Search

The research presented in the following paper focuses on the effectiveness of a modern standard Arabic corpus, AraFast, in training transformer models for natural language processing tasks, particularly in Arabic. In the study described herein, four experiments were conducted to evaluate the use of AraFast across different configurations: segmented, unsegmented, and mini versions. The main outcomes of the present study are as follows: Transformer models trained with larger and cleaner versions of AraFast, especially in question-answering, indicate the impact of corpus quality and size on model efficacy. Secondly, a dramatic reduction in training loss was observed with the mini version of AraFast, underscoring the importance of optimizing corpus size for effective training. Moreover, the segmented text format led to a decrease in training loss, highlighting segmentation as a beneficial strategy in Arabic NLP. In addition, using the study findings, challenges in managing noisy data derived from web sources are identified, which were found to significantly hinder model performance. These findings collectively demonstrate the critical role of well-prepared, segmented, and clean corpora in advancing Arabic NLP capabilities. The insights from AraFast's application can guide the development of more efficient NLP models and suggest directions for future research in enhancing Arabic language processing tools. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) consists of complex and dynamically aggregated elements or smart entities that need decentralized supervision for data exchanging throughout different networks. The artificial bee colony (ABC) is utilized in optimization problems for the big data in IoT, cloud and central repositories. The main limitation during the searching mechanism is that every single food site is compared with every other food site to find the best solution in the neighboring regions. In this way, an extensive number of redundant comparisons are required, which results in a slower convergence rate, greater time consumption and increased delays. This paper presents a solution to optimize search operations with an enhanced ABC (E-ABC) approach. The proposed algorithm compares the best food sites with neighboring sites to exclude poor sources. It achieves an efficient mechanism, where the number of redundant comparisons is decreased during the searching mechanism of the employed bee phase and the onlooker bee phase. The proposed algorithm is implemented in a replication scenario to validate its performance in terms of the mean objective function values for different functions, as well as the probability of availability and the response time. The results prove the superiority of the E-ABC in contrast to its counterparts. [ABSTRACT FROM AUTHOR]

Artificial intelligence-based question-answering (QA) systems can expedite the performance of various tasks. These systems either read passages and answer questions given in natural languages or if a question is given, they extract the most accurate answer from documents retrieved from the internet. Arabic is spoken by Arabs and Muslims and is located in the middle of the Arab world, which encompasses the Middle East and North Africa. It is difficult to use natural language processing techniques to process modern Arabic owing to the language's complex morphology, orthographic ambiguity, regional variations in spoken Arabic, and limited linguistic and technological resources. Only a few Arabic QA experiments and systems have been designed on small datasets, some of which are yet to be made available. Although several reviews of Arabic QA studies have been conducted, the number of studies covered has been limited and recent trends have not been included. To the best of our knowledge, only two systematic reviews focused on Arabic QA have been published to date. One covered only 26 primary studies without considering recent techniques, while the other covered only nine studies conducted for Holy Qur'an QA systems. Here, the included studies were analyzed in terms of the datasets used, domains covered, types of Arabic questions asked, information retrieved, the mechanism used to extract answers, and the techniques used. Based on the results of the analysis, several limitations, concerns, and recommendations for future research were identified. Additionally, a novel taxonomy was developed to categorize the techniques used based on the domains and approaches of the QA system. [ABSTRACT FROM AUTHOR]

The Intrusion Detection System (IDS) is the most widely used network security mechanism for distinguishing between normal and malicious traffic network activities. It aids network security in that it may identify unforeseen hazards in network traffic. Several techniques have been put forth by different researchers for network intrusion detection. However, because network attacks have increased dramatically, making it difficult to execute precise detection rates quickly, the demand for effectively recognizing network incursion is growing. This research proposed an improved solution that uses Long Short-Term Memory (LSTM) and hash functions to construct a revolutionary double-layer security solution for IoT Network Intrusion Detection. The presented framework utilizes standard and well-known real-time IDS datasets such as KDDCUP99 and UNSWNB-15. In the presented framework, the dataset was pre-processed, and it employed the Shuffle Shepherd Optimization (SSO) algorithm for tracking the most informative attributes from the filtered database. Further, the designed model used the LSTM algorithm for classifying the normal and malicious network traffic precisely. Finally, a secure hash function SHA3-256 was utilized for countering the attacks. The intensive experimental assessment of the presented approach with the conventional algorithms emphasized the efficiency of the proposed framework in terms of accuracy, precision, recall, etc. The analysis showed that the presented model attained attack prediction accuracy of 99.92% and 99.91% for KDDCUP99 and UNSWNB-15, respectively. [ABSTRACT FROM AUTHOR]

