ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Measure the Difference between Current and Expected Performance Using Machine Learning "For Autonomous Driving Systems"

المصدر: المجلة العربية للنشر العلمي
الناشر: مركز البحث وتطوير الموارد البشرية - رماح
المؤلف الرئيسي: Alghamdi, Ahmad Abdullah (Author)
المجلد/العدد: ع34
محكمة: نعم
الدولة: الأردن
التاريخ الميلادي: 2021
الشهر: آب
الصفحات: 10 - 19
ISSN: 2663-5798
رقم MD: 1435831
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: EduSearch, HumanIndex
مواضيع:
رابط المحتوى:
صورة الغلاف QR قانون
حفظ في:
المستخلص: Measuring the performance of the program is one of the most important stages of testing, as we first test the program to detect problems that may occur to the user in the future, and these problems are the difference between the performance of the program and what is required of it, and we search for the difference and from it the program is evaluated and to measure this difference we need to measure Performance with measurable and comparable measures The problem with this is that we need to measure something qualitative, which is the quality of the program with a quantitative thing, which is its standards, and if the quality is calculated by reducing the difference between what is expected and what is in place, the problem arises in how to define what is expected, especially since the subject goes beyond defining what It is required because the program can have achieved all the points required of it in the current circumstances, but what happens if the circumstances and capabilities change in the future, of course, there are many methods and models that help in evaluating the program’s performance in the future through different tests, but it is not possible to measure all possibilities as well. Using the human element in conducting this research increases the time and cost, especially if it deals with a large number of possibilities and special circumstances Therefore, in this research, we use more effective methods to detect future problems of the system through the use of machine learning to reach the best performance, speed and accuracy as it is less in cost and time.

ISSN: 2663-5798

عناصر مشابهة