Alzheimer's disease (AD) in elderly populations is widespread through progressive dementia occurs due to age or family history. A prognosis of Alzheimer's disease using biomarker synthesis responses analyzed by Artificial Intelligence (AI) models such as Genetic Algorithms (GA) and Neural Networks (NN) delivers definite prediction for different protein levels. In this paper, a Neuro-Gen Evo-Synthesis (NGES) framework is proposed to identify biomarker discovery in Alzheimer's prognosis among elderly populations. In this framework, the patient data is analyzed from multivariate protein signatures of pre-clinical Alzheimer's Disease Neuroimaging Initiative (ADNI) plasma proteome dataset. The initial step is to extract the biomarker synthesis production for their composition during various human activities. Using offspring function, which is a genetic function, the extracted tuples are examined for the total-ti protein level. The co-existing protein compositions with A and /1 activity levels are cross validated for calculating mutation. The resultant mutation trains a neural network connected to either of the tau protein levels. In this process, the neural network excludes the offspring of either A or /1 that happens independently. This estimation reaching its tiniest level provides a premier prognosis value towards Alzheimer's disease analysis. The proposed Neuro-Gen Evo-Synthesis framework is carried out using the Python 3.10 setup and PyTorch is utilized for training the Neuro-Gen learning model. The performance of the proposed model is validated by evaluating metrics, such as prognosis accuracy, seizure estimation, estimation error, estimation time, and precision. The experimental results show the proposed Neuro-Gen Evo-Synthesis framework's superiority over existing models. Findings-The proposed framework shows improvement results, based on P - tau (pg/mL), in which the model achieves 0.78% higher prediction accuracy, 4.73% greater seizure estimation, 1.10% higher estimation precision, a 1.78% reduction in estimation error, and a 48.49% less in processing time. Based on specificity criteria the improvement analysis of proposed model achieves 1.02% higher prediction accuracy, 6.00% higher seizure estimation, and 1.60% higher estimation precision. Additionally, it minimizes estimation error by 20.17% and minimizes processing time by 17.70%, providing an optimal solution with enhanced accuracy.

Unmanned Aerial Vehicles (UAVs) or drones are flying robots, which can be controlled either remotely or autonomously to accomplish a certain mission. Drones have now become incredibly well-known and are being used in different applications such as defense, telecommunication, agricultural, and disaster management. However, they continue to face several challenges in their design; one challenge of drones is the energy consumption of their batteries during mission execution. Drones need relatively high energy for cancellation of gravity force; as a result, their flight duration is highly constrained. Another challenge that might happen is the failure of any of the drone’s motors. In this case, either hardware or software system should be used to attain safe landing. Therefore, there is a need for a design that can reduce the power consumption in drones and assist in safe landing in case of failure of any drone’s subsystem. This study addresses these issues and proposes an energy-efficient and safe landing design for drones. The proposed design suggests that a drone is constructed from a soft silicon material with Helium injection and uses a Penta-copter that has a fixed motor at the center and four motors around the tube. The advantage of this design is the reduction of drone’s weight which helps to reduce power consumption, increase flight time, and provide safe landing. However, delicate materials can be pierced and environmental factors like wind can quickly alter the motion.

Human–computer interaction (HCI) is deployed in various real-time applications, including healthcare, for automated patient response. In such applications, robot-assisted interactive scenarios are modeled to handle patient queries and provide precise information. Timely query sensing and accurate data analysis are required to achieve accurate patient responses. In this study, responsive policy decision (RPD) using manifold mediator learning (MML) is introduced to improve data detection accuracy and accuracy in robot-assisted HCI applications. The initial decision-making process in data analytics is based on interaction stages and medical data detection. After identifying the most appropriate policy, respondents are provided with time-based responses based on the patient’s queries. When it comes to improving the accuracy of data analysis decisions, machine learning uses policies based on interaction stages and previous state efficiency of HCI responses. The experimental analysis proves the reliability of the proposed method by improving the accuracy of data analysis and reducing its complexity and response time for the varying queries and time intervals.