The Federated Cloud Computing (FCC) paradigm provides scalability advantages to Cloud Service Providers (CSP) in preserving their Service Level Agreement (SLA) as opposed to single Data Centers (DC). However, existing research has primarily focused on Virtual Machine (VM) placement, with less emphasis on energy efficiency and SLA adherence. In this paper, we propose a novel solution, Federated Cloud Workload Prediction with Deep Q-Learning (FEDQWP). Our solution addresses the complex VM placement problem, energy efficiency, and SLA preservation, making it comprehensive and beneficial for CSPs. By leveraging the capabilities of deep learning, our FEDQWP model extracts underlying patterns and optimizes resource allocation. Real-world workloads are extensively evaluated to demonstrate the efficacy of our approach compared to existing solutions. The results show that our DQL model outperforms other algorithms in terms of CPU utilization, migration time, finished tasks, energy consumption, and SLA violations. Specifically, our QLearning model achieves efficient CPU utilization with a median value of 29.02, completes migrations in an average of 0.31 units, finishes an average of 699 tasks, consumes the least energy with an average of 1.85 kWh, and exhibits the lowest number of SLA violations with an average of 0.03 violations proportionally. These quantitative results highlight the superiority of our proposed method in optimizing performance in FCC environments. [ABSTRACT FROM AUTHOR]

Today, fake news is a growing concern due to its devastating impacts on communities. The rise of social media, which many users consider the main source of news, has exacerbated this issue because individuals can easily disseminate fake news more quickly and inexpensive with fewer checks and filters than traditional news media. Numerous approaches have been explored to automate the detection and prevent the spread of fake news. However, achieving accurate detection requires addressing two crucial aspects: obtaining the representative features of effective news and designing an appropriate model. Most of the existing solutions rely solely on content-based features that are insufficient and overlapping. Moreover, most of the models used for classification are constructed with the concept of a dense features vector unsuitable for short news sentences. To address this problem, this study proposed a Web-Informed-Augmented Fake News Detection Model using Stacked Layers of Convolutional Neural Network and Deep Autoencoder called ICNN-AEN-DM. The augmented information is gathered from web searches from trusted sources to either support or reject the claims in the news content. Then staked layers of CNN with a deep autoencoder were constructed to train a probabilistic deep learning-base classifier. The probabilistic outputs of the stacked layers were used to train decision-making by staking multilayer perceptron (MLP) layers to the probabilistic deep learning layers. The results based on extensive experiments challenging datasets show that the proposed model performs better than the related work models. It achieves 26.6% and 8% improvement in detection accuracy and overall detection performance, respectively. Such achievements are promising for reducing the negative impacts of fake news on communities. [ABSTRACT FROM AUTHOR]

