Publications Scientifiques
Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10
Browse
27 results
Search Results
Item Detection of knee osteoarthritis based on wavelet and random forest model(2021) Messaoudene, Khadidja; Harrar, KhaledThe most recurrent kind of osteoarthritis is Knee osteoarthritis (KOA). Doctors encounter difficulties for a precise diagnosis through its features and to the naked eye. In this paper, we propose a new approach for the classification of KOA by combining the discrete wavelet decomposition (DWT) and random forest classifier from knee X-ray images. A total of 50 images from patients suffering or not from osteoarthritis were used in this study. The suggested technique includes image enhancement using the Gaussian filter followed by Haar wavelet transform. Five texture features namely, contrast, entropy, correlation, energy, and homogeneity were extracted from the transformed image, and these attributes were used to differentiate the radiographs into two groups: normal (KL 0) or affected with osteoarthritis (KL2). Four classifiers including random forest, SVM, RNN, and Naïve Bayes were tested and compared. The results obtained reveal that random forest achieved the highest performance in terms of accuracy (ACC = 88%) on X-Ray images of the Osteoarthritis Initiative (OAI) dataset.Item Recent progress on field-effect transistor-based biosensors: device perspective(Beilstein-Institut Zur Forderung der Chemischen Wissenschaften, 2024) Smaani, Billel; Nafa, Fares; Benlatrech, Mohamed Salah; Mahdi, Ismahan; Akroum, Hamza; Azizi, Mohamed walid; Harrar, Khaled; Kanungo, SayanOver the last few decades, field-effect transistor (FET)-based biosensors have demonstrated great potential across various industries, including medical, food, agriculture, environmental, and military sectors. These biosensors leverage the electrical properties of transistors to detect a wide range of biomolecules, such as proteins, DNA, and antibodies. This article presents a comprehensive review of advancements in the architectures of FET-based biosensors aiming to enhance device performance in terms of sensitivity, detection time, and selectivity. The review encompasses an overview of emerging FET-based biosensors and useful guidelines to reach the best device dimensions, favorable design, and realization of FET-based biosensors. Consequently, it furnishes researchers with a detailed perspective on design considerations and applications for future generations of FET-based biosensors. Finally, this article proposes intriguing avenues for further research on the topology of FET-based biosensors.Item A comparative study between convolutional and multilayer perceptron neural networks classification models(2019) Bachiri, Mohamed Elssaleh; Harrar, KhaledImage classification plays an important role in image processing, computer vision, and machine learning. This paper deals with image classification using deep learning. For this, a conventional neural network (CNN) and multilayer perceptron neural network (MLP) models were used for the classification. The two models were implemented on the MNIST dataset which was used at 100% and half of capacity, The models were trained with fixed and flexible number of epochs in two runs. CNN provided an accuracy of 98,43% with a loss of 4,44%, where MLP reached 92,80% of classification with a loss of 25,87%. Indeed, for each model, variables as number of filters, size, and activation functions were discussed. The CNN demonstrated a good performance providing high accuracy for image and also proved to be a better candidate for data applications.Item Subchondral tibial bone texture of conventional X-rays predicts total knee arthroplasty(Nature Research, 2022) Almhdie-Imjabbar, Ahmad; Toumi, Hechmi; Harrar, Khaled; Pinti, Antonio; Lespessailles, EricLacking disease-modifying osteoarthritis drugs (DMOADs) for knee osteoarthritis (KOA), Total Knee Arthroplasty (TKA) is often considered an important clinical outcome. Thus, it is important to determine the most relevant factors that are associated with the risk of TKA. The present study aims to develop a model based on a combination of X-ray trabecular bone texture (TBT) analysis, and clinical and radiological information to predict TKA risk in patients with or at risk of developing KOA. This study involved 4382 radiographs, obtained from the OsteoArthritis Initiative (OAI) cohort. Cases were defined as patients with TKA on at least one knee prior to the 108-month follow-up time point and controls were defined as patients who had never undergone TKA. The proposed TKA-risk prediction model, combining