عجوة أو مجدول: مجموعة بيانات متوازنة الصنفين لتدريس تعلم الآلة

غسان بن فاروق باتي

Article Details

عجوة أو مجدول: مجموعة بيانات متوازنة الصنفين لتدريس تعلم الآلة

Authors:

غسان بن فاروق باتي

Publisher:

HBKU Press

Journal:

Journal of Information Studies and Technology Issue 2, pp.0-0

Document Type:

Article

Publication Date:

9/2023

Document Language:

Arabic

Document ID (Org No.):

2001939992

pISSN:

2616-4930

Keywords:

Supervised learning, deep learning, image classification, image embedding, dates classification, organic, no code

Abstract:

 Saudi Arabia is one of the world's largest producers of dates. Moreover, Saudi Arabia has been ranked first worldwide in the government strategy index for Artificial Intelligence. Machine learning is also one of the most widespread topics of artificial intelligence and one of the emerging technologies with a potential future paving the way for the fourth industrial revolution. The Saudi government is giving a primary importance to machine-learning teaching to produce a generation capable of creative solutions. However, many of the teaching sources of this discipline are in English, with an apparent lack of Arabic sources. Thus, this paper seeks to bridge this gap by creating a dataset generated from our Saudi environment using two of the easiest data mining platforms: Orange and Teachable Machine and none of them requires programming. This study is the first work to establish a balanced dataset to classify two categories of organic Saudi dates. The dataset contains three subsets: 1) a dataset containing hand-crafted features to classify two types of organic dates (Ajwa or Medjool); 2) a dataset containing tabular data with features created automatically using deep learning to classify the two organic date types (Ajwa or Medjool), and 3) a dataset for images of Ajwa and Medjool dates. In addition, this study is considered the first work in Arabic using shallow machine learning and deep learning to create accurate models for classifying organic Saudi dates, which would enable scholars, researchers, and developers to create machine learning applications for classifying Saudi dates in various forms like websites, mobile apps, microcontrollers, tiny machine learning and internet of things applications.

Article Details

عجوة أو مجدول: مجموعة بيانات متوازنة الصنفين لتدريس تعلم الآلة

Authors: غسان بن فاروق باتي

Publisher: HBKU Press

Journal: Journal of Information Studies and Technology Issue 2, pp.0-0

Document Type: Article

Publication Date: 9/2023

Document Language: Arabic

Document ID (Org No.): 2001939992

pISSN: 2616-4930

Supervised learning, deep learning, image classification, image embedding, dates classification, organic, no code

Issues

Authors:

غسان بن فاروق باتي

Publisher:

HBKU Press

Journal:

Journal of Information Studies and Technology Issue 2, pp.0-0

Document Type:

Article

Publication Date:

9/2023

Document Language:

Arabic

Document ID (Org No.):

2001939992

pISSN:

2616-4930