Search

Smart devices are used in the era of the Internet of Things (IoT) to provide efficient and reliable access to services. IoT technology can recognize comprehensive information, reliably deliver information, and intelligently process that information. Modern industrial systems have become increasingly dependent on data networks, control systems, and sensors. The number of IoT devices and the protocols they use has increased, which has led to an increase in attacks. Global operations can be disrupted, and substantial economic losses can be incurred due to these attacks. Cyberattacks have been detected using various techniques, such as deep learning and machine learning. In this paper, we propose an ensemble staking method to effectively reveal cyberattacks in the IoT with high performance. Experiments were conducted on three different datasets: credit card, NSL-KDD, and UNSW datasets. The proposed stacked ensemble classifier outperformed the individual base model classifiers.

Perception is the fundamental task of any autonomous driving system, which gathers all the necessary information about the surrounding environment of the moving vehicle. The decision-making system takes the perception data as input and makes the optimum decision given that scenario, which maximizes the safety of the passengers. This paper surveyed recent literature on autonomous vehicle perception (AVP) by focusing on two primary tasks: Semantic Segmentation and Object Detection. Both tasks play an important role as a vital component of the vehicle’s navigation system. A comprehensive overview of deep learning for perception and its decision-making process based on images and LiDAR point clouds is discussed. We discussed the sensors, benchmark datasets, and simulation tools widely used in semantic segmentation and object detection tasks, especially for autonomous driving. This paper acts as a road map for current and future research in AVP, focusing on models, assessment, and challenges in the field.

This paper aims to apply deep learning to identify autism spectrum disorder (ASD) patients from a large brain imaging dataset based on the patients’ brain activation patterns. The brain images are collected from the ABIDE (Autism Brain Imaging Data Exchange) database. The proposed convolutional neural network (CNN) architecture investigates functional connectivity patterns between different brain areas to identify specifics patterns to diagnose ASD. The enhanced CNN uses blocks of temporal convolutional layers that employ casual convolutions and dilations; hence, it is suitable for sequential data with temporality large receptive fields. Experimental results show that the proposed ECNN achieves an accuracy of up to 80% accuracy. These patterns show an anticorrelation of brain function between anterior and posterior areas of the brain; that is, the disruption in brain connectivity is one primary evidence of ASD.

Blockchain technology (BT) allows market participants to keep track of digital transactions without central recordkeeping. The features of blockchain, including decentralization, persistency, and attack resistance, allow data security and privacy. Machine learning (ML) involves the analytical platform on a massive amount of data to provide precise decisions. Since data reliability, integration, and data security are crucial in machine learning, the emergence of blockchain technology and machine learning has become a unique, most disruptive, and trending research in the last few years, achieving comparable and precise performance. The combination of blockchain and machine learning (BT–ML) has been applied across different applications to assist decision-makers in retrieving valuable data insights while preserving privacy and integration. This paper summarizes the state-of-the-art research in combing BT and ML in e-commerce and other various applications, including healthcare, smart transportation, and the Internet of Things (IoT). The challenges and benefits of integrating machine learning and blockchain technologies are outlined in the paper. We also discuss the advantages and limitations of current algorithms in the BT–ML integration. This paper provides a roadmap for researchers to pave the way for current and future research directions in combing the BT and ML research areas.

Data Analytics has become an essential part of the Internet of Things (IoT), mainly text analytics-related applications, since they can be utilized to benefit educational institutions, consumers, and enterprises. Text Analytics is excessively used in Smart Education after the emerging technologies such as personal computers, tablets, and even smartphones transformed the education system and improved the teaching methods by helping the teachers to evaluate the students' performance or determine the degree of similarity between a lecturer’s and the students’ posts in the discussion forum, and by collecting the students’ feedback on the teaching method, in order to categorize each feedback into positive or negative, which will help the lecturers in optimizing their way of teaching. In this paper, we highlight the main components of IoT analytics, along with a comprehensive background of text analytics used techniques and applications. This paper provides a comprehensive survey and comparison of the leveraged IoT Text Analytics models and methods in Smart Education and many other applications.

