@article {Asaad2022, title = {AsthmaKGxE: An asthma{\textendash}environment interaction knowledge graph leveraging public databases and scientific literature}, journal = {Computers in Biology and Medicine}, volume = {148}, year = {2022}, note = {cited By 1}, abstract = {Motivation: Asthma is a complex heterogeneous disease resulting from intricate interactions between genetic and non-genetic factors related to environmental and psychosocial aspects. Discovery of such interactions can provide insights into the pathophysiology and etiology of asthma. In this paper, we propose an asthma knowledge graph (KG) built using a hybrid methodology for graph-based modeling of asthma complexity with a focus on environmental interactions. Using a heterogeneous set of public sources, we construct a genetic and pharmacogenetic asthma knowledge graph. The construction of this KG allowed us to shed more light on the lack of curated resources focused on environmental influences related to asthma. To remedy the lack of environmental data in our KG, we exploit the biomedical literature using state-of-the-art natural language processing and construct the first Asthma{\textendash}Environment interaction catalog incorporating a continuously updated ensemble of environmental, psychological, nutritional and socio-economic influences. The catalog{\textquoteright}s most substantiated results are then integrated into the KG. Results: The resulting environmentally rich knowledge graph {\textquotedblright}AsthmaKGxE{\textquotedblright} aims to provide a resource for several potential applications of artificial intelligence and allows for a multi-perspective study of asthma. Our insight extraction results indicate that stress is the most frequent asthma association in the corpus, followed by allergens and obesity. We contend that studying asthma{\textendash}environment interactions in more depth holds the key to curbing the complexity and heterogeneity of asthma. Availability: A user interface to browse and download the extracted catalog as well as the KG are available at http://asthmakgxe.moreair.info/. The code and supplementary data are available on github (https://github.com/ChaiAsaad/MoreAIRAsthmaKGxE). {\textcopyright} 2022 Elsevier Ltd}, keywords = {allergen, Article, Artificial intelligence, Association reactions, asthma, Automated, automated pattern recognition, data base, data extraction, Databases, Diseases, environmental factor, Factual, factual database, Gene-Environment Interaction, Genetic factors, genotype environment interaction, Graphic methods, Heterogeneous disease, human, Humans, Knowledge graph, Knowledge graphs, Knowledge management, Language processing, Learning algorithms, Machine learning, Machine-learning, NAtural language processing, Natural language processing systems, Natural languages, nutritional assessment, obesity, pathophysiology, Pattern recognition, pharmacogenetics, physiological stress, psychological aspect, Public database, Scientific literature, socioeconomics, User interfaces}, doi = {10.1016/j.compbiomed.2022.105933}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85135702024\&doi=10.1016\%2fj.compbiomed.2022.105933\&partnerID=40\&md5=2022f55e1de0bbaa947ba6699af6a143}, author = {Asaad, C. and Ghogho, M.} } @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 {Elghomary202236, title = {Design of a Smart MOOC Trust Model: Towards a Dynamic Peer Recommendation to Foster Collaboration and Learner{\textquoteright}s Engagement}, journal = {International Journal of Emerging Technologies in Learning}, volume = {17}, number = {5}, year = {2022}, note = {cited By 2}, pages = {36-56}, abstract = {Recent evolutions in the Internet of Things (IoT) and Social IoT (SIoT) are facilitating collaboration as well as social interactions between entities in various environments, especially Smart Learning Ecosystems (SLEs). However, in these contexts, trust issues become more intense, learners feel suspicious and avoid collaborating with their peers, leading to their demotivation and disengagement. Hence, a Trust Management System (TMS) has become a crucial challenge to promote qualified collaboration and stimulate learners{\textquoteright} engagement. In the literature, several trust models were proposed in various domains, but rarely those that address trust issues in SLEs, especially in MOOCs. While these models exclusively rank the best nodes and fail to detect the untrustworthy ones. Therefore, in this paper, we propose Machine Learning-based trust evaluation model that considers social and dynamic trust parameters to quantify entities{\textquoteright} behaviors. It can distinguish trustworthy and untrustworthy behaviors in MOOCs to recommend benign peers while blocking malicious ones to build a dynamic trust-based peer recommendation in the future phase. Our model prevents learners from wasting their time in unprofitable interactions, protects them from malicious actions, and boosts their engagement. A simulation experiment using real-world SIoT datasets and encouraging results show the performance of our trust model {\textcopyright} 2022, International Journal of Emerging Technologies in Learning. All Rights Reserved.}, keywords = {Curricula, e-learning, Internet of things, Learning ecosystems, Machine learning, Massive open online course, Peer recommendation, Security of data, Smart education, Social internet of thing, Trust management system, Trust management systems, Trust models}, doi = {10.3991/ijet.v17i05.27705}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127011761\&doi=10.3991\%2fijet.v17i05.27705\&partnerID=40\&md5=5d062bc0485ddb7b7d27830779b55330}, author = {Elghomary, K. and Bouzidi, D. and Daoudi, N.} } @article {Wadghiri2022, title = {Ensemble blood glucose prediction in diabetes mellitus: A review}, journal = {Computers in Biology and Medicine}, volume = {147}, year = {2022}, note = {cited By 0}, abstract = {Considering the complexity of blood glucose dynamics, the adoption of a single model to predict blood glucose level does not always capture the inter- and intra-patients{\textquoteright} context changes. Ensembles are a set of machine learning techniques combining multiple single learners to find a better variance/bias trade-off and hence improve the prediction accuracy. The present paper aims to review the state of the art in predicting blood glucose using ensemble methods with regard to 8 criteria: publication year and sources, datasets used to train/evaluate the models, types of ensembles used, single learners involved to construct ensembles, combination schemes used to aggregate the base learners, metrics and validation methods adopted to assess the performance of ensembles, reported overall performance of the predictors and accuracy comparison of ensemble techniques with single models. A systematic literature review has been conducted in order to analyze and synthetize primary studies published between 2000 and 2020 in six digital libraries. A total of 32 primary papers were selected and reviewed with regard to eight review questions. The results show that ensembles have gained wider interest during the last years and improved in general the performance compared with other single models. However, multiple gaps have been identified concerning the ensembles construction process and the performance metrics used. Several recommendations have been made in this regard to design accurate ensembles for blood glucose level prediction. {\textcopyright} 2022 Elsevier Ltd}, keywords = {algorithm, Algorithms, Blood, Blood glucose, Blood glucose level, Data mining, Diabetes mellitus, Digital libraries, Economic and social effects, Ensemble methods, Forecasting, Glucose, glucose blood level, Glucose dynamics, human, Humans, Machine learning, Machine learning techniques, Machine-learning, Performance, Single models, Trade off}, doi = {10.1016/j.compbiomed.2022.105674}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85132341147\&doi=10.1016\%2fj.compbiomed.2022.105674\&partnerID=40\&md5=05bd59c3726654494a4be346e4e6a682}, author = {Wadghiri, M.Z. and Idri, A. and El Idrissi, T. and Hakkoum, H.