The advent of Artificial Intelligence (AI) and the Internet of Things (IoT) have recently created previously unimaginable opportunities for boosting clinical and patient services, reducing costs and improving community health. Yet, a fundamental challenge that the modern healthcare management system faces is storing and securely transferring data. Therefore, this research proposes a novel Lionized remora optimization-based serpent (LRO-S) encryption method to encrypt sensitive data and reduce privacy breaches and cyber-attacks from unauthorized users and hackers. The LRO-S method is the combination of hybrid metaheuristic optimization and improved security algorithm. The fitness functions of lion and remora are combined to create a new algorithm for security key generation, which is provided to the serpent encryption algorithm. The LRO-S technique encrypts sensitive patient data before storing it in the cloud. The primary goal of this study is to improve the safety and adaptability of medical professionals' access to cloud-based patient-sensitive data more securely. The experiment's findings suggest that the secret keys generated are sufficiently random and one of a kind to provide adequate protection for the data stored in modern healthcare management systems. The proposed method minimizes the time needed to encrypt and decrypt data and improves privacy standards. This study found that the suggested technique outperformed previous techniques in terms of reducing execution time and is cost-effective. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is one of the most widely used technologies today, and it has a significant effect on our lives in a variety of ways, including social, commercial, and economic aspects. In terms of automation, productivity, and comfort for consumers across a wide range of application areas, from education to smart cities, the present and future IoT technologies hold great promise for improving the overall quality of human life. However, cyber-attacks and threats greatly affect smart applications in the environment of IoT. The traditional IoT security techniques are insufficient with the recent security challenges considering the advanced booming of different kinds of attacks and threats. Utilizing artificial intelligence (AI) expertise, especially machine and deep learning solutions, is the key to delivering a dynamically enhanced and up-to-date security system for the next-generation IoT system. Throughout this article, we present a comprehensive picture on IoT security intelligence, which is built on machine and deep learning technologies that extract insights from raw data to intelligently protect IoT devices against a variety of cyber-attacks. Finally, based on our study, we highlight the associated research issues and future directions within the scope of our study. Overall, this article aspires to serve as a reference point and guide, particularly from a technical standpoint, for cybersecurity experts and researchers working in the context of IoT. [ABSTRACT FROM AUTHOR]

Proactive resource management in Cloud Services not only maximizes cost effectiveness but also enables issues such as Service Level Agreement (SLA) violations and the provisioning of resources to be overcome. Workload prediction using Deep Learning (DL) is a popular method of inferring complicated multidimensional data of cloud environments to meet this requirement. The overall quality of the model depends on the quality of the data as much as the architecture. Therefore, the data sourced to train the model must be of good quality. However, existing works in this domain have either used a singular data source or have not taken into account the importance of uniformity for unbiased and accurate analysis. This results in the efficacy of DL models suffering. In this paper, we provide a technical analysis of using DL models such as Recurrent Neural Networks (RNN), Multilayer Perception (MLP), Long Short-Term Memory (LSTM), and, Convolutional Neural Networks (CNN) to exploit the time series characteristics of real-world workloads from the Parallel Workloads Archive of the Standard Workload Format (SWF) with the aim of conducting an unbiased analysis. The robustness of these models is evaluated using the Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) error metrics. The findings of these highlight that the LSTM model exhibits the best performance compared to the other models. Additionally, to the best of our knowledge, insights of DL in workload prediction of cloud computing environments is insufficient in the literature. To address these challenges, we provide a comprehensive background on resource management and load prediction using DL. Then, we break down the models, error metrics, and data sources across different bodies of work. [ABSTRACT FROM AUTHOR]

Recently, malware has become more abundant and complex as the Internet has become more widely used in daily services. Achieving satisfactory accuracy in malware detection is a challenging task since malicious software exhibit non-relevant features when they change the performed behaviors as a result of their awareness of the analysis environments. However, the existing solutions extract features from the entire collected data offered by malware during the run time. Accordingly, the actual malicious behaviors are hidden during the training, leading to a model trained using unrepresentative features. To this end, this study presents a feature extraction scheme based on the proposed dynamic initial evasion behaviors determination (DIEBD) technique to improve the performance of evasive malware detection. To effectively represent evasion behaviors, the collected behaviors are tracked by examining the entropy distributions of APIs-gram features using the box-whisker plot algorithm. A feature set suggested by the DIEBD-based feature extraction scheme is used to train machine learning algorithms to evaluate the proposed scheme. Our experiments' outcomes on a dataset of benign and evasive malware samples show that the proposed scheme achieved an accuracy of 0.967, false positive rate of 0.040, and F1 of 0.975. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has triggered a global humanitarian disaster that has never been seen before. Medical experts, on the other hand, are undecided on the most valuable treatments of therapy because people ill with this infection exhibit a wide range of illness indications at different phases of infection. Further, this project aims to undertake an experimental investigation to determine which treatments for COVID-19 disease is the most effective and preferable. The research analysis is based on vast data gathered from professionals and research journals, making this study a comprehensive reference. To solve this challenging task, the researchers used the HF AHPTOPSIS Methodology, which is a well-known and highly effective MultiCriteria Decision Making (MCDM) technique. The technique assesses the many treatment options identified through various research papers and guidelines proposed by various countries, based on the recommendations of medical practitioners and professionals. The review process begins with a ranking of different treatments based on their effectiveness using the HF-AHP approach and then evaluates the results in five different hospitals chosen by the authors as alternatives. We also perform robustness analysis to validate the conclusions of our analysis. As a result, we obtained highly corroborative results that can be used as a reference. The results suggest that convalescent plasma has the greatest rank and priority in terms of effectiveness and demand, implying that convalescent plasma is the most effective treatment for SARS-CoV-2 in our opinion. Peepli also has the lowest priority in the estimation. [ABSTRACT FROM AUTHOR]

