@article {Zerouaoui2022, title = {Deep hybrid architectures for binary classification of medical breast cancer images}, journal = {Biomedical Signal Processing and Control}, volume = {71}, year = {2022}, note = {cited By 16}, abstract = {The diagnosis of breast cancer in the early stages significantly decreases the mortality rate by allowing the choice of adequate treatment. This study developed and evaluated twenty-eight hybrid architectures combining seven recent deep learning techniques for feature extraction (DenseNet 201, Inception V3, Inception ReseNet V2, MobileNet V2, ResNet 50, VGG16, and VGG19), and four classifiers (MLP, SVM, DT, and KNN) for a binary classification of breast pathological images over the BreakHis and FNAC datasets. The designed architectures were evaluated using: (1) four classification performance criteria (accuracy, precision, recall, and F1-score), (2) Scott Knott (SK) statistical test to cluster the proposed architectures and identify the best cluster of the outperforming architectures, and (3) the Borda Count voting method to rank the best performing architectures. The results showed the potential of combining deep learning techniques for feature extraction and classical classifiers to classify breast cancer in malignant and benign tumors. The hybrid architecture using the MLP classifier and DenseNet 201 for feature extraction (MDEN) was the top performing architecture with higher accuracy values reaching 99\% over the FNAC dataset, 92.61\%, 92\%, 93.93\%, and 91.73\% over the four magnification factor values of the BreakHis dataset: 40X, 100X, 200X, and 400X, respectively. The results of this study recommend the use of hybrid architectures using DenseNet 201 for the feature extraction of the breast cancer histological images because it gave the best results for both datasets BreakHis and FNAC, especially when combined with the MLP classifier. {\textcopyright} 2021 Elsevier Ltd}, keywords = {accuracy, algorithm, Article, augmentation index, Binary classification, biopsy technique, Breast Cancer, Breast Cancer Histopathological Image Classification, Classification (of information), Classification algorithm, classifier, Cluster computing, clustering algorithm, Clustering algorithms, colloid carcinoma, Computer aided diagnosis, Computer architecture, construct validity, contrast limited adaptive histogram equalization, Convolutional neural network, Convolutional neural networks, deep hybrid architecture, Deep learning, Deep neural networks, Diseases, ductal carcinoma, external validity, Extraction, F1 score, Feature extraction, Features extraction, feed forward neural network, fibroadenoma, fine needle aspiration biopsy, histogram, Histological images, histology, Hybrid architectures, Image classification, image processing, Images processing, internal validity, learning algorithm, Learning algorithms, Learning techniques, lobular carcinoma, Machine learning, measurement precision, Medical imaging, MLP classifiers, Mortality rate, Network architecture, papillary carcinoma, Pathological images, phyllodes tumor, recall, residual neural network, scoring system, Scott Knott, Support vector machines}, doi = {10.1016/j.bspc.2021.103226}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125746862\&doi=10.1016\%2fj.bspc.2021.103226\&partnerID=40\&md5=b9b74d0dcb135861bc2e3d820f836efa}, author = {Zerouaoui, H. and Idri, A.} } @article {Idri20201239, title = {Assessing the impact of parameters tuning in ensemble based breast Cancer classification}, journal = {Health and Technology}, volume = {10}, number = {5}, year = {2020}, note = {cited By 12}, pages = {1239-1255}, abstract = {Breast cancer is one of the major causes of death among women. Different decision support systems were proposed to assist oncologists to accurately diagnose their patients. These decision support systems mainly used classification techniques to categorize the diagnosis into Malign or Benign tumors. Given that no consensus has been reached on the classifier that can perform best in all circumstances, ensemble-based classification, which classifies patients by combining more than one single classification technique, has recently been investigated. In this paper, heterogeneous ensembles based on three well-known machine learning techniques (support vector machines, multilayer perceptron, and decision trees) were developed and evaluated by investigating the impact of parameter values of the ensemble members on classification performance. In particular, we investigate three parameters tuning techniques: Grid Search (GS), Particle Swarm Optimization (PSO) and the default parameters of the Weka Tool to evaluate whether setting ensemble parameters permits more accurate classification in breast cancer over four datasets obtained from the Machine Learning repository. The heterogeneous ensembles of this study were built using the majority voting technique as a combination rule. The overall results obtained suggest that: (1) Using GS or PSO techniques for single techniques provide more accurate classification; (2) In general, ensembles generate more accurate classification than their single techniques regardless of the optimization techniques used. (3) Heterogeneous ensembles based on optimized single classifiers generate better results than the Uniform Configuration of Weka (UC-WEKA) ensembles, and (4) PSO and GS slightly have the same impact on the performances of ensembles. {\textcopyright} 2020, IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature.}, keywords = {accuracy, Article, Breast Cancer, cancer classification, classifier, decision tree, experimental design, grid search, human, multilayer perceptron, particle swarm optimization, recall, support vector machine}, doi = {10.1007/s12553-020-00453-2}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087361107\&doi=10.1007\%2fs12553-020-00453-2\&partnerID=40\&md5=7398903f3007d71e535b12c2ef9a90a6}, author = {Idri, A. and Bouchra, E.O. and Hosni, M. and Abnane, I.} } @article {Abnane2020, title = {Fuzzy case-based-reasoning-based imputation for incomplete data in software engineering repositories}, journal = {Journal of Software: Evolution and Process}, volume = {32}, number = {9}, year = {2020}, note = {cited By 6}, abstract = {Missing data is a serious issue in software engineering because it can lead to information loss and bias in data analysis. Several imputation techniques have been proposed to deal with both numerical and categorical missing data. However, most of those techniques used is simple reuse techniques originally designed for numerical data, which is a problem when the missing data are related to categorical attributes. This paper aims (a) to propose a new fuzzy case-based reasoning (CBR) imputation technique designed for both numerical and categorical data and (b) to evaluate and compare the performance of the proposed technique with the k-nearest neighbor (KNN) imputation technique in terms of error and accuracy under different missing data percentages and missingness mechanisms in four software engineering data sets. The results suggest that the proposed fuzzy CBR technique outperformed KNN in terms of imputation error and accuracy regardless of the missing data percentage, missingness mechanism, and data set used. Moreover, we found that the missingness mechanism has an important impact on the performance of both techniques. The results are encouraging in the sense that using an imputation technique designed for both categorical and numerical data is better than reusing methods originally designed for numerical data. {\textcopyright} 2020 John Wiley \& Sons, Ltd.}, keywords = {accuracy, Case based reasoning, Categorical data, Clustering algorithms, Empirical Software Engineering, Fuzzy analogy, imputation, Missing data, Nearest neighbor search, Numerical methods, Software engineering}, doi = {10.1002/smr.2260}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85081904769\&doi=10.1002\%2fsmr.2260\&partnerID=40\&md5=762cb4270c6a55d209feaa8eb6df5c5f}, author = {Abnane, I. and Idri, A. and Abran, A.} } @article {11406228320150701, title = {The impact of data accuracy on user-perceived business service{\textquoteright}s quality.}, journal = {CISTI (Iberian Conference on Information Systems \& Technologies / Confer{\^e}ncia Ib{\'e}rica de Sistemas e Tecnologias de Informa{\c c}{\~a}o) Proceedings}, volume = {2}, year = {2015}, pages = {145 - 148}, abstract = {As business processes have become increasingly automated, data quality becomes the limiting and penalizing factor in the business service{\textquoteright}s overall quality, and thus impacts customer satisfaction, whether it is an end-user, an institutional partner or a regulatory authority. The available research that is related to business services{\textquoteright} quality paid very little attention to the impact of poor data quality on good services delivery and customer satisfaction, and to the calculation of the optimal level of data quality. The aim of this paper is to present a customer-oriented approach that will help to understand and analyze how an organization business service{\textquoteright}s overall quality is linked to the quality of upstream business processes and of data objects in use. This paper also introduces a calculation framework that allows the identification of an optimal level of data quality {\textendash} data accuracy dimension in the case of this paper - taking into account the business processes{\textquoteright} execution accura}, keywords = {accuracy, Business process management {\textendash} Research, Business process outsourcing, Business service and process quality, Consumers {\textendash} Attitudes, Customer satisfaction {\textendash} Research, data quality, Data quality {\textendash} Research, enterprise architecture, user satisfaction}, url = {http://search.ebscohost.com/login.aspx?direct=true\&db=iih\&AN=114062283\&site=ehost-live}, author = {Belhiah, Meryam and Bounabat, Bouchalb and Achchab, Said} }