Miguel A. Labrador
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
Research Subjects
Miguel A. Labrador has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Pedro M. Wightman
School of Sciences and Engineering, Universidad del Rosario, Bogotá D.C., Colombia
15 shared publications - Cesar D. Guerrero
Universidad Autónoma de Bucaramanga
3 shared publications - Diego Mendez
Electronics Engineering Department, Pontificia Universidad Javeriana, Bogotá 110231, Colombia
2 shared publications - Rafael Perez
Department of Computer Science and Engineering, University of South Florida
2 shared publications - Sean J. Barbeau
Center for Urban Transportation Research, University of South Florida, Tampa, FL
2 shared publications - Steven Bassi
University of South Florida, Department of Computer Science & Engineering, 4202 E. Fowler Ave., ENB 118, Tampa, FL 33620
2 shared publications
Latest Publications
- 22 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 275-280
Evaluating Models for Estimating Schedule Deviation in Public Transit
According to a survey performed in 2013 on public transportation riders, there is an increasing number of users relying solely on real-time information for route schedules. As this trend continues, researchers and transit providers have developed algorithms to better predict schedule deviations and arrival time estimations. However, several number of these approaches have not been thoroughly documented and evaluated, limiting the reproducibility of results across publications. This paper identifies these limitations and proposes evaluation methods that can be more easily compared. To showcase these approaches, we evaluated three different predicting models used for schedule deviation across two cities.
- 22 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 275-280
Evaluating Models for Estimating Schedule Deviation in Public Transit
According to a survey performed in 2013 on public transportation riders, there is an increasing number of users relying solely on real-time information for route schedules. As this trend continues, researchers and transit providers have developed algorithms to better predict schedule deviations and arrival time estimations. However, several number of these approaches have not been thoroughly documented and evaluated, limiting the reproducibility of results across publications. This paper identifies these limitations and proposes evaluation methods that can be more easily compared. To showcase these approaches, we evaluated three different predicting models used for schedule deviation across two cities.
- 4 September 2020
- Published by American Society for Engineering Education
- p. 13.1051.1-13.1051.13
Reu Sites: Much More Than A Research Experience For Undergraduates
REU Sites: Much More than a Research Experience for Undergraduates Abstract Undergraduate research is one of the most important recommended vehicles to address current educational concerns in Science and Engineering, such as high dropout rates, low graduation rates, and low enrollment in graduate programs. In this paper we describe our experience running an NSF-sponsored Research Experiences for Undergraduates (REU) Site in Computer Science and Engineering (CS&E), an area where these problems have been recently exacerbated and where under-represented minority student groups with important growth rates have had a very low participation. The most important aspects that need to be included in these programs to address these concerns and some other initiatives that can bring additional benefits at low cost are also described. For each of these aspects, successful strategies or best practices are included. Finally, the effectiveness of the program is demonstrated with the results of the program evaluation. 1. Introduction Over the last several years, the United States has witnessed alarming statistics and trends in graduate and undergraduate enrollment, graduation rates, and participation of minority groups in Science and Engineering (S&E) fields, and in Computer Science in particular. For example, according to the National Science Foundation’s Science and Engineering indicators 2006, underrepresented minorities did not enroll in or completed college at the same rate as whites. In 2003, the percentage of African Americans and Hispanics who completed ba3lor’s or higher degrees were 18% and 10%, respectively, compared with 34% of whites1. The graduation rate for African Americans and Hispanics in Engineering has remained at 11% over the last ten years2. Underrepresented minority students are also less likely than other groups to be enrolled in research institutions and instead, a high percentage of them (47%) enrolled in 2-yr institutions. Regarding freshmen intentions to major in S&E1, shows that in 2004, although 9% of the students planned to major in engineering only 2%-5% had plans to major in Computer Science. At the graduate level, enrollment in S&E has declined since 2003 mainly as a consequence of the decline observed in foreign students, which declined 12% in Engineering and 23% in Computer Science. Meanwhile, the country has experienced unequal population growth rates of certain minority groups compared to the rest of the U.S. population. In recent reports3,4, Hispanics are shown to be the fastest growing population in the United States and the largest minority group in the country since 2005. Even though the reports indicate that Hispanics will account for one quarter of the U.S.’s population by 20503, they also indicate that Hispanics only account for 6, 4 and 3 percent of the bachelor’s, master’s and doctoral degrees, respectively. Furthermore, they are the least educated major ethnic group, and the group with the lowest graduate school enrollment. The conclusion is that these trends and numbers combined represent serious problems for the United States. In order to maintain the competitiveness and leadership in technology, the U.S.
