Benjamín Maraza-Quispe
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
Research Interests
Benjamín Maraza-Quispe has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
Walter Choquehuanca-Quispe
Universidad Nacional de San Agustn de Arequipa, Arequipa, Peru
9 shared publications- Nicolas Caytuiro-Silva
Faculty of Physical and Formal Sciences and Engineering, Catholic University of Santa Maria, Peru
8 shared publications Jorge Luis Torres-Loayza
Department of Education, Universidad Nacional de San Agustin de Arequipa, Arequipa, Peru
6 shared publications- Angel Choquehuayta
Universidad Nacional de San Agustí n de Arequipa, Arequipa, Perú
4 shared publications - Giuliana Feliciano-Yucra
Universidad Nacional de San Agustín de Arequipa
4 shared publications Victor Hugo Rosas-Iman
Universidad Nacional de San Agustn de Arequipa, Arequipa, Peru
4 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by Elsevier in Social Sciences & Humanities Open
- Vol. 14
Immersive virtual reality for qualitative fieldwork training in doctoral Education: A quasi-experimental mixed-methods study
- 28 October 2026
- Published by Elsevier in Social Sciences & Humanities Open
- Vol. 14
Open AccessImmersive virtual reality for qualitative fieldwork training in doctoral Education: A quasi-experimental mixed-methods study
- 8 August 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (6) , 680
Artificial Intelligence Literacy and Metacognitive Self-Regulation in Immersive Virtual Reality Environments with Haptic Interaction for Teacher Education
- 8 August 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (6) , 680
Artificial Intelligence Literacy and Metacognitive Self-Regulation in Immersive Virtual Reality Environments with Haptic Interaction for Teacher Education
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 21, 356-364
Digital Competence Development Through AI-Supported Teaching Models in Higher Education: A Quasi-Experimental Study
Artificial intelligence (AI) has progressively transformed higher education by enabling personalized and interactive learning experiences. However, there is still limited empirical evidence on the effectiveness of structured AI-supported pedagogical models in the development of digital competence. The objective of the study was to determine the impact of an AI-supported teaching model on the development of digital competence in university students. A quasi-experimental design with pretest–posttest and a control group was employed, with a sample of 120 students. The experimental group participated in a structured instructional model based on the guided use of generative AI tools, while the control group followed a traditional approach. A validated instrument based on the DigCompEdu framework was used, evaluating five dimensions: Information literacy, digital communication, content creation, security, and problem solving. The results showed statistically significant improvements in all dimensions in the experimental group compared to the control group (p < 0.001). Mean scores increased from approximately 3.0 to 3.8 in the experimental group, while the control group showed minimal improvements. High effect sizes were identified (Cohen’s d = 1.7–1.8), indicating a significant impact of the intervention. In conclusion, structured AI-supported pedagogical models significantly improve digital competence in higher education, highlighting the importance of integrating AI through guided and well-founded pedagogical approaches.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 21, 356-364
Digital Competence Development Through AI-Supported Teaching Models in Higher Education: A Quasi-Experimental Study
Artificial intelligence (AI) has progressively transformed higher education by enabling personalized and interactive learning experiences. However, there is still limited empirical evidence on the effectiveness of structured AI-supported pedagogical models in the development of digital competence. The objective of the study was to determine the impact of an AI-supported teaching model on the development of digital competence in university students. A quasi-experimental design with pretest–posttest and a control group was employed, with a sample of 120 students. The experimental group participated in a structured instructional model based on the guided use of generative AI tools, while the control group followed a traditional approach. A validated instrument based on the DigCompEdu framework was used, evaluating five dimensions: Information literacy, digital communication, content creation, security, and problem solving. The results showed statistically significant improvements in all dimensions in the experimental group compared to the control group (p < 0.001). Mean scores increased from approximately 3.0 to 3.8 in the experimental group, while the control group showed minimal improvements. High effect sizes were identified (Cohen’s d = 1.7–1.8), indicating a significant impact of the intervention. In conclusion, structured AI-supported pedagogical models significantly improve digital competence in higher education, highlighting the importance of integrating AI through guided and well-founded pedagogical approaches.
