Mahfuz Ashraf
Mahfuz Ashraf has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Thai Son Chu
AIBI Higher Education Australia, Haymarket, NSW 2000, Australia
3 shared publications
Latest Publications
- Top Cited PapersOpen Access
Artificial Intelligence in Curriculum Design: A Data-Driven Approach to Higher Education Innovation
This paper shows that artificial intelligence is fundamentally transforming college curricula by enabling data-driven personalization, which enhances student outcomes and better aligns educational programs with evolving workforce demands. Specifically, predictive analytics, machine learning algorithms, and natural language processing were applied here, grounded in constructivist learning theory and Human–Computer Interaction principles, to evaluate student performance and identify at-risk students to propose personalized learning pathways. Results indicated that the AI-based curriculum achieved much higher course completion rates (89.72%) as well as retention (91.44%) and dropout rates (4.98%) compared to the traditional model. Sentiment analysis of learner feedback showed a more positive learning experience, while regression and ANOVA analyses proved the impact of AI on enhancing academic performance to be real. Therefore, the learning content delivery for each student was continuously improved based on individual learner characteristics and industry trends by AI-enabled recommender systems and adaptive learning models. Its advantages notwithstanding, the study emphasizes the need to address ethical concerns, ensure data privacy safeguards, and mitigate algorithmic bias before an equitable outcome can be claimed. These findings can inform institutions aspiring to adopt AI-driven models for curriculum innovation to build a more dynamic, responsive, and learner-centered educational ecosystem.
Top Cited PapersOpen AccessArtificial Intelligence in Curriculum Design: A Data-Driven Approach to Higher Education Innovation
This paper shows that artificial intelligence is fundamentally transforming college curricula by enabling data-driven personalization, which enhances student outcomes and better aligns educational programs with evolving workforce demands. Specifically, predictive analytics, machine learning algorithms, and natural language processing were applied here, grounded in constructivist learning theory and Human–Computer Interaction principles, to evaluate student performance and identify at-risk students to propose personalized learning pathways. Results indicated that the AI-based curriculum achieved much higher course completion rates (89.72%) as well as retention (91.44%) and dropout rates (4.98%) compared to the traditional model. Sentiment analysis of learner feedback showed a more positive learning experience, while regression and ANOVA analyses proved the impact of AI on enhancing academic performance to be real. Therefore, the learning content delivery for each student was continuously improved based on individual learner characteristics and industry trends by AI-enabled recommender systems and adaptive learning models. Its advantages notwithstanding, the study emphasizes the need to address ethical concerns, ensure data privacy safeguards, and mitigate algorithmic bias before an equitable outcome can be claimed. These findings can inform institutions aspiring to adopt AI-driven models for curriculum innovation to build a more dynamic, responsive, and learner-centered educational ecosystem.
- Open Access
- 2 May 2025
- Published by MDPI AG in Preprints.org
Artificial Intelligence in Curriculum Design: A Data-Driven Approach to Higher Education Innovation
This paper presents evidence that Artificial Intelligence has fundamentally reshaped college curricula by promoting a data-driven personalization approach that improves student outcomes and aligns educational programs with workforce needs. Specifically, predictive analytics, machine learning algorithms, and natural language processing were applied here to evaluate student performance and identify at-risk students to propose personalized learning pathways. Results indicated that AI-based curriculum achieved much higher course completion rates (89.72%) as well as retention (91.44%) and dropout rates (4.98%) compared to the traditional model. Sentiment analysis of learner feedback showed a more positive learning experience, while regression and ANOVA analyses proved the impact of AI on enhancing academic performance to be real. Learning content delivery for each student was therefore continuously improved based on individual learner characteristics and industry trends by AI-enabled recommender systems and adaptive learning models. Its advantages notwithstanding, the study emphasizes the need to address ethical concerns, ensure data privacy safeguards, and mitigate algorithmic bias before an equitable outcome can be claimed. These findings can inform institutions aspiring to adopt AI-driven models for curriculum innovation to build a more dynamic, responsive, and learner-centered educational ecosystem.
- 2 May 2025
- Published by MDPI AG in Preprints.org
Open AccessArtificial Intelligence in Curriculum Design: A Data-Driven Approach to Higher Education Innovation
This paper presents evidence that Artificial Intelligence has fundamentally reshaped college curricula by promoting a data-driven personalization approach that improves student outcomes and aligns educational programs with workforce needs. Specifically, predictive analytics, machine learning algorithms, and natural language processing were applied here to evaluate student performance and identify at-risk students to propose personalized learning pathways. Results indicated that AI-based curriculum achieved much higher course completion rates (89.72%) as well as retention (91.44%) and dropout rates (4.98%) compared to the traditional model. Sentiment analysis of learner feedback showed a more positive learning experience, while regression and ANOVA analyses proved the impact of AI on enhancing academic performance to be real. Learning content delivery for each student was therefore continuously improved based on individual learner characteristics and industry trends by AI-enabled recommender systems and adaptive learning models. Its advantages notwithstanding, the study emphasizes the need to address ethical concerns, ensure data privacy safeguards, and mitigate algorithmic bias before an equitable outcome can be claimed. These findings can inform institutions aspiring to adopt AI-driven models for curriculum innovation to build a more dynamic, responsive, and learner-centered educational ecosystem.
- Open Access
- 26 September 2024
- Published by Dewspublication
- Vol. 20 (S12) , 753-765
Detecting Intrusion In Internet Of Things (Iot) With Deep Learning Bi-Directional Recurrent Neural Network (BRNN)
Distributed Denial of Service (DDoS) attacks could lead to enormous problems, which raises important security issues in many organizations and corporations. By using Bi-directional Long Short-Term Memory Recurrent Neural Network (BLSTM RNN), this paper presents a novel deep learning technique for detecting DDoS attacks within the networks. To achieve highly effective intrusion detection models, we first train our deep learning neural network with multiple layers using a benchmark data set, CICDDOS2019. We examine the binary classification of normal and attack patterns on the web. The result of the experiment shows that our proposed model achieves excellent outcomes in precision, recall, F-1 score, and FPR. Our proposed BLSTM RNN model can detect attacks with over 98% accuracy on practical data sets, better than other Kumar models (31) and even our previous model (30).
- 26 September 2024
- Published by Dewspublication
- Vol. 20 (S12) , 753-765
Open AccessDetecting Intrusion In Internet Of Things (Iot) With Deep Learning Bi-Directional Recurrent Neural Network (BRNN)
Distributed Denial of Service (DDoS) attacks could lead to enormous problems, which raises important security issues in many organizations and corporations. By using Bi-directional Long Short-Term Memory Recurrent Neural Network (BLSTM RNN), this paper presents a novel deep learning technique for detecting DDoS attacks within the networks. To achieve highly effective intrusion detection models, we first train our deep learning neural network with multiple layers using a benchmark data set, CICDDOS2019. We examine the binary classification of normal and attack patterns on the web. The result of the experiment shows that our proposed model achieves excellent outcomes in precision, recall, F-1 score, and FPR. Our proposed BLSTM RNN model can detect attacks with over 98% accuracy on practical data sets, better than other Kumar models (31) and even our previous model (30).