An essential goal of recommendation systems is to provide users with accurate and personalized recommendations that meet their preferences. With the rapid growth of IoT-connected sensors, the availability of contextual information has increased, and this has necessitated the fast development of Context-Aware Recommendation Systems (CARS). Context-Aware recommenders are different from traditional recommenders because of their ability to predict the ratings of target users/items by exploiting the knowledge of contextual information. Context-aware recommenders define the context as any information that characterizes the situations of items and users at a particular interaction. They are essential for some contexts where prediction can be more precise in generating specific personalized recommendations. This paper provides a comprehensive review of context-based recommendation systems in IoT environments, namely IoT-CARS, and sheds light on their requirements, characteristics, and applications. We characterize context-aware recommenders in terms of the different IoT contexts and how these contexts are modeled. We also highlight the used metrics to evaluate the performance of various context-based recommenders.

An essential goal of recommendation systems is to provide users with accurate and personalized recommendations that meet their preferences. With the rapid growth of IoT-connected sensors, the availability of contextual information has increased, and this has necessitated the fast development of Context-Aware Recommendation Systems (CARS). Context-Aware recommenders are different from traditional recommenders because of their ability to predict the ratings of target users/items by exploiting the knowledge of contextual information. Context-aware recommenders define the context as any information that characterizes the situations of items and users at a particular interaction. They are essential for some contexts where prediction can be more precise in generating specific personalized recommendations. This paper provides a comprehensive review of context-based recommendation systems in IoT environments, namely IoT-CARS, and sheds light on their requirements, characteristics, and applications. We characterize context-aware recommenders in terms of the different IoT contexts and how these contexts are modeled. We also highlight the used metrics to evaluate the performance of various context-based recommenders.

The increasing number of car accidents is a significant issue in current transportation systems. According to the World Health Organization (WHO), road accidents are the eighth highest top cause of death around the world. More than 80% of road accidents are caused by distracted driving, such as using a mobile phone, talking to passengers, and smoking. A lot of efforts have been made to tackle the problem of driver distraction; however, no optimal solution is provided. A practical approach to solving this problem is implementing quantitative measures for driver activities and designing a classification system that detects distracting actions. In this paper, we have implemented a portfolio of various ensemble deep learning models that have been proven to efficiently classify driver distracted actions and provide an in-car recommendation to minimize the level of distractions and increase in-car awareness for improved safety. This paper proposes E2DR, a new scalable model that uses stacking ensemble methods to combine two or more deep learning models to improve accuracy, enhance generalization, and reduce overfitting, with real-time recommendations. The highest performing E2DR variant, which included the ResNet50 and VGG16 models, achieved a test accuracy of 92% as applied to state-of-the-art datasets, including the State Farm Distracted Drivers dataset, using novel data splitting strategies.

The outbreak of the coronavirus 2019 (COVID-19) has created an excellent challenge for the care system worldwide. One in every of the foremost vital points of this challenge is that the management of COVID-19 patients needing acute and/or vital metastasis care. The main objective of applying data mining to Covid-19 dataset is essential to propel learning by empowering data-oriented decision making to improve existing clinical practices and learning materials. Current data mining techniques offer patient data analysis for achieving an automated diagnosis of the diseases as an example; however, the results are not very accurate nor reliable, especially with a dynamic virus as the COVID-19. In this paper, we are proposing a multi-stage diagnostic (MSD-Covid19) model to enhance the diagnosis of the COVID-19, and to provide a sustainable automated system to improve the healthcare systems and patient outcomes. The first stage includes a selection of a classification model with no reduction attributes. Tested classification algorithms include Deep learning, Multilayer Perceptron, KNN, Bayesian Auto Regression, Logistic Model Trees (LMT), Hoeffding tree (VFDT), and Fuzzy Unordered Rule Induction Algorithm. In the second stage, a rough set reduction algorithm based on genetic algorithms is employed, and finally, an optimization of the classification is conducted using the reduced attributes. The proposed model is evaluated on a global COVID-19 dataset. Experimental results demonstrate that the proposed MSD-Covid19 has a great contribution to increase the diagnostic accuracy of the COVID-19 disease behaviour.

The Internet of Things (IoT) allows the connection of various devices/things to achieve a particular goal. The emergence of smart systems using IoT technology obtains efficient solutions for challenging problems in various industries. This will lead to a significant reduction in the costs for many different domains. With a focus on the healthcare sector, the Internet of Medical things (IoMT) improves various decision-making processes such as diagnosis, treatment, assessment, and rehabilitation. In this paper, our focus will be on the IoT and its impact on healthcare systems. Various algorithms and methods used for the IoMT, along with a comparative analysis of the performance, are discussed. Communication systems requirements, cloud computing's role, and security and privacy issues in the IoMT are also addressed. This paper acts as a comprehensive roadmap for future research direction the IoMT.