TBT parameters and Kellgren–Lawrence (KL) grades, was performed using logistic regression. The proposed model achieved an AUC of 0.92 (95% Confidence Interval [CI] 0.90, 0.93), while the KL model achieved an AUC of 0.86 (95% CI 0.84, 0.86; p < 0.001). This study presents a new TKA prediction model with a good performance permitting the identification of at risk patient with a good sensitivy and specificity, with a 60% increase in TKA case prediction as reflected by the recall valuesItem Feature extraction using CNN for peripheral blood cells recognition(European Alliance for Innovation, 2022) Ammar, Mohammed; Daho, Mostafa El Habib; Harrar, Khaled; Laidi, AmelINTRODUCTION: The diagnosis of hematological diseases is based on the morphological differentiation of the peripheral blood cell types. OBJECTIVES: In this work, a hybrid model based on CNN features extraction and machine learning classifiers were proposed to improve peripheral blood cell image classification. METHODS: At first, a CNN model composed of four convolution layers and three fully connected layers was proposed. Second, the features from the deeper layers of the CNN classifier were extracted. Third, several models were trained and tested on the data. Moreover, a combination of CNN with traditional machine learning classifiers was carried out. This includes CNN_KNN, CNN_SVM (Linear), CNN_SVM (RBF), and CNN_AdaboostM1. The proposed methods were validated on two datasets. We have used a public dataset containing 12444 images with four types of leukocytes to find the best optimizer function(eosinophil, lymphocyte, monocyte, and neutrophil images). The second dataset contains 17,092 images divided into eight groups: lymphocytes, neutrophils, monocytes). the second public dataset was used to find the best combination of CNN and the machine learning algorithms. the dataset containing 17,092 images: lymphocytes, neutrophils, monocytes, eosinophils, basophils, immature granulocytes, erythroblasts, and platelets. RESULTS: The results reveal that CNN combined with AdaBoost decision tree classifier provided the best performance in terms of cells recognition with an accuracy of 88.8%, demonstrating the performance of the proposed approach. CONCLUSION: The obtained results show that the proposed system can be used in clinical practiceItem Combining GLCM with LBP features for knee osteoarthritis prediction: data from the osteoarthritis initiative(EAI, 2021) Harrar, Khaled; Messaoudene, Khadidja; Ammar, MohammedKnee osteoarthritis is a chronic disease that can make a person more susceptible to develop health complications. It is a significant cause of disability among adults. In advanced stages, people can die from these complications. OBJECTIVES: This paper introduces a quick and effective approach to classify knee X-ray images using LogitBoost and wavelet-based Gray Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) to increase image classification accuracy and minimize training and testing time. METHODS: The proposed technique involves image enhancement followed by Haar wavelet transformation. GLCM and LBP were extracted from the transformed image and these attributes were used to differentiate the radiographs into two groups of patients composed of 100 normal subjects (KL 0) and 100 pathological cases with osteoarthritis (KL 2). The validation of the classification was carried out using the K-fold cross-validation technique with k = 10. RESULTS: The results revealed that the GLCM provided an accuracy of 77 % and the LBP approach achieved an accuracy of 82.5 %. Moreover, the combination of the two techniques LBP-GLCM improved the accuracy of the prediction with the LogitBoost model (91.16 %). Compared to other classifiers (SVM, logistic regression, and decision tree), the LogitBoost provided a low root mean square error (RMSE) of 27.5 %. CONCLUSION: In addition, the proposed method was compared to the state-of-the-art and revealed the highest accuracy in the prediction of KOA, outperforming the methods existing in the literatureItem Classification of surface defects on steel strip images using convolution neural network and support vector machine(Springer, 2022) Boudiaf, Adel; Benlahmidi, Said; Harrar, Khaled; Zaghdoudi, RachidQuality control of the surfaces of rolled products has received wide attention due to the crucial role that these products play in the manufacture of various car bodies, planes, ships, and trains. The process of quality control has undergone remarkable development. Previously, it was based on the human eye and characterized by slowness, fatigue, and error. To overcome these problems, nowadays