A large component of the Health Information Systems now comprises numerous independent apps created in the past that need to be merged to provide a more uniform service. In addition to affecting the Intelligent Health Board Functionality and dependability, the quality of these additional apps may also have an impact. A critical characteristic of the SHS's management and upkeep is the SHS's reliance on the real benefits provided to it. In speaking, an HMIS (Healthcare Management Information System) is a computer-based device that benefits medical practitioners to perform their duties more efficiently by coordinating all of their data. Even though these systems are widely used by most of the world, there is a significant need to comprehend these technologies and indeed the potential they provide. Healthcare data warehouses in Saudi Arabia have evolved through time, and this research examines how key service improvements in Saudi present varied viewpoints on how premium initiative help may be attained in health as well as how this could be done. When it comes to understanding how different types of medical professionals interact with healthcare systems throughout history, researchers developed stages of the maturity model. [ABSTRACT FROM AUTHOR]

Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community's behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency–inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques. [ABSTRACT FROM AUTHOR]

Machine learning is a technique that is widely employed in both the academic and industrial sectors all over the world. Machine learning algorithms that are intuitive can analyse risks and respond swiftly to breaches and security issues. It is crucial in offering a proactive security system in the field of cybersecurity. In real time, cybersecurity protects information, information systems, and networks from intruders. In the recent decade, several assessments on security and privacy estimates have noted a rapid growth in both the incidence and quantity of cybersecurity breaches. At an increasing rate, intruders are breaching information security. Anomaly detection, software vulnerability diagnosis, phishing page identification, denial of service assaults, and malware identification are the foremost cyber-security concerns that require efficient clarifications. Practitioners have tried a variety of approaches to address the present cybersecurity obstacles and concerns. In a similar vein, the goal of this research is to assess the idealness of machine learning-based intrusion detection systems under fuzzy conditions using a Multi-Criteria Decision Making (MCDM)-based Analytical Hierarchy Process (AHP) and a Technique for Order of Preference by Similarity to Ideal-Solutions (TOPSIS). Fuzzy sets are ideal for dealing with decision-making scenarios in which experts are unsure of the best course of action. The projected work would support practitioners in identifying, prioritising, and selecting cybersecurity-related attributes for intrusion detection systems, allowing them to design more optimal and effective intrusion detection systems. [ABSTRACT FROM AUTHOR]

The current cyber-attack environment has put even the most protected systems at risk as the hackers are now modifying technologies to exploit even the tiniest of weaknesses and infiltrate networks. In this situation, it's critical to design and construct software that is both secure and long-lasting. While security is the most well-defined aspect of health information software systems, it is equally significant to prioritise sustainability because any health information software system will be more effective if it provides both security and sustainability to the customers at the same time. In this league, it is crucial to determine those characteristics in the systems that can help in the accurate assessment of the sustainable-security of the health information software during the development stage. This research work employed the Fuzzy Analytic Network Process (Fuzzy ANP) to estimate the impact of the overall sustainable-security of health information software systems and their characteristics in order to achieve a high level of sustainable-security. Furthermore, the study validates the efficacy of the Fuzzy ANP procedure by testing it on five different versions of a health information software system through Fuzzy Technique for Order of Preference by Similarity to Ideal Solutions (Fuzzy TOPSIS). Despite the sensitivity of the health information software systems, this study employed multiple versions of health information software system. When compared with the existing procedures for testing the sustainable-security of health information software systems, the outcomes were conclusive and significantly more effective. Besides saving time and resources, the mechanism suggested in this research work aims to establish an outline that software practitioners can follow to enhance the sustainable-security of health information software systems. [ABSTRACT FROM AUTHOR]