- 17 February 2026
- Published by Springer Nature
- p. 3-20
Immersive Virtual Reality with Haptic Feedback for Software Evaluation Skills
- 17 February 2026
- Published by Springer Nature
- p. 3-20
Immersive Virtual Reality with Haptic Feedback for Software Evaluation Skills
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 21, 558-568
A Multimodal Immersive Intervention for Artificial Intelligence Literacy and Metacognitive Self-Regulation in Pre-Service Teacher Education
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 21, 558-568
A Multimodal Immersive Intervention for Artificial Intelligence Literacy and Metacognitive Self-Regulation in Pre-Service Teacher Education
- Open Access
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (8) , 1544-1556
A Low-cost Ergonomic Device for Banknote Recognition Using Computer Vision and IoT
This study presents the design, implementation, and validation of a low-cost ergonomic assistive device for autonomous recognition of Peruvian banknotes using computer vision and Internet of Things (IoT) technologies. A dataset of 9054 images distributed across 16 classes was constructed to train and evaluate five pretrained convolutional Neural Network (CNN) architectures: Visual Geometry Group 16-layer network (VGG16), Visual Geometry Group 19-layer network (VGG19), 50-layer Residual Network (ResNet50), MobileNet version 2 (MobileNetV2), and Extreme Inception (Xception). Among these models, Xception achieved the best performance, with 99.8% test accuracy, macro-averaged precision of 0.997, macro-averaged recall of 0.997, and macro-averaged F1-Score of 0.997. Five-fold cross-validation confirmed the model’s stability, yielding a mean accuracy of 99.68% with a standard deviation of 0.12 percentage points. Robustness tests under low-light conditions, partial occlusion, and folded banknote scenarios showed recognition performance above 96%. The selected model was deployed on a Raspberry Pi 4B+ IoT platform with audio feedback. Hardware benchmarking reported an average inference time of 3.82 ± 0.27 s and 3.2 h of battery autonomy. Usability evaluation with 44 visually impaired participants produced a System Usability Scale (SUS) score above 80 and high User Experience Questionnaire (UEQ) ratings. The economic feasibility analysis, including sensitivity scenarios, confirmed financial sustainability, with an Internal Rate of Return (IRR) of 11.85% and a Net Present Value (NPV) of 13,013.02 Peruvian soles (S/). Ethical approval was obtained, and informed consent procedures were completed. These findings demonstrate that the proposed assistive device is technically robust, socially relevant, and economically viable.
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (8) , 1544-1556
Open AccessA Low-cost Ergonomic Device for Banknote Recognition Using Computer Vision and IoT
This study presents the design, implementation, and validation of a low-cost ergonomic assistive device for autonomous recognition of Peruvian banknotes using computer vision and Internet of Things (IoT) technologies. A dataset of 9054 images distributed across 16 classes was constructed to train and evaluate five pretrained convolutional Neural Network (CNN) architectures: Visual Geometry Group 16-layer network (VGG16), Visual Geometry Group 19-layer network (VGG19), 50-layer Residual Network (ResNet50), MobileNet version 2 (MobileNetV2), and Extreme Inception (Xception). Among these models, Xception achieved the best performance, with 99.8% test accuracy, macro-averaged precision of 0.997, macro-averaged recall of 0.997, and macro-averaged F1-Score of 0.997. Five-fold cross-validation confirmed the model’s stability, yielding a mean accuracy of 99.68% with a standard deviation of 0.12 percentage points. Robustness tests under low-light conditions, partial occlusion, and folded banknote scenarios showed recognition performance above 96%. The selected model was deployed on a Raspberry Pi 4B+ IoT platform with audio feedback. Hardware benchmarking reported an average inference time of 3.82 ± 0.27 s and 3.2 h of battery autonomy. Usability evaluation with 44 visually impaired participants produced a System Usability Scale (SUS) score above 80 and high User Experience Questionnaire (UEQ) ratings. The economic feasibility analysis, including sensitivity scenarios, confirmed financial sustainability, with an Internal Rate of Return (IRR) of 11.85% and a Net Present Value (NPV) of 13,013.02 Peruvian soles (S/). Ethical approval was obtained, and informed consent procedures were completed. These findings demonstrate that the proposed assistive device is technically robust, socially relevant, and economically viable.
