Abstract

Serverless Computing, also named Function as a Service (FaaS) in the Azure cloud provider, is a new feature of cloud computing. This is another brick, after managed and fully managed services, allowing to provide on-demand services instead of provisioned resources and it is used to strengthen the company’s ability in order to master its IT system and consequently to make its business processes more profitable. Knowing that decision making is one of the important tasks in business processes, the improvement of this task was the concern of both the industry and the academy communities. Those efforts have led to several models, mainly the two Object Management Group (OMG) models: Business Process Model and Notation (BPMN) and Decision Model and Notation (DMN) in order to support this need. The DMN covers the decision-making task in business processes mainly the eligibility of business rules. This eligibility can be automated in order to help designers in the mastering of this important task by the running of an algorithm or a method such as the Multiple Criteria Decision Making (MCDM). This feature can be designed and implemented and deployed in various architectures to integrate it in existing Business Process Management Systems (BPMS). It could then improve supporting several business areas such as the Business Intelligence (BI) process. In this paper, our main contribution is the enrichment of the DMN model by the automation of the business rules eligibility through Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using FaaS to further streamline the decision-making task in business processes. Results show to strengthen business-IT alignment and reduce the gap between the real world and associated IT solutions.

Abstract

Hyperheuristics represent a generic method that provides a high level of abstraction, enabling solving several problems in the combinatorial optimization domain while reducing the need for human intervention in parameters tuning. This category consists in managing a set of low-level heuristics and attempting to find the optimal sequence that produces high-quality results. This paper proposes a hyperheuristic that simulates the honey bees mating behavior called “Honey bee Mating Optimization HyperHeuristic”  to solve the Patient Admission Scheduling Problem (PASP). The PASP is an NP-hard problem that represents an important field in the health care discipline. In order to perceive the influence of low-level heuristics on the model’s performance, we implemented two versions of the hyperheuristic that each one works on a different set of low-level heuristics. The results show that one of the versions generates better results than the other, revealing the important role of low-level heuristics’ quality leading to enhancing the hyperheuristic performance.

Abstract

Abstract

Financial markets are dynamic and open systems. They are subject to the influence of environmental changes. For this reason, predicting stock market prices is a difficult task for investors due to the volatility of the financial stock markets nature. Stock market forecasting leads investors to make decisions with more confidence based on the prediction of stock market price behavior. Indeed, a lot of analysts are greatly focused in the research domain of stock market prediction. Generally, the stock market prediction tools are categorized into two types of algorithms: (1) linear models like Auto Regressive (AR), Moving Average (MA), Auto-Regressive Integrated Moving Average (ARIMA), and (2) non-linear models like Autoregressive Conditionally Heteroscedastic (ARCH), Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and recently Neural Network (NN)). This paper aspires to crucially predict the stock index movement for National Association of Securities Dealers Automated Quotations (NASDAQ) based on deep learning networks. We propose a hybrid stock price prediction model using Convolutional Neural Network (CNN) for feature selection and Neural Network models to perform the task of prediction. To evaluate the performance of the proposed models, we use five regression evaluation metrics: Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and R-Square (R2), and the Execution Time (ET) metric to calculate the necessary time for running each hybrid model. The results reveal that error rates in the CNN-BGRU model are found to be lower compared to CNN-GRU, CNN-LSTM, CNN-BLSTM and the the existing hybrid models. This research work produces a practical experience for decision makers on financial time series data.

Abstract

The prediction of stock price movements is one of the most challenging tasks in financial market field. Stock price trends depended on various external factors like investor’s sentiments, health and political crises which can make stock prices more volatile and chaotic. Lately, two crises affected the variation of stock prices, COVID-19 pandemic and Russia-Ukraine conflict. Investors need a robust system to predict future stock trends in order to make successful investments and to face huge losses in uncertainty situations. Recently, various machine learning (ML) models have been proposed to make accurate stock movement predictions. In this paper, a framework including five ML classifiers (Gaussian Naive Bayes (GNB), Random Forest (RF), Gradient Boosting (GB), Support Vector Machine (SVM), and K-Nearest Neighbors (kNN))) is proposed to predict the closing price trends. Technical indicators are calculated and used with historical stock data as input. These classifiers are hybridized with Principal Component Analysis method (PCA) for feature selection and Grid Search (GS) Optimization Algorithm for hyper-parameters tuning. Experimental results are conducted on National Association of Securities Dealers Automated Quotations (NASDAQ) stock data covering the period from 2018 to 2023. The best result was found with the Random Forest classifier model which achieving the highest accuracy (61%).

Abstract

Since more and more organizations deploy their applications through the cloud, an increasing demand for using inter-cloud solutions is noticed. Such demands could inherently result in overutilization of resources, which leads to resource starvation that is vital for time-intensive and life-critical applications. In this paper, we are interested in the scheduling problem in such environments. On the one hand, a new taxonomy of criteria to classify task scheduling problems and resolution approaches in inter-cloud environments is introduced. On the other hand, a bi-level multi-follower model is proposed to solve the budget-constrained dynamic Bag-of-Tasks (BoT) scheduling problem in heterogeneous multi-cloud environments. In the proposed model, the upper-level decision maker aims to minimize the BoT’ makespan under budget constraints. While each lower-level decision maker minimizes the completion time of tasks it received. Experimental results demonstrated the outperformance of the proposed bi-level algorithm and revealed the advantages of using a bi-level scheme with an improvement rate of 32%, 29%, and 21% in terms of makespan for the small, medium, and big size instances, respectively.

Abstract

Multi-Objective Evolutionary Algorithms (MOEAs) is actually one of the most attractive and active research field in computer science. Significant research has been conducted in handling complex multi-objective optimization problems within this research area. The Non-Dominated Sorting Genetic Algorithm (NSGA-II) has garnered significant attention in various domains, emphasizing its specific popularity. However, the complexity of this algorithm is found to be O(MN2) with M objectives and N solutions, which is considered computationally demanding. In this paper, we are proposing a new variant of NSGA-II termed (Efficient-NSGA-II) based on our recently proposed quick non-dominated sorting algorithm with quasi-linear average time complexity; thereby making the NSGA-II algorithm efficient from a computational cost viewpoint. Experiments demonstrate that the improved version of the algorithm is indeed much faster than the previous one. Moreover, comparisons results against other multi-objective algorithms on a variety of benchmark problems show the effectiveness and the efficiency of this multi-objective version

Abstract

Drug target interaction is an important area of drug discovery, development, and repositioning. Knowing that in vitro experiments are time-consuming and computationally expensive, the development of an efficient predictive model is a promising challenge for Drug-Target Interactions (DTIs) prediction. Motivated by this problem, we propose in this paper a new prediction model called DeepCNN-DTI to efficiently solve such complex real-world activities. The main motivation behind this work is to explore the advantages of a deep learning strategy with feature extraction techniques, resulting in an advanced model that effectively captures the complex relationships between drug molecules and target proteins for accurate DTIs prediction. Experimental results generated based on a set of data in terms of accuracy, precision, sensitivity, specificity, and F1-score demonstrate the superiority of the model compared to other competing learning strategies.

Abstract

Among the well-known scheduling problems, the customer order scheduling problem (COSP) has
always been of great importance in manufacturing. To reflect the reality of COSPs as much as
possible, this study considers that jobs from different orders are classified in various classes. This
paper addresses a tri-criteria single-machine scheduling model with multiple job classes and
customer orders on which the measurement minimizes a linear combination of the sum of the ranges
of all orders, the tardiness of all orders, and the total completion times of all jobs. Due to the NPhard complexity of the problem, a lower bound and a property are developed and utilized in a
branch-and-bound for solving an exact solution. Afterward, four heuristics with three local
improved searching methods each and a water wave optimality algorithm with four variants of
wavelengths are proposed. The tested outputs report the performances of the proposed methods

Abstract

The multiple job class scheduling problem arises in contexts where a group of jobs belong to multiple classes and in which if all jobs in the same class are operated together, extra setup times would not be needed. On the other hand, the customer order scheduling problem focuses on finishing all jobs from the same order at the same time in order to reduce shipping costs. However, works on customer orders coupled with class setup times do not appear often in the literature. Hence we address here a bicriteria single machine customer order scheduling problem together with multiple job classes. The optimality criterion minimizes a linear combination of the sum of the ranges and sum of tardiness of all customer orders. In light of the high complexity of the concerned problem, we propose a lower bound formula and a property to be used in a branch-and-bound method for optimal solutions. To find approximate solutions, we then propose four heuristics together with a local search method, four cloudy theoretical simulated annealing and a cloudy theoretical simulated annealing hyperheuristic along with five low-level heuristics. The simulation results of the proposed heuristics and algorithms are analyzed.