Recommendation systems are widely used in various areas to personalize recommendations and suggestions to users. However, they are vulnerable to shilling attacks in which malicious users try to promote their products or diminish their competitors'. Therefore, detecting shilling attacks can significantly improve the quality of recommender systems and user experience. With the increasing complexity of attacks and changes in attackers' behavior, more advanced approaches are required to find the hidden patterns in data. This paper proposes a CNN-based hybrid model and architecture to integrate self-learning and flexible aspects of CNN with other approaches to enhance the prediction results of shilling attacks. Two benchmark datasets are used in the experimental analysis, the Movie-Lens 100K and Netflix. The performance of the proposed hybrid models is compared to that of the traditional deep learning and machine learning detection methods. Experimental results show that the superiority of hybrid models over individual models depends on the sparsity level of data and divergence of results.

With the current growth of the number of airline passengers using JFK airport on everyday basis, massive delays occur throughout the system, which causes a significant bottleneck. This paper presents a discrete simulation model of the aircraft arrival and departure process at JFK airport. This paper's main objective is to identify where the bottleneck lies and provide recommendations to ease the congestion within the airport. The simulation model includes the calculations of taxi-in and taxi-out time distributions and the development of a conceptual queuing model of the runway system. The simulation model is trained using data from 2015 from the US Customs and Border Protection, the United States Department of Transportation, and the JFK airport. The results show that the bottleneck is caused by congestion during taxi-out, waiting for take-off. It is recommended that JFK utilizes optimization methods to minimize flight delays.

The problem of measuring the availability of generation units in electric power systems has been addressed in the literature by using a set of analytical equations and Monte Carlo Simulation (MCS). MCS, as a powerful simulation tool, is much easier to use than analytical approaches in measuring the availability of large applications. However, the simulated process using MCS entails deducing the operating state sequences for each component along the simulated time followed by combining all sequences for all components in order to deduce system availability. This simulated process is both lengthy and time-consuming. This paper introduces a new method to measure the availability of generation units and optimize their utilization using Discrete Event Simulation (DES) model. The experimental result of a real case study illustrates the efficiency of using DES.

A blockchain is a digitized, decentralized, public ledger of all cryptocurrency transactions. The blockchain is transforming industries by enabling innovative business practices. Its revolutionary power has permeated areas such as bank-ing, financing, trading, manufacturing, supply chain management, healthcare, and government. Blockchain and the Internet of Things (BIOT) apply the us-age of blockchain in the inter-IOT communication system, therefore, security and privacy factors are achievable. The integration of blockchain technology and IoT creates modern decentralized systems. The BIOT models can be ap-plied by various industries including e-commerce to promote decentralization, scalability, and security. This research calls for innovative and advanced re-search on Blockchain and recommendation systems. We aim at building a se-cure and trust-based system using the advantages of blockchain-supported secure multiparty computation by adding smart contracts with the main blockchain protocol. Combining the recommendation systems and blockchain technology allows online activities to be more secure and private. A system is constructed for enterprises to collaboratively create a secure database and host a steadily updated model using smart contract systems. Learning case studies include a model to recommend movies to users. The accuracy of models is evaluated by an incentive mechanism that offers a fully trust-based recom-mendation system with acceptable performance.

The Internet of Things (IoT) connects heterogeneous physical devices with the ability to collect data using sensors and actuators. These data can infer useful information for decision-makers in many applications systems monitoring, healthcare, transportations, data storage, smart homes, and many others. In the Era of the Internet of Things (IoT), recommender systems can support scenarios such as recommending apps, IoT workflows, services, sensor equipment, hotels, and drugs to users and customers. Current state-of-art recommendation systems, including collaborative filtering methods, suffer from scalability and sparsity problems. This article proposes a clustering-based recommendation system that adopts the vector space model from information retrieval to obtain highly accurate recommendations. The proposed algorithm uses four well-known clustering techniques as k-means (KM), fuzzy c-mean (FCM), Single-Linkage (SLINK), and Self-Organizing-Maps (SOM). Various experiments and benchmarking on seven IoT rating datasets from different fields are conducted to assess the performance of the proposed recommender system. The experimental results using both error and prediction metrics indicate that the proposed algorithm outperforms the traditional collaborative filtering approach. Besides, adopting the self-organizing strategy obtains recommendations of significant accuracy as compared to the partitional learning approaches.

Artificial intelligence research in the stock market sector has been heavily geared towards stock price prediction rather than stock price manipulation. As online trading systems have increased the amount of high volume and re-al-time data transactions, the stock market has increased vulnerability to at-tacks. This paper aims to detect these attacks based on normal trade behavior using an Artificial Immune System (AIS) approach combined with one of four clustering algorithms. The AIS approach is inspired by its proven ability to handle time-series data and its ability to detect abnormal behavior while only being trained on regular trade behavior. These two main points are essential as the models need to adapt over time to adjust to normal trade behavior as it evolves, and due to confidentiality and data restrictions, real-world manipula-tions are not available for training. This paper discovers a competitive alterna-tive to the leading approach and investigates the effects of combining AIS with clustering algorithms; Kernel Density Estimation, Self-Organized Maps, Densi-ty-Based Spatial Clustering of Applications with Noise and Spectral clustering. The best performing solution achieves leading performance using common clustering metrics, including Area Under the Curve, False Alarm Rate, False Negative Rate, and Computation Time.

Point clouds are one of the most widely used data formats produced by depth sensors. There is a lot of research into feature extraction from unordered and irregular point cloud data. Deep learning in computer vision achieves great performance for data classification and segmentation of 3D data points as point clouds. Various research has been conducted on point clouds and remote sensing tasks using deep learning (DL) methods. However, there is a research gap in providing a road map of existing work, including limitations and challenges. This paper focuses on introducing the state-of-the-art DL models, categorized by the structure of the data they consume. The models’ performance is collected, and results are provided for benchmarking on the most used datasets. Additionally, we summarize the current benchmark 3D datasets publicly available for DL training and testing. In our comparative study, we can conclude that convolutional neural networks (CNNs) achieve the best performance in various remote-sensing applications while being light-weighted models, namely Dynamic Graph CNN (DGCNN) and ConvPoint.

The impact of many factors on stock price has made the prediction of the stock market a problematic and highly complicated task to achieve. IoT analytics has enabled predictive analysis concerning the stock market, with internet search trends, reactions to current events, Twitter data, and historical stock returns as input data. Although inconsistencies remain as to which data sources are deemed most adequate, data preprocessing techniques have successfully overcome data integrity issues and unstructured data formats in specific applications. Additionally, advancements in computational power and machine learning technologies have led to the ability to handle tremendous amounts of information, accompanied by the growth of interest in this specific domain. In this paper, a Multivariate Multistep Output Long-Short-Term-Memory (MMLSTM) model is proposed to provide a one-week prediction on the stock close value for the technology company, “Apple Inc.” with the stock name “AAPL”. A large variety of data sources enabled by IoT platforms have been employed to model the impact of public sentiment and engagement on the closing price of this particular stock by looking at Google Search Trends, e-News headlines, and Tweets involving AAPL and its products. The proposed MMLSTM has improved the Mean Square Error (MSE) of up to 65% compared to ARIMA and Random Forest models. In addition, the proposed MMLSTM has outperformed most of the LSTM models introduced in the literature.

Various clustering algorithms use diverse settings, parameters, and initializations, generally result in different clustering solutions. Therefore, it is essential to compare and evaluate the clustering results and select the methods that best fits the “actual” data distribution. This can be achieved by using informative quality metrics that reflect the “goodness” of the resulting solutions compared to the ground truth. Different Extrinsic validation metrics have been provided in the literature, including F-measure, Entropy, Rand Index, and Purity. However, there is a gap in the literature in evaluating the level of divergence between multiple clusterings in an aggregate, especially in consensus clustering. In this paper, we propose three scattering measures that calculate the divergence level (i.e., scattering level) between two or more clustering algorithms. The proposed metrics are Scatter F-score, Scatter Entropy, and Scatter Purity. The proposed scattering measures are variants of the traditional F-measure, Entropy, and Purity quality measures. The scattering measures are used as pre-assessment criteria for deciding which clustering algorithms to combine in an aggregate. Experimental results on artificial, real, and text datasets show that the scattering measures play an important role in enhancing the clustering quality in consensus clustering and increasing the feasibility of the consensus.

