Juan Carlos Martinez-Santos

Juan Carlos Martinez-Santos

Auto-generated profile, based on publicly available information

Juan Carlos Martinez-Santos

Universidad Tecnológica de Bolívar

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications

5 June 2024 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
NHNicolás Hernández-Díaz
Nicolás Hernández-Díaz
YPYersica C. Peñaloza
Yersica C. Peñaloza
YRY. Yuliana Rios
Y. Yuliana Rios
JMJuan Carlos Martinez-Santos
Juan Carlos Martinez-Santos
EPEdwin Puertas
Edwin Puertas
This paper presents a system that relies on computer vision to identify instances of motorcycle violations in crosswalks utilizing CNNs. The system was trained and evaluated on a novel public dataset published by the authors, which contains traffic images classified into four categories: motorcycles in crosswalks, motorcycles outside crosswalks, pedestrians in crosswalks, and only motorbike outside. We demonstrate the viability of leveraging deep learning models such as YOLOv8 for this purpose and provide details on the training and performance of the model. This system has the potential to enable intelligent traffic enforcement to mitigate accidents in pedestrian zones; to develop the system, a dataset comprising over 6,000 images was amassed from publicly available traffic cameras and subsequently annotated. Several models, including YOLOv8, SSD, and MobileNet, were trained on this dataset. The YOLOv8 model attained the highest performance with a mean average precision of 84.6% across classes. The study presents the system architecture and training process. Results illustrate the potential of utilizing deep learning to detect traffic violations in pedestrian zones, which can promote intelligent traffic enforcement and improved safety.

14 October 2016
Verified
Book Chapter
Closed access
PDF file
EAeugenia arrieta
eugenia arrieta
FEFrancisco Edna Estrada
Francisco Edna Estrada
WTWilliam Caicedo Torres
William Caicedo Torres
JSJuan Carlos Martínez Santos
Juan Carlos Martínez Santos

1 October 2012
Verified
Conference Paper
Closed access
JSJuan Carlos Martinez Santos
Juan Carlos Martinez Santos
YFYunsi Fei
Yunsi Fei
We report our experiences in designing and implementing several hardware Trojans within the framework of the Malicious Processor Design Challenge competition. It was held as part of the Cyber Security Awareness Week (CSAW) at the Polytechnic Institute of New York University in November 2011. A malicious processor provides an attacker the ability to bypass traditional defensive techniques as they occupy a layer below the entire software stack. To show that, we present several attack techniques employing hardware Trojans to compromise the security of an 8051 processor performing RC-5 encryption algorithm implemented on a Digilent ATLYS Spartan-6 FPGA development board. We show three powerful attacks using extra hardware: a back door Trojan allows an attacker dump the whole or partial memory region, a bomb counter Trojan disables/enables special/extra functions, and a power sink Trojan exposes the state of the carry flag by changing the power profile of the system.

15 October 2009
Verified
Conference Paper
Open access
PDF file
JSJuan Carlos Martinez Santos
Juan Carlos Martinez Santos
YFYunsi Fei
Yunsi Fei
ZSZhijie Jerry Shi
Zhijie Jerry Shi

1 January 2020
Verified
Conference Paper
Closed access
AVAlvaro Jose Ortega Vargas
Alvaro Jose Ortega Vargas
JCJairo E. Serrano C.
Jairo E. Serrano C.
LALeonardo Castellanos Acuna
Leonardo Castellanos Acuna
JMJuan Carlos Martinez-Santos
Juan Carlos Martinez-Santos
Search and planning is a common Artificial Intelligence task on videogames development. This exercise covers the design of Non-player character (NPC) behavior, content generation, and narrative's construction. This work focus on NPC behavior, specifically on path planning. This paper presents an implementation of an arcade videogame (Ms. Pacman type) with Unity, where the NPC's behavior (Ghosts) applies the Wavefront algorithm to find the shortest path to the Player Character (Mr. Pacman). This algorithm is an alternative to traditional algorithms the Djikstra algorithm and A-star used to solve this problem.