} } @article {Hakkoum2022, title = {Interpretability in the medical field: A systematic mapping and review study}, journal = {Applied Soft Computing}, volume = {117}, year = {2022}, note = {cited By 4}, abstract = {Context: Recently, the machine learning (ML) field has been rapidly growing, mainly owing to the availability of historical datasets and advanced computational power. This growth is still facing a set of challenges, such as the interpretability of ML models. In particular, in the medical field, interpretability is a real bottleneck to the use of ML by physicians. Therefore, numerous interpretability techniques have been proposed and evaluated to help ML gain the trust of its users. Methods: This review was carried out according to the well-known systematic map and review process to analyze the literature on interpretability techniques when applied in the medical field with regard to different aspects: publication venues and publication year, contribution and empirical types, medical and ML disciplines and objectives, ML black-box techniques interpreted, interpretability techniques investigated, their performance and the best performing techniques, and lastly, the datasets used when evaluating interpretability techniques. Results: A total of 179 articles (1994{\textendash}2020) were selected from six digital libraries: ScienceDirect, IEEE Xplore, ACM Digital Library, SpringerLink, Wiley, and Google Scholar. The results showed that the number of studies dealing with interpretability increased over the years with a dominance of solution proposals and experiment-based empirical type. Diagnosis, oncology, and classification were the most frequent medical task, discipline, and ML objective studied, respectively. Artificial neural networks were the most widely used ML black-box techniques investigated for interpretability. Additionally, global interpretability techniques focusing on a specific black-box model, such as rules, were the dominant explanation types, and most of the metrics used to evaluate interpretability were accuracy, fidelity, and number of rules. Moreover, the variety of the techniques used by the selected papers did not allow categorization at the technique level, and the high number of the sum of evaluations (671) of the articles raised a suspicion of subjectivity. Datasets that contained numerical and categorical attributes were the most frequently used in the selected studies. Conclusions: Further effort is needed in disciplines other than diagnosis and classification. Global techniques such as rules are the most used because of their comprehensibility to doctors, but new local techniques should be explored more in the medical field to gain more insights into the model{\textquoteright}s behavior. More experiments and comparisons against existing techniques are encouraged to determine the best performing techniques. Lastly, quantitative evaluation of interpretability and physicians{\textquoteright} implications in interpretability techniques evaluation is highly recommended to evaluate how the techniques will perform in real-world scenarios. It can ensure the soundness of the techniques and help gain trust in black-box models in medical environments. {\textcopyright} 2022 Elsevier B.V.}, keywords = {Black box modelling, Black boxes, Computational power, Computer aided diagnosis, Digital libraries, Explainability, Historical dataset, Interpretability, Machine learning, Medical fields, Neural networks, Systematic mapping, Systematic Review, XAI}, doi = {10.1016/j.asoc.2021.108391}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122624142\&doi=10.1016\%2fj.asoc.2021.108391\&partnerID=40\&md5=38db4d1f5c417a07d0a3204639e157a2}, author = {Hakkoum, H. and Abnane, I. and Idri, A.} } @article {Ismaili-Alaoui2022900, title = {IoDEP: Towards an IoT-Data Analysis and Event Processing Architecture for Business Process Incident Management}, journal = {International Journal of Advanced Computer Science and Applications}, volume = {13}, number = {4}, year = {2022}, note = {cited By 0}, pages = {900-915}, abstract = {IoT is becoming a hot spot area of technological innovations and economic development promises for many industries and services. This new paradigm shift affects all the enterprise architecture layers from infrastructure to business. Business Process Management (BPM) is a field among others that is affected by this new technology. To assist data and events explosion resulting, among others, from IoT, data analytic processes combined with event processing techniques, examine large data sets to uncover hidden patterns, unknown correlations between collected events, either at a very technical level (incident/anomaly detection, predictive maintenance) or at business level (customer preferences, market trends, revenue opportunities) to provide improved operational efficiency, better customer service and competitive advantages over rival organizations. In order to capitalize the business value of data and events generated by IoT sensors, IoT, Data Analytics and BPM need to meet in the middle. In this paper, we propose an end-to-end IoT-BPM integration architecture (IoDEP: IoT-Data-Event-Process) for a proactive business process incident management. A case study is presented and the obtained results from our experimentations demonstrate the benefit of our approach and allowed us to confirm the efficiency of our assumptions. {\textcopyright} 2022. All Rights Reserved.}, keywords = {Big data, Business Process, Competition, Complex event processing, Complex events, Data Analytics, Data handling, Economic development, Efficiency, Enterprise resource management, Event Processing, Event processing architectures, Hot spot area, Incident Management, Information management, Internet of things, Machine learning, Technological innovation}, doi = {10.14569/IJACSA.2022.01304104}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130098329\&doi=10.14569\%2fIJACSA.2022.01304104\&partnerID=40\&md5=af3b2fd1443242906731e18007ed61ab}, author = {Ismaili-Alaoui, A. and Baina, K. and Benali, K.} } @conference {Rachidi202213, title = {Network intrusion detection using Machine Learning approach}, booktitle = {ACM International Conference Proceeding Series}, year = {2022}, note = {cited By 0}, pages = {13-17}, abstract = {Today, intrusion detection has become an active research area. Due to the rapidly increasing number of intrusion variants, intrusion detection system analyses and notifies the activities of users as normal (or) anomaly. In our paper, we built a model of intrusion detection system applied to the NSL-KDD data set using different supervised classifiers such as KNN and Na{\"\i}ve Bayes. We also proposed two algorithms for multi-classification based on the Random Forest (RF) which is an ensemble classifier and KNN. Then we used the K-folds method to evaluate and validate our model. To evaluate the performances, we realized experiments on NSL-KDD data set. The result shows that the second proposed algorithm is efficient with high accuracy and time optimization. {\textcopyright} 2022 ACM.}, keywords = {Barium compounds, Classification (of information), Computer crime, data set, Decision trees, Intrusion detection, Intrusion Detection Systems, Intrusion-Detection, Machine learning, Machine learning approaches, Multi-classification, Network intrusion detection, NSL-KDD, Random forests, Research areas, Sodium compounds, Supervised classifiers}, doi = {10.1145/3551690.3551693}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139141127\&doi=10.1145\%2f3551690.3551693\&partnerID=40\&md5=e47a5f8038487b706673543f7fdf2de4}, author = {Rachidi, Z. and Chougdali, K. and Kobbane, A. and Ben-Othman, J.} } @conference {Ba{\"\i}na202273, title = {NEW INSIGHT OF DATA MINING-BASED FRAUD DETECTION IN FINANCIAL IT-SYSTEMS}, booktitle = {Proceedings of the 15th IADIS International Conference Information Systems 2022, IS 2022}, year = {2022}, note = {cited By 0}, pages = {73-80}, abstract = {Nowadays, money exchanges are oriented to be more digitized in order to reduce personal contacts and maintain safety from the pandemic covid-19. The most important aspect of any financial institute is to be secure and protected from any suspicious action that can harm the security system and be ready for any type of fraud that can happen such as money laundering, internet frauds, credit card frauds or any other financial fraud. In this paper we present a state of the art of the newest and the most efficient strategies that help financial institutes to be well secure, more reliable, starting from a state of the art of existing ML algorithms used and ending by a benchmark of those algorithms. {\textcopyright} 2022 CURRAN-CONFERENCE. All rights reserved.}, keywords = {Credit card frauds, Crime, Data mining, Efficient strategy, Finance, Financial fraud, Financial institutes, Fraud detection, Internet fraud, IT system, Laundering, Machine learning, Machine-learning, Personal contacts, State of the art}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85137716391\&partnerID=40\&md5=e93045c4bdb15afeefea2672681ef6a3}, author = {Baina, S. and Rihi, A.} } @article {Toub20221, title = {Operating room scheduling 2019 survey}, journal = {International Journal of Medical Engineering and Informatics}, volume = {14}, number = {1}, year = {2022}, note = {cited By 2}, pages = {1-30}, abstract = {Numerous optimisation problems in healthcare have been approached by researchers over the last three to four decades. Hospital logistics - organised and structured to secure patient satisfaction in terms of quality, quantity, time, security and least cost - forms part of the quest for global performance. We provide herein a review of recent study and applications of operations research in healthcare. In particular, we survey work on optimisation problems, focusing on the planning and scheduling of operating rooms. The latter is a highly strategic place within the hospital as it requires key medical competence and according to Macario (2008) surgical sector expenditure represents nearly a third of a hospital{\textquoteright}s budget. We analyse recent research on operating room planning and scheduling from 2008 to 2019; our evaluation is based on patient characteristics, performance measurement, the solution techniques used in the research and the applicability of the research to real life cases. The searches were based on PubMed, Web of Science, Science Direct and Google Scholar databases. Copyright {\textcopyright} 2022 Inderscience Enterprises Ltd.