The outbreak of COVID-19 has promoted distance learning and rapidly increased the usage of online learning platforms. As a result, more and more IT companies are competing to offer high-quality Web-based E-Learning Platforms (WELPs). However, the problem facing educational institutions is how to evaluate the quality of WELPs to choose the one that best fulfills their needs. In order to select the most appropriate WELP among different alternatives, many evaluation criteria must be considered by the Decision Maker (DM). Hence, evaluating WELPs is a complex Multi-Criteria Decision Making (MCDM) problem that needs to be addressed efficiently. In literature, we have noticed that MCDM methods are rarely used for evaluating WELPs. In addition, traditional MCDM methods suffer from additive complexity and inconsistency due to the numerous pairwise comparisons of criteria. In contrast, Hybrid MCDM (HMCDM is a promising and more efficient decision-support tool. In this paper, we propose a HMCDM approach for evaluating and ranking WELPs which is more efficient and more reliable than traditional approaches. The proposed approach incorporates different techniques (i.e., BWM, SAW, and Delphi) and comprises the following three phases: 1) a Hierarchical Structure Quality Model (HSQM) is defined in which the evaluation criteria are identified; 2) a Criteria Preference Structure (CPS) is developed where the criteria identified in HSQM are weighted using the pairwise comparison Best-Worst Method (BWM); 3) the performance of alternative WELPs w.r.t criteria is estimated and integrated with the CPS using the Simple Additive Weighting (SAW) method to determine their ranking. The widely used consensus method, Delphi, has been utilized in phases 2 and 3 to estimate the relative preferences of the criteria and the scores of alternatives over these criteria. The proposed approach has been validated and compared to the widely accepted MCDM method, Analytical Hierarchy Process (AHP). The results revealed that the proposed approach surpasses AHP.

Medical healthcare services rely on communication technologies for exchanging digital records of patients. The new digitalizing of health records brings a specific change in healthcare services. The Electronic Health Records (EHRs) contains cumulative information about patients, such as medical history, observations, diagnostics, specimens, and reports. EHRs are sensitive information readily available for patient's and healthcare providers' access while maintaining privacy. Therefore, preserving security and privacy is of utmost importance for healthcare systems since it reduces the impact of adversaries on EHR exchange and transmissions through wearable antennas. This research introduces Healthcare Data Privacy (HDP) through Backpropagation Learning (BL) to improve privacy maintenance in medical healthcare transmission services using wearable devices. The proposed method identifies the need for encrypting and decrypting the accumulated healthcare data based on data integrity verifications. It operates on two levels for verifying the security measures to prevent data losses in successive transmissions of wearable devices.

Many replication protocols, which can be used in various distributed applications such as distributed databases, collaborative applications, and distributed agenda, sacrifice strong consistency to achieve lower latency and higher throughput. This paper describes the design, specification, implementation, and evaluation of Unidirectional and Multidirectional Replication, which challenge this inflexible tradeoff. By propagating the resulting states parallelly, as in Primary-Backup Replication, but with fewer messages, while having a head that processes write requests and a tail that processes read requests, as in Chain Replication, Unidirectional Replication improves the latency and throughput of the two protocols without compromising strong consistency. To improve the utilization of computing and communication resources of Unidirectional Replication, Multidirectional Replication divides objects into several logical shards and runs an instance of Unidirectional Replication on each logical shard. We have accomplished the proposed protocols in three steps: (1) merging Primary-Backup Replication and Chain Replication into Unidirectional Replication; (2) merging Unidirectional Replication and logical sharding into Multidirectional Replication; and (3) implementation and evaluation. Empirical results show that, compared to Primary-Backup Replication, when handling read requests with write-read conflicts, Unidirectional Replication shows an improvement of roughly 66% in latency; compared to Chain Replication, when handling write requests with basic settings, Unidirectional Replication shows an improvement of roughly 59% in throughput; and compared to Unidirectional Replication, Multidirectional Replication shows an improvement of 150% in the number of clients that it can handle.