Recommendation systems are involved in many industries, for example (e-health, transportation, e-commerce, and agriculture), where Recommendation systems aim to benefit both market and user levels. They help consumers make the right decision based on their preferences without being exposed to data overload. Nowadays, there is a wide range of recommenders based on different filtering approaches, such as Collaborative-based, Content-based, hybrid-based, demographic-based filtering approaches. In this paper, we present clustering-based recommendation systems. We also experiment and show the results for a collaborative-based movie recommender using different clustering techniques such as Kmeans, BIRCH Balanced Iterative Reducing and Clustering using Hierarchies) and DBSCAN (Density-based Spatial Clustering of Applications with Noise). We intended to choose different clustering approaches such as partitional, hierarchical, and density-based clustering approaches. We incorporated Item-based Collaborative filtering, then applied multiple clustering techniques on the dataset based on the users’ ratings. We checked the performance using accuracy measures such as MAE (Mean Absolute Error), RMSE (Root mean square error), and the computed time. These measures were calculated for analysis and comparison purposes.

Network traffic classification provides an essential contribution in network administration functions and network management such as QoS, security, and billing. Those functions need a timely and accurate detection of specific traffics. Current network traffic classification methods offer supervised and unsupervised learning capabilities for network traffic prediction or classification. Classical machine learning classifiers that use a single classification model suffer from low prediction and classification accuracy, especially for high dimensional datasets with a high sparsity level. These challenges in individual-based learning models have created a need for hybrid learning. Recently, hybriddeep learning has shown a significant role in traffic forecasting and classification due to its efficiency. However, a tradeoff between the aggregate models and the classification accuracy presents a substantial challenge in network traffic classification problems. In this paper, we have suggested two hybrid models that combine the Convolutional Neural Network (CNN) along with the Recurrent Neural Network (RNN) models, inclusive of the Gated recurrent unit (GRU) and Long Short-Term Memory (LSTM), to improve traffic classification accuracy. The efficiency of the suggested models has been evaluated by comparing them with various individual-based models using real network traffic traces. The hybrid CNN-LSTM and CNN-GRU have achieved an accuracy of up to 99.23% and 93.92%, respectively, for binary classification and 67.16% for multiclass classification.

In the era of secure communication and the constantly changing pattern of internet applications, traditional packet classification methods fail to achieve the accuracy needed for diverse network management functions. Recently Machine Learning (ML) techniques have been used to design viable packet classification solutions. However, due to the complexity and dynamic feature of internet traffic, efficient packet classification is still challenging for various machine learning algorithms. In this paper, we propose the adoption of feature selection methods through dimensionality reduction to enhance the classifiers' performance. We evaluated the performance of four well-known classifiers, including K-nearest neighbour (KNN), Support Vector Machines (SVM), Decision Trees (DT), and Logistic Regression (LR) with and without feature selection. We used two feature selection methods, including principal component analysis and Autoencoder. Experimental analysis is performed on real network traffic datasets with binary and multi-class categories. We assessed each classifier's performance using precision, recall, f-score, accuracy, and ROC. Experimental results show that the Precision, Recall, and F-score for the Multi-class problem are improved by 4.7 %, 6%, and 9%, respectively, after adopting either PCA or Autoencoder methods. The classification accuracy is also improved by up to 13%. We can also conclude that Autoencoder performed better for the KNN and LR, while PCA achieved comparable results for both the SVM and DT classifiers.

Detecting communities of common behaviors, interests, and interactions in social networks is essential to model a network's structure. Overlapping community detection is an NP-Hard problem. Several solutions have been proposed; however, most of these techniques are computationally expensive. We have developed a fast-hierarchical algorithm using the notion of segmentation by weighted aggregation. Experimental results on synthetic and real benchmark networks show that the proposed algorithm effectively finds communities (Clusters) with varied overlap and non-exhaustiveness structures. Our method outperforms the state-of-the-art hierarchical clustering algorithms measured by the F-measure and the computational time.

A cyber-attack is precautious manipulation of computer systems and networks using malware to conciliate data or restrict processes or operations. These types of attacks are vastly growing over the years. This increase in structure and complexity calls for advanced innovation in defensive strategies and detection. Traditional approaches for detecting cyber-attacks suffer from low efficiency, especially with the high demands of increasing security threats. With the substitutional increase of computational power, machine learning and deep learning methods are considered significant solutions for defending and detecting those threats or attacks. In this paper, we performed a comparative analysis of IoT cyberattack detection methods. We utilized six different algorithms including, Random Forest, Logistic Regression, SVM, NB, KNN, and MLP. Each model is evaluated using precision, recall, F-score, and ROC.