Ivan Cabezas
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
Ivan Cabezas has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Maria Trujillo
Universidad del Valle
7 shared publicationsAndres Felipe Hurtado
2 shared publicationsJairo Alejandro Gomez
2 shared publicationsJhonatan Hernandez
Axede
2 shared publicationsLuis Bernardo Villa
SIO, Cali, Colombia
2 shared publications- Luis Vives
Faculty of Engineering, Peruvian University of Applied Sciences, Lima, Peru
2 shared publications
Latest Publications
- Open Access
- 28 May 2026
- Published by Elsevier in Healthcare Analytics
- Vol. 9
An analytics framework for secure and intelligent telemedicine in sustainable healthcare
- 28 May 2026
- Published by Elsevier in Healthcare Analytics
- Vol. 9
Open AccessAn analytics framework for secure and intelligent telemedicine in sustainable healthcare
- Open Access
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 5882-5898
Prediction of Students’ Academic Performance in the Programming Fundamentals Course Using Long Short-Term Memory Neural Networks
In recent years, there has been evidence of a growing interest on the part of universities to know in advance the academic performance of their students and allow them to establish timely strategies to avoid desertion and failure. One of the biggest challenges to predicting student performance is presented in the course “Programming Fundamentals” of Computer Science, Software Engineering, and Information Systems Engineering careers in Peruvian universities for high student dropout rates. The objective of this research was to explore the efficiency of Long-Short Term Memory Networks (LSTM) in the field of Educational Data Mining (EDM) to predict the academic performance of students during the seventh, eighth, twelfth, and sixteenth weeks of the academic semester, which allowed us to identify students at risk of failing the course. This research compares several predictive models, such as Deep Neural Network (DNN), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Support Vector Classifier (SVM), and K-Nearest Neighbor (KNN). A major challenge machine learning algorithms face is a class imbalance in a dataset, resulting in over-fitting to the available data and, consequently, low accuracy. We use Generative Adversarial Networks (GAN) and Synthetic Minority Over-sampling Technique (SMOTE) to balance the data needed in our proposal. From the experimental results based on accuracy, precision, recall, and F1-Score, the superiority of our model is verified concerning a better classification, with 98.3% accuracy in week 8 using LSTM-GAN, followed by DNN-GAN with 98.1% accuracy.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 5882-5898
Open AccessPrediction of Students’ Academic Performance in the Programming Fundamentals Course Using Long Short-Term Memory Neural Networks
In recent years, there has been evidence of a growing interest on the part of universities to know in advance the academic performance of their students and allow them to establish timely strategies to avoid desertion and failure. One of the biggest challenges to predicting student performance is presented in the course “Programming Fundamentals” of Computer Science, Software Engineering, and Information Systems Engineering careers in Peruvian universities for high student dropout rates. The objective of this research was to explore the efficiency of Long-Short Term Memory Networks (LSTM) in the field of Educational Data Mining (EDM) to predict the academic performance of students during the seventh, eighth, twelfth, and sixteenth weeks of the academic semester, which allowed us to identify students at risk of failing the course. This research compares several predictive models, such as Deep Neural Network (DNN), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Support Vector Classifier (SVM), and K-Nearest Neighbor (KNN). A major challenge machine learning algorithms face is a class imbalance in a dataset, resulting in over-fitting to the available data and, consequently, low accuracy. We use Generative Adversarial Networks (GAN) and Synthetic Minority Over-sampling Technique (SMOTE) to balance the data needed in our proposal. From the experimental results based on accuracy, precision, recall, and F1-Score, the superiority of our model is verified concerning a better classification, with 98.3% accuracy in week 8 using LSTM-GAN, followed by DNN-GAN with 98.1% accuracy.
- 10 September 2020
- Published by American Society for Engineering Education
Teaching and Assessing Sustainability Based on the Karlskrona Manifesto
- 10 September 2020
- Published by American Society for Engineering Education
Teaching and Assessing Sustainability Based on the Karlskrona Manifesto
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2015, 2227-2231
How Video Object Tracking Is Affected by In-capture Distortions?
Video Object Tracking -VOT- in realistic scenarios is a difficult task. Image factors such as occlusion, clutter, confusion, object shape, and zooming, among others, have an impact on video tracker methods performance. While these conditions do affect trackers performance, there is not a clear distinction between the scene content challenges like occlusion and clutter, against challenges due to distortions generated by capture, compression, processing, and transmission of videos. This paper is concerned with the latter interpretation of quality as it affects VOT performance. The contribution of this paper is two-fold. We have constructed a database of 537 surveillance videos containing different levels of authentic distortions such as low exposure and out-of-focus. It is available at https://tinyurl.com/DSVD-Test. Based on this database, we assessed seven state-of-the-art trackers with the A-R plot performance measure. We demonstrate that in-capture distortions severely hamper VOT methods performance in a non intuitive way.