The estimated 30 million children and adults are suffering with diabetes across the world. A person with diabetes can recognize several symptoms, and it can also be tested using retina image as diabetes also affects the human eye. The doctor is usually able to detect retinal changes quickly and can help prevent vision loss. Therefore, regular eye examinations are very important. Diabetes is a chronic disease that affects various parts of the human body including the retina. It can also be considered as major cause for blindness in developed countries. This paper deals with classification of retinal image into diabetes or not with the help of deep learning algorithms and architecture. Hence, deep learning is beneficial for classification of medical images specifically such a complex image of human retina. A large number of image data are considered throughout the project on which classification is performed by using binary classifier. On applying certain deep learning algorithms, model results into the training accuracy of 96.68% and validation accuracy of 66.82%. Diabetic retinopathy can be considered as an effective and efficient method for diabetes detection. [ABSTRACT FROM AUTHOR]

The blockchain technology plays a significant role in the present era of information technology. In the last few years, this technology has been used effectively in several domains. It has already made significant differences in human life, as well as is intended to have noticeable impact in many other domains in the forthcoming years. The rapid growth in blockchain technology has created numerous new possibilities for use, especially for healthcare applications. The digital healthcare services require highly effective security methodologies that can integrate data security with the availablemanagement strategies. To test and understand this goal of security management in Saudi Arabian perspective, the authors performed a numerical analysis and simulation through a multi criteria decision making approach in this study. The authors adopted the fuzzy Analytical Hierarchy Process (AHP) for evaluating the effectiveness and then applied the fuzzy Technique forOrder of Preference by Similarity to Ideal Solution (TOPSIS) technique to simulate the validation of results. For eliciting highly corroborative and conclusive results, the study referred to a real time project of diabetes patients' management application of Kingdom of Saudi Arabia (KSA). The results discussed in this paper are scientifically proven and validated through various analysis approaches. Hence the present study can be a credible basis for other similar endeavours being undertaken in the domain of blockchain research. [ABSTRACT FROM AUTHOR]

Security is an important component in the process of developing healthcare web applications. We need to ensure security maintenance; therefore the analysis of healthcare web application's security risk is of utmost importance. Properties must be considered to minimise the security risk. Additionally, security risk management activities are revised, prepared, implemented, tracked, and regularly set up efficiently to design the security of healthcare web applications. Managing the security risk of a healthcare web application must be considered as the key component. Security is, in specific, seen as an add-on during the development process of healthcare web applications, but not as the key problem. Researchers must ensure that security is taken into account right from the earlier developmental stages of the healthcare web application. In this row, the authors of this study have used the hesitant fuzzy-based AHP-TOPSIS technique to estimate the risks of various healthcare web applications for improving security-durability. This approach would help to design and incorporate security features in healthcare web applications that would be able to battle threats on their own, and not depend solely on the external security of healthcare web applications. Furthermore, in terms of healthcare web application's security-durability, the security risk variable is measured, and vice versa. Hence, the findings of our study will also be useful in improving the durability of several web applications in healthcare. [ABSTRACT FROM AUTHOR]

In Alzheimer's disease (AD) progression, it is imperative to identify the subjects with mild cognitive impairment before clinical symptoms of AD appear. This work proposes a technique for decision support in identifying subjects who will show transition from mild cognitive impairment (MCI) to Alzheimer's disease (AD) in the future. We used robust predictors from multivariate MRI-derived biomarkers and neuropsychological measures and tracked their longitudinal trajectories to predict signs of AD in the MCI population. Assuming piecewise linear progression of the disease, we designed a novel weighted gradient offset-based technique to forecast the future marker value using readings from at least two previous follow-up visits. Later, the complete predictor trajectories are used as features for a standard support vector machine classifier to identify MCI-to-AD progressors amongst the MCI patients enrolled in the Alzheimer's disease neuroimaging initiative (ADNI) cohort. We explored the performance of both unimodal and multimodal models in a 5-fold cross-validation setup. The proposed technique resulted in a high classification AUC of 91.2% and 95.7% for 6-month- and 1-year-ahead AD prediction, respectively, using multimodal markers. In the end, we discuss the efficacy of MRI markers as compared to NM for MCI-to-AD conversion prediction. [ABSTRACT FROM AUTHOR]

Ever since its outbreak in the Wuhan city of China, COVID-19 pandemic has engulfed more than 211 countries in the world, leaving a trail of unprecedented fatalities. Even more debilitating than the infection itself, were the restrictions like lockdowns and quarantine measures taken to contain the spread of Coronavirus. Such enforced alienation affected both the mental and social condition of people significantly. Social interactions and congregations are not only integral part of work life but also formthe basis of human evolvement. However, COVID-19 brought all such communication to a grinding halt. Digital interactions have failed to enthuse the fervor that one enjoys in face-to-face meets. The pandemic has shoved the entire planet into an unstable state. The main focus and aim of the proposed study is to assess the impact of the pandemic on different aspects of the society in Saudi Arabia. To achieve this objective, the study analyzes two perspectives: the early approach, and the late approach of COVID-19 and the consequent effects on different aspects of the society. We used a Machine Learning based framework for the prediction of the impact of COVID-19 on the key aspects of society. Findings of this research study indicate that financial resources were the worst affected. Several countries are facing economic upheavals due to the pandemic and COVID-19 has had a considerable impact on the lives as well as the livelihoods of people. Yet the damage is not irretrievable and the world's societies can emerge out of this setback through concerted efforts in all facets of life. [ABSTRACT FROM AUTHOR]

Most of the security strategies today are primarily designed to provide security protection, rather than to solve one of the basic security issues related to adequate software product architecture. Several models, frameworks and methodologies have been introduced by the researchers for a secure and sustainable software development life cycle. Therefore it is important to assess the usability of the popular security requirements engineering (SRE) approaches.Asignificant factor in themanagement and handling of successful security requirements is the assessment of security requirements engineering method performance. This assessment will allow changes to the engineering process of security requirements. The consistency of security requirements depends heavily on the usability of security requirements engineering. Several SRE approaches are available for use and each approach takes into account several factors of usability but does not cover every element of usability. There seems to be no realistic implementation of such models because the concept of usability is not specific. This paper aims at specifying the different taxonomy of usability and design hierarchical usability model. The taxonomy takes into account the common quality assessment parameters that combine variables, attributes, and characteristics identified in different approaches used for security requirements engineering. The multiple-criteria decision-making (MCDM) model used in this paper for usability evaluation is called the fuzzy AHP-TOPSIS model which can conveniently be incorporated into the current approach of software engineering. Five significant usability criteria are identified and used to evaluate the six different alternatives. Such strategies are graded as per their expected values of usability. [ABSTRACT FROM AUTHOR]

Nowadays, machine learning classification techniques have been successfully used while building data-driven intelligent predictive systems in various application areas including smartphone apps. For an effective context-aware system, context pre-modeling is considered as a key issue and task, as the representation of contextual data directly influences the predictive models. This paper mainly explores the role of major context pre-modeling tasks, such as context vectorization by defining a good numerical measure through transformation and normalization, context generation and extraction by creating new brand principal components, context selection by taking into account a subset of original contexts according to their correlations, and eventually context evaluation, to build effective context-aware predictive models utilizing multi-dimensional contextual data. For creating models, various popular machine learning classification techniques such as decision tree, random forest, k-nearest neighbor, support vector machines, naive Bayes classifier, and deep learning by constructing a neural network of multiple hidden layers, are used in our study. Based on the context pre-modeling tasks and classification methods, we experimentally analyze user-centric smartphone usage behavioral activities utilizing their contextual datasets. The effectiveness of these machine learning context-aware models is examined by considering prediction accuracy, in terms of precision, recall, f-score, and ROC values, and has been made an empirical discussion in various dimensions within the scope of our study. [ABSTRACT FROM AUTHOR]

