Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber services.The complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning ones.Federated Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT applications.Even though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d setting.FL is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other contributors.This paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d data.PP-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each class.The PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 datasets.The empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

Explainable Conformer Network for Detection of COVID-19 Pneumonia from Chest CT Scan: From Concepts toward Clinical Explainability

The early implementation of treatment therapies necessitates the swift and precise identification of COVID-19 pneumonia by the analysis of chest CT scans.This study aims to investigate the indispensable need for precise and interpretable diagnostic tools for improving clinical decision-making for COVID-19 diagnosis.This paper proposes a novel deep learning approach,called Conformer Network,for explainable discrimination of viral pneumonia depending on the lung Region of Infections(ROI)within a single modality radiographic CT scan.Firstly,an efficient U-shaped transformer network is integrated for lung image segmentation.Then,a robust transfer learning technique is introduced to design a robust feature extractor based on pre-trained lightweight Big Transfer(BiT-L)and finetuned on medical data to effectively learn the patterns of infection in the input image.Secondly,this work presents a visual explanation method to guarantee clinical explainability for decisions made by Conformer Network.Experimental evaluation of real-world CT data demonstrated that the diagnostic accuracy of ourmodel outperforms cutting-edge studies with statistical significance.The Conformer Network achieves 97.40% of detection accuracy under cross-validation settings.Our model not only achieves high sensitivity and specificity but also affords visualizations of salient features contributing to each classification decision,enhancing the overall transparency and trustworthiness of our model.The findings provide obvious implications for the ability of our model to empower clinical staff by generating transparent intuitions about the features driving diagnostic decisions.

An Improved Jellyfish Algorithm for Multilevel Thresholding of Magnetic Resonance Brain Image Segmentations

Image segmentation is vital when analyzing medical images,especially magnetic resonance(MR)images of the brain.Recently,several image segmentation techniques based on multilevel thresholding have been proposed for medical image segmentation;however,the algorithms become trapped in local minima and have low convergence speeds,particularly as the number of threshold levels increases.Consequently,in this paper,we develop a new multilevel thresholding image segmentation technique based on the jellyfish search algorithm(JSA)(an optimizer).We modify the JSA to prevent descents into local minima,and we accelerate convergence toward optimal solutions.The improvement is achieved by applying two novel strategies:Rankingbased updating and an adaptive method.Ranking-based updating is used to replace undesirable solutions with other solutions generated by a novel updating scheme that improves the qualities of the removed solutions.We develop a new adaptive strategy to exploit the ability of the JSA to find a best-so-far solution;we allow a small amount of exploration to avoid descents into local minima.The two strategies are integrated with the JSA to produce an improved JSA(IJSA)that optimally thresholds brain MR images.To compare the performances of the IJSA and JSA,seven brain MR images were segmented at threshold levels of 3,4,5,6,7,8,10,15,20,25,and 30.IJSA was compared with several other recent image segmentation algorithms,including the improved and standard marine predator algorithms,the modified salp and standard salp swarm algorithms,the equilibrium optimizer,and the standard JSA in terms of fitness,the Structured Similarity Index Metric(SSIM),the peak signal-to-noise ratio(PSNR),the standard deviation(SD),and the Features Similarity Index Metric(FSIM).The experimental outcomes and the Wilcoxon rank-sum test demonstrate the superiority of the proposed algorithm in terms of the FSIM,the PSNR,the objective values,and the SD;in terms of the SSIM,IJSA was competitive with the others.

Efcient MCDM Model for Evaluating the Performance of Commercial Banks: A Case Stud

Evaluation of commercial banks(CBs)performance has been a signicant issue in the nancial world and deemed as a multi-criteria decision making(MCDM)model.Numerous research assesses CB performance according to different metrics and standers.As a result of uncertainty in decision-making problems and large economic variations in Egypt,this research proposes a plithogenic based model to evaluate Egyptian commercial banks’performance based on a set of criteria.The proposed model evaluates the top ten Egyptian commercial banks based on three main metrics including nancial,customer satisfaction,and qualitative evaluation,and 19 subcriteria.The proportional importance of the selected criteria is evaluated by the Analytic Hierarchy Process(AHP).Furthermore,the Technique for Order of Preference by Similarity to Ideal Solution(TOPSIS),Vlse Kriterijumska Optimizacija Kompro-misno Resenje(VIKOR),and COmplex PRoportional ASsessment(COPRAS)are adopted to rank the top ten Egyptian banks based on their performance,comparatively.The main role of this research is to apply the proposed integrated MCDM framework under the plithogenic environment to measure the performance of the CBs under uncertainty.All results show that CIB has the best performance while Faisal Islamic Bank and Bank Audi have the least performance among the top 10 CBs in Egypt.

Network Analysis for Projects with High Risk Levels in Uncertain Environments

The critical path method is one of the oldest and most important techniques used for planning and scheduling projects.The main objective of project management science is to determine the critical path through a network representation of projects.The critical path through a network can be determined by many algorithms and is useful for managing,monitoring,and controlling the time and cost of an entire project.The essential problem in this case is that activity durations are uncertain;time presents considerable uncertainty because the time of an activity is not always easily or accurately estimated.This issue increases the need to use neutrosophic theory to solve the critical path problem.Real-world problems are characterized by a lack of precision,consistency,and completeness.The concept of neutrosophic sets has been introduced as a generalization of fuzzy,intuitionistic fuzzy,and crisp sets to overcome the ambiguity surrounding real-world problems.Truth-,falsity-,and indeterminacy-membership functions are used to express neutrosophic elements.This study was performed to examine a neutrosophic event-oriented algorithm for determining the critical path in activity-on-arc networks.The activity time estimates are presented as trapezoidal neutrosophic numbers,and score and accuracy functions are used to obtain a crisp model of the problem.An appropriate numerical example is then used to explain the proposed method.

