Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/4714
Full metadata record
DC FieldValueLanguage
dc.contributorFereshteh Motahari-
dc.contributorSaeed Rouhani-
dc.contributorMohammad Amin Zare-
dc.date.accessioned2023-05-04T17:50:15Z-
dc.date.available2023-05-04T17:50:15Z-
dc.date.issued2016en_US
dc.identifier.otherdoi: 10.5812/ijvlms.12171-
dc.identifier.urihttp://localhost/handle/Hannan/4714-
dc.description.abstractIntroduction: The implementation of smart schools has significantly progressed in current times due to the execution of intelligent systems. School administrators are also seeking the implementation of smart schools so that they can improve their educational process efficiency. The purpose of this research was to design a system recommending smartening mechanisms for use at the current level, and provide recommendations for improving the quality of schools. Methods: This is a design science and survey research. The surveyed population consisted of experts in implementing smart schools in the country. Based on convenience accidental sampling method, 32 experts were elected. In this study, previous works on effective factors for the implementation of smart schools were reviewed and categorized. Using the e-learning maturity model and capability maturity model, some questions were prepared and accordingly, the decision tree was drawn in the identified areas. For proper assessment of performance of the recommender system, a QUIS-based questionnaire was developed and experts’ opinions were collected through it. For greater certainty and assessment of the face and content validity, the relevant opinions were used. The questionnaire’s reliability was calculated using Cronbach’s alpha coefficient (92%). Data analysis was performed using SPSS version 21 and descriptive statistics (mean and SD) as well as inferential statistics (Kolmogorov-Smirnov and Pearson correlation coefficient tests). Results: The results showed that this system had great potential for improving the implementation quality of smart schools such that the weighted average grades rose above the mean (3.95 to 4.187 of 5) in the assessment. Conclusions: With regard to the required training criteria, a model was presented and an expert system was designed to recommend mechanisms for implementing smart schools. Finally, this recommender system was evaluated.en_US
dc.language.isoen_USen_US
dc.subjectArtificial Intelligence, Education, Schools, Decision Treeen_US
dc.titleModel Design and Evaluation for Recommender System of Smart Schools Implementation Mechanisms-
dc.typeArticleen_US
Appears in Collections:مدیریت فناوری اطلاعات

Files in This Item:
File SizeFormat 
47.pdf370.23 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorFereshteh Motahari-
dc.contributorSaeed Rouhani-
dc.contributorMohammad Amin Zare-
dc.date.accessioned2023-05-04T17:50:15Z-
dc.date.available2023-05-04T17:50:15Z-
dc.date.issued2016en_US
dc.identifier.otherdoi: 10.5812/ijvlms.12171-
dc.identifier.urihttp://localhost/handle/Hannan/4714-
dc.description.abstractIntroduction: The implementation of smart schools has significantly progressed in current times due to the execution of intelligent systems. School administrators are also seeking the implementation of smart schools so that they can improve their educational process efficiency. The purpose of this research was to design a system recommending smartening mechanisms for use at the current level, and provide recommendations for improving the quality of schools. Methods: This is a design science and survey research. The surveyed population consisted of experts in implementing smart schools in the country. Based on convenience accidental sampling method, 32 experts were elected. In this study, previous works on effective factors for the implementation of smart schools were reviewed and categorized. Using the e-learning maturity model and capability maturity model, some questions were prepared and accordingly, the decision tree was drawn in the identified areas. For proper assessment of performance of the recommender system, a QUIS-based questionnaire was developed and experts’ opinions were collected through it. For greater certainty and assessment of the face and content validity, the relevant opinions were used. The questionnaire’s reliability was calculated using Cronbach’s alpha coefficient (92%). Data analysis was performed using SPSS version 21 and descriptive statistics (mean and SD) as well as inferential statistics (Kolmogorov-Smirnov and Pearson correlation coefficient tests). Results: The results showed that this system had great potential for improving the implementation quality of smart schools such that the weighted average grades rose above the mean (3.95 to 4.187 of 5) in the assessment. Conclusions: With regard to the required training criteria, a model was presented and an expert system was designed to recommend mechanisms for implementing smart schools. Finally, this recommender system was evaluated.en_US
dc.language.isoen_USen_US
dc.subjectArtificial Intelligence, Education, Schools, Decision Treeen_US
dc.titleModel Design and Evaluation for Recommender System of Smart Schools Implementation Mechanisms-
dc.typeArticleen_US
Appears in Collections:مدیریت فناوری اطلاعات

Files in This Item:
File SizeFormat 
47.pdf370.23 kBAdobe PDF
Full metadata record
DC FieldValueLanguage
dc.contributorFereshteh Motahari-
dc.contributorSaeed Rouhani-
dc.contributorMohammad Amin Zare-
dc.date.accessioned2023-05-04T17:50:15Z-
dc.date.available2023-05-04T17:50:15Z-
dc.date.issued2016en_US
dc.identifier.otherdoi: 10.5812/ijvlms.12171-
dc.identifier.urihttp://localhost/handle/Hannan/4714-
dc.description.abstractIntroduction: The implementation of smart schools has significantly progressed in current times due to the execution of intelligent systems. School administrators are also seeking the implementation of smart schools so that they can improve their educational process efficiency. The purpose of this research was to design a system recommending smartening mechanisms for use at the current level, and provide recommendations for improving the quality of schools. Methods: This is a design science and survey research. The surveyed population consisted of experts in implementing smart schools in the country. Based on convenience accidental sampling method, 32 experts were elected. In this study, previous works on effective factors for the implementation of smart schools were reviewed and categorized. Using the e-learning maturity model and capability maturity model, some questions were prepared and accordingly, the decision tree was drawn in the identified areas. For proper assessment of performance of the recommender system, a QUIS-based questionnaire was developed and experts’ opinions were collected through it. For greater certainty and assessment of the face and content validity, the relevant opinions were used. The questionnaire’s reliability was calculated using Cronbach’s alpha coefficient (92%). Data analysis was performed using SPSS version 21 and descriptive statistics (mean and SD) as well as inferential statistics (Kolmogorov-Smirnov and Pearson correlation coefficient tests). Results: The results showed that this system had great potential for improving the implementation quality of smart schools such that the weighted average grades rose above the mean (3.95 to 4.187 of 5) in the assessment. Conclusions: With regard to the required training criteria, a model was presented and an expert system was designed to recommend mechanisms for implementing smart schools. Finally, this recommender system was evaluated.en_US
dc.language.isoen_USen_US
dc.subjectArtificial Intelligence, Education, Schools, Decision Treeen_US
dc.titleModel Design and Evaluation for Recommender System of Smart Schools Implementation Mechanisms-
dc.typeArticleen_US
Appears in Collections:مدیریت فناوری اطلاعات

Files in This Item:
File SizeFormat 
47.pdf370.23 kBAdobe PDF