A coupled damped Klein–Gordon–Schrödinger equations are considered where Ω is a bounded domain of R 2 , with smooth boundary Γ and ω is a neighbourhood of ∂ Ω satisfying the geometric control condition. The aim of the paper is to prove the existence, uniqueness and uniform decay for the solutions.

Applying the iterative methodology for dimensionality reduction/feature selection using categorical gradient boosted trees, as it has been defined in and has been successfully applied on similar datasets in and , on a dataset consisted of 12708 gene expressions coming from 5052 individuals from 105 studies, we classify whether a person has acute myeloid leukaemia (AML) or is healthy. A CatBoost model on a dataset with reduced dimensions of 72 genes reached a ROC-AUC score of 0.9973 using ten fold cross validation (10CV) and ROC-AUC: 0.9988 on an inference dataset. We further investigate the options of using less genes that potentially could be used in clinical practise and genes than have not been associated to AML yet, or to blood cancer in general. On the same folds of the 10CV and on the same inference dataset the performance of the tuned CatBoost models show that it could be the case that not all genes with an association to AML have been found yet and 19 genes could be enough to predict AML: CatBoost63 (ROC-AUC: 0.9941, Test: 0.9942), CatBoost19: (ROC-AUC: 0.9946, Test: 0.9941) and CatBoost15: (ROC-AUC: 0.9922, Test: 0.9900). In addition, our results verify that a gene diagnostic test for AML could be possible in the future as well as further research is needed on these 15 genes that it could lead to new and better drugs.

The use of systems to calculate mathematical operations has facilitated people to automate processes in the corporate sector. Such systems lie behind everything from calculating the final amount on a grocery receipt, to complex mathematical operations involving finding behaviors in a business's customers. However, when a company or organization has a large amount of data on which to perform mathematical operations, the procedure becomes time-consuming, whereas to execute mathematical operations on entire datasets, one typically needs strong programming skills. In this paper, a service called MathBlock is analyzed that is able to be used as a language agnostic mathematical expression parser and executioner, on batch data. MathBlock consists of four types of functions, including arithmetic, comparison, logical, and statistical. To evaluate the applicability of MathBlock, an experiment is carried out on the mentioned service as a proof of concept. This experimentation uses batch and synthetic data, covering the domains of maritime and healthcare, with the aim of performing mathematical operations through MathBlock. The derived results showcase that MathBlock can assist users on their need to calculate and gather results for many different datasets. Overall, it can be clearly stated that through MathBlock the challenge of the need to perform arithmetic, logical, comparison and statistical operations on different datasets to get results in an automated manner is well addressed, whereas additional experimentation with datasets from multiple domains should take place in order to conclude to more concrete and reliable results.

Serverless computing has reshaped the cloud computing landscape by offering benefits such as auto-scalability, streamlined operational management, and granular billing. As its adoption grows, challenges related to performance and cost optimization in hybrid architectures combining private servers and public cloud clusters have emerged. Central to these challenges are achieving optimal response latency and balancing performance and cost. To address these challenges, this paper introduces an adaptive routing service specifically designed for hybrid environments, proficient in leveraging real-time function metrics. Our proposed service pivots on three integral components: a monitor that captures performance metrics and raises alarms for predefined anomalies; a forecaster that predicts function latency across clusters, which includes wait and execution times and produces request distributions for each cluster to equalize the overall function latency; and a router then processes incoming requests, taking cues from the forecaster’s predictions. Notably, based on user-defined objectives, the forecaster can be directed to either minimize latency or optimize execution costs through trading off wait or execution time. Comprehensive evaluations on AWS and Azure clusters using the open source FaaS framework Apache OpenWhisk showcase our approach’s effectiveness, yielding a 9% improvement in average latency, a 45% decrease in standard deviation latency and a 17% cost reduction compared to conventional 50-50 routing. The advantages of elevated monitoring frequency are also illuminated, emphasizing quicker convergence times.

