Moad Hicham Safhi
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
Moad Hicham Safhi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Diego Hernán Peluffo Ordoñez
Corporación Universitaria Autónoma de Nariño, Pasto, Colombia; Ecotec University, Guayaquil, Ecuador; School of Mathematical Sciences and Computational Sciences, Yachay University, Urcuquí, Ecuador; Universidad ECOTEC, Samborondón, Ecuador; Faculty of Engineering, Corporación Universitaria Autónoma de Nariño;, Nariño, Ecuador, Ecuador
3 shared publications Bouchra Frikh
Sidi Mohammed Ben Abdellah University Fez,LIASSE Lab,Morocco
2 shared publicationsBrahim Ouhbi
ENSAM, Moulay Ismail University Meknes,LM2I Lab,Morocco
2 shared publications- Diego Peña
Faculty of Engineering Sciences, Technical State University of Quevedo, Quevedo 120301, Ecuador
2 shared publications - Fernando Ortega-Loza
Departamento de Ciencias de la Energía y Mecánica, Universidad de las Fuerzas Armadas ESPE, Av. Gral. Rumiñahui s/n, Sangolquí 171103, Ecuador
2 shared publications - Fernando Toapanta-Ramos
Mechanical Engineering, Research Group in Engineering, Productivity and Industrial Simulation (GIIPSI), Master’s Program in Mechanical Engineering, Universidad Politécnica Salesiana, Quito 170702, Ecuador
2 shared publications
Latest Publications
- Open Access
- 29 July 2026
- Published by MDPI AG in Horticulturae
- Vol. 12 (8) , 935
Decoupled Geometric Measurement and Machine Learning Classification for Automated Post-Harvest Quality Assessment of Ruscus hypophyllum Foliage
This paper presents a hybrid computer vision framework that explicitly decouples geometric stem measurement from visual foliage condition classification for automated post-harvest quality assessment of Ruscus hypophyllum ornamental foliage. The proposed approach addresses a gap in the literature where heterogeneous quality attributes are typically treated within a single unified learning framework. In the first stage, stem size is estimated using a pixel-based geometric method that incorporates trigonometric orientation correction and spatial calibration via a reference marker of known length, enabling accurate conversion of image measurements to real-world physical dimensions. In the second stage, foliage condition is classified as good or poor using supervised machine learning models trained on Bag of Features representations extracted with the SIFT descriptor. A dataset of 1233 Ruscus hypophyllum images was acquired under controlled conditions using a consumer-grade smartphone camera and processed using open-source Python 3.11 libraries. Twenty-four classifier configurations across six model families were evaluated using stratified 10-fold cross-validation. The geometric estimation stage achieved a Mean Absolute Error (MAE) of 1.2 mm, a Root Mean Square Error (RMSE) of approximately 1.3 mm, and a size categorization accuracy of 99.84%. For foliage condition classification, the Linear Support Vector Machine achieved the best performance, with an accuracy of % and an F1-score of %, outperforming all other evaluated configurations. The proposed framework provides an interpretable, computationally efficient, and accessible solution for automated foliage quality grading, with potential applications in export-oriented ornamental foliage processing facilities.- 29 July 2026
- Published by MDPI AG in Horticulturae
- Vol. 12 (8) , 935
Open AccessDecoupled Geometric Measurement and Machine Learning Classification for Automated Post-Harvest Quality Assessment of Ruscus hypophyllum Foliage
This paper presents a hybrid computer vision framework that explicitly decouples geometric stem measurement from visual foliage condition classification for automated post-harvest quality assessment of Ruscus hypophyllum ornamental foliage. The proposed approach addresses a gap in the literature where heterogeneous quality attributes are typically treated within a single unified learning framework. In the first stage, stem size is estimated using a pixel-based geometric method that incorporates trigonometric orientation correction and spatial calibration via a reference marker of known length, enabling accurate conversion of image measurements to real-world physical dimensions. In the second stage, foliage condition is classified as good or poor using supervised machine learning models trained on Bag of Features representations extracted with the SIFT descriptor. A dataset of 1233 Ruscus hypophyllum images was acquired under controlled conditions using a consumer-grade smartphone camera and processed using open-source Python 3.11 libraries. Twenty-four classifier configurations across six model families were evaluated using stratified 10-fold cross-validation. The geometric estimation stage achieved a Mean Absolute Error (MAE) of 1.2 mm, a Root Mean Square Error (RMSE) of approximately 1.3 mm, and a size categorization accuracy of 99.84%. For foliage condition classification, the Linear Support Vector Machine achieved the best performance, with an accuracy of % and an F1-score of %, outperforming all other evaluated configurations. The proposed framework provides an interpretable, computationally efficient, and accessible solution for automated foliage quality grading, with potential applications in export-oriented ornamental foliage processing facilities. - Open Access
- 23 June 2026
- Published by MDPI AG in Preprints.org
Decoupled Geometric Measurement and Machine Learning Classification for Automated Post-Harvest Quality Assessment of Ruscus hypophyllum Foliage
This paper presents a hybrid computer vision framework that explicitly decouples geometric stem measurement from visual foliage condition classification for automated post-harvest quality assessment of Ruscus hypophyllum ornamental foliage. The proposed approach addresses a gap in the literature where heterogeneous quality attributes are typically treated within a single unified learning framework. In the first stage, stem size is estimated using a pixel-based geometric method that incorporates trigonometric orientation correction and spatial calibration via a reference marker of known length, enabling accurate conversion of image measurements to real-world physical dimensions. In the second stage, foliage condition is classified as good or poor using supervised machine learning models trained on Bag of Features representations extracted with the SIFT descriptor. A dataset of 1,233 Ruscus hypophyllum images was acquired under controlled conditions using a consumer-grade smartphone camera and processed using open-source Python libraries. Twenty-four classifier configurations across six model families were evaluated using stratified 10-fold cross-validation. The geometric estimation stage achieved a Mean Absolute Error (MAE) of 1.2 mm, a Root Mean Square Error (RMSE) of approximately 1.3 mm, and a size categorization accuracy of 99.84%. For foliage condition classification, the Linear Support Vector Machine achieved the best performance, with an accuracy of 92.4 ± 1.0% and an F1-score of 91.1±1.2%, outperforming all other evaluated configurations. The proposed framework provides an interpretable, computationally efficient, and accessible solution for automated foliage quality grading, with potential applications in export-oriented ornamental foliage processing facilities.
