An intrusion detection system (IDS) is an important protection instrument for detecting complex network attacks. Various machine learning (ML) or deep learning (DL) algorithms have been proposed for implementing anomaly-based IDS (AIDS). Our review of the AIDS literature identifies some issues in related work, including the randomness of the selected algorithms, parameters, and testing criteria, the application of old datasets, or shallow analyses and validation of the results. This paper comprehensively reviews previous studies on AIDS by using a set of criteria with different datasets and types of attacks to set benchmarking outcomes that can reveal the suitable AIDS algorithms, parameters, and testing criteria. Specifically, this paper applies 10 popular supervised and unsupervised ML algorithms for identifying effective and efficient ML-AIDS of networks and computers. These supervised ML algorithms include the artificial neural network (ANN), decision tree (DT), k-nearest neighbor (k-NN), naive Bayes (NB), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) algorithms, whereas the unsupervised ML algorithms include the expectation-maximization (EM), k-means, and self-organizing maps (SOM) algorithms. Several models of these algorithms are introduced, and the turning and training parameters of each algorithm are examined to achieve an optimal classifier evaluation. Unlike previous studies, this study evaluates the performance of AIDS by measuring the true positive and negative rates, accuracy, precision, recall, and F-Score of 31 ML-AIDS models. The training and testing time for ML-AIDS models are also considered in measuring their performance efficiency given that time complexity is an important factor in AIDSs. The ML-AIDS models are tested by using a recent and highly unbalanced multiclass CICIDS2017 dataset that involves real-world network attacks. In general, the k-NN-AIDS, DT-AIDS, and NB-AIDS models obtain the best results and show a greater capability in detecting web attacks compared with other models that demonstrate irregular and inferior results.

Recently, development in intelligent transportation systems (ITS) requires the input of various kinds of data in real-time and from multiple sources, which imposes additional research and application challenges. Ongoing studies on Data Fusion (DF) have produced significant improvement in ITS and manifested an enormous impact on its growth. This paper reviews the implementation of DF methods in ITS to facilitate traffic flow analysis (TFA) and solutions that entail the prediction of various traffic variables such as driving behavior, travel time, speed, density, incident, and traffic flow. It attempts to identify and discuss real-time and multi-sensor data sources that are used for various traffic domains, including road/highway management, traffic states estimation, and traffic controller optimization. Moreover, it attempts to associate abstractions of data level fusion, feature level fusion, and decision level fusion on DF methods to better understand the role of DF in TFA and ITS. Consequently, the main objective of this paper is to review DF methods used for real-time and multi-sensor (heterogeneous) TFA studies. The review outcomes are (i) a guideline of constructing DF methods which involve preprocessing, filtering, decision, and evaluation as core steps, (ii) a description of the recent DF algorithms or methods that adopt real-time and multi-sensor sources data and the impact of these data sources on the improvement of TFA, (iii) an examination of the testing and evaluation methodologies and the popular datasets and (iv) an identification of several research gaps, some current challenges, and new research trends.

Systems based on fog computing produce massive amounts of data; accordingly, an increasing number of fog computing apps and services are emerging. In addition, machine learning (ML), which is an essential area, has gained considerable progress in various research domains, including robotics, neuromorphic computing, computer graphics, natural language processing (NLP), decision-making, and speech recognition. Several researches have been proposed that study how to employ ML to settle fog computing problems. In recent years, an increasing trend has been observed in adopting ML to enhance fog computing applications and provide fog services, like efficient resource management, security, mitigating latency and energy consumption, and traffic modeling. Based on our understanding and knowledge, there is no study has yet investigated the role of ML in the fog computing paradigm. Accordingly, the current research shed light on presenting an overview of the ML functions in fog computing area. The ML application for fog computing become strong end-user and high layers services to gain profound analytics and more smart responses for needed tasks. We present a comprehensive review to underline the latest improvements in ML techniques that are associated with three aspects of fog computing: management of resource, accuracy, and security. The role of ML in edge computing is also highlighted. Moreover, other perspectives related to the ML domain, such as types of application support, technique, and dataset are provided. Lastly, research challenges and open issues are discussed.

Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep Learning. In this paper, a pre-trained Convolutional Neural Network (CNN) was applied to a dataset of voice pathology to maximize the classification accuracy. This study also proposes a distinguished training method combined with various training strategies in order to generalize the application of the proposed system on a wide range of problems related to voice disorders. The proposed system has tested using a voice database, namely the Saarbrücken voice database (SVD). The experimental results show the proposed CNN method for speech pathology detection achieves accuracy up to 95.41%. It also obtains 94.22% and 96.13% for F1-Score and Recall. The proposed system shows a high capability of the real-clinical application that offering a fast-automatic diagnosis and treatment solutions within 3 s to achieve the classification accuracy.

Nowadays, coronavirus (COVID-19) is getting international attention due it considered as a life-threatened epidemic disease that hard to control the spread of infection around the world. Machine learning (ML) is one of intelligent technique that able to automatically predict the event with reasonable accuracy based on the experience and learning process. In the meantime, a rapid number of ML models have been proposed for predicate the cases of COVID-19. Thus, there is need for an evaluation and benchmarking of COVID-19 ML models which considered the main challenge of this study. Furthermore, there is no single study have addressed the problem of evaluation and benchmarking of COVID diagnosis models. However, this study proposed an intelligent methodology is to help the health organisations in the selection COVID-19 diagnosis system. The benchmarking and evaluation of diagnostic models for COVID-19 is not a trivial process. There are multiple criteria requires to evaluate and some of the criteria are conflicting with each other. Our study is formulated as a decision matrix (DM) that embedded mix of ten evaluation criteria and twelve diagnostic models for COVID-19. The multi-criteria decision-making (MCDM) method is employed to evaluate and benchmarking the different diagnostic models for COVID19 with respect to the evaluation criteria. An integrated MCDM method are proposed where TOPSIS applied for the benchmarking and ranking purpose while Entropy used to calculate the weights of criteria. The study results revealed that the benchmarking and selection problems associated with COVID19 diagnosis models can be effectively solved using the integration of Entropy and TOPSIS. The SVM (linear) classifier is selected as the best diagnosis model for COVID19 with the closeness coefficient value of 0.9899 for our case study data. Furthermore, the proposed methodology has solved the significant variance for each criterion in terms of ideal best and worst best value, beside issue when specific diagnosis models have same ideal best value.