Heiner Castro Gutierrez

Mr. Heiner Castro Gutierrez

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
28 November 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
SPSuranjan Panigrahi
Suranjan Panigrahi
Sensor systems that comprise interdigitated electrode (IDE) transducer(s) and selectivity layer(s) are an appropriate platform for versatile sensor applications. Such systems have generally used non-faradic, label-free impedance spectroscopic methods for harnessing the signal from the IDEs. While there is an increasing need for sensors (or sensor systems) to be sensitive, smaller, easier to operate, and cost-effective, the development and use of IDE-based sensors in multiple application domains make it very challenging. Thus, a state-of-the-art review of interdigitated electrode-based sensors is justified and is the primary focus of this paper. This paper reviews the working principles, mathematical models, design architectures, and fabrication methods of IDE-based sensors in three specific application domains (gaseous, biological, and inorganic). The performance of the IDE-based sensors across different applications, along with their limitation, have been illustrated. The emerging trend of 3-D interdigitated electrodes as sensing platforms has been discussed with additional perspectives on their overall future research needs.

28 May 2025 in Processes
Verified
Journal Article
Open access
PDF file
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
CRCarlos Robles-Algarín
Carlos Robles-Algarín
APAura Polo
Aura Polo
Laser-induced breakdown spectroscopy (LIBS) is a rapid, cost-effective technique for elemental analysis that enables real-time measurements with minimal sample preparation. However, LIBS datasets are often high-dimensional and imbalanced, limiting the performance of conventional machine-learning models due to small sample sizes. To address this, we propose a novel data augmentation method that generates synthetic samples using normal distribution sampling. This approach is justified by the central limit theorem, since each spectrum in the dataset used in this study results from averaging over 80 measurements per sample, yielding approximately Gaussian-distributed features. We also apply a dimensionality reduction method based on random forest feature importance, selecting features that account for 95% of cumulative importance. This selection reduces model complexity while preserving performance. Using random forest for both feature selection and modeling, our approach achieves superior accuracy for copper and competitive performance for chromium detection in mulberry leaves. Additionally, the selected wavelengths partially match reference lines reported by NIST, supporting model interpretability. These findings highlight the potential of combining data augmentation and machine learning for more robust and interpretable LIBS-based heavy metal detection.

1 November 2012
Verified
Conference Paper
Closed access
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
JTJohn Alexander Taborda
John Alexander Taborda
In this paper, the development of a rapid prototyping system for chaotic generators using LabVIEW-FPGA is described. This system was envisioned as an essential tool for testing and evaluation of applications based on chaos theory such as encryption algorithms or chaos controllers. Production of a new chip realization involves design, simulation, development and evaluation phases. LabVIEW FPGA environment is well suited for creating systems very quickly. Two discrete-time chaotic generators are used to illustrate the rapid prototyping system. The paper also shows how LabVIEW code can be reused to implement coupled chaotic generators. The laboratory results are compared and verified using MATLAB simulations. Differences between experimental and simulated bifurcation diagrams are discussed.

1 January 2025 in Respuestas
Verified
Journal Article
Open access
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
CRCarlos Robles-Algarín
Carlos Robles-Algarín
LALuis Leonardo Camargo Ariza
Luis Leonardo Camargo Ariza
The identification and controlled replacement of defective parts in a machine increases equipment reliability. A pump is a device used to move fluids, and the pump impeller is one of its critical components, as it converts the mechanical energy of the motor into the kinetic energy of the fluid. If the impeller is damaged, the pump may fail. This paper presents a comparative analysis of two machine learning algorithms—decision trees and support vector machines—applied to the classification of pump impellers as "good" or "bad" based on their physical condition, a key task in preventive maintenance. The experiment uses a balanced dataset of impeller images to compare the performance of both algorithms by evaluating metrics such as accuracy, total cost, training time, prediction speed, and the confusion matrix. The main results show a test accuracy of 87.9% using decision trees and 98.7% using support vector machines; however, the latter requires more training time. It is concluded that both algorithms are effective for classifying the component under study. They are computationally efficient but pose challenges such as overfitting and hyperparameter tuning. Additionally, the use of hyperplanes and an optimized kernel in the SVM algorithm makes classification more efficient, although it requires more time and data for training.

19 September 2024
Verified
Conference Paper
Closed access
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
SPSuranjan Panigrahi
Suranjan Panigrahi
SSSteven R. Steinhubl
Steven R. Steinhubl
This paper explores the development of predictive models aimed at improving the detection of out-of-hospital cardiac arrest (OHCA) using electrocardiogram (ECG) data and shallow machine learning techniques. Publicly available datasets, including ECG data before sudden cardiac arrest (SCA), are used to evaluate the performance of selected machine learning algorithms, such as Decision Trees, Random Forests, and Support Vector Machines (SVM), in predicting OHCA. It was found that SVM with a radial basis function kernel outperformed other models with an average accuracy of $0.938 \pm$ 0.01. This paper presents the development and testing of this and other selected machine learning models, along with the recommendations for future work.

30 May 2024
Verified
Conference Paper
Closed access
Heiner Castro GutierrezHeiner Castro Gutierrez
Heiner Castro Gutierrez
SPSuranjan Panigrahi
Suranjan Panigrahi