In this paper, seven greedy heuristics for construction of association rules are compared from the point of view of the length and coverage of constructed rules. The obtained rules are compared also with optimal ones constructed by dynamic programming algorithms. The average relative difference between length of rules constructed by the best heuristic and minimum length of rules is at most 4%. The same situation is with coverage. [ABSTRACT FROM AUTHOR]

We consider bi-criteria optimization problems for decision rules and rule systems relative to length and coverage. We study decision tables with many-valued decisions in which each row is associated with a set of decisions as well as single-valued decisions where each row has a single decision. Short rules are more understandable; rules covering more rows are more general. Both of these problems—minimization of length and maximization of coverage of rules are NP-hard. We create dynamic programming algorithms which can find the minimum length and the maximum coverage of rules, and can construct the set of Pareto optimal points for the corresponding bi-criteria optimization problem. This approach is applicable for medium-sized decision tables. However, the considered approach allows us to evaluate the quality of various heuristics for decision rule construction which are applicable for relatively big datasets. We can evaluate these heuristics from the point of view of (i) single-criterion—we can compare the length or coverage of rules constructed by heuristics; and (ii) bi-criteria—we can measure the distance of a point (length, coverage) corresponding to a heuristic from the set of Pareto optimal points. The presented results show that the best heuristics from the point of view of bi-criteria optimization are not always the best ones from the point of view of single-criterion optimization. [ABSTRACT FROM AUTHOR]

In the paper, an application of dynamic programming approach for optimization of association rules from the point of view of knowledge representation is considered. The association rule set is optimized in two stages, first for minimum cardinality and then for minimum length of rules. Experimental results present cardinality of the set of association rules constructed for information system and lower bound on minimum possible cardinality of rule set based on the information obtained during algorithm work as well as obtained results for length. [ABSTRACT FROM AUTHOR]

DNA profiling involves the analysis of sequences of an individual or mixed DNA profiles to identify the persons that these profiles belong to. A critically important application of DNA profiling is in forensic science to identify criminals by finding a match between their blood samples and the DNA profile found on the crime scene. Other applications include paternity tests, disaster victim identification, missing person investigations, and mapping genetic diseases. A crucial task in DNA profiling is the determination of the number of contributors in a DNA mixture profile, which is challenging due to issues that include allele dropout, stutter, blobs, and noise in DNA profiles; these issues negatively affect the estimation accuracy and the computational complexity. Machine-learning-based methods have been applied for estimating the number of unknowns; however, there is limited work in this area and many more efforts are required to develop robust models and their training on large and diverse datasets. In this paper, we propose and develop a software tool called TAWSEEM that employs a multilayer perceptron (MLP) neural network deep learning model for estimating the number of unknown contributors in DNA mixture profiles using PROVEDIt, the largest publicly available dataset. We investigate the performance of our developed deep learning model using four performance metrics, namely accuracy, F1-score, recall, and precision. The novelty of our tool is evident in the fact that it provides the highest accuracy (97%) compared to any existing work on the most diverse dataset (in terms of the profiles, loci, multiplexes, etc.). We also provide a detailed background on the DNA profiling and literature review, and a detailed account of the deep learning tool development and the performance investigation of the deep learning method. [ABSTRACT FROM AUTHOR]

The Global Positioning System (GPS) is not the only way to solve connected objects' geo-localization problems; it is also possible to use the mobile network infrastructure to geo-locate objects connected to the network, using antennas and signals designed for voice and data transfer, such as the 5th generation network. 5G is considered as a least expensive solution because there is no specific equipment to set up. As long as the object is in an area covered by the network, it connects to the nearest 5G Micro-Cell (MC). Through exchange of signals with the MC node we can locate the object. Currently, this location is very fast with less than 5 s but not very precise because it depends on the number of MC antennas of the operator in question and their distance. This paper presents a novel technique to geo-locate connected object in a covered 5G area. We exploit the 5G SS-RSRP used for signal quality measurement, to estimate the distance between two Connected Objects (COs) in move and in a dense urban area. The overall goal is to present a new concept laying on the 5G SS-RSRP signalling. The proposed solution takes into consideration the Deterministic and the Stochastic effect of the received signals which is not treated by the previous works. The accuracy is optimum even after approaching to the distance of one meter which is not reached in previous works too. Our method can also be deployed in the upcoming 5G network since it relies on 5G signals itself. This work and that of Wang are both based on RSRP and give comparable theoretical complexities therefore comparable theoretical execution times as well. However, to obtain a reliable learning Wang requires a huge amount of data which makes it difficult to get a real time aspect of this algorithm. The use of RSRP and the elimination of the learning phase will give more chance to our work to achieve desired performances. Numerical results show the appropriateness of the proposed algorithms and good location accuracy of around one meter. The Cramer Rao Lower Bound derivations shows the robustness of the proposed estimator and consolidate the work. [ABSTRACT FROM AUTHOR]

