La prédiction des Maladies Basée sur les Symptômes à l’Aide de l’apprentissage Automatique

dc.contributor.authorBENSACI SAHRA
dc.contributor.authorKHRAMSSIA NOUR EL HOUDA
dc.date.accessioned2023-09-14T08:32:17Z
dc.date.available2023-09-14T08:32:17Z
dc.date.issued2023
dc.description.abstractDetecting disease before it occurs is one of the most important factors in medical treatment. In recent years, the medical field has seen a huge expansion in the field of computer science, such as machine learning and deep learning, these modern techniques have been widely used to detect various diseases. This preventive procedure is essential to treat diseases at an early stage before they develop into more devastating diseases. The objective of our project is the detection of diseases using supervised machine learning methods. To do this, we used four supervised classification algorithms: Support Vector Machine (SVM), Decision Tree (DT), K-nearest neighbors (KNN) and Logistic regression (LR), to find the one with the highest performance. The selected algorithms are used for the prediction of two diseases: diabetes and heart disease. The obtained results prove the efficiency of our improved algorithms. Specially, KNN who got the best performance. يعد اكتشاف المرض قبل حدوثه من أهم العوامل في العلاج الطبي. في السنوات الأخيرة، شهد المجال الطبي توسعًا هائلاً في مجال علوم الكمبيوتر، مثل التعلم الآلي والتعلم العميق، وقد تم استخدام هذه التقنيات الحديثة على نطاق واسع للكشف عن الأمراض المختلفة. هذا الإجراء الوقائي ضروري لعلاج الأمراض في مرحلة مبكرة قبل أن تتطور إلى أمراض أكثر تدميراً. الهدف من مشروعنا هو الكشف عن الأمراض باستخدام طرق التعلم الآلي الخاضعة للإشراف. للقيام بذلك، استخدمنا أربع خوارزميات تصنيف خاضعة للإشراف: دعم آلة المتجهات ) SVM ( ، شجرة القرار ( DT ( ، خوارزمية أقرب جيران K (KNN) والانحدار اللوجستي ) LR ( ، للتعرف على أحسن خوارزمي من حيث الأداء. استخدمت الخوارزميات المختارة للتنبؤ بمرضين: مرض السكري وأمراض القلب. النتائج التي تم الحصول عليها تثبت كفاءة خوارزمياتنا المحسنة. على وجه الخصوص، KNN الذي حصل على أفضل أداء Detecting disease before it occurs is one of the most important factors in medical treatment. In recent years, the medical field has seen a huge expansion in the field of computer science, such as machine learning and deep learning, these modern techniques have been widely used to detect various diseases. This preventive procedure is essential to treat diseases at an early stage before they develop into more devastating diseases. The objective of our project is the detection of diseases using supervised machine learning methods. To do this, we used four supervised classification algorithms: Support Vector Machine (SVM), Decision Tree (DT), K-nearest neighbors (KNN) and Logistic regression (LR), to find the one with the highest performance. The selected algorithms are used for the prediction of two diseases: diabetes and heart disease. The obtained results prove the efficiency of our improved algorithms. Specially, KNN who got the best performanceen_US
dc.identifier.issnMM/7762
dc.identifier.urihttp://10.10.1.6:4000/handle/123456789/3863
dc.language.isofren_US
dc.publisherUNIVERSITY BBAen_US
dc.subjectApprentissage automatique, prédiction, classificationen_US
dc.subjectmachine learning, prediction, classificationen_US
dc.subjectالتعلم الآلي، التنبؤ، التصنيفen_US
dc.titleLa prédiction des Maladies Basée sur les Symptômes à l’Aide de l’apprentissage Automatiqueen_US
dc.typeThesisen_US

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
mémoire.pdf
Size:
2.39 MB
Format:
Adobe Portable Document Format
Description:
Thumbnail Image
Name:
mémoire.pdf
Size:
2.39 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description: