Flight delay is the most common preoccupation of aviation stakeholders around the world. Airlines, which suffer from a monetary and customer loyalty loss, are the most affected. Various studies have attempted to analyze and solve flight delays using machine learning algorithms. This research aims to predict flights’ arrival delay using Artificial Neural Network (ANN). We applied a MultiLayer Perceptron (MLP) to train and test our data. Two approaches have been adopted in our work. In the first one, we used historical flight data extracted from Bureau of Transportation Statistics (BTS). The second approach improves the efficiency of the model by applying selective-data training. It consists of selecting only most relevant instances from the training dataset which are delayed flights. According to BTS, a flight whose difference between scheduled and actual arrival times is 15 minutes or greater is considered delayed. Departure delays and flight distance proved to be very contributive to flight delays. An adjusted and optimized hyperparameters using grid search technique helped us choose the right architecture of the network and have a better accuracy and less error than the existing literature. The results of both traditional and selective training were compared. The efficiency and time complexity of the second method are compared against those of the traditional training procedure. The neural network MLP was able to predict flight arrival delay with a coefficient of determination R 2 of 0.9048, and the selective procedure achieved a time saving and a better R 2 score of 0.9560. To enhance the reliability of the proposed method, the performance of the MLP was compared with that of Gradient Boosting (GB) and Decision Trees (DT). The result is that the MLP outperformed all existing benchmark methods.
Abstract:Using the association rules in datamining is one of the most relevant techniques in modern society, aiming to extract the interesting correlation and relation among sets of items or products in large transactional databases. The huge number of extracted association rules represents the main problem that a decision maker can face. Hence, the knowledge post-processing phase becomes very important and challenging to define the most interesting association rules, many interestingness measures have been proposed. Currently, there is no optimal measure that can be selected to evaluate the extracted association rules. To bypass this problem, we propose an approach based on multi-criteria optimization aiming to find a good compromise without excluding any measures. The experiments performed on numerous benchmark datasets show that the proposed algorithm is properly reducing a large number of association rules and keeping the most significant and interesting ones compared to other approaches which illustrate the efficiency and the applicability our approach.
In the early phases of the software development process, specifications are mostly written in a natural language rather than formal models, which is not supported by the Model Driven Architecture (MDA). For this reason, the Semantic of Business Vocabulary and Rules (SBVR) is proposed by the Object Management Group to represent the textual specifications in a language comprehensible by both of humans and machines, to facilitate its integration in the MDA lifecycle. However, businesspeople are usually not familiar with SBVR standard. In this paper we present an approach to automatically transform textual business rules to an SBVR model, to facilitate its integration in nowadays information technology infrastructures. Our approach is distinguished from existing works in that it uses an in-depth Natural Language Processing to extract a more comprehensible SBVR model that includes the semantic formulation of each business rule statement, coupled with a Terminological Dictionary of extracted concepts, to which we have added further specifications such as definitions and synonyms. The evaluation of our approach shows that for three sets of business rules statements taken from different domains, we could generate the correct meaning with an average of F1-score exceeding 87%.
The extraction of association rules is a very attractive data mining task and the most widespread in the business world and in modern society, trying to obtain the interesting relationship and connection between collections of articles, products or items in high transactional databases. The immense quantity of association rules obtained expresses the main obstacle that a decision maker can handle. Consequently, in order to establish the most interesting association rules, several interestingness measures have been introduced. Currently, there is no optimal measure that can be chosen to judge the selected association rules. To avoid this problem we suggest to apply ELECTRE method one of the multi-criteria decision making, taking into consideration a formal study of measures of interest according to structural properties, and intending to find a good compromise and select the most interesting association rