طراحي و پیاد هسازی نر مافزار مبتني بر هوش مصنوعي جهت انتخاب رژیم تغذیهای شخص يسازیشده برای پرسنل نظام ي
Background and Aim: Given the operational conditions and the need to maintain the physical readiness of military personnel, the use of intelligent systems based on artificial intelligence can facilitate precise and personalized nutrition and dietary planning. By analyzing individuals' clinical and p...
| Publicado en: | Journal of Military Medicine Vol. 27; no. 6; pp. 3093 - 3104 |
|---|---|
| Autores principales: | , |
| Formato: | pictorial research tables/charts Journal Article |
| Publicado: |
Baqiyatallah University of Medical Sciences
Mar/Apr2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194156703&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 194156703 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 17351537 B9ZL jtl: Journal of Military Medicine issn: 17351537 maglogo: N pubinfo: dt: Mar/Apr2026 vid: 27 iid: 6 pid: 63671 pub: Baqiyatallah University of Medical Sciences place: , <Blank> artinfo: ui: 194156703 194156703 194156703 10.30491/jmm.2025.1006930.1385 194156703 ppf: 3093 ppct: 11 formats: tig: atl: طراحي و پیاد هسازی نر مافزار مبتني بر هوش مصنوعي جهت انتخاب رژیم تغذیهای شخص يسازیشده برای پرسنل نظام ي aug: au: علي خلیل ي محمدعباد رفع ت affil: گروه رایانه و سایبر، دانشکده مهندسی و پرواز ، دانشگاه افسری امام عل ی)ع(، تهران، ایرا ن sug: subj: Military Personnel Psychosocial Factors Artificial Intelligence Diet Exercise Software Design Program Development Iran Human Female Male Program Implementation Machine Learning Algorithms Qualitative Studies Descriptive Statistics Correlational Studies Support Vector Machine Neural Networks (Computer) Programming Languages Models, Theoretical Sensitivity and Specificity Nutritional Status Data Mining Decision Support Techniques Military Medicine Female Male ab: Background and Aim: Given the operational conditions and the need to maintain the physical readiness of military personnel, the use of intelligent systems based on artificial intelligence can facilitate precise and personalized nutrition and dietary planning. By analyzing individuals' clinical and physiological status, this system selects the most appropriate dietary pattern from among standard nutritional regimens, thereby contributing to the improvement of health and performance among the forces. This study aimed to design and develop a machine-learning-based system for recommending dietary and exercise programs tailored to the individual conditions of military personnel. Methods: In the first step, a qualitative study based on scientific documents and specialized articles was conducted to identify general indicators influencing dietary determination. In the second step, through consultation with experts in nutrition and military fields, specific components and operational requirements related to the military organization were extracted. In the third step, by designing a dataset consisting of more than 2,700 clinical and operational samples, technical modeling was initiated. During preprocessing, the data were normalized and standardized, and dimensionality reduction of features was performed using correlation analysis and PCA. Three machine learning algorithms, SVM with an RBF kernel, Random Forest, and a neural network, then implemented, and to prevent overfitting, K-Fold Cross Validation was used. In the fourth step, using the Python programming language, a software application executable on the Windows operating system was developed for use by personnel. Results: The results showed that all three models were able to correctly select the appropriate dietary regimen among seven dietary options with an accuracy above 90%. The Random Forest model achieved the best performance with an accuracy of 97% and an F1-score of 0.9726. The neural network achieved an accuracy of 95%, and the SVM model achieved 92%. Error analysis also indicated that the Random Forest algorithm demonstrated higher stability and accuracy in correctly classifying dietary patterns. Conclusion: The findings of this study indicate that integrating clinical data mining with machine learning algorithms can provide a powerful decision-support tool for determining dietary plans in military environments. The proposed model, when implemented as an operational system, can help reduce human error, optimize nutritional resources, and enhance the physical readiness of military personnel. pubtype: Academic Journal doctype: pictorial research tables/charts Journal Article ougenre: Article language: Persian refInfo: holdings: @attributes: islocal: N |
|---|