In light of the development in computer science and modern technologies, the impersonation crime rate has increased. Consequently, face recognition technology and biometric systems have been employed for security purposes in a variety of applications including human-computer interaction, surveillance systems, etc. Building an advanced sophisticated model to tackle impersonation-related crimes is essential. This study proposes classification Machine Learning (ML) and Deep Learning (DL) models, utilizing Viola-Jones, Linear Discriminant Analysis (LDA), Mutual Information (MI), and Analysis of Variance (ANOVA) techniques. The two proposed facial classification systems are J48 with LDA feature extraction method as input, and a one-dimensional Convolutional Neural Network Hybrid Model (1D-CNNHM). The MUCT database was considered for training and evaluation. The performance, in terms of classification, of the J48 model reached 96.01% accuracy whereas the DL model that merged LDA with MI and ANOVA reached 100% accuracy. Comparing the proposed models with other works reflects that they are performing very well, with high accuracy and low processing time.
A mixture model is used to model data that come from more than one component. In recent years, it became an effective tool in drawing inferences about the complex data that we might come across in real life. Moreover, it can represent a tremendous confirmatory tool in classification observations based on similarities amongst them. In this paper, several mixture regression-based methods were conducted under the assumption that the data come from a finite number of components. A comparison of these methods has been made according to their results in estimating component parameters. Also, observation membership has been inferred and assessed for these methods. The results showed that the flexible mixture model outperformed the others
... Show MoreThe issue of image captioning, which comprises automatic text generation to understand an image’s visual information, has become feasible with the developments in object recognition and image classification. Deep learning has received much interest from the scientific community and can be very useful in real-world applications. The proposed image captioning approach involves the use of Convolution Neural Network (CNN) pre-trained models combined with Long Short Term Memory (LSTM) to generate image captions. The process includes two stages. The first stage entails training the CNN-LSTM models using baseline hyper-parameters and the second stage encompasses training CNN-LSTM models by optimizing and adjusting the hyper-parameters of
... Show MoreThe study focuses on Kamez model and the Claus Meyer model of instructional design, which are models that provide the learner with educational experiences to suit the logical information of the learner and the variety of instructional models. Research Objective: The present research aims to identify Limitations of the study. The current research is determined by ((fourth grade preparatory students, the book of the date of the fourth preparatory course)) Chapter II includes Arabic and foreign studies on the model of Kemp and Claus Mayer in the acquisition of concepts and direction towards the material. Chapter III Experimental Design: The researcher adopted an experimental design with two experimental groups and a control group. The resea
... Show MoreIn this study, we have created a new Arabic dataset annotated according to Ekman’s basic emotions (Anger, Disgust, Fear, Happiness, Sadness and Surprise). This dataset is composed from Facebook posts written in the Iraqi dialect. We evaluated the quality of this dataset using four external judges which resulted in an average inter-annotation agreement of 0.751. Then we explored six different supervised machine learning methods to test the new dataset. We used Weka standard classifiers ZeroR, J48, Naïve Bayes, Multinomial Naïve Bayes for Text, and SMO. We also used a further compression-based classifier called PPM not included in Weka. Our study reveals that the PPM classifier significantly outperforms other classifiers such as SVM and N
... Show MoreThe continuous advancement in the use of the IoT has greatly transformed industries, though at the same time it has made the IoT network vulnerable to highly advanced cybercrimes. There are several limitations with traditional security measures for IoT; the protection of distributed and adaptive IoT systems requires new approaches. This research presents novel threat intelligence for IoT networks based on deep learning, which maintains compliance with IEEE standards. Interweaving artificial intelligence with standardization frameworks is the goal of the study and, thus, improves the identification, protection, and reduction of cyber threats impacting IoT environments. The study is systematic and begins by examining IoT-specific thre
... Show MoreAutorías: Mariam Liwa Abdel Fattah, Liqaa Abdullah Ali. Localización: Revista iberoamericana de psicología del ejercicio y el deporte. Nº. 4, 2023. Artículo de Revista en Dialnet.
ABSTRACT: BACKGROUND: Left ventricular hypertrophy is a significant risk factor for cardiovascular complications such as ischemic heart disease, heart failure, sudden death, atrial fibrillation, and stroke. A proper non-expensive tool is required for detection of this pathology. Different electrocardiographic (ECG) criteria were investigated; however, the results were conflicting regarding the accuracy of these criteria. OBJECTIVE: To assess the accuracy of three electrocardiographic criteria in diagnosis of left ventricular hypertrophy in adult patients with hypertension using echocardiography as a reference test. PATIENTS AND METHODS: This is a hospital-based cross sectional observational study which included 340 adult patients with a his
... Show MoreIn this paper, two elements of the multi-input multi-output (MIMO) antenna had been used to study the five (3.1-3.55GHz and 3.7-4.2GHz), (3.4-4.7 GHz), (3.4-3.8GHz) and (3.6-4.2GHz) 5G bands of smartphone applications that is to be introduced to the respective US, Korea, (Europe and China) and Japan markets. With a proposed dimension of 26 × 46 × 0.8 mm3, the medium-structured and small-sized MIMO antenna was not only found to have demonstrated a high degree of isolation and efficiency, it had also exhibited a lower level of envelope correlation coefficient and return loss, which are well-suited for the 5G bands application. From the fabrication of an inexpensive FR4 substrate with a 0.8 mm thickness level, a loss tang
... Show More