Data modelling and analysis have become a recent trend in medical and healthcare applications for their ease of visualization and handling. To keep up with the vast amount of information generated by such medical and healthcare applications, the need for computer-aided modelling and intelligent data handling is expected to increase the quality of assessment and visualization. Moreover, reliable modelling requires structured data handling for achieving better data visualization. The un-ordered and raw disease/medical data require formal structuring and grouping for improving the visualization process. Existing models consume too much time for processing a huge volume of data. This, in turn, causes a high error rate in classification, which directly affects system performance. In this paper, biosensors gather patient health information and examine the infectious with a high prediction rate. A biosensor rapidly collects patient health data changes and reduces the time complexity of data modelling and analysis. Moreover, a supervised Non-Variant Structuring (NVS) approach for grouping infectious disease data is introduced. This approach helps improve the visualization of sensor-based acquired raw data. In this structuring process, the associativity and disparity features of the infectious disease data are identified for grouping and analyzing the disease-related features. The introduced structuring method employs a supervised learning technique for identifying the associativity and disparity in different instances of accumulation based on a Hidden Markov Model (HMM). This learning technique reduces the chances of non-partial organization of infectious disease data for better modelling and analysis. The performance of the suggested approach is verified with a sensitivity ratio of 98.2%, a specificity ratio of 96.7%, and accuracy ratio of 95.5%, a prediction error rate of 7.8% less, and a classification time of 10.1% less compared to other existing methods.

Recently, the leading cause of preventable blindness is diabetic retinopathy (DR). Although there are several undiagnosed and non-treated cases of DR, accurate and adequate retinal screening could facilitate the early detection and treatment of DR. The goal of this research is to develop a reliable DR screening and detection model to reduce the risk of DR-related blindness. DR-infected eyes describe ophthalmologist for further examination and diagnosis might reduce the risk of vision loss and provide timely and accurate diagnostic information. Hence, this paper proposes a hybrid inductive machine learning algorithm (HIMLA) as an automated DR detection diagnostic tool. HIMLA processes and classifies colored fundus images as healthy (no retinopathy) or unhealthy (presence of DR) by identifying the appropriate medical DR cases. The proposed algorithm comprises four stages: pre-processing, segmentation, feature extraction, and classification. At the pre-processing stage, colored fundus images are normalized to a specific brightness level to enhance the quality of the images. In the segmentation stage, the processed image is encoded and decoded to segment the images for improving image quality. Furthermore, feature extraction and classification are performed using multiple instance learning (MIL). The proposed method was evaluated on CHASE datasets for the detection of DR. The accuracy, sensitivity, and specificity of the proposed approach are 96.62%, 95.31%, and 96.88%, respectively. These results indicates that HIMLA outperforms other DR models, such as ML-based neovascularization detection in the optic disc (MLB-NVD), genetic algorithm–based diabetic retinopathy (GAB-DR), DL algorithm diabetic retinopathy (DLA-DR), and diagnostic assessment–based DL for diabetic retinopathy (DAD-DR ), which reduces the risk of vision loss.

Cloud Computing (CC) has become increasingly popular since it provides a wide variety of customized and reliable computational services. With the rapid growth of this technology, more and more IT services providers compete to offer high-quality and cost-effective cloud services that best fulfill their customers' needs. Given the vast diversity of these offers, the choice of the most appropriate Cloud Service Provider (CSP) became a dilemma that confuses most cloud customers. Many diverged criteria have to be considered to precisely evaluate services offered by several CSPs, some of these criteria cannot be quantified easily such as usability and security. The selection of the best CSP is thus a complex Multi-Criteria Decision Making (MCDM) problem that needs to be addressed efficiently. Previous studies of this problem employed MCDM methods that are either unfeasible when it is difficult or meaningless to quantify alternatives over criteria or computationally expensive and inconsistent when relative preferences of alternatives and criteria are used instead. In this paper, we propose a novel MCDM approach that is feasible, efficient and consistent using relative preferences of criteria and alternatives. The proposed approach incorporates Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and the Best Worst Method (BWM) to rank CSPs using evaluation criteria characterizing their services. The integrated approach has been tested and validated through a use-case scenario which demonstrates its effectiveness and correctness. We have also compared the proposed approach to the most commonly used MCDM approach, Analytical Hierarchical Process (AHP). The results clearly show that the proposed approach outperforms AHP in terms of computational complexity and consistency; hence, it is more efficient and reliable than AHP.