We define an iterative method for dimensionality reduction using categorical gradient boosted trees and Shapley values and created four machine learning models which potentially could be used as diagnostic tests for acute myeloid leukaemia (AML). For the final Catboost model we use a dataset of 2177 individuals using as features 16 probe sets and the age in order to classify if someone has AML or is healthy. The dataset is multicentric and consists of data from 27 organizations, 25 cities, 15 countries and 4 continents. The performance of our last model is specificity: 0.9909, sensitivity: 0.9985, F1-score: 0.9976 and its ROC-AUC: 0.9962 using ten fold cross validation. On an inference dataset the perormance is: specificity: 0.9909, sensitivity: 0.9969, F1-score: 0.9969 and its ROC-AUC: 0.9939. To the best of our knowledge the performance of our model is the best one in the literature, as regards the diagnosis of AML using similar or not data. Moreover, there has not been any bibliographic reference which associates AML or any other type of cancer with the 16 probe sets we used as features in our final model.

The rapid growth of the Industrial Internet of Things (IIoT) has led to the generation of vast amounts of data, which has significant implications for decision-making in various industrial sectors and is increasingly being traded on data marketplaces. Quantifying IIoT data quality and providing measures to improve, it is critical for both operational efficiency and business value. This paper presents a comprehensive architecture for data quality assessment in the IIoT, aimed at ensuring the quality, trustworthiness, and reliability of the data generated by the IIoT. The architecture facilitates both objective and subjective assessments, taking into account the intended task for the data, and includes data enhancement operations to address data quality issues. The architecture provides a standardized and modular approach to data quality evaluation, allowing data owners and data market participants to make informed decisions about the quality and value of their data. The proposed architecture has the potential to significantly impact various industrial sectors and data marketplaces, providing a valuable tool for ensuring the reliability and accuracy of IIoT data. As the architecture is a work in progress, the preliminary evaluation of its effectiveness has been omitted for future work.

The viral outbreak of COVID-19 that started in the year 2019, radically changed our everyday life, with a detrimental impact on the simple, daily habits of citizens. In many countries around the world, the usage of mask is necessary as a protection measure against covid-19. Every service, organization, various stores, schools, universities, hospitals, companies and many other places, which are attended by hundreds of people every day, make the use of a mask necessary to enter them. This fact requires the control of the persons when they enter the respective spaces to determine if they are wearing a mask when entering the area. In this research we compared performance on YOLOv4 and the Tiny-YOLOv4 algorithm on images, recorded video, and real time video. In the next step we will implement the YOLOv4 TFlite and Tiny YOLOv4 TFlite model for mobile applications using the Android Studio platform. On the proposed dataset YOLOv4 achieved 92.91% mAP and training took around 2 hours for 1000 iterations. On the other hand, YOLOv4-tiny achieved 74.75% mAP and training took less than half an hour for 1000 iterations. For further improvement we convert YOLOv4 and YOLOv4-tiny to YOLOv4 TFlite and YOLOv4-tiny TFlite respectively. After this step we compare YOLOv4 TFlite and YOLOv4-tiny TFlite model performance on mobile device. YOLOv4 TFlite achieved 96.92% accuracy on real time video at 5017ms and YOLOv4-tiny 74.72% accuracy on real time video at 491ms.

Determining and minimizing risk exposure pose one of the biggest challenges in the financial industry as an environment with multiple factors that affect (non-)identified risks and the corresponding decisions. Various estimation metrics are utilized towards robust and efficient risk management frameworks, with the most prevalent among them being the Value at Risk (VaR). VaR is a valuable risk-assessment approach, which offers traders, investors, and financial institutions information regarding risk estimations and potential investment insights. VaR has been adopted by the financial industry for decades, but the generated predictions lack efficiency in times of economic turmoil such as the 2008 global financial crisis and the COVID-19 pandemic, which in turn affects the respective decisions. To address this challenge, a variety of well-established variations of VaR models are exploited by the financial community, including data-driven and data analytics models. In this context, this paper introduces a probabilistic deep learning approach, leveraging time-series forecasting techniques with high potential of monitoring the risk of a given portfolio in a quite efficient way. The proposed approach has been evaluated and compared to the most prominent methods of VaR calculation, yielding promising results for VaR 99

This is a comprehensive paper on the oil spill phenomenon on what mechanisms change the oil spill displacement, what Computational Fluid Dynamic (CFD) applications of Finite Volume and Eulerian/Lagragian equations are used to solve oil-spill simulations and to provide a brief analysis of the models used. An oil spill is defined as a form of pollution caused by human activity and as the discharge of liquid petroleum hydrocarbons into the environment, mainly in the marine eco-system. This description is commonly used for marine oil spills, where the hydrocarbons are discharged into the ocean or coastal waters, but they can also occur inland. Oil spills occur because of discharges of hydrocarbons from platforms, rigs, wells, tankers and from refined petroleum products along with their by-products, also from heavier fuels. Thus, oil spill simulation is used to predict transport and weathering processes. State-of-the-art tools such as OILMAP, TRANSAS, OILFLOW2D, OSCAR and ANSYS, work by simulating the processes mentioned prior. In contrary to these tools, the aim of this paper is to provide a comparison of the weathering models used and propose a mathematical model using python to predict the spreading phenomenon of an oil spill.

Towards enabling the automated and optimized FaaS deployment of applications in a hybrid-cloud setting, the application requirements should be met by comparing them to the capabilities of the available resources of available clusters. To this end, semantic matching between the application characteristics and the individual descriptions of available compute clusters (e.g. from public or private cloud or edge facilities available) is required. In this work, such a system is proposed, namely the Reasoning Framework, which performs semantic matching between application and resource (meta)data and facilitates information sharing among the FaaS platform components leveraging Knowledge Graphs, ontology technologies, and semantic reasoning. The proposed system harvests information from the application function workflow, provided as a graph by the function editor specification (based on Node-RED), including developer-inserted annotations during the design process, and maps them to the dynamic information retrieved from the available clusters. The Reasoning Framework interprets these data as graphs and automatically applies several semantic rules that enable filtering of the available resources and efficient information retrieval through a RESTfull interface. The paper also discusses experimental results to further showcase the advantages of the proposed approach.

Abstract Applying the iterative methodology for dimensionality reduction using categorical gradient boosted trees, as it has been defined in [9], on a dataset consisted of 12708 genes expressions coming from 5052 individuals from 105 studies, we classify whether a person has acute myeloid leukaemia (AML) or is healthy. A CatBoost model on the dataset with reduced dimensions of 72 genes reached a ROC- AUC score of 0.9973 and F1-score: 0.9983 using ten fold cross validation and ROC-AUC: 0.9988 and F1-score: 0.9988 on an inference dataset. The dimension of the genes used by the previous model is then further reduced by removing the genes that do not have any bibliographic reference to AML. A CatBoost model is trained on this final dataset consisting of 63 genes, providing a ROC-AUC score of 0.9941 and F1-score: 0.9973 on ten fold cross validation and ROC-AUC: 0.9942 and F1-score: 0.9964 showing that not all genes with a correlation to AML have been found yet. This work could be considered as complimentary to the work of [9] where they used probe-sets. We conclude that the iterative method defined in [9] can lead to the identification of the gene profile of AML and also to identification of genes associated to AML which have never been correlated to the disease before.

In this paper four machine learning algorithms are compared in order to predict if a cell nucleus is benign or malignant using the Breast Cancer Wisconsin (Diagnostic) Data Set. The algorithms are K-Nearest Neighbours, Classification and Regression Trees (CART), Naïve Bayes and Support Vector Machines with Radial Basis Function Kernel. Data visualization and Pre- Processing using PCA will help in the understanding and the preparation of the dataset for the training phase while parameter tuning will determine the optimal parameter for every model using R as programming language. Also, 10-fold Cross Validation is used as a resampling method after comparing it with Bootstrapping, as it is the most efficient out of the two. In the end, our comparison shows that the machine learning model that marked the highest Accuracy is the one that is trained using K Nearest Neighbours. Nowadays, one of the most common forms of cancer among women is breast cancer with more than one million cases and nearly 600,000 deaths occurring worldwide annually [1]. It is the second leading cause of death among women and thus it must be detected at an early stage in order not to become fatal [2]. Thus, the importance of diagnosing if a biopsied cell is benign or malignant is vital. However, this process is quite complicated as it involves several stages of gathering and analysing samples with many variables, making the final diagnosis a demanding and timely procedure. The rapid growth of Artificial Intelligence and Machine learning and their implementation in Medicine give us a new perspective in the way we process and analyse medical data. Medical experts can use Data Mining techniques and improve their decision making by extracting useful information from massive amounts of data.

