simple and stable processes that differ from practical...
- 17 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Convolutional Neural Network Classification for Machine Tool Wear Based on Unsupervised Gaussian Mixture Model
In today's manufacturing industry it is of great importance to know the condition of a tool as it wears out. This knowledge allows us to reduce possible errors and failures in the manufacturing process. This work focuses on classifying the level of wear of a machine tool, allowing us to know its current state using measurements of forces and accelerations. First, tool wear levels are obtained by unsupervised learning (through the Gaussian mixture model). Then a convolutional neural network trained directly using the measured time series predicts the level of tool wear. After careful selection of the optimal window length, optimization algorithm, and number of epochs, wear levels were predicted with accuracy greater than 85%.
- 17 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Convolutional Neural Network Classification for Machine Tool Wear Based on Unsupervised Gaussian Mixture Model
In today's manufacturing industry it is of great importance to know the condition of a tool as it wears out. This knowledge allows us to reduce possible errors and failures in the manufacturing process. This work focuses on classifying the level of wear of a machine tool, allowing us to know its current state using measurements of forces and accelerations. First, tool wear levels are obtained by unsupervised learning (through the Gaussian mixture model). Then a convolutional neural network trained directly using the measured time series predicts the level of tool wear. After careful selection of the optimal window length, optimization algorithm, and number of epochs, wear levels were predicted with accuracy greater than 85%.
- 27 October 2021
- Published by Springer Nature in Production Engineering
- Vol. 16 (4) , 465-480
Tool wear and remaining useful life (RUL) prediction based on reduced feature set and Bayesian hyperparameter optimization
- 27 October 2021
- Published by Springer Nature in Production Engineering
- Vol. 16 (4) , 465-480
Tool wear and remaining useful life (RUL) prediction based on reduced feature set and Bayesian hyperparameter optimization
- 9 April 2019
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 123 (17) , 3607-3617
Crowding-Induced Elongated Conformation of Urea-Unfolded Apoazurin: Investigating the Role of Crowder Shape in Silico
Here, we show by solution nuclear magnetic resonance measurements that urea-unfolded protein, apoazurin, becomes elongated when the synthetic crowding agent, dextran 20, is present, which disagrees with the prediction from the macromolecular crowding effect based on the argument of volume exclusion. To explore the complex interactions beyond volume exclusion, we have employed coarse-grained molecular dynamics simulations to explore the conformational ensemble of apoazurin in a box of monodisperse crowders under strong chemically denaturing conditions. The elongated conformation of unfolded apoazurin appears to result from the interplay of an effective attraction between the protein and crowders and the shape of the crowder. With a volume-conserving crowder model, we show that the crowder shape provides an anisotropic direction of the depletion force, in which a bundle of surrounding rod-like crowders stabilizes an elongated conformation of unfolded apoazurin when in the presence of effective attraction between protein and a crowder.
- 9 April 2019
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 123 (17) , 3607-3617
Crowding-Induced Elongated Conformation of Urea-Unfolded Apoazurin: Investigating the Role of Crowder Shape in Silico
Here, we show by solution nuclear magnetic resonance measurements that urea-unfolded protein, apoazurin, becomes elongated when the synthetic crowding agent, dextran 20, is present, which disagrees with the prediction from the macromolecular crowding effect based on the argument of volume exclusion. To explore the complex interactions beyond volume exclusion, we have employed coarse-grained molecular dynamics simulations to explore the conformational ensemble of apoazurin in a box of monodisperse crowders under strong chemically denaturing conditions. The elongated conformation of unfolded apoazurin appears to result from the interplay of an effective attraction between the protein and crowders and the shape of the crowder. With a volume-conserving crowder model, we show that the crowder shape provides an anisotropic direction of the depletion force, in which a bundle of surrounding rod-like crowders stabilizes an elongated conformation of unfolded apoazurin when in the presence of effective attraction between protein and a crowder.