the quality control is based mainly on computer vision. In this context, we propose in this work to develop an intelligent recognition system of surface defects for hot-rolled steel strips images using modified AlexNet convolution neural network and support vector machine model. Furthermore, we conducted a study on the effect of layers selection on classification accuracy. We have trained and tested our classification model using a public database of Northeastern University composed of 1800 images of defects. The results showed that our classifier model can be used easily for effective screening of surface defects for hot-rolled steel strips with very a high classification accuracy up to 99.7%, using only 7% of the total extracted features for each image with activations on the fully connected layer “FC7.” In addition, we addressed through this research a comparative study between the proposed classification model and the well-known modern classification models. This study highlighted the efficiency and effectiveness of our proposed model for the classification of surface defectsItem Topological analysis for osteoporosis assessment in X-Ray images using random forest model(Springer, 2021) Harrar, KhaledThis paper deals with the characterization of the texture of the bone. The objective is to combine clinical parameters and topological attributes extracted from X-Ray images for osteoporosis assessment. A total of 120 women are included in this study, divided into two populations, composed of 60 healthy subjects, and 60 osteoporotic patients. Nine features are involved and a random forest model is used to differentiate the patients. Different configurations are tested, trained, and validated using k-fold cross-validation technique with different values of k. The aim is to seek the combination giving the best accuracy for discriminating between the populations. Several classifiers are also tested and compared. The obtained results affirm that the tenfold cross-validation technique with the random forest model combining the topological and the clinical parameters outperform the other classifiers, and provide high accuracy (ACC = 87,5%) demonstrating the efficiency of this modelItem Text-Independent Speaker Identification using Mel-Frequency Energy Coefficients and Convolutional Neural Networks(IEEE, 2020) Abdiche, Déhia; Harrar, KhaledAutomatic Speaker Identification (ASI) is a biometric technique, which had achieved reliability in real applications, with standard feature extraction methods such as Linear Predictive Cepstral Coefficients (LPCC), Perceptual Linear Prediction (PLP), and modeling methods such as Gaussian mixture model (GMM), etc. However, the success of these manual approaches was quickly hampered by the emergence of big data, and the inability of scientists to manipulate large amounts of data, which led researchers to move towards automatic methods such as deep neural networks. In this work, a Convolutional Neural Network (CNN) is suggested for speaker identification in text-independent mode. Mel-Frequency Energy Coefficients (MFEC) method was used for extracting the characteristics of audio signals and the obtained coefficients were injected into the convolutional neural network model for classification (identification). In addition, a comparison was made between the proposed method and the existing traditional methods. Experimental results show that the proposed structure resulted in a speaker identification rate of 97.89%, which is much higher than the rates obtained in the old state of the art methods.Item Trabecular Texture Analysis using Morpho-Clinical Features and Bayes Classifiers(Institute of Electrical and Electronics Engineers Inc., 2019) Harrar, KhaledThe objective of this paper is to analyze radiographic images of patients and to discriminate between them using nine morphological and clinical parameters. Four models were constructed and trained using three Bayes classifiers: Bayesian logistic regression, Byes Net, and Naive Bayes. The purpose was to find the best configuration combining selected features and the best classifier providing the highest rate of classification. The validation was done using the '10-fold cross-validation' technique. A total of 100 images were collected from patients, divided into two groups, 50 healthy subjects, and 50 osteoporotic patients. The results obtained reveal that the selected features model combined with the Bayesian logistic regression classifier provided accurate discrimination between the two populations, with ACC = 87% demonstrating the performance of this configuration
- «
- 1 (current)
- 2
- 3
- »