In this paper we study the local and global well posedness of a fractional dissipative Klein–Gordon–Schrödinger type system in dimension 1 and establish the existence of a global attractor.

We consider a semilinear Robin problem driven by the negative Laplacian plus an indefinite, unbounded potential. The reaction term is a Caratheodory function of arbitrary structure outside an interval \([-c,c]\) (\(c>0\)), odd on \([-c,c]\) and concave near zero. Using a variant of the symmetric mountain pass theorem, together with truncation, perturbation and comparison techniques, we show that the problem has a whole sequence \(\{u_n\}_{n\ge 1}\) of distinct nodal solutions converging to zero in \(C^1({\overline{\Omega }})\).

In this paper four machine learning algorithms are compared in order to predict if a cell nucleus is benign or malignant using the Breast Cancer Wisconsin (Diagnostic) Data Set. The algorithms are K-Nearest Neighbours, Classification and Regression Trees (CART), Naïve Bayes and Support Vector Machines with Radial Basis Function Kernel. Data visualization and Pre-Processing using PCA will help in the understanding and the preparation of the dataset for the training phase while parameter tuning will determine the optimal parameter for every model using R as programming language. Also, 10-fold Cross Validation is used as a resampling method after comparing it with Bootstrapping, as it is the most efficient out of the two. In the end, our comparison shows that the machine learning model that marked the highest Accuracy is the one that is trained using K Nearest Neighbours. Nowadays, one of the most common forms of cancer among women is breast cancer with more than one million cases and nearly 600,000 deaths occurring worldwide annually [1]. It is the second leading cause of death among women and thus it must be detected at an early stage in order not to become fatal [2]. Thus, the importance of diagnosing if a biopsied cell is benign or malignant is vital. However, this process is quite complicated as it involves several stages of gathering and analysing samples with many variables, making the final diagnosis a demanding and timely procedure. The rapid growth of Artificial Intelligence and Machine learning and their implementation in Medicine give us a new perspective in the way we process and analyse medical data. Medical experts can use Data Mining techniques and improve their decision making by extracting useful information from massive amounts of data.

We consider a nonlinear nonhomogeneous Robin problem that has the sum of a p-Laplacian and a q-Laplacian (a (p; q)-equation). The reaction term is a Caratheodory function which is resonant at +/-infinity with respect to any nonprincipal variational eigenvalue of the Robin p-Laplacian. Using variational methods and Morse theory (critical groups), we show the existence of at least three nontrivial smooth solutions.

. In this paper we consider a nonlinear parametric Dirichlet problem driven by a nonhomogeneous differential operator (special cases are the p -Laplacian and the (p,q) differential operator) and with a reaction which has the combined effects of concave (( p − 1 ) -sublinear) and convex ( (p − 1 ) -superlinear) terms. We do not employ the usual in such cases AR-condition. Using variational methods based on critical point theory, together with truncation and comparison techniques and Morse theory (critical groups), we show that for all small λ > 0 ( λ is a parameter), the problem has at least five nontrivial smooth solutions (two positive, two negative and the fifth nodal). We also prove two auxiliary results of independent interest. The first is a strong comparison principle and the second relates Sobolev and Hölder local minimizers for C 1 functionals.

We consider a parametric nonlinear elliptic Neumann problem driven by a nonhomogeneous differential operator. Using variational methods combined with truncation and comparison techniques, we prove a bifurcation-type theorem describing the dependence of the set of positive solutions on the parameter lambda > 0.

We consider a nonlinear elliptic Neumann problem driven by a nonhomogeneous differential operator, which is strictly monotone and incorporates as special cases the p-Laplacian, the (p, q)-differential operator and the generalized p-mean curvature differential operator. Using variational methods coupled with suitable truncation and comparison techniques and Morse theory (critical groups), we show that the problem has at least three nontrivial smooth solutions, one positive, the second negative and the third nodal. Also we show that the problem has extremal nontrivial constant sign solutions.