Expert systems, a form of artificial intelligence (AI), are typically designed to solve many real-world problems by reasoning through knowledge, which is primarily represented as IF–THEN rules, with the information acquired from humans or domain experts. However, to assume such rules for personalized decision-making in an intelligent, context-aware mobile application is a challenging issue. The reason is that different mobile users may behave differently in various day-to-day situations, i.e., not identical, and thus the rules for personalized services must be reflected according to their symmetrical or asymmetrical behavioral activities. Therefore, our key focus is to solve this issue through adding personalized decision-making intelligence to develop powerful mobile applications to assist the end-users. To achieve our goal, in this paper, we explore on "Mobile Expert System", where we take into account machine-learning rules as knowledge-base rather than traditional handcrafted static rules. Thus, the concept of a mobile expert system enables the computing and decision-making processes more actionable and intelligent than traditional ones in the domain of mobile analytics and applications. Our experiment section shows that the context-aware machine learning rules discovered from users' mobile phone data can contribute in building a mobile expert system to solve a particular problem, through making personalized decisions in various context-aware test cases. [ABSTRACT FROM AUTHOR]

Cloud computing offers new features of sharing resources and applications to meet users' computing requirements. It is a model by which the users can access computing resources as services offered on the Internet (cloud services). Cloud service providers offer a highly diverse range of asymmetric cloud services with heterogeneous features, which makes it difficult for the users to find the best service that fits his needs. Many research studies have been done on cloud service discovery, and several models and solutions that applied different techniques have been proposed. This paper aims at presenting the state of the art in the area of cloud services discovery by exploring the current approaches, techniques, and models. Furthermore, it proposes a taxonomy of cloud service discovery approaches. An integrative review approach was used to explore the related literature. Then, by analyzing the existing cloud service discovery solutions, a taxonomy of discovery approaches was suggested based on several perspectives including the discovery environment and the discovery process methods. The proposed taxonomy allows easily classifying and comparing cloud services discovery solutions. Moreover, it may reveal issues and gaps for further research and expose new insights for more innovative and effective cloud services discovery solutions. [ABSTRACT FROM AUTHOR]

Cyber security has recently received enormous attention in today's security concerns, due to the popularity of the Internet-of-Things (IoT), the tremendous growth of computer networks, and the huge number of relevant applications. Thus, detecting various cyber-attacks or anomalies in a network and building an effective intrusion detection system that performs an essential role in today's security is becoming more important. Artificial intelligence, particularly machine learning techniques, can be used for building such a data-driven intelligent intrusion detection system. In order to achieve this goal, in this paper, we present an Intrusion Detection Tree ("IntruDTree") machine-learning-based security model that first takes into account the ranking of security features according to their importance and then build a tree-based generalized intrusion detection model based on the selected important features. This model is not only effective in terms of prediction accuracy for unseen test cases but also minimizes the computational complexity of the model by reducing the feature dimensions. Finally, the effectiveness of our IntruDTree model was examined by conducting experiments on cybersecurity datasets and computing the precision, recall, fscore, accuracy, and ROC values to evaluate. We also compare the outcome results of IntruDTree model with several traditional popular machine learning methods such as the naive Bayes classifier, logistic regression, support vector machines, and k-nearest neighbor, to analyze the effectiveness of the resulting security model. [ABSTRACT FROM AUTHOR]