Search

Analysis and classification of lung diseases using X-ray images is a primary step in the procedure of pneumonia diagnosis, especially in a critical period as pandemic of COVID-19 that is type of pneumonia Therefore, an automatic method with high accuracy of classification is needed to perform classification of lung diseases due to the increasing number of cases Convolutional Neural Networks (CNN) based classification has gained a big popularity over the last few years because of its speed and level of accuracy on the image’s classification tasks Through this article, we propose an implementation a CNN-based classification models using transfer learning technique to perform pneumonia detection and compare the results in order to detect the best model for the task according to certain parameters As this has become a fast expanding field, there are several models but we will focus on the best outperforming algorithms according to their architecture, length and type of layers and evaluation parameters for the classification tasks Firstly, we review the existing conventional methods and deep learning architectures used for segmentation in general Next, we perform a deep performance and analysis based on accuracy and loss function of implemented models A critical analysis of the results is made to highlight all important issues to improve © 2020 ASTES Publishers All rights reserved

Nowadays, the biomedical signal processing area (MSP) is one of the most important research fields. It is often applied in medical diagnosis and early detection of neurological diseases. Thereby, the MSP is deployed in Parkinson’s disease (PD) detection from voice disorder. Therefore, Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN) are employed to classify healthy patients from PD ones, based on vocal features. We accomplished our study using two UCI Machine Learning repository databases, denoted database I and database II in the whole article. These datasets include 22 and 45 acoustic features, respectively. Accuracy, sensitivity, and specificity were calculated in order to qualify and evaluate the performance of the detection system. The experiment results reveal that the accuracy reached a rate of 93.10 % as the highest value when we applied the CNN model to database I.

Atherosclerosis known as coronary artery disease (CAD) becomes epidemic in any society that relies on an industrial-technological system with an associated behavioral alteration in people's lifestyles as junk food consumerism and stressful habits. However, this disease residue the first cause of death in industrialized countries, despite many new therapeutic approaches and risk factors prevention. Moreover, atherosclerosis misdiagnosis has side costly effects. In this paper, we have proposed a computer-aided diagnosis system based on K-Nearest Neighbors (KNN) and Artificial Neural Network (ANN) algorithms. Then, we applied K-fold cross-validation in order to split the databases and reach the best model with the higher accuracy and fewer side effects. In this proposed work, we tested the reached model on 573 patients with several effective features which collecting from Cleveland and Z-Alizadeh Sani datasets. Then Area Under the Curve (AUC), F1-Score, and accuracy were used to enrich and determine the effectiveness of each predictive model. Using Machine Learning (ML) methods, K-fold cross-validation, and performance evaluation metrics, 96.78% average accuracy is achieved with the original training accuracy of 100%, which means the prediction system is obtained as the best predictive model comparing to the previous studies.

Handwriting recognition still considered a difficult problem statement. In this paper, we present a new database containing educational vocabulary written by adolescent’s learners. 200 Moroccan secondary school students whose age varies between 14 and 16 years participated in the development of the first version of the Computer Science Vocabulary Database (CSVD). Our database contains a set of 15000 images. Word images are scanned and converted to image format to prepare them for subsequent processing steps. Preprocessing techniques were applied to the images to decrease the variability of colors, contrast, and brightness often presented in handwritten word images. This database is designed for the training and testing of handwritten French word recognition systems. Furthermore, the CSVD database can constitute an opportunity for other researchers to evaluate their recognition methods and systems.