- Open Access
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (8) , 1429-1441
Explainable Machine Learning for Household Electricity Demand Forecasting Using Hybrid Residual Modeling
This study proposes an interpretable hybrid residual learning framework for household electricity demand prediction under limited data conditions. The framework integrates statistical forecasting models with machine learning residual learners and SHapley Additive exPlanations (SHAP)-based explainability to improve predictive accuracy while preserving transparency. Using 1,000 hourly household electricity consumption observations collected over approximately 41.7 consecutive days, the proposed model was compared with Linear Regression, Autoregressive Integrated Moving Average (ARIMA), Random Forest, Support Vector Machine, and Deep Neural Network baselines under identical chronological train-validation-test conditions. Results show that the hybrid framework achieved the best predictive performance, with Mean Absolute Error (MAE) = 0.141, Root Mean Squared Error (RMSE) = 0.198, Mean Absolute Percentage Error (MAPE) = 7.5%, and Coefficient of Determination (R²) = 0.90, outperforming both statistical and standalone machine learning models. The results are interpreted within a short-term limited-data forecasting scenario. Although the proposed framework showed the best performance on the independent chronological test set, robustness under progressive training-data reduction is considered a direction for future validation because the available dataset contains only 1,000 hourly observations, while statistical comparison was performed using the Diebold-Mariano test. SHAP explanations identified temperature, hour-of-day patterns, and household occupancy as the most influential demand drivers, providing physically meaningful insights for residential energy planning. The findings suggest that interpretable hybrid residual models represent a reliable alternative for short-term household electricity forecasting in data-scarce urban environments.
- 1 January 2026
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 17 (8) , 1429-1441
Open AccessExplainable Machine Learning for Household Electricity Demand Forecasting Using Hybrid Residual Modeling
This study proposes an interpretable hybrid residual learning framework for household electricity demand prediction under limited data conditions. The framework integrates statistical forecasting models with machine learning residual learners and SHapley Additive exPlanations (SHAP)-based explainability to improve predictive accuracy while preserving transparency. Using 1,000 hourly household electricity consumption observations collected over approximately 41.7 consecutive days, the proposed model was compared with Linear Regression, Autoregressive Integrated Moving Average (ARIMA), Random Forest, Support Vector Machine, and Deep Neural Network baselines under identical chronological train-validation-test conditions. Results show that the hybrid framework achieved the best predictive performance, with Mean Absolute Error (MAE) = 0.141, Root Mean Squared Error (RMSE) = 0.198, Mean Absolute Percentage Error (MAPE) = 7.5%, and Coefficient of Determination (R²) = 0.90, outperforming both statistical and standalone machine learning models. The results are interpreted within a short-term limited-data forecasting scenario. Although the proposed framework showed the best performance on the independent chronological test set, robustness under progressive training-data reduction is considered a direction for future validation because the available dataset contains only 1,000 hourly observations, while statistical comparison was performed using the Diebold-Mariano test. SHAP explanations identified temperature, hour-of-day patterns, and household occupancy as the most influential demand drivers, providing physically meaningful insights for residential energy planning. The findings suggest that interpretable hybrid residual models represent a reliable alternative for short-term household electricity forecasting in data-scarce urban environments.
- Open Access
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Evaluation and Research in Education (IJERE)
- Vol. 14 (6) , 5054-5066
Emotional intelligence in teaching: a key to performance and institutional climate in basic education
This study addresses the lack of understanding regarding the relationship between emotional intelligence (EI), teaching performance, and institutional climate (IC) in basic education. As a solution, the study proposes evaluating and strengthening teachers’ EI to enhance both their performance and the school environment. Using a quantitative, non-experimental, correlational design, the research analyzed a randomly selected sample of 145 teachers. Validated questionnaires measured dimensions such as self-awareness, self-regulation, motivation, empathy, and social skills, as well as teaching preparation and IC. The results reveal significant positive correlations between EI and IC (r=0.85) and between teaching performance and IC (r=0.78). This suggests that higher EI not only improves teaching effectiveness but also fosters a positive institutional environment. The study concludes that enhancing teachers’ EI can optimize both their performance and institutional dynamics, contributing to higher-quality education. The findings support the implementation of EI training programs as a key strategy to improve teaching performance and the school climate (SC).
