Josué Martínez-Martínez

Mr. Josué Martínez-Martínez

Ana G. Méndez University, Gurabo Campus
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 November 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JMJosué Martínez-Martínez
Josué Martínez-Martínez
DADiego Aponte-Roa
Diego Aponte-Roa
IVIdalides Vergara-Laurens
Idalides Vergara-Laurens
Wayne WeaverWayne Weaver
Wayne Weaver
The use of Internet-connected devices at homes has increased to monitor energy consumption. Furthermore, renewable energy sources have also increased, reducing electricity bills. However, the high cost of the equipment limits the use of these technologies. This paper presents a low-cost secured-distributed Internet of Things (IoT) system to monitor and control devices connected in a polygeneration microgrid, as a combined power system for local loads with renewable sources. The proposed mechanism includes a Wireless Sensor Actuator Networked Control System that links network nodes using the IEEE 802.15.4 standard. The Internet communication enables the monitor and control of devices using a mobile application to increase the efficiency. In addition, security mechanisms are implemented at several levels including the authentication, encryption, and decryption of the transmitted data. Furthermore, a firewall and a network intrusion detection-and-prevention program are implemented to increase the system protection against cyber-attack. The feasibility of the proposed solution was demonstrated using a DC microgrid test bench consisting of a diverse range of renewable energy sources and loads.

1 January 2020
Verified
Conference Paper
Closed access
PDF file
AFAngel Flores-Abad
Angel Flores-Abad
NHNoshin Habib
Noshin Habib
DADiego Aponte-Roa
Diego Aponte-Roa
AEAlbert Espinoza
Albert Espinoza
JMJosué Martínez-Martínez
Josué Martínez-Martínez

11 November 2025
Verified
Book Chapter
Closed access
PDF file
JMJosué Martínez-Martínez
Josué Martínez-Martínez
OBOlivia Brown
Olivia Brown
MKMostafa Karami
Mostafa Karami
SNSheida Nabavi
Sheida Nabavi

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
JMJosué Martínez-Martínez
Josué Martínez-Martínez
OBOlivia Brown
Olivia Brown
RCRajmonda Caceres
Rajmonda Caceres
This research focuses on improving the robustness of machine learning systems to natural variations and distribution shifts. A design trade space is presented, and various methods are compared, including adversarial training, data augmentation techniques, and novel approaches inspired by model-based robust optimization formulations.

1 January 2020
Verified
Conference Paper
Closed access
JMJosué Martínez-Martínez
Josué Martínez-Martínez
CCCarmen Carvajal-Jimenez
Carmen Carvajal-Jimenez
DADiego A. Aponte-Roa
Diego A. Aponte-Roa
A microgrid is a small-scale grid for electricity generation and distribution to small communities using different energy sources such as the sun and the wind. This paper presents a secured IoT scheme to monitor a DC microgrid components for improving its performance. The key idea is to set up a Wireless Sensor Network in which the sensor nodes are connected to a network using the Zigbee protocol and allow external communication through a sink node. A mobile application allows the user to monitor and control the system via the Internet to minimize the waste of energy. For security purposes, data are authenticated, encrypted, and decrypted for avoiding malicious attacks. In addition, the sink node has an encrypted key-based protocol for establishing a secured remote login with the authorized users. Also, a firewall and network intrusion detection & prevention system was implemented to protect the devices and their local data. Our results demonstrate the feasibility of this proposed scheme in a real microgrid.

20 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
JMJosué Martínez-Martínez
Josué Martínez-Martínez
OBOlivia Brown
Olivia Brown
MKMostafa Karami
Mostafa Karami
SNSheida Nabavi
Sheida Nabavi
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.