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2015, 2227-2231
How Video Object Tracking Is Affected by In-capture Distortions?
Video Object Tracking -VOT- in realistic scenarios is a difficult task. Image factors such as occlusion, clutter, confusion, object shape, and zooming, among others, have an impact on video tracker methods performance. While these conditions do affect trackers performance, there is not a clear distinction between the scene content challenges like occlusion and clutter, against challenges due to distortions generated by capture, compression, processing, and transmission of videos. This paper is concerned with the latter interpretation of quality as it affects VOT performance. The contribution of this paper is two-fold. We have constructed a database of 537 surveillance videos containing different levels of authentic distortions such as low exposure and out-of-focus. It is available at https://tinyurl.com/DSVD-Test. Based on this database, we assessed seven state-of-the-art trackers with the A-R plot performance measure. We demonstrate that in-capture distortions severely hamper VOT methods performance in a non intuitive way.
- Open Access
Evaluation of Object Trackers in Distorted Surveillance Videos
Object tracking in realistic scenarios is a difficult problem affected by various image factors such as occlusion, clutter, confusion, object shape, unstable speed, and zooming. While these conditions do affect tracking performance, there is no clear distinction between the scene dependent challenges like occlusion, clutter, etc., and the challenges imposed by traditional notions of impairments from capture, compression, processing, and transmission. This paper is concerned with the latter interpretation of quality as it affects video tracking performance. In this work we aim to evaluate two state-of-the-art trackers (STRUCK and TLD) systematically and experimentally in surveillance videos affected by in-capture distortions such as under-exposure and defocus. We evaluate these trackers with the area under curve (AUC) values of success plots and precision curves. In spite of the fact that STRUCK and TLD have ranked high in video tracking surveys. This study concludes that incapture distortions severely affect the performance of these trackers. For this reason, the design and construction of a robust tracker with respect to these distortions remains an open question that can be answered by creating algorithms that makes use of perceptual features to compensate the degradations provided by these distortions.
Open AccessEvaluation of Object Trackers in Distorted Surveillance Videos
Object tracking in realistic scenarios is a difficult problem affected by various image factors such as occlusion, clutter, confusion, object shape, unstable speed, and zooming. While these conditions do affect tracking performance, there is no clear distinction between the scene dependent challenges like occlusion, clutter, etc., and the challenges imposed by traditional notions of impairments from capture, compression, processing, and transmission. This paper is concerned with the latter interpretation of quality as it affects video tracking performance. In this work we aim to evaluate two state-of-the-art trackers (STRUCK and TLD) systematically and experimentally in surveillance videos affected by in-capture distortions such as under-exposure and defocus. We evaluate these trackers with the area under curve (AUC) values of success plots and precision curves. In spite of the fact that STRUCK and TLD have ranked high in video tracking surveys. This study concludes that incapture distortions severely affect the performance of these trackers. For this reason, the design and construction of a robust tracker with respect to these distortions remains an open question that can be answered by creating algorithms that makes use of perceptual features to compensate the degradations provided by these distortions.
- 17 August 2017
- Published by Springer Nature
- p. 267-281
Architectural Design of a Clinical Decision Support System for Clinical Triage in Emergency Departments
- 17 August 2017
- Published by Springer Nature
- p. 267-281
Architectural Design of a Clinical Decision Support System for Clinical Triage in Emergency Departments
- 1 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 323-328
An innovative practice in a graduate course combining startups evaluation and image processing
A joint development of business and engineering skills should be a nowadays concern in order to fulfill with the expectation and the vision of educating the engineer of 2020. However, in practice, such harmonization of abilities and skills during the educational experience provided by a course may be challenging due to several reasons. The lack of homogeneity regarding students' background within a specific course, as well as a short duration of the course itself are among the reasons. In this paper, an innovative practice conducted for engaging students in the development of skills in business and engineering is presented. The practice was focused on image processing startups evaluation. It involved professionals from different areas such as management, accounting, and engineering in a master's program of information technology. The course had a duration of eighth sessions, in a time period of a month. Student outcomes were evaluated according to a rubric designed for this context. It considers engineering, business, and communication skills. This practice was motivated on previous experiences of the same course where the instructor found the challenges mentioned above. Analysis of obtained results during the innovative practice indicate that is indeed challenging for students to properly enhance the considered skills during the course. Presented activity and designed rubric may be useful for further innovative practices aiming a development of engineering and business skills. Details are provided in this paper in order to allow its reproducibility.