- 4 September 2020
- Published by American Society for Engineering Education
- p. 13.1051.1-13.1051.13
Reu Sites: Much More Than A Research Experience For Undergraduates
REU Sites: Much More than a Research Experience for Undergraduates Abstract Undergraduate research is one of the most important recommended vehicles to address current educational concerns in Science and Engineering, such as high dropout rates, low graduation rates, and low enrollment in graduate programs. In this paper we describe our experience running an NSF-sponsored Research Experiences for Undergraduates (REU) Site in Computer Science and Engineering (CS&E), an area where these problems have been recently exacerbated and where under-represented minority student groups with important growth rates have had a very low participation. The most important aspects that need to be included in these programs to address these concerns and some other initiatives that can bring additional benefits at low cost are also described. For each of these aspects, successful strategies or best practices are included. Finally, the effectiveness of the program is demonstrated with the results of the program evaluation. 1. Introduction Over the last several years, the United States has witnessed alarming statistics and trends in graduate and undergraduate enrollment, graduation rates, and participation of minority groups in Science and Engineering (S&E) fields, and in Computer Science in particular. For example, according to the National Science Foundation’s Science and Engineering indicators 2006, underrepresented minorities did not enroll in or completed college at the same rate as whites. In 2003, the percentage of African Americans and Hispanics who completed ba3lor’s or higher degrees were 18% and 10%, respectively, compared with 34% of whites1. The graduation rate for African Americans and Hispanics in Engineering has remained at 11% over the last ten years2. Underrepresented minority students are also less likely than other groups to be enrolled in research institutions and instead, a high percentage of them (47%) enrolled in 2-yr institutions. Regarding freshmen intentions to major in S&E1, shows that in 2004, although 9% of the students planned to major in engineering only 2%-5% had plans to major in Computer Science. At the graduate level, enrollment in S&E has declined since 2003 mainly as a consequence of the decline observed in foreign students, which declined 12% in Engineering and 23% in Computer Science. Meanwhile, the country has experienced unequal population growth rates of certain minority groups compared to the rest of the U.S. population. In recent reports3,4, Hispanics are shown to be the fastest growing population in the United States and the largest minority group in the country since 2005. Even though the reports indicate that Hispanics will account for one quarter of the U.S.’s population by 20503, they also indicate that Hispanics only account for 6, 4 and 3 percent of the bachelor’s, master’s and doctoral degrees, respectively. Furthermore, they are the least educated major ethnic group, and the group with the lowest graduate school enrollment. The conclusion is that these trends and numbers combined represent serious problems for the United States. In order to maintain the competitiveness and leadership in technology, the U.S.
- Open Access
- 11 August 2017
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 1 (2) , e3
A Mobile Health Intervention to Improve Self-Care in Patients With Heart Failure: Pilot Randomized Control Trial
Heart failure (HF) is a progressive chronic disease affecting 6.5 million Americans and over 15 million individuals globally. Patients with HF are required to engage in complex self-care behaviors. Although the advancements in medicine have enabled people with HF to live longer, they often have poor health-related quality of life and experience severe and frequent symptoms that limit several aspects of their lives. Mobile phone apps have not only created new and interactive ways of communication between patients and health care providers but also provide a platform to enhance adherence to self-care management. The aim of this pilot study was to test the feasibility of a newly developed mobile app (HeartMapp) in improving self-care behaviors and quality of life of patients with HF and to calculate effect sizes for sample size calculation for a larger study. This was a pilot feasibility randomized controlled trial. Participants were enrolled in the hospital before discharge and followed at home for 30 days. The intervention group used HeartMapp (n=9), whereas the control group (n=9) received HF education. These apps were downloaded onto their mobile phones for daily use. A total of 72% (13/18) participants completed the study; the mean age of the participants was 53 (SD 4.02) years, 56% (10/18) were females, 61% (11/18) lived alone, 33% (6/18) were African Americans, and 61% (11/18) used mobile phone to get health information. The mean engagement with HeartMapp was 78%. Results were promising with a trend that participants in the HeartMapp group had a significant mean score change on self-care management (8.7 vs 2.3; t3.38=11, P=.01), self-care confidence (6.7 vs 1.8; t2.53=11, P=.28), and HF knowledge (3 vs -0.66; t2.37=11, P=.04. Depression improved among both groups, more so in the control group (-1.14 vs -5.17; t1.97=11, P=.07). Quality of life declined among both groups, more so in the control group (2.14 vs 9.0; t-1.43=11, P=.18). The trends demonstrated in this pilot feasibility study warrant further exploration on the use of HeartMapp to improve HF outcomes. Pilot study, no funding from National agencies, hence not registered.