Detecting Internet malicious activities has been and continues to be a critical issue that needs to be addressed effectively. This is essential to protect our personal information, computing resources, and financial capitals from unsolicited actions, such as, credential information theft, downloading and installing malware, extortion, etc. The introduction of the social media such as Twitter has given malicious users a new and a promising platform to perform their activities, ranging from a simple spam message to taking a full control over the victim’s machine. Twitter revealed that its algorithms for detecting spam are not very effective; most of the trending hashtags include unrelated spam and advertising tweets which indicates that there is a problem with the currently used spam detection framework. This paper proposes a new approach for detecting spam in Twitter microblogging using Machine Learning (ML) techniques and domain popularity services. The proposed approach comprises two main stages: 1) Tweets are collected periodically and filtered by selecting the ones that appear more frequently than a decided threshold in the specified period (i.e. common tweets). Then, an inspection is conducted on the common tweets by checking the associated URL domain with Alexa’s top one million globally viewed websites. If a tweet is common on Twitter but does not appear on the top one million globally viewed websites, it is flagged as a potential spam. 2) The second stage kicks in by running ML algorithms on the flagged tweets to extract features that help detect the cluster of spam and prevent it in real-time. The performance of the proposed approach has been evaluated using three most popular classification models (random forest, J48, and Naïve Bayes). For all classifiers, results showed the effectiveness of the proposed method in terms of different performance metrics (e.g. precision, sensitivity, F1score, accuracy) and using different test scenarios. Keywords—Spam detection; phishing detection; domain popularity; machine learning; Twitter

Nowadays, robotics plays a vital role in medical applications, especially in dentistry, where robots can track oral hygiene and perform dental surgeries. Dental implant replacement is one of the most challenging issues in dental surgery; quality procedures and safety measures need to be considered during this process. Manual dental implant is usually incapable to reach the satisfactory levels of accuracy and safety. In addition, it requires well-trained dentists and consumes a long time. Therefore, robot-assisted surgery systems are of utmost importance for dental implant placement as they can maintain higher level of dental examination precision and safety. More specifically, robotic arms can be manufactured with intelligent models for drilling identified locations in teeth. These intelligent robots have a high degree of autonomy, can automatically adjust during intraoperative procedures, and can execute dental surgical tasks directly on patients without any apparent control by a surgeon. In this article, we propose a novel approach to develop a robot-assisted intelligent system that improves the efficiency of dental implant process based on Guided Local Search with Continuous Time Neural Network (GLCTNN). Firstly, dental facts are collected from PubMed articles and Maryland school children datasets. Secondly, using the collected facts, an intelligent robot-assisted model based on GLCTNN is developed. The second step comprises data preprocessing to remove unsolicited details, extracting useful features from the clean data, and utilizing the extracted features to train the GLCTNN model. The proposed system recognizes the implantation location with high accuracy and maximizes implantation rate. The efficiency of the system is evaluated using experimental analysis at lab scale. The proposed GLCTNN-based approach ensures maximum average accuracy (99.5%) and minimum average deviation error (0.323) compared to W-J48, Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighboring (KNN), Nearest Neighbors with Structural Risk Minimization (NNSRM) and Generalized Regression Neural Network (GRNN) approaches.

Cloud computing (CC) reveals a remarkable potential to provide on-demand services to a wide variety of enterprises over the Internet with greater flexibility in a cost-effective manner. However, it presents an added level of security and privacy risks because essential services are often outsourced to a third party. Security risks are the most critical issue that hinders enterprises from adopting CC since they may result in loss of satisfaction for many business objectives. On the other hand, Cloud Service Providers (CSP) are struggling with the cloud platform security issues since the cloud model has a very complex architecture with many characteristics and different stakeholders’ security requirements. Hence, there is an essential need for an indepth assessment of cloud related security risks. Traditional risk assessment methods do not fit CC well due to its complex environment and the assumption by those methods that assets are owned and fully controlled by the enterprise itself. In this paper, we propose a Delphi-based Cloud Security Risk Assessment Model (DCSRAM) that identifies, analyzes, and evaluates security risks affecting CC adoption in enterprises. The proposed model supports a higher level of trust in cloud technologies from the side of enterprises and a costeffective and reliable productivity from the side of CSP. The model has been tested for applicability and usability through a use case scenario.