- Open Access
- 5 March 2018
- Published by American Physical Society (APS) in Physical Review E
- Vol. 97 (3) , 032402
Impact of hydrodynamic interactions on protein folding rates depends on temperature
We investigated the impact of hydrodynamic interactions (HI) on protein folding using a coarse-grained model. The extent of the impact of hydrodynamic interactions, whether it accelerates, retards, or has no effect on protein folding, has been controversial. Together with a theoretical framework of the energy landscape theory (ELT) for protein folding that describes the dynamics of the collective motion with a single reaction coordinate across a folding barrier, we compared the kinetic effects of HI on the folding rates of two protein models that use a chain of single beads with distinctive topologies: a 64-residue chymotrypsin inhibitor 2 (CI2) protein, and a 57-residue -barrel -spectrin Src-homology 3 domain (SH3) protein. When comparing the protein folding kinetics simulated with Brownian dynamics in the presence of HI to that in the absence of HI, we find that the effect of HI on protein folding appears to have a “crossover” behavior about the folding temperature. This means that at a temperature greater than the folding temperature, the enhanced friction from the hydrodynamic solvents between the beads in an unfolded configuration results in lowered folding rate; conversely, at a temperature lower than the folding temperature, HI accelerates folding by the backflow of solvent toward the folded configuration of a protein. Additionally, the extent of acceleration depends on the topology of a protein: for a protein like CI2, where its folding nucleus is rather diffuse in a transition state, HI channels the formation of contacts by favoring a major folding pathway in a complex free energy landscape, thus accelerating folding. For a protein like SH3, where its folding nucleus is already specific and less diffuse, HI matters less at a temperature lower than the folding temperature. Our findings provide further theoretical insight to protein folding kinetic experiments and simulations.- 5 March 2018
- Published by American Physical Society (APS) in Physical Review E
- Vol. 97 (3) , 032402
Open AccessImpact of hydrodynamic interactions on protein folding rates depends on temperature
We investigated the impact of hydrodynamic interactions (HI) on protein folding using a coarse-grained model. The extent of the impact of hydrodynamic interactions, whether it accelerates, retards, or has no effect on protein folding, has been controversial. Together with a theoretical framework of the energy landscape theory (ELT) for protein folding that describes the dynamics of the collective motion with a single reaction coordinate across a folding barrier, we compared the kinetic effects of HI on the folding rates of two protein models that use a chain of single beads with distinctive topologies: a 64-residue chymotrypsin inhibitor 2 (CI2) protein, and a 57-residue -barrel -spectrin Src-homology 3 domain (SH3) protein. When comparing the protein folding kinetics simulated with Brownian dynamics in the presence of HI to that in the absence of HI, we find that the effect of HI on protein folding appears to have a “crossover” behavior about the folding temperature. This means that at a temperature greater than the folding temperature, the enhanced friction from the hydrodynamic solvents between the beads in an unfolded configuration results in lowered folding rate; conversely, at a temperature lower than the folding temperature, HI accelerates folding by the backflow of solvent toward the folded configuration of a protein. Additionally, the extent of acceleration depends on the topology of a protein: for a protein like CI2, where its folding nucleus is rather diffuse in a transition state, HI channels the formation of contacts by favoring a major folding pathway in a complex free energy landscape, thus accelerating folding. For a protein like SH3, where its folding nucleus is already specific and less diffuse, HI matters less at a temperature lower than the folding temperature. Our findings provide further theoretical insight to protein folding kinetic experiments and simulations. - 6 March 2009
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 11 (20) , 4019-4024
Free energies and forces in helix–coil transition of homopolypeptides under stretching
We show here that constant velocity steered molecular dynamics (SMD) simulations of α-helices in a vacuum present a well defined plateau in the force–extension relationship for homopolypeptides having more than (approximately) twenty residues. With the processes being far away from equilibrium, the energies strongly depend on the stretching velocity. Importantly, for a given velocity variation, the energy variation depends also on the helix sequence. Additionally, our observations show that homopolypeptides made of ten different amino acids (Ala, Cys, Gln, Ile, Leu, Met, Phe, Ser, Thr and Val) present a linear helix–coil transition.
- 6 March 2009
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 11 (20) , 4019-4024
Free energies and forces in helix–coil transition of homopolypeptides under stretching
We show here that constant velocity steered molecular dynamics (SMD) simulations of α-helices in a vacuum present a well defined plateau in the force–extension relationship for homopolypeptides having more than (approximately) twenty residues. With the processes being far away from equilibrium, the energies strongly depend on the stretching velocity. Importantly, for a given velocity variation, the energy variation depends also on the helix sequence. Additionally, our observations show that homopolypeptides made of ten different amino acids (Ala, Cys, Gln, Ile, Leu, Met, Phe, Ser, Thr and Val) present a linear helix–coil transition.