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Evaluation and Research in Education (IJERE)
- Vol. 14 (6) , 5054-5066
Open AccessEmotional intelligence in teaching: a key to performance and institutional climate in basic education
This study addresses the lack of understanding regarding the relationship between emotional intelligence (EI), teaching performance, and institutional climate (IC) in basic education. As a solution, the study proposes evaluating and strengthening teachers’ EI to enhance both their performance and the school environment. Using a quantitative, non-experimental, correlational design, the research analyzed a randomly selected sample of 145 teachers. Validated questionnaires measured dimensions such as self-awareness, self-regulation, motivation, empathy, and social skills, as well as teaching preparation and IC. The results reveal significant positive correlations between EI and IC (r=0.85) and between teaching performance and IC (r=0.78). This suggests that higher EI not only improves teaching effectiveness but also fosters a positive institutional environment. The study concludes that enhancing teachers’ EI can optimize both their performance and institutional dynamics, contributing to higher-quality education. The findings support the implementation of EI training programs as a key strategy to improve teaching performance and the school climate (SC).
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 20, 401-411
Virtual Reality With Sensory Feedback Gloves: A Pedagogical Strategy for Medical Training
This study explores the pedagogical potential of integrating haptic glove technology within immersive virtual reality environments for medical training. A quasi-experimental design was conducted with 50 second-year medical students from a private university in Arequipa, randomly assigned to control and experimental groups. The experimental group participated in three 90-minute sessions over two weeks, using Hi5 Noitom 2.0 gloves and VR platforms (Hand Physics Lab and VR Surgery Simulator) to perform tasks such as suturing, forceps manipulation, and anatomical palpation. Three validated instruments were employed, a psychomotor rubric, a self-assessment questionnaire, and an observation checklist, all demonstrating strong reliability (α = 0.83–0.88). Statistical analyses (independent samples t-tests, ANCOVA, and repeated-measures ANOVA) revealed significant improvements (p < 0.001) in movement precision, visuomotor coordination, technical sequencing, execution time, safety, and feedback in the experimental group, supported by large effect sizes (η² up to 0.86). Students also reported higher confidence and motivation, reflecting both objective and perceived benefits. Under controlled exploratory conditions, these findings suggest that haptic-feedback VR environments can foster realistic, safe, and engaging learning experiences that support the development of psychomotor competencies. The study highlights the pedagogical promise of immersive simulation as a complementary tool to traditional instruction and recommends future longitudinal and multi-site research to validate and generalize the results.
- 19 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Revista Iberoamericana de Tecnologias del Aprendizaje
- Vol. 20, 401-411
Virtual Reality With Sensory Feedback Gloves: A Pedagogical Strategy for Medical Training
This study explores the pedagogical potential of integrating haptic glove technology within immersive virtual reality environments for medical training. A quasi-experimental design was conducted with 50 second-year medical students from a private university in Arequipa, randomly assigned to control and experimental groups. The experimental group participated in three 90-minute sessions over two weeks, using Hi5 Noitom 2.0 gloves and VR platforms (Hand Physics Lab and VR Surgery Simulator) to perform tasks such as suturing, forceps manipulation, and anatomical palpation. Three validated instruments were employed, a psychomotor rubric, a self-assessment questionnaire, and an observation checklist, all demonstrating strong reliability (α = 0.83–0.88). Statistical analyses (independent samples t-tests, ANCOVA, and repeated-measures ANOVA) revealed significant improvements (p < 0.001) in movement precision, visuomotor coordination, technical sequencing, execution time, safety, and feedback in the experimental group, supported by large effect sizes (η² up to 0.86). Students also reported higher confidence and motivation, reflecting both objective and perceived benefits. Under controlled exploratory conditions, these findings suggest that haptic-feedback VR environments can foster realistic, safe, and engaging learning experiences that support the development of psychomotor competencies. The study highlights the pedagogical promise of immersive simulation as a complementary tool to traditional instruction and recommends future longitudinal and multi-site research to validate and generalize the results.