- 1 April 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 323-328
An innovative practice in a graduate course combining startups evaluation and image processing
A joint development of business and engineering skills should be a nowadays concern in order to fulfill with the expectation and the vision of educating the engineer of 2020. However, in practice, such harmonization of abilities and skills during the educational experience provided by a course may be challenging due to several reasons. The lack of homogeneity regarding students' background within a specific course, as well as a short duration of the course itself are among the reasons. In this paper, an innovative practice conducted for engaging students in the development of skills in business and engineering is presented. The practice was focused on image processing startups evaluation. It involved professionals from different areas such as management, accounting, and engineering in a master's program of information technology. The course had a duration of eighth sessions, in a time period of a month. Student outcomes were evaluated according to a rubric designed for this context. It considers engineering, business, and communication skills. This practice was motivated on previous experiences of the same course where the instructor found the challenges mentioned above. Analysis of obtained results during the innovative practice indicate that is indeed challenging for students to properly enhance the considered skills during the course. Presented activity and designed rubric may be useful for further innovative practices aiming a development of engineering and business skills. Details are provided in this paper in order to allow its reproducibility.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 65, 42-47
Architectural Approaches for Implementing Clinical Decision Support Systems in Cloud: A Systematic Review
Clinical Decision Support Systems (CDSS) were explicitly introduced in the 90's with the aim of providing knowledge to clinicians in order to influence its decisions and, therefore, improve patients' health care. There are different architectural approaches for implementing CDSS. Some of these approaches are based on cloud computing, which provides on-demand computing resources over internet. The goal of this paper is to determine and discuss key issues and approaches involving architectural designs in implementing a CDSS using cloud computing. To this end, we performed a standard Systematic Literature Review (SLR) of primary studies showing the intervention of cloud computing on CDSS implementations. Twenty-one primary studies were reviewed. We found that CDSS architectural components are similar in most of studies. Cloud-based CDSS are most used in Home Healthcare and Emergency Medical Systems. Alerts/Reminders and Knowledge Service are the most common implementations. Major challenges are around security, performance and compatibility. We concluded on the benefits of implementing a cloud-based CDSS, since it allows cost-efficient, ubiquitous and elastic computing resources. We highlight that some studies show weaknesses regarding the conceptualization of a cloud-based computing approach and lack of a formal methodology in the architectural design process.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 65, 42-47
Architectural Approaches for Implementing Clinical Decision Support Systems in Cloud: A Systematic Review
Clinical Decision Support Systems (CDSS) were explicitly introduced in the 90's with the aim of providing knowledge to clinicians in order to influence its decisions and, therefore, improve patients' health care. There are different architectural approaches for implementing CDSS. Some of these approaches are based on cloud computing, which provides on-demand computing resources over internet. The goal of this paper is to determine and discuss key issues and approaches involving architectural designs in implementing a CDSS using cloud computing. To this end, we performed a standard Systematic Literature Review (SLR) of primary studies showing the intervention of cloud computing on CDSS implementations. Twenty-one primary studies were reviewed. We found that CDSS architectural components are similar in most of studies. Cloud-based CDSS are most used in Home Healthcare and Emergency Medical Systems. Alerts/Reminders and Knowledge Service are the most common implementations. Major challenges are around security, performance and compatibility. We concluded on the benefits of implementing a cloud-based CDSS, since it allows cost-efficient, ubiquitous and elastic computing resources. We highlight that some studies show weaknesses regarding the conceptualization of a cloud-based computing approach and lack of a formal methodology in the architectural design process.
- 12 July 2016
- Published by Springer Nature
- p. 71-86
Towards a Sustainable Architectural Design by an Adaptation of the Architectural Driven Design Method
- 12 July 2016
- Published by Springer Nature
- p. 71-86
Towards a Sustainable Architectural Design by an Adaptation of the Architectural Driven Design Method
- 18 December 2015
- Published by Springer Nature
- p. 102-111
Stereo Correspondence Evaluation Methods: A Systematic Review
- 18 December 2015
- Published by Springer Nature
- p. 102-111
Stereo Correspondence Evaluation Methods: A Systematic Review