- 23 June 2026
- Published by MDPI AG in Preprints.org
Open AccessDecoupled Geometric Measurement and Machine Learning Classification for Automated Post-Harvest Quality Assessment of Ruscus hypophyllum Foliage
This paper presents a hybrid computer vision framework that explicitly decouples geometric stem measurement from visual foliage condition classification for automated post-harvest quality assessment of Ruscus hypophyllum ornamental foliage. The proposed approach addresses a gap in the literature where heterogeneous quality attributes are typically treated within a single unified learning framework. In the first stage, stem size is estimated using a pixel-based geometric method that incorporates trigonometric orientation correction and spatial calibration via a reference marker of known length, enabling accurate conversion of image measurements to real-world physical dimensions. In the second stage, foliage condition is classified as good or poor using supervised machine learning models trained on Bag of Features representations extracted with the SIFT descriptor. A dataset of 1,233 Ruscus hypophyllum images was acquired under controlled conditions using a consumer-grade smartphone camera and processed using open-source Python libraries. Twenty-four classifier configurations across six model families were evaluated using stratified 10-fold cross-validation. The geometric estimation stage achieved a Mean Absolute Error (MAE) of 1.2 mm, a Root Mean Square Error (RMSE) of approximately 1.3 mm, and a size categorization accuracy of 99.84%. For foliage condition classification, the Linear Support Vector Machine achieved the best performance, with an accuracy of 92.4 ± 1.0% and an F1-score of 91.1±1.2%, outperforming all other evaluated configurations. The proposed framework provides an interpretable, computationally efficient, and accessible solution for automated foliage quality grading, with potential applications in export-oriented ornamental foliage processing facilities.
- 25 August 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (7) , 1-10
Evaluating the RISCV-EC: A Comparative Analysis of Instruction Efficiency and Power Performance for Edge Computing
- 25 August 2025
- Published by Springer Nature in SN Computer Science
- Vol. 6 (7) , 1-10
Evaluating the RISCV-EC: A Comparative Analysis of Instruction Efficiency and Power Performance for Edge Computing
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 72, 1-6
Energy load forecasting in big data context
Smart grid is now making a significant impact on energy management. In fact, adding smart meters to the power grid allow a better system monitoring and control. In addition, it has also allowed a variety of data to be captured. Handling consumers needs is beneficial for a wise energy production and consumption. However, a challenging task in energy management concerns estimating the future energy demand of consumers, especially when consumers change their behavior. A key element to tackle this issue, is by analyzing smart grid data, and discovering hidden patterns and factors that can effectively be used to predict energy consumption. In this paper, we are interested in the effect of external variables on energy consumption. We first present the state of art of energy load forecasting approaches, also highlight the challenges associated with big energy data. Then we provide a comparison of machine learning approaches for energy load production in a big data context. Experimental results show the contribution of external variables on the model’s accuracy and interpretability.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 72, 1-6
Energy load forecasting in big data context
Smart grid is now making a significant impact on energy management. In fact, adding smart meters to the power grid allow a better system monitoring and control. In addition, it has also allowed a variety of data to be captured. Handling consumers needs is beneficial for a wise energy production and consumption. However, a challenging task in energy management concerns estimating the future energy demand of consumers, especially when consumers change their behavior. A key element to tackle this issue, is by analyzing smart grid data, and discovering hidden patterns and factors that can effectively be used to predict energy consumption. In this paper, we are interested in the effect of external variables on energy consumption. We first present the state of art of energy load forecasting approaches, also highlight the challenges associated with big energy data. Then we provide a comparison of machine learning approaches for energy load production in a big data context. Experimental results show the contribution of external variables on the model’s accuracy and interpretability.
- Open Access
- 2 December 2019
- Published by Association for Computing Machinery (ACM)
- p. 611-616
Data Source Selection in Big Data Context
- 2 December 2019
- Published by Association for Computing Machinery (ACM)
- p. 611-616
Open AccessData Source Selection in Big Data Context
- Open Access
- 1 January 2019
- Published by Elsevier in Procedia Computer Science
- Vol. 148, 30-36
Assessing reliability of Big Data Knowledge Discovery process
- 1 January 2019
- Published by Elsevier in Procedia Computer Science
- Vol. 148, 30-36
Open AccessAssessing reliability of Big Data Knowledge Discovery process