Machine learning (ML) technique behind the most existing abilities fields in several areas like languages processing, robotics, including medicine. The most important medical applications are the early prediction system for heart diseases especially, coronary artery disease (CAD) also called atherosclerosis. The need for a medical diagnosis support system is to detect atherosclerosis at the earlier stages to optimize the diagnosis, avoid the advanced cases, and reduce treatment costs. Here, a supervised machine learning medical diagnosis support system (MDSS) for atherosclerosis prediction is presented that is able to obtain and learn automatically knowledge from each patient’s clinical data. Therefore, we used the various ML classifiers for the proposed medical diagnosis support system for atherosclerosis. Two supervised ML algorithms (Artificial Neural Network and Adaptive Boosting) were used in order to compare which one is more efficient for atherosclerosis diagnosis. Thus, this work is accomplished using databases collected from the UCI repository (Cleveland, Hungarian) and Sani Z-Alizadeh dataset. The performance metrics were computed utilizing Recall, Accuracy and Precision. Furthermore and F1 score measures were also calculated to greatly increase the proposed system performance. Consequently, the proposed model can be used to support healthcare and facilitate large-scale clinical diagnostic of atherosclerosis diseases.

Atherosclerosis disease, also known as coronary artery disease (CAD) is the major reason to increase the mortality rate around the world. Indeed, there is a lack of improvement in the early diagnosis of cardiovascular diseases. Thus, doctors need a trustworthy system to minimize diagnostic errors and to avoid critically surgeries. This contribution is articulated around a Medical Decision Support System (MDSS) design for atherosclerosis, able to take precautionary steps using the patient's clinical parameters. This MDSS is based on supervised machine learning (ML) algorithms. We use Artificial Neural Network (ANN) and K-Nearest Neighbor (KNN) to predict patients with or without atherosclerosis disease in an established database. The system is validated on Cleveland heart disease, Hungarian, Switzerland, and Long Beach VA databases. The performance of the proposed system is evaluated using accuracy, sensitivity and specificity as well-known similarity measures. Our system outperforms currently similar published research.

atherosclerosis disease is the major reason that increases the mortality rate around the world. This ailment diagnosis becomes difficult due to the inattention of initial symptoms. Thus, there is a need to improve the prediction accuracy of cardiovascular diseases in order to minimize treatment costs and to avoid critical cases. This contribution is articulated to define a medical decision support system (MDSS) of atherosclerosis disease. This system is able to give heart disease prediction using the patient's clinical data. This MDSS is based on machine learning techniques such as K-medoids and k-means clustering for classification, Artificial Neural Network (ANN) and K-Nearest Neighbor (KNN) for prediction the presence and the absence of Atherosclerosis disease. The system is validated on the Cleveland heart diseases database. This data is split into training and testing data with 13 features for each patient. We evaluated the proposed system using many similarity measures such as Matthews’s correlation coefficient (MCC). We reached 96% accuracy and 0.92 MCC, significantly outperforms currently published research.

cardiovascular diseases are the leading cause of death around the world. These illnesses related to the malfunction of the heart or blood vessels. The aim of this research work is to establish a fuzzy expert system (FES) for heart diseases diagnosis. This FES design based on cardiovascular risk factors and the major clinical diagnosis parameters using fuzzy logic approach. In this cardiovascular system, we proposed a decision tree based solution for the higher number of rules in order to increase the degree of efficiency. The patient's clinical data extracted from the risk factor of the atherosclerosis disease. This disease is one of specific type of coronary artery disease (CAD) that supported by Cleveland Heart Disease Database (CHDD). The medical system are tested and validated with the data from CHDD and the results show efficiency and accuracy of the developed approach.

Over the years, the use of artificial intelligence methods in medical analysis has flourished with the development of diagnostic tests and medical knowledge. Thus, the techniques of classification and detection have made much progress towards offering to medical experts and the doctors, organized and hierarchical systems to provide them with more information and knowledge for their daily function. Diagnostic assistance or diagnostic aid is an important tool for identifying abnormalities such as heart diseases. Having an appropriate model to increase the accuracy of the system, even in cases where inputs are generally low, is necessary. This paper aims to set up a medical diagnostic support system for the early detection of heart diseases, depending on cardiovascular risk factors to determine different clinical parameters useful for diagnosis. The validation of the suggested method is made using the sensitivity and specificity measures.