- 11 August 2017
- Published by JMIR Publications Inc. in JMIR Cardio
- Vol. 1 (2) , e3
Open AccessA Mobile Health Intervention to Improve Self-Care in Patients With Heart Failure: Pilot Randomized Control Trial
Heart failure (HF) is a progressive chronic disease affecting 6.5 million Americans and over 15 million individuals globally. Patients with HF are required to engage in complex self-care behaviors. Although the advancements in medicine have enabled people with HF to live longer, they often have poor health-related quality of life and experience severe and frequent symptoms that limit several aspects of their lives. Mobile phone apps have not only created new and interactive ways of communication between patients and health care providers but also provide a platform to enhance adherence to self-care management. The aim of this pilot study was to test the feasibility of a newly developed mobile app (HeartMapp) in improving self-care behaviors and quality of life of patients with HF and to calculate effect sizes for sample size calculation for a larger study. This was a pilot feasibility randomized controlled trial. Participants were enrolled in the hospital before discharge and followed at home for 30 days. The intervention group used HeartMapp (n=9), whereas the control group (n=9) received HF education. These apps were downloaded onto their mobile phones for daily use. A total of 72% (13/18) participants completed the study; the mean age of the participants was 53 (SD 4.02) years, 56% (10/18) were females, 61% (11/18) lived alone, 33% (6/18) were African Americans, and 61% (11/18) used mobile phone to get health information. The mean engagement with HeartMapp was 78%. Results were promising with a trend that participants in the HeartMapp group had a significant mean score change on self-care management (8.7 vs 2.3; t3.38=11, P=.01), self-care confidence (6.7 vs 1.8; t2.53=11, P=.28), and HF knowledge (3 vs -0.66; t2.37=11, P=.04. Depression improved among both groups, more so in the control group (-1.14 vs -5.17; t1.97=11, P=.07). Quality of life declined among both groups, more so in the control group (2.14 vs 9.0; t-1.43=11, P=.18). The trends demonstrated in this pilot feasibility study warrant further exploration on the use of HeartMapp to improve HF outcomes. Pilot study, no funding from National agencies, hence not registered.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10910050,p. 1-4
Recognizing mental stress in chess players using vital sign data
The identification of psychological stress can provide important feedback in order to perform critical activities. While a certain amount of stress may increase performance, an overly stressful reaction may hinder it. Because subjective bias can make it difficult to accurately recognize psychological stress, it would be advantageous for an external system to perform the task instead. We present a platform for psychological stress detection using physiological sensors during a chess match. The sensors are inside an unobtrusive chest strap that can be worn by the player during a match. By playing games on an Android phone, the system can apply machine learning techniques to the player's vital sign data to give important feedback such as which moves caused the player to become stressed during a match.
- 1 April 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10910050,p. 1-4
Recognizing mental stress in chess players using vital sign data
The identification of psychological stress can provide important feedback in order to perform critical activities. While a certain amount of stress may increase performance, an overly stressful reaction may hinder it. Because subjective bias can make it difficult to accurately recognize psychological stress, it would be advantageous for an external system to perform the task instead. We present a platform for psychological stress detection using physiological sensors during a chess match. The sensors are inside an unobtrusive chest strap that can be worn by the player during a match. By playing games on an Android phone, the system can apply machine learning techniques to the player's vital sign data to give important feedback such as which moves caused the player to become stressed during a match.
- 23 November 2012
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 9 (1) , 132-148
Data interpolation for participatory sensing systems
- 23 November 2012
- Published by Elsevier in Pervasive and Mobile Computing
- Vol. 9 (1) , 132-148
Data interpolation for participatory sensing systems
- 1 July 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-71
Removing spatial outliers in PS applications
In this paper we study the problem of sensor data verification in Participatory Sensing (PS) systems using an air quality/pollution monitoring application as a validation example. Data verification, in the context of PS, consists of the process of removing spatial outliers to properly reconstruct the variables of interest. We propose a hybrid neighborhood-aware algorithm for outlier detection that considers the uneven spatial density of the users, the number of malicious users, the level of conspiracy, and the lack of accuracy and malfunctioning sensors. The algorithm utilizes the Delaunay triangulation and Gaussian Mixture Models to build neighborhoods based on the spatial and non-spatial attributes of each location. Our experimental results show that our hybrid algorithm performs as good as the best estimator while considerably reducing the execution time.
- 1 July 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-71
Removing spatial outliers in PS applications
In this paper we study the problem of sensor data verification in Participatory Sensing (PS) systems using an air quality/pollution monitoring application as a validation example. Data verification, in the context of PS, consists of the process of removing spatial outliers to properly reconstruct the variables of interest. We propose a hybrid neighborhood-aware algorithm for outlier detection that considers the uneven spatial density of the users, the number of malicious users, the level of conspiracy, and the lack of accuracy and malfunctioning sensors. The algorithm utilizes the Delaunay triangulation and Gaussian Mixture Models to build neighborhoods based on the spatial and non-spatial attributes of each location. Our experimental results show that our hybrid algorithm performs as good as the best estimator while considerably reducing the execution time.
- 29 October 2009
- Published by Elsevier in Computer Networks
- Vol. 54 (6) , 977-990
Traceband: A fast, low overhead and accurate tool for available bandwidth estimation and monitoring
- 29 October 2009
- Published by Elsevier in Computer Networks
- Vol. 54 (6) , 977-990
Traceband: A fast, low overhead and accurate tool for available bandwidth estimation and monitoring
- 27 August 2009
- Published by Elsevier in Computer Communications
- Vol. 33 (1) , 11-22
On the applicability of available bandwidth estimation techniques and tools
- 27 August 2009
- Published by Elsevier in Computer Communications
- Vol. 33 (1) , 11-22
On the applicability of available bandwidth estimation techniques and tools