}, keywords = {adult, agricultural worker, Article, budget, clinical evaluation, computer assisted tomography, Computer simulation, cost effectiveness analysis, eutrophication, febrile neutropenia, female, genetic algorithm, health care cost, health care facility, health care system, hip replacement, hospital cost, hospitalization, human, intensive care unit, length of stay, Machine learning, male, mathematical model, operating room personnel, operation duration, Patient satisfaction, population size, stochastic model, system analysis, Time series analysis, total quality management, vaccination, work environment, workload}, doi = {10.1504/IJMEI.2022.119307}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85120773204\&doi=10.1504\%2fIJMEI.2022.119307\&partnerID=40\&md5=a2ac2109f88463231d4e37b0a988843f}, author = {Toub, M. and Souissi, O. and Achchab, S.} } @article {Lamrhari2022, title = {A social CRM analytic framework for improving customer retention, acquisition, and conversion}, journal = {Technological Forecasting and Social Change}, volume = {174}, year = {2022}, note = {cited By 4}, abstract = {Social Customer Relationship Management (social CRM) has become one of the central points for many companies seeking to improve their customer experience. It comprises a set of processes that allows decision-makers to analyze customer data, in order to launch an efficient, customer-centric, and cost-effective marketing strategy. Nonetheless, the inclusion of social media data in CRM introduces new challenges, as it requires advanced analytical approaches to extract actionable insight from such a huge amount of data. Thus, in this paper, we propose a social CRM analytic framework, which includes various analytical approaches, aiming at improving customer retention, acquisition, and conversion. This framework has been tested on various datasets and extensively evaluated based on several performance metrics. The obtained results suggest that the proposed framework can effectively extract relevant information and support decision-making processes. From an academics perspective, the study contributes to an understanding of customers{\textquoteright} experiences throughout their engagement on social media and focuses on long-term relationships with customers. From a managerial perspective, companies should leverage the insight generated through every customer engagement on social media to drive effective marketing strategies. {\textcopyright} 2021}, keywords = {Acquisition, Conversion, Cost effectiveness, Customer acquisition, Customer conversion, Customer relationship management, Customer retention, Customer satisfaction, Customers{\textquoteright} satisfaction, Decision making, Digital storage, Machine learning, management, marketing, Public relations, Sales, Sentiment analysis, Social CRM, social media, Social networking (online), Strategic planning}, doi = {10.1016/j.techfore.2021.121275}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118116967\&doi=10.1016\%2fj.techfore.2021.121275\&partnerID=40\&md5=10ffdb7f551bf1e135c01fb362d1a559}, author = {Lamrhari, S. and Ghazi, H.E. and Oubrich, M. and Faker, A.E.} } @article {Khaldi20221377, title = {TimeSpec4LULC: a global multispectral time series database for training LULC mapping models with machine learning}, journal = {Earth System Science Data}, volume = {14}, number = {3}, year = {2022}, note = {cited By 0}, pages = {1377-1411}, abstract = {Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated time series of satellite images, which are not available yet. This paper presents TimeSpec4LULC 10.5281/zenodo.5913554;Currency sign, a smart open-source global dataset of multispectral time series for 29 LULC classes ready to train machine learning models. TimeSpec4LULC was built based on the seven spectral bands of the MODIS sensors at 500gh{\texteuro}{\textasciimacron}m resolution, from 2000 to 2021, and was annotated using spatial-temporal agreement across the 15 global LULC products available in Google Earth Engine (GEE). The 22-year monthly time series of the seven bands were created globally by (1) applying different spatial-temporal quality assessment filters on MODIS Terra and Aqua satellites; (2) aggregating their original 8gh{\texteuro}{\textasciimacron}d temporal granularity into monthly composites; (3) merging Terragh{\texteuro}{\textasciimacron}+gh{\texteuro}{\textasciimacron}Aqua data into a combined time series; and (4) extracting, at the pixel level, 6gh{\texteuro}{\textasciimacron}076gh{\texteuro}{\textasciimacron}531 time series of size 262 for the seven bands along with a set of metadata: geographic coordinates, country and departmental divisions, spatial-temporal consistency across LULC products, temporal data availability, and the global human modification index. A balanced subset of the original dataset was also provided by selecting 1000 evenly distributed samples from each class such that they are representative of the entire globe. To assess the annotation quality of the dataset, a sample of pixels, evenly distributed around the world from each LULC class, was selected and validated by experts using very high resolution images from both Google Earth and Bing Maps imagery. This smartly, pre-processed, and annotated dataset is targeted towards scientific users interested in developing various machine learning models, including deep learning networks, to perform global LULC mapping. {\textcopyright} 2022 Rohaifa Khaldi et al.}, keywords = {Land cover, Land use, Machine learning, MODIS, multispectral image, spatiotemporal analysis, Time series analysis}, doi = {10.5194/essd-14-1377-2022}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127624906\&doi=10.5194\%2fessd-14-1377-2022\&partnerID=40\&md5=90f9e45c7b39e149ab387a54f4392d6a}, author = {Khaldi, R. and Alcaraz-Segura, D. and Guirado, E. and Benhammou, Y. and El Afia, A. and Herrera, F. and Tabik, S.} } @article {Hakkoum2021587, title = {Assessing and Comparing Interpretability Techniques for Artificial Neural Networks Breast Cancer Classification}, journal = {Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization}, volume = {9}, number = {6}, year = {2021}, note = {cited By 11}, pages = {587-599}, abstract = {Breast cancer is the most common type of cancer among women. Thankfully, early detection and treatment improvements helped decrease the number of deaths. Data Mining techniques have always assisted BC tasks whether it is screening, diagnosis, prognosis, treatment, monitoring, and/or management. Nowadays, the use of Data Mining is witnessing a new era. In fact, the main objective is no longer to replace humans but to enhance their capabilities, which is why Artificial Intelligence is now referred to as Intelligence Augmentation. In this context, interpretability is used to help domain experts learn new patterns and machine learning experts debug their models. This paper aims to investigate three black-boxes interpretation techniques: Feature Importance, Partial Dependence Plot, and LIME when applied to two types of feed-forward Artificial Neural Networks: Multilayer perceptrons, and Radial Basis Function Network, trained on the Wisconsin Original dataset for breast cancer diagnosis. Results showed that local LIME explanations were instance-level interpretations that came in line with the global interpretations of the other two techniques. Global/local interpretability techniques can thus be combined to define the trustworthiness of a black-box model. {\textcopyright} 2021 Informa UK Limited, trading as Taylor \& Francis Group.}, keywords = {Article, Artificial intelligence, artificial neural network, Breast Cancer, Breast cancer classifications, cancer diagnosis, Computer aided diagnosis, cross validation, Data mining, Data-mining techniques, Diseases, Domain experts, early diagnosis, entropy, Explainability, Feature importance, Interpretability, Learn+, learning, learning algorithm, Lime, Machine learning, Multilayer neural networks, nerve cell, nonhuman, Partial dependence plot, perceptron, prediction, prognosis, Radial basis function networks, Treatment monitoring}, doi = {10.1080/21681163.2021.1901784}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103249025\&doi=10.1080\%2f21681163.2021.1901784\&partnerID=40\&md5=78e1e57a62692bab2b39984182af7904}, author = {Hakkoum, H. and Idri, A. and Abnane, I.} } @article {ElOuassif202150, title = {Classification techniques in breast cancer diagnosis: A systematic literature review}, journal = {Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization}, volume = {9}, number = {1}, year = {2021}, note = {cited By 12}, pages = {50-77}, abstract = {Data mining (DM) consists in analysing a~set of observations to find unsuspected relationships and then summarising the data in new ways that are both understandable and useful. It has become widely used in various medical fields including breast cancer (BC), which is the most common cancer and the leading cause of death among women~worldwide.~BC diagnosis is a~challenging medical task and many studies have attempted to apply classification techniques to it. The objective of the present study is to identify studies on classification techniques~in~BC diagnosis and to analyse them from~three perspectives: classification techniques used, accuracy of the classifiers, and comparison of performance. We performed a~systematic literature review (SLR) of 176 selected studies published between January~2000 and November~2018. The results show that, of the nine classification techniques investigated, artificial neural networks, support vector machines and decision trees were the most frequently used. Moreover, artificial neural networks, support vector machines and ensemble classifiers performed better than the other techniques, with median accuracy values of 95\%, 95\% and 96\% respectively. Most of the selected studies (57.4\%) used datasets containing different types of images such as mammographic, ultrasound, and microarray images. {\textcopyright} 2021 Informa UK Limited, trading as Taylor \& Francis Group.}, keywords = {Article, Artificial intelligence, artificial neural network, Breast Cancer, Breast cancer diagnosis, cancer diagnosis, cause of death, Causes of death, Classification (of information), Classification technique, Comparison of performance, Computer aided diagnosis, data extraction, Data mining, data synthesis, decision tree, Decision trees, Diseases, human, k nearest neighbor, Machine learning, Medical fields, Medical informatics, Network support, Neural networks, publication, qualitative research, Quality control, support vector machine, Support vector machine classifiers, Support vector machines, Support vectors machine, Systematic literature review, Systematic Review, validity}, doi = {10.1080/21681163.2020.1811159}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098842973\&doi=10.1080\%2f21681163.2020.1811159\&partnerID=40\&md5=9a48998b1c44d263863efcfb25f9920f}, author = {ElOuassif, B. and Idri, A. and Hosni, M. and Abran, A.} } @conference {Choukri2021, title = {Context aware Hidden Markov Model for Intention process mining}, booktitle = {5th International Conference on Intelligent Computing in Data Sciences, ICDS 2021}, year = {2021}, note = {cited By 0}, abstract = {Nowadays, the omnipresence of digital devices and solutions in daily life made the digital footprints of individuals and the traces of their activities widely available. Smart devices generate a tremendous amount of data that and enables tracking their users{\textquoteright} activity. Extensive research has been conducted to produce generic process models based on the analysis of user{\textquoteright}s activity recorded during the enactment of operational processes. Unfortunately, these approaches considered only the relation between the observed activities and their sequences to infer the underlying process. Thus, ignoring the goal conditioning the user{\textquoteright}s behavior when triggering the actual process. Nevertheless, the same activity traces could serve to unhide the intention behind each process. This article will focus on presenting our approach to Contextual intention mining using Hidden Markov Model (HMM). This approach explores the close relationships between intention and context to construct the process model while ensuring consistency between observed context and actual intentions. {\textcopyright} 2021 IEEE.}, keywords = {Behavioral research, Context, Data mining, Digital devices, Event logs, Goal mining, Goal models, Hidden Markov models, Information systems, Information use, Intention-oriented process modeling, Intentional process modeling, Machine learning, Markov modeling, Oriented process, Process Discovery, Process engineering, Process mining, Process recommendation, Process-aware information systems, Process-models, Supervised learning, Unsupervised learning, User profile}, doi = {10.1109/ICDS53782.2021.9626765}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123483088\&doi=10.1109\%2fICDS53782.2021.9626765\&partnerID=40\&md5=d61fab7bfc96ede4658a8984da68ef3f}, author = {Choukri, I. and Guermah, H. and Daosabah, A. and Nassar, M.} } @article {Houmz2021, title = {Detecting the impact of software vulnerability on attacks: A case study of network telescope scans}, journal = {Journal of Network and Computer Applications}, volume = {195}, year = {2021}, note = {cited By 1}, abstract = {Network scanning is one of the first steps in gathering information about a target before launching attacks. It is used to scan for vulnerable devices and exposed services in order to exploit them. Such exploits can result in data breaches or network disruption, which can be very costly for organizations. There are many factors, including technical and non-technical, affecting the volume of scanning activities. In this paper, we study the impact of vulnerability disclosure on the volume of scans over time and propose a machine learning-based approach to predict this impact. We conducted a comprehensive data collection of network scans from two network telescopes hosted in different countries, as well as the disclosed vulnerabilities from 2014 to 2019. We then designed a set of features to characterize the disclosed vulnerabilities and used several classifiers to predict whether a vulnerability will impact the volume of daily scans. The resulting classifier achieves over 85\% accuracy in predicting the impact. In addition, we performed an analysis of the key characteristics of vulnerabilities that directly affect scanning activities. Our findings show that this approach is able to classify vulnerabilities that have an impact on network scans. The implementation of our model and validation tests proved the efficiency of the selected features, as well as the robustness of our model to classify vulnerabilities{\textquoteright} impact on scans. {\textcopyright} 2021 Elsevier Ltd}, keywords = {Case-studies, Classification algorithm, CVE, Forecasting, Machine learning, Network scan, Network scanning, Network security, Network telescopes, NVD, OR-networks, Scanning, Software vulnerabilities, Telescopes, Times series}, doi = {10.1016/j.jnca.2021.103230}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116335984\&doi=10.1016\%2fj.jnca.2021.103230\&partnerID=40\&md5=1d7f8d5d4111761b27fc93badc70f925}, author = {Houmz, A. and Mezzour, G. and Zkik, K. and Ghogho, M. and Benbrahim, H.} } @article {ElHafidy2021, title = {Gamified mobile applications for improving driving behavior: A systematic mapping study}, journal = {Mobile Information Systems}, volume = {2021}, year = {2021}, note = {cited By 4}, abstract = {Many research works and official reports approve that irresponsible driving behavior on the road is the main cause of accidents. Consequently, responsible driving behavior can significantly reduce accidents{\textquoteright} number and severity. Therefore, in the research area as well as in the industrial area, mobile technologies are widely exploited in assisting drivers in reducing accident rates and preventing accidents. For instance, several mobile apps are provided to assist drivers in improving their driving behavior. Recently and thanks to mobile cloud computing, smartphones can benefit from the computing power of servers in the cloud for executing machine learning algorithms. Therefore, many mobile applications of driving assistance and control are based on machine learning techniques to adjust their functioning automatically to driver history, context, and profile. Additionally, gamification is a key element in the design of these mobile applications that allow drivers to develop their engagement and motivation to improve their driving behavior. To have an overview concerning existing mobile apps that improve driving behavior, we have chosen to conduct a systematic mapping study about driving behavior mobile apps that exist in the most common mobile apps repositories or that were published as research works in digital libraries. In particular, we should explore their functionalities, the kinds of collected data, the used gamification elements, and the used machine learning techniques and algorithms. We have successfully identified 220 mobile apps that help to improve driving behavior. In this work, we will extract all the data that seem to be useful for the classification and analysis of the functionalities offered by these applications. {\textcopyright} 2021 Abderrahim El hafidy et al.}, keywords = {Accidents, Computing power, Digital libraries, Driving assistance, Driving behavior, Gamification, Industrial area, Industrial research, Learning algorithms, Machine learning, Machine learning techniques, Mapping, Mobile applications, Mobile cloud computing, Mobile computing, Mobile Technology, Systematic mapping studies}, doi = {10.1155/2021/6677075}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114117887\&doi=10.1155\%2f2021\%2f6677075\&partnerID=40\&md5=6ad1b624deabb49917039716eb133f13}, author = {El Hafidy, A. and Rachad, T. and Idri, A. and Zellou, A.} } @article {HalhoulMerabet2021, title = {Intelligent building control systems for thermal comfort and energy-efficiency: A systematic review of artificial intelligence-assisted techniques}, journal = {Renewable and Sustainable Energy Reviews}, volume = {144}, year = {2021}, note = {cited By 42}, abstract = {Building operations represent a significant percentage of the total primary energy consumed in most countries due to the proliferation of Heating, Ventilation and Air-Conditioning (HVAC) installations in response to the growing demand for improved thermal comfort. Reducing the associated energy consumption while maintaining comfortable conditions in buildings are conflicting objectives and represent a typical optimization problem that requires intelligent system design. Over the last decade, different methodologies based on the Artificial Intelligence (AI) techniques have been deployed to find the sweet spot between energy use in HVAC systems and suitable indoor comfort levels to the occupants. This paper performs a comprehensive and an in-depth systematic review of AI-based techniques used for building control systems by assessing the outputs of these techniques, and their implementations in the reviewed works, as well as investigating their abilities to improve the energy-efficiency, while maintaining thermal comfort conditions. This enables a holistic view of (1) the complexities of delivering thermal comfort to users inside buildings in an energy-efficient way, and (2) the associated bibliographic material to assist researchers and experts in the field in tackling such a challenge. Among the 20 AI tools developed for both energy consumption and comfort control, functions such as identification and recognition patterns, optimization, predictive control. Based on the findings of this work, the application of AI technology in building control is a promising area of research and still an ongoing, i.e., the performance of AI-based control is not yet completely satisfactory. This is mainly due in part to the fact that these algorithms usually need a large amount of high-quality real-world data, which is lacking in the building or, more precisely, the energy sector. Based on the current study, from 1993 to 2020, the application of AI techniques and personalized comfort models has enabled energy savings on average between 21.81 and 44.36\%, and comfort improvement on average between 21.67 and 85.77\%. Finally, this paper discusses the challenges faced in the use of AI for energy productivity and comfort improvement, and opens main future directions in relation with AI-based building control systems for human comfort and energy-efficiency management. {\textcopyright} 2021 Elsevier Ltd}, keywords = {Building-control system, Conditioning systems, Control systems, energy efficiency, Energy savings, Energy utilization, Energy-savings, Heating ventilation and air conditioning, Heating ventilation and air-conditioning system, HVAC, Information management, Intelligent buildings, Intelligent systems, Machine learning, Machine-learning, Occupant, Pattern recognition, Quality control, Systematic literature review, Systematic Review, Thermal comfort}, doi = {10.1016/j.rser.2021.110969}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103719088\&doi=10.1016\%2fj.rser.2021.110969\&partnerID=40\&md5=252263802ee70f683e9929b1ff76d93a}, author = {Halhoul Merabet, G. and Essaaidi, M. and Ben Haddou, M. and Qolomany, B. and Qadir, J. and Anan, M. and Al-Fuqaha, A. and Abid, M.R. and Benhaddou, D.} } @article {Yassine2021, title = {Intelligent recommender system based on unsupervised machine learning and demographic attributes}, journal = {Simulation Modelling Practice and Theory}, volume = {107}, year = {2021}, note = {cited By 22}, abstract = {Recommendation systems aim to predict users interests and recommend items most likely to interest them. In this paper, we propose a new intelligent recommender system that combines collaborative filtering (CF) with the popular unsupervised machine learning algorithm K-means clustering. Also, we use certain user demographic attributes such as the gender and age to create segmented user profiles, when items (movies) are clustered by genre attributes using K-means and users are classified based on the preference of items and the genres they prefer to watch. To recommend items to an active user, Collaborative Filtering approach then is applied to the cluster where the user belongs. Following the experimentation for well known movies, we show that the proposed system satisfies the predictability of the CF algorithm in GroupLens. In addition, our proposed system improves the performance and time response speed of the traditional collaborative Filtering technique and the Content-Based technique too. {\textcopyright} 2020 Elsevier B.V.}, keywords = {Collaborative filtering, Collaborative filtering techniques, Content-based techniques, Intelligent recommender system, K-means, K-means clustering, Learning algorithms, Machine learning, Most likely, Population statistics, Recommender Systems, Response speed, Unsupervised machine learning, User profile}, doi = {10.1016/j.simpat.2020.102198}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096665603\&doi=10.1016\%2fj.simpat.2020.102198\&partnerID=40\&md5=37861e6691cce74784d0555379aae57f}, author = {Yassine, A. and Mohamed, L. and Al Achhab, M.} } @article {Zerouaoui2021, title = {Reviewing Machine Learning and Image Processing Based Decision-Making Systems for Breast Cancer Imaging}, journal = {Journal of Medical Systems}, volume = {45}, number = {1}, year = {2021}, note = {cited By 19}, abstract = {Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40~years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. {\textcopyright} 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.}, keywords = {Article, breast, Breast Cancer, cancer diagnosis, classifier, Computer-Assisted, Convolutional neural network, Decision making, Deep learning, deep neural network, diagnostic accuracy, diagnostic imaging, echography, Feature extraction, feature selection, female, human, Humans, image processing, image segmentation, Machine learning, Magnetic Resonance Imaging, mammography, multilayer perceptron, nuclear magnetic resonance imaging}, doi = {10.1007/s10916-020-01689-1}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100125842\&doi=10.1007\%2fs10916-020-01689-1\&partnerID=40\&md5=3074b3d443373f75f5a3c1c6134512ee}, author = {Zerouaoui, H. and Idri, A.} } @conference {Trabelsi2021341, title = {Towards an Approach of Recommendation in Business Processes Using Decision Trees}, booktitle = {Proceedings - 2021 International Symposium on Computer Science and Intelligent Controls, ISCSIC 2021}, year = {2021}, note = {cited By 0}, pages = {341-347}, abstract = {A recommender system analyses users{\textquoteright} data in order to extract their interests and preferences and suggest them relevant items. The recommendation systems have shown their applicability in many domains, especially in business processes (BP). Business processes are defined as a set of tasks that are performed by an organization to achieve a business goal. Using recommendation techniques in business processes consists of proposing relevant tasks at a certain point, which helps managers making the right decisions. In this paper, we propose an approach of recommending in BPMN-based business processes. The recommendation technique that we considered in this approach is the decision trees. {\textcopyright} 2021 IEEE.}, keywords = {BPMN model, Business goals, Business Process, Decision trees, Forestry, Machine learning, Machine-learning, Recommendation techniques, Recommender Systems, User data}, doi = {10.1109/ISCSIC54682.2021.00068}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124144617\&doi=10.1109\%2fISCSIC54682.2021.00068\&partnerID=40\&md5=aa31af21d6c3ad066ee71e9e9456ad84}, author = {Trabelsi, F.Z. and Khtira, A. and El Asri, B.} } @conference {Boumahdi2020603, title = {Crisis management systems: Big data and machine learning approach}, booktitle = {ENASE 2020 - Proceedings of the 15th International Conference on Evaluation of Novel Approaches to Software Engineering}, year = {2020}, note = {cited By 0}, pages = {603-610}, abstract = {A crisis is defined as an event that, by its nature or its consequences, poses a threat to the vital national interests or the basic needs of the population, encourages rapid decision making, and requires coordination between the various departments and agencies. Hence the need and importance of crisis and disaster management systems. These crisis and disaster management systems have several phases and techniques, and require many resources and tactics and needs. Among the needs of these systems are useful and necessary information that can be used to improve the making of good decisions, such as data on past and current crises. The application of machine learning and big data technologies in data processing of crises and disasters can yield important results in this area. In this document, we address in the first part the crisis management systems, and the tools of big data and machine learning that can be used. Then in the second part, we have established a literature review that includes a state of the art, and a discussion. Then we established a machine learning and big data approach for crisis management systems, with a description and experimentation, as well as a discussion of results and future work. {\textcopyright} Copyright 2020 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.}, keywords = {Big data, Crisis management systems, Data handling, Data technologies, Decision making, Disaster management, Disaster prevention, Disasters, Information management, Literature reviews, Machine learning, Machine learning approaches, Software engineering, State of the art}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088381343\&partnerID=40\&md5=b90b38f94e34455a12781472d1aba3ab}, author = {Boumahdi, A. and El Hamlaoui, M. and Nassar, M.} } @article {Benhar2020, title = {Data preprocessing for heart disease classification: A systematic literature review.}, journal = {Computer Methods and Programs in Biomedicine}, volume = {195}, year = {2020}, note = {cited By 25}, abstract = {Context: Early detection of heart disease is an important challenge since 17.3 million people yearly lose their lives due to heart diseases. Besides, any error in diagnosis of cardiac disease can be dangerous and risks an individual{\textquoteright}s life. Accurate diagnosis is therefore critical in cardiology. Data Mining (DM) classification techniques have been used to diagnosis heart diseases but still limited by some challenges of data quality such as inconsistencies, noise, missing data, outliers, high dimensionality and imbalanced data. Data preprocessing (DP) techniques were therefore used to prepare data with the goal of improving the performance of heart disease DM based prediction systems. Objective: The purpose of this study is to review and summarize the current evidence on the use of preprocessing techniques in heart disease classification as regards: (1) the DP tasks and techniques most frequently used, (2) the impact of DP tasks and techniques on the performance of classification in cardiology, (3) the overall performance of classifiers when using DP techniques, and (4) comparisons of different combinations classifier-preprocessing in terms of accuracy rate. Method: A systematic literature review is carried out, by identifying and analyzing empirical studies on the application of data preprocessing in heart disease classification published in the period between January 2000 and June 2019. A total of 49 studies were therefore selected and analyzed according to the aforementioned criteria. Results: The review results show that data reduction is the most used preprocessing task in cardiology, followed by data cleaning. In general, preprocessing either maintained or improved the performance of heart disease classifiers. Some combinations such as (ANN + PCA), (ANN + CHI) and (SVM + PCA) are promising terms of accuracy. However the deployment of these models in real-world diagnosis decision support systems is subject to several risks and limitations due to the lack of interpretation. {\textcopyright} 2020 Elsevier B.V.}, keywords = {Cardiology, Classification (of information), Classification technique, classifier, clinical practice, clinical research, Computer aided diagnosis, data classification, Data mining, Data preprocessing, data processing, Decision support systems, Deep learning, Diagnosis decision, diagnostic accuracy, disease classification, Diseases, empiricism, evidence based practice, feature selection, Heart, heart disease, Heart Diseases, High dimensionality, human, Humans, intermethod comparison, Machine learning, Performance of classifier, prediction, Prediction systems, Preprocessing techniques, publication, Review, Support vector machines, Systematic literature review, Systematic Review, task performance}, doi = {10.1016/j.cmpb.2020.105635}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087500300\&doi=10.1016\%2fj.cmpb.2020.105635\&partnerID=40\&md5=cae53ce36903d5d8b817ec96deb39b45}, author = {Benhar, H. and Idri, A. and L Fern{\'a}ndez-Alem{\'a}n, J.} } @article {Chlioui2020547, title = {Data preprocessing in knowledge discovery in breast cancer: systematic mapping study}, journal = {Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization}, volume = {8}, number = {5}, year = {2020}, note = {cited By 5}, pages = {547-561}, abstract = {Data Mining (DM) is a set of techniques that allow to analyse data from different perspectives and summarising it into useful information. Data mining has been increasingly used in medicine, especially in oncology. Data preprocessing is the most important step of knowledge extraction process and allows to improve the performance of the DM models. Breast cancer (BC) becomes the most common cancer among females worldwide and the leading cause of women{\textquoteright}s death. This paper aims to perform a systematic mapping study to analyse and synthesise studies on the application of preprocessing techniques for a DM task in breast cancer.Therefore, 66 relevant articles published between 2000 and October 2018 were selected and analysed according to five criteria: year/channel of publication, research type, medical task, empirical type and preprocessing task. The results show that Conferences and journals are the most targeted publication sources, researchers were more interested in applying preprocessing techniques for the diagnosis of BC, historical-based evaluation was the most used empirical type in the evaluation of preprocessing techniques in BC, and data reduction was the most investigated task of preprocessing in BC. However, A low number of papers discussed treatment which encourages researchers to devote more efforts to this task. {\textcopyright} 2020 Informa UK Limited, trading as Taylor \& Francis Group.}, keywords = {algorithm, Article, Breast Cancer, cancer classification, cancer prognosis, clinical assessment, clinical outcome, Data mining, Data mining models, Data mining tasks, Data preprocessing, Diagnosis, diagnostic accuracy, Diseases, Extraction process, health promotion, human, image analysis, knowledge, knowledge discovery, Knowledge extraction, Machine learning, Mapping, Medical informatics, nerve cell network, neural crest cell, Performance, Pre-processing techniques, processing, screening test, Systematic mapping studies, Systematic Review, validity}, doi = {10.1080/21681163.2020.1730974}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85080112312\&doi=10.1080\%2f21681163.2020.1730974\&partnerID=40\&md5=befb1bc3f31f676a8e95bbc5bff5ab6d}, author = {Chlioui, I. and Idri, A. and Abnane, I.} } @article {RHANOUI2020, title = {A hybrid recommender system for patron driven library acquisition and weeding}, journal = {Journal of King Saud University - Computer and Information Sciences}, year = {2020}, abstract = {Nowadays the explosion of information sources has shaped how library users access information and provide feedback on their preferences. Therefore, faced with this explosion and the blossoming of digital libraries, modern libraries must take up the challenge of meeting the needs of their users and considering their opinions and preferences in order to offer them adequate resources and henceforth eliminate those that are unsatisfactory. Almost all library recommender systems aim to provide users with items of interest to them. However, despite its definite interest, the staff-oriented adaptation and application of this revolutionary technique to the collection development process is still in an embryonic stage. We propose a patron-driven hybrid library recommender system that uses machine learning techniques to recommend and assist in the acquisition and weeding decision-making operations by extracting and analyzing users{\textquoteright} opinions and ratings. The recommender system is applied and validated in a real national library case using Amazon{\textquoteright}s digital library and the library{\textquoteright}s catalog as a data source.}, keywords = {Acquisition, Library Management, Machine learning, Recommender Systems, Weeding}, issn = {1319-1578}, doi = {https://doi.org/10.1016/j.jksuci.2020.10.017}, url = {https://www.sciencedirect.com/science/article/pii/S1319157820305103}, author = {Maryem Rhanoui and Mounia Mikram and Siham Yousfi and Ayoub Kasmi and Naoufel Zoubeidi} } @article {Zerouaoui202044, title = {Machine Learning and Image Processing for Breast Cancer: A Systematic Map}, journal = {Advances in Intelligent Systems and Computing}, volume = {1161 AISC}, year = {2020}, note = {cited By 3}, pages = {44-53}, abstract = {Machine Learning (ML) combined with Image Processing (IP) gives a powerful tool to help physician, doctors and radiologist to make more accurate decisions. Breast cancer (BC) is a largely common disease among women worldwide; it is one of the medical sub-field that are experiencing an emergence of the use of ML and IP techniques. This paper explores the use of ML and IP techniques for BC in the form of a systematic mapping study. 530 papers published between 2000 and August 2019 were selected and analyzed according to 6 criteria: year and publication channel, empirical type, research type, medical task, machine learning objectives and datasets used. The results show that classification was the most used ML objective. As for the datasets most of the articles used private datasets belonging to hospitals, although papers using public data choose MIAS (Mammographic Image Analysis Society) which make it as the most used public dataset. {\textcopyright} 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.}, keywords = {Breast Cancer, Common disease, Diseases, Information systems, Information use, Machine learning, Mammographic image analysis, mammography, Medical imaging, Public data, Public dataset, Sub fields, Systematic mapping studies, Systematic maps}, doi = {10.1007/978-3-030-45697-9_5}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85085473168\&doi=10.1007\%2f978-3-030-45697-9_5\&partnerID=40\&md5=e980b38be1c8a8499c579b990b79b909}, author = {Zerouaoui, H. and Idri, A. and El Asnaoui, K.} } @article {Kamri2020298, title = {Machine Learning Approach for Smart Self-diagnosing Autonomic Computing Systems}, journal = {Advances in Intelligent Systems and Computing}, volume = {1105 AISC}, year = {2020}, note = {cited By 0}, pages = {298-307}, abstract = {While modern systems and networks are continuously growing in size, complexity and diversity, the monitoring and diagnosing of such systems is becoming a real challenge. Technically and economically, more automation of the classical diagnosing tasks is needed. This has triggered a considerable research initiative, grouped under the terms self-management and Autonomic Computing. In this paper we propose a new model for smart self-diagnosing systems based on Autonomic Computing principles and Machine Learning techniques. {\textcopyright} 2020, Springer Nature Switzerland AG.}, keywords = {Autonomic Computing, Autonomic computing system, Diagnosing system, Intelligent systems, Learning systems, Machine learning, Machine learning approaches, Machine learning techniques, planning, Research initiatives, Self management, Self-diagnosing, Sustainable development, wireless networks}, doi = {10.1007/978-3-030-36674-2_31}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85080896883\&doi=10.1007\%2f978-3-030-36674-2_31\&partnerID=40\&md5=3dce8bc657338047166fb3ded16c10c8}, author = {Kamri, H. and Bounabat, B.} } @article {Gryech2020379, title = {Machine learning for air quality prediction using meteorological and traffic related features}, journal = {Journal of Ambient Intelligence and Smart Environments}, volume = {12}, number = {5}, year = {2020}, note = {cited By 4}, pages = {379-391}, abstract = {The presence of pollutants in the air has a direct impact on our health and causes detrimental changes to our environment. Air quality monitoring is therefore of paramount importance. The high cost of the acquisition and maintenance of accurate air quality stations implies that only a small number of these stations can be deployed in a country. To improve the spatial resolution of the air monitoring process, an interesting idea is to develop data-driven models to predict air quality based on readily available data. In this paper, we investigate the correlations between air pollutants concentrations and meteorological and road traffic data. Using machine learning, regression models are developed to predict pollutants concentration. Both linear and non-linear models are investigated in this paper. It is shown that non-linear models, namely Random Forest (RF) and Support Vector Regression (SVR), better describe the impact of traffic flows and meteorology on the concentrations of pollutants in the atmosphere. It is also shown that more accurate prediction models can be obtained when including some pollutants{\textquoteright} concentration as predictors. This may be used to infer the concentrations of some pollutants using those of other pollutants, thereby reducing the number of air pollution sensors. {\textcopyright} 2020 - IOS Press and the authors. All rights reserved.}, keywords = {Accurate prediction, Air quality, Air quality monitoring, Air quality prediction, Data-driven model, Decision trees, Forecasting, Machine learning, Non-linear model, Nonlinear systems, Pollution sensors, Predictive analytics, Spatial resolution, Support vector regression, Support vector regression (SVR)}, doi = {10.3233/AIS-200572}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85093821240\&doi=10.3233\%2fAIS-200572\&partnerID=40\&md5=f8b7d726f054f01a2be432560d359fc5}, author = {Gryech, I. and Ghogho, M. and Elhammouti, H. and Sbihi, N. and Kobbane, A.} } @article {Sebbar20205875, title = {MitM detection and defense mechanism CBNA-RF based on machine learning for large-scale SDN context}, journal = {Journal of Ambient Intelligence and Humanized Computing}, volume = {11}, number = {12}, year = {2020}, note = {cited By 15}, pages = {5875-5894}, abstract = {Software defined network (SDN) is a promising new network abstraction that aims to improve and facilitate network management. Due to its centralized architecture and the lack of intelligence on the data plane, SDN suffers from many security issues that slows down its deployment. Man in the Middle (MitM) attack is considered as one of the most devastating attacks in an SDN context. In fact, MitM attack allows the attackers to capture, duplicate and spoof flows by targeting southbound interfaces and SDN nodes. Furthermore, it{\textquoteright}s very difficult to detect MitM attacks since it is performed passively at the SDN level. To reduce the impact of this attack, we generally set up security policies and authentication mechanisms. However, these techniques are not applicable for a large scale SDN architecture as they require complexes and static configurations and as they negatively influence on network performance. In this paper, we propose an intrusion detection and prevention framework by using machine learning techniques to detect and stop MitM attempts. To do so, we build a context-based node acceptance based on the random forest model (CBNA-RF), which helps to setting-up appropriate security policies and to automating defense operations on a large-scale SDN context. This mechanism can realize a quick and early detection of MitM attacks by automatically detecting malicious nodes without affecting performances. The evaluation of the proposed framework demonstrates that our model can correctly classify and detect malicious connections and nodes while keeping high accuracy and precision scores. {\textcopyright} 2020, Springer-Verlag GmbH Germany, part of Springer Nature.}, keywords = {Authentication mechanisms, Centralized architecture, Decision trees, Defense operations, Intrusion detection, Intrusion detection and prevention, Machine learning, Machine learning techniques, Man-In-The-Middle (MITM) Attack, Network abstractions, Network architecture, Network security, Random forest modeling, Security systems}, doi = {10.1007/s12652-020-02099-4}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85085987877\&doi=10.1007\%2fs12652-020-02099-4\&partnerID=40\&md5=cf120767ba875958e97b87ce22203057}, author = {Sebbar, A. and Zkik, K. and Baddi, Y. and Boulmalf, M. and Kettani, M.D.E.-C.E.} } @article {Gryech2020, title = {Moreair: A low-cost urban air pollution monitoring system}, journal = {Sensors (Switzerland)}, volume = {20}, number = {4}, year = {2020}, note = {cited By 25}, abstract = {MoreAir is a low-cost and agile urban air pollution monitoring system. This paper describes the methodology used in the development of this system along with some preliminary data analysis results. A key feature of MoreAir is its innovative sensor deployment strategy which is based on mobile and nomadic sensors as well as on medical data collected at a children{\textquoteright}s hospital, used to identify urban areas of high prevalence of respiratory diseases. Another key feature is the use of machine learning to perform prediction. In this paper, Moroccan cities are taken as case studies. Using the agile deployment strategy of MoreAir, it is shown that in many Moroccan neighborhoods, road traffic has a smaller impact on the concentrations of particulate matters (PM) than other sources, such as public baths, public ovens, open-air street food vendors and thrift shops. A geographical information system has been developed to provide real-time information to the citizens about the air quality in different neighborhoods and thus raise awareness about urban pollution. {\textcopyright} 2020 by the authors. Licensee MDPI, Basel, Switzerland.