Anatomically, oral cavity and central nervous system have a close relationship; the mouth and face are the location for 30-40% of the body's sensory and motor nerves. The identification of orofacial manifestations of neurological disorders is usually in direct relation with the responsibilities of a dental surgeon. Therefore, familiarizing dental surgeons with theses manifestations is essential to have better recognition, diagnosis, and correct decisions upon treating their associated Neurological Disorders. These manifestations should be efficiently analyzed using novel effective techniques since their related neurological disorders need to be early identified to avoid serious consequences. Furthermore, preventive dental care for patients with neurological disorders and all kind of rehabilitative treatments necessitates well-planned and effective novel approaches. The Internet of Medical Thing (IoMT) is a relatively new technology that allows the transfer of medical data over a secure network of medical sensors and wearable devices. The data transferred are of utmost importance in diseases diagnosis and treatment. In this paper, an IoMT-based Intelligent Guided Particle Local Search with Optimized Neural Networks (IGPLONN) approach is proposed. Firstly, dental data are collected from the International Collaboration on Cancer Reporting (ICCR) oral cavity and central nervous system. Secondly, features are extracted from data and IGPLONN algorithm is utilized to select the effective features by minimizing the feature dimension that helps improve the overall prediction rate. Finally, the obtained features are transferred to the central health application through the IoMT platform where they can be analyzed by dental practitioners for neurological disorders prediction. The hybrid optimized technique improves the overall oral-linked neurological diseases detection rate. Moreover, it efficiently manages the forecast parameters that are used to predict the dental metastasis with minimum computational complexity. The performance of the proposed system has been experimentally evaluated on MATLAB to verify its excellence. The results revealed that proposed IoMT-based IGPLONN method attains the maximum accuracy of 98.3% compared to other methods.

The rapid growth of Information and Communication Technologies (ICT) —specifically, the Internet—has given emergence to e-learning. Resultantly, web-based e-learning systems are being increasingly developed to enhance the learning process. However, the utilization of such systems is low, mainly owing to poor quality content and overall design problems. To improve usage, it is imperative to identify the factors with the most significant impact on the quality of these systems so that the e-learning industry keeps these factors in consideration while developing e-learning systems. This study focused on the identification and prioritization of factors related to the design quality of e-learning systems through a hierarchical quality model. Thus, firstly, an extensive literature review was conducted to identify the factors that most affect the quality of web-based e-learning systems. Secondly, among the identified factors, only those with the most significant effect were considered. To identify the most important quality criteria, a survey was conducted. An instrument was deployed among 157 subjects, including e-learning designers, developers, students, teachers, and educational administrators. Finally, a second instrument was distributed among 51 participants to make a pairwise comparison among the criteria and rank them according to their relative importance. The identified and prioritized factors were classified into four main categories. Among these four factors, content was identified as the most important factor, whereas design was found to be the least important factor.

Provision of higher throughput without sacrificing consistency guarantees in replication systems is a critical problem. In this paper, we propose a novel approach called Bidirectional Chain Replication (BCR) to improve throughput in traditional Chain Replication (CR) through better utilization of computing and communication resources of the chain. Unlike CR where the whole replicated data store is treated as a single unit, in BCR the replicated shared data at each server in the chain is split into two disjoint Logical Partitions (LP1, LP2). This forms two chains running concurrently on the same hardware in two opposite directions; the first chain (CR1) exclusively manipulates data objects in LP1 , while the second chain (CR2) exclusively manipulates data objects in LP2, therefore, conflict is avoided and concurrency is guaranteed. The simultaneous employment of these two chains results in better utilization of hardware in the sense that the two chains can evenly share the workload, hence, throughput can be improved without sacrificing consistency. Experimental results showed an improvement of approximately 85% in throughput of BCR over CR.

