DeepECG :Building an Efficient Framework for Automatic Arrhythmia classification model

This paper aims to determine the most accurate algorithm for predicting the Egyptian gross domestic product (GDP) and not only and also to determine the relative weight of the effect of the components of the output on it to assist decision-makers in making good economic policies. It turned out that the gradient algorithm is the most accurate and highly efficient algorithm for predicting the Egyptian GDP. It also became clear that government investment is the biggest influence on the Egyptian GDP at 21%, followed by the consumer spending of the family sector at 19%, followed by investment spending by the private sector and imports by the same 15%, then exports and government spending by 14% and 13%, respectively. Thus, to stimulate and maximize the size of the Egyptian GDP, the decision-maker must focus on stimulating government investment spending and consumer spending for the household sector and investment spending for the private sector.

Section: Related Workmentioning

confidence: 99%

Nowcasting Egypt GDP Using machine learning Algorithms

AbdElminaam

El-Aal

abdellatif³

2023

“…For the recommendation portion, they used the ResNet-50 model as their backbone model Dataset for the recommendation part. Also, other related work in [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36] has been proposed in recent years to address machine learning and its application in different fields.…”

Section: Related Workmentioning

confidence: 99%

Fit Moi: Online Virtual Fitting Room With Texture Identification And Recommendation System

AbdElminaam,

mohamed,

osama

et al. 2023

Virtual fitting rooms have attracted the sights of the market need in the past two years; The world faced a colossal pandemic that led everything to be online. This proposed framework aims to solve the online shopping problem using deep learning algorithms and techniques. Users face significant issues, whether finding the perfect fit, recognizing the fabric, or styling their outfits. As a result, merchants' profit is impacted, resulting in a high percentage of returns. This proposed model aims to generate a 3D human model. Based on the measurements extracted from the user's images and the user's weight and height for more accurate results. The user can see how simulated 3D clothes will look on his 3D body model, and Then he will know the exact size that fits him and can view the texture. Finally, the user will have styling tips recommended according to his chosen outfit.

“…They use different approaches, and the SVM has achieved the best results with an accuracy of around 91%. Also, other related work in [19][20][21][22][23][24][25][26][27] has been proposed in recent years to address machine learning and its application in different fields.…”

Section: Related Workmentioning

confidence: 99%

FER_ML: Facial Emotion Recognition using Machine Learning

AbdElminaam

Mostafa

Ghareeb

et al. 2023

Recently, facial recognition has been one of the most crucial technologies people need. Facial recognition has attracted a lot of the crowd; for example, it has been used in security on most modern devices. Using machine and deep learning, overall performance will be improved, and the identification accuracy will be more precise. We aim to discover how well these algorithms perform in classifying human facial expressions and whether or not we can depend on them. The steps are as follows. First, we embed the images from the dataset, then split the dataset into 70% training data and 30% testing data; after that, we apply five different algorithms: Support Vector Machine, K-nearest Neighbor, Logistic Regression, Naive Bayes, and Random Forest. Support Vector Machine achieved an accuracy rate of 36%, K-nearest Neighbor achieved an accuracy rate of 52.3%, Logistic regression achieved an accuracy rate of 64.2%, and Naive Bayes achieved an accuracy rate of 38.1%. Random Forest achieved an accuracy rate of 51.7%. The dataset used was a cleaned version of the FER13 dataset, which contains 16,780 images divided into five classes (angry, happy, neutral, disgust, and fear). The results show that Logistic Regression proved to be the most accurate classifier among the presented ones, with an F1-Score of 63.8% and an accuracy of 64.2%.