}, keywords = {Agile deployments, Agile manufacturing systems, Air quality, Costs, Decision trees, Geographic information systems, Information systems, Information use, Learning systems, Machine learning, Mobile sensing, Monitoring, Particles (particulate matter), Particulate Matter, Pollution detection, Pollution monitoring, Random forests, Real-time information, Sensor deployment, Urban air pollution, Urban pollutions}, doi = {10.3390/s20040998}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079609813\&doi=10.3390\%2fs20040998\&partnerID=40\&md5=dc90b4357fcdc64d82d12f57a45f971f}, author = {Gryech, I. and Ben-Aboud, Y. and Guermah, B. and Sbihi, N. and Ghogho, M. and Kobbane, A.} } @article {Oudouar2020, title = {A novel approach based on heuristics and a neural network to solve a capacitated location routing problem}, journal = {Simulation Modelling Practice and Theory}, volume = {100}, year = {2020}, note = {cited By 12}, abstract = {In this work, we describe a method to solve the capacitated location-routing problem (CLRP) to minimize the delivery distance for a vehicle. The CLRP consists of locating depots, assigning each customer to one depot, and determining routes. The objective is to minimize the cost (distance). In the locating problem, we use a self-organizing map (SOM) to determine the depots and assign customers to depots. The SOM is an unsupervised learning method with two layers and has proven effective in several research areas, such as clustering. In the routing problem, we use the Clarke and Wright technique to determine routes. In the present work, we propose an improvement of the capacitated self-organizing map (CSOM) to optimize the location of depots and the Or-Opt algorithm to ameliorate the routes obtained by Clarke and Write (CSOM\&CW). The numerical results show that the proposed method can meet many benchmarks of small and medium instances. Computational results assess the higher performance of our approach and demonstrate its efficiency in solving large-size instances. {\textcopyright} 2019 Elsevier B.V.}, keywords = {Capacitated location, Clustering, Computational results, Conformal mapping, Its efficiencies, Location, Location routing problem, Machine learning, Network routing, Neural networks, Numerical methods, Numerical results, Optimization, Routing problems, Self organizing maps, Unsupervised learning, Unsupervised learning method}, doi = {10.1016/j.simpat.2019.102064}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85077516665\&doi=10.1016\%2fj.simpat.2019.102064\&partnerID=40\&md5=a650efb5ef7f1f150f0e4f6f9af68e91}, author = {Oudouar, F. and Lazaar, M. and Miloud, Z.E.} } @article {Elkhoukhi2020, title = {A platform architecture for occupancy detection using stream processing and machine learning approaches}, journal = {Concurrency and Computation: Practice and Experience}, volume = {32}, number = {17}, year = {2020}, note = {cited By 15}, abstract = {Context-awareness in energy-efficient buildings has been considered as a crucial fact for developing context-driven control approaches in which sensing and actuation tasks are performed according to the contextual changes. This could be done by including the presence of occupants, number, actions, and behaviors in up-to-date context, taking into account the complex interlinked elements, situations, processes, and their dynamics. However, many studies have shown that occupancy information is a major leading source of uncertainty when developing control approaches. Comprehensive and real-time fine-grained occupancy information has to be, therefore, integrated in order to improve the performance of occupancy-driven control approaches. The work presented in this paper is toward the development of a holistic platform that combines recent IoT and Big Data technologies for real-time occupancy detection in smart building. The purpose of this work focuses mainly on the presence of occupants by comparing both static and dynamic machine learning techniques. An open-access occupancy detection dataset was first used to assess the usefulness of the platform and the effectiveness of static machine learning strategies for data processing. This dataset is used for applications that follow the strategy aiming at storing data first and processing it later. However, many smart buildings{\textquoteright} applications, such as HVAC and ventilation control, require online data streams processing. Therefore, a distributed real-time machine learning framework was integrated into the platform and tested to show its effectiveness for this kind of applications. Experiments have been conducted for ventilation systems in energy-efficient building laboratory (EEBLab) and preliminary results show the effectiveness of this platform in detecting on-the-fly presence of occupants, which is required to either make ON or OFF the system and then activate the corresponding embedded control technique (eg, ON/OFF, PID, state-feedback). {\textcopyright} 2019 John Wiley \& Sons, Ltd.}, keywords = {Context- awareness, Data streams, Embedded systems, energy efficiency, Energy efficient building, Intelligent buildings, Internet of things, Learning systems, Machine learning, Machine learning approaches, Machine learning techniques, Occupancy detections, Platform architecture, Real-time data processing, State feedback, Ventilation, Ventilation control}, doi = {10.1002/cpe.5651}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076920865\&doi=10.1002\%2fcpe.5651\&partnerID=40\&md5=f34bbe0cd8dadd04282227e1a5698c57}, author = {Elkhoukhi, H. and NaitMalek, Y. and Bakhouya, M. and Berouine, A. and Kharbouch, A. and Lachhab, F. and Hanifi, M. and El Ouadghiri, D. and Essaaidi, M.} } @article {Aissaoui2020117, title = {Toward a hybrid machine learning approach for extracting and clustering learners{\textquoteright} behaviours in adaptive educational system}, journal = {International Journal of Computing Science and Mathematics}, volume = {12}, number = {2}, year = {2020}, note = {cited By 0}, pages = {117-131}, abstract = {The learning style is a vital learner{\textquoteright}s characteristic that must be considered while recommending learning materials. In this paper we have proposed an approach to identify learning styles automatically. The first step of the proposed approach aims to preprocess the data extracted from the log file of the E-learning environment and capture the learners{\textquoteright} sequences. The captured learners{\textquoteright} sequences were given as an input to the K-means clustering algorithm to group them into sixteen clusters according to the FSLSM. Then the naive Bayes classifier was used to predict the learning style of a student in real time. To perform our approach, we used a real dataset extracted from an e-learning system{\textquoteright}s log file, and in order to evaluate the performance of the used classifier, the confusion matrix method was used. The obtained results demonstrate that our approach yields excellent results. Copyright {\textcopyright} 2020 Inderscience Enterprises Ltd.}, keywords = {Adaptive systems, Classification (of information), Classifiers, Computer aided instruction, Confusion matrices, e-learning, E-learning environment, Educational systems, Hybrid machine learning, K-means clustering, Learning materials, Learning Style, Machine learning, Naive Bayes classifiers, Preprocess}, doi = {10.1504/IJCSM.2020.111113}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096034864\&doi=10.1504\%2fIJCSM.2020.111113\&partnerID=40\&md5=e39786511c32be21cc0fef5be68a0822}, author = {Aissaoui, O.E. and El Alami El Madani, Y. and Oughdir, L. and Dakkak, A. and El Allioui, Y.} } @article {1344754220010801, title = {Integrating WordNet knowledge to supplement training data in semi-supervised agglomerative hierarchical clustering for text categorization.}, journal = {International Journal of Intelligent Systems}, volume = {16}, number = {8}, year = {2001}, pages = {929 - 947}, abstract = {The text categorization (TC) is the automated assignment of text documents to predefined categories based on document contents. TC has been an application for many learning approaches, which proved effective. Nevertheless, TC provides many challenges to machine learning. In this paper, we suggest, for text categorization, the integration of external WordNet lexical information to supplement training data for a semi-supervised clustering algorithm which (i) uses a finite design set of labeled data to (ii) help agglomerative hierarchical clustering algorithms (AHC) partition a finite set of unlabeled data and then (iii) terminates without the capacity to classify other objects. This algorithm is the {\textquotedblleft}semi-supervised agglomerative hierarchical clustering algorithm{\textquotedblright} (ssAHC). Our experiments use Reuters 21578 database and consist of binary classifications for categories selected from the 89 TOPICS classes of the Reuters collection. Using the vector space model (VSM), each document is repre}, keywords = {Algorithms, Artificial intelligence, Hierarchy (Linguistics), John Wiley \& Sons Inc., Linguistic analysis (Linguistics), Machine learning}, issn = {08848173}, url = {http://search.ebscohost.com/login.aspx?direct=true\&db=iih\&AN=13447542\&site=ehost-live}, author = {Benkhalifa, Mohammed and Mouradi, Abdelhak and Bouyakhf, Houssaine} }