Cloud Computing (CC) has become an important milestone information technology that attracts many organizations. With the potential to transform business processes, lower IT expenses, and offer access to unlimited computing resources with minimal management effort, organizations look to cloud-based solutions to achieve business efficiencies. Thus, it would seem that these organizations could easily migrate to CC. However, enterprises are still concerned about moving their business-critical applications to the cloud. Among the reasons are that it is an emerging technology that has not reached a level of maturity; the lack of industry-specific conformity to standards; and a high level of security risks. As a result, there is a big dispute among organizations on the decision of whether it is more business-efficient to embark on the cloud or remain with their interior IT infrastructures. In this paper, we aim to solve this debate by proposing a novel approach that supports decision-making on CC adoption in organizations. Unlike traditional decision-making approaches that pay little or no consideration to organizational high-level business objectives, our proposed approach is driven by the business objectives of the organization. First, we identify driving and restraining forces that influence CC adoption in organizations. Second, a formal decision-making model is proposed based on Force Field Analysis (FFA) augmented by pairwise comparison and Delphi methods, this model estimates the values of the driving and restraining forces based on their impacts on the organization's objectives. By analyzing the forces for and against CC adoption, organizations can decide whether or not to move forward with the adoption. Alternatively, organizations can use the analysis to think about how they can strengthen the forces that support the adoption and weaken the forces opposing it, so that the adoption is more successful. The proposed model is validated for usability and applicability through a use case scenario.

Security is considered one of the top ranked risks of Cloud Computing (CC) due to the outsourcing of sensitive data onto a third party. In addition, the complexity of the cloud model results in a large number of heterogeneous security controls that must be consistently managed. Hence, no matter how strongly the cloud model is secured, organizations continue suffering from lack of trust on CC and remain uncertain about its security risk consequences. Traditional risk management frameworks do not consider the impact of CC security risks on the business objectives of the organizations. In this paper, we propose a novel Cloud Security Risk Management Framework (CSRMF) that helps organizations adopting CC identify, analyze, evaluate, and mitigate security risks in their Cloud platforms. Unlike traditional risk management frameworks, CSRMF is driven by the business objectives of the organizations. It allows any organization adopting CC to be aware of cloud security risks and align their low-level management decisions according to high-level business objectives. In essence, it is designed to address impacts of cloud-specific security risks into business objectives in a given organization. Consequently, organizations are able to conduct a cost-value analysis regarding the adoption of CC technology and gain an adequate level of confidence in Cloud technology. On the other hand, Cloud Service Providers (CSP) are able to improve productivity and profitability by managing cloud-related risks. The proposed framework has been validated and evaluated through a use-case scenario.

Cloud computing is advancing rapidly. With such advancement, it has become possible to develop and host large scale distributed applications on the Internet more economically and more flexibly. However, the geographical distribution of user bases, the available Internet infrastructure within those geographical areas, and the dynamic nature of usage patterns of the user bases are critical factors that affect the performance of these applications. Therefore, it is necessary to compromise between datacenters, service broker policies, and load balancing algorithms to optimize the performance of the application and the cost to the owners. This paper aims at studying the effect of service broker policies and load balancing algorithms on the performance of large-scale Internet applications under different configurations of datacenters. To achieve this goal, we modeled the behavior of the popular Facebook application with the most recent worldwide users' statistics. Then, we evaluated the performance of this application under different configurations of datacenters using: 1) two different service broker policies, namely, closest datacenter and optimum response time; and 2) three loadbalancing algorithms, namely, round robin, equally spread current execution, and throttled load balancer. The overall average response time of the application and the overall average time spent for processing a user request by a datacenter are measured and the results are discussed. This study would help service providers generate valuable insights on coordination between datacenters, service policies, and load balancing algorithms when designing Cloud infrastructure services in geographically distributed areas. In addition, application designers would benefit greatly from this study in identifying the optimal arrangement for their applications.