A New Decision-Making Model Based on Plithogenic Set for Supplier Selection

Supplier selection is a common and relevant phase to initialize the supply chain processes and ensure its sustainability.The choice of supplier is a multicriteria decision making(MCDM)to obtain the optimal decision based on a group of criteria.The health care sector faces several types of problems,and one of the most important is selecting an appropriate supplier that fits the desired performance level.The development of service/product quality in health care facilities in a country will improve the quality of the life of its population.This paper proposes an integrated multi-attribute border approximation area comparison(MABAC)based on the best-worst method(BWM),plithogenic set,and rough numbers.BWM is applied to regulate the weight vector of the measures in group decision-making problems with a high level of consistency.For the treatment of uncertainty,a plithogenic set and rough number(RN)are used to improve the accuracy of results.Plithogenic set operations are used to deal with information in the desired manner that handles uncertainty and vagueness.Then,based on the plithogenic aggregation and the results of BWM evaluation,we use MABAC to find the optimal alternative according to defined criteria.To examine the proposed integrated algorithm,an empirical example is produced to select an optimal supplier within five options in the healthcare industry.

Scheduling Multi-Mode Resource-Constrained Projects Using Heuristic Rules Under Uncertainty Environment

Project scheduling is a key objective of many models and is the proposed method for project planning and management.Project scheduling problems depend on precedence relationships and resource constraints,in addition to some other limitations for achieving a subset of goals.Project scheduling problems are dependent on many limitations,including limitations of precedence relationships,resource constraints,and some other limitations for achieving a subset of goals.Deterministic project scheduling models consider all information about the scheduling problem such as activity durations and precedence relationships information resources available and required,which are known and stable during the implementation process.The concept of deterministic project scheduling conflicts with real situations,in which in many cases,some data on the activity’s durations of the project and the degree of availability of resources change or may have different modes and strategies during the process of project implementation for dealing with multi-mode conditions surrounded by projects and their activity durations.Scheduling the multi-mode resource-constrained project problem is an optimization problem whose minimum project duration subject to the availability of resources is of particular interest to us.We use the multi-mode resource allocation and schedulingmodel that takes into account the dynamicity features of all parameters,that is,the scheduling process must be flexible to dynamic environment features.In this paper,we propose five priority heuristic rules for scheduling multi-mode resource-constrained projects under dynamicity features for more realistic situations,in which we apply the proposed heuristic rules(PHR)for scheduling multi-mode resource-constrained projects.Five projects are considered test problems for the PHR.The obtained results rendered by these priority rules for the test problems are compared by the results obtained from 10 well-known heuristics rules rendered for the same test problems.The results in many cases of the proposed priority rules are very promising,where they achieve better scheduling dates in many test case problems and the same results for the others.The proposed model is based on the dynamic features for project topography.

Medical Feature Selection Approach Based on Generalized Normal Distribution Algorithm

This paper proposes a new pre-processing technique to separate the most effective features from those that might deteriorate the performance of the machine learning classifiers in terms of computational costs and classification accuracy because of their irrelevance,redundancy,or less information;this pre-processing process is often known as feature selection.This technique is based on adopting a new optimization algorithm known as generalized normal distribution optimization(GNDO)supported by the conversion of the normal distribution to a binary one using the arctangent transfer function to convert the continuous values into binary values.Further,a novel restarting strategy(RS)is proposed to preserve the diversity among the solutions within the population by identifying the solutions that exceed a specific distance from the best-so-far and replace them with the others created using an effective updating scheme.This strategy is integrated with GNDO to propose another binary variant having a high ability to preserve the diversity of the solutions for avoiding becoming stuck in local minima and accelerating convergence,namely improved GNDO(IGNDO).The proposed GNDO and IGNDO algorithms are extensively compared with seven state-of-the-art algorithms to verify their performance on thirteen medical instances taken from the UCI repository.IGNDO is shown to be superior in terms of fitness value and classification accuracy and competitive with the others in terms of the selected features.Since the principal goal in solving the FS problem is to find the appropriate subset of features that maximize classification accuracy,IGNDO is considered the best.

Efficient Model for Emergency Departments:Real Case Study

There are several challenges that hospitals are facing according to the emergency department(ED).Themain two issues are department capacity and lead time.However,the lack of consensus on performance criteria to evaluateEDincreases the complication of this process.Thus,this study aims to evaluate the efficiency of the emergency department in 20 Egyptian hospitals(12 private and 8 general hospitals)based on 13 performance metrics.This research suggests an integrated evaluation model assess ED under a framework of plithogenic theory.The proposed framework addressed uncertainty and ambiguity in information with an efficient manner via presenting the evaluation expression by plithogenic numbers.Data Envelopment Analysis(DEA)technique is used in order to measure the efficiency of the emergency department of 20 hospitals according to the number of treated patients and effect on patient’s life quality based on 11 factors.Using the Analytic Hierarchy Process(AHP),the weight of efficiency factors will be measured based on neutrosophic linguistic scale pairwise comparison.Plithogenic operations provide more accurate aggregation result according to contradiction degree between criteria values.The results show that ten of the hospitals are providing efficient service in their emergency department,while the other ten are less efficient.The analysis of the results shows that 58%of private hospitals emergency department is operating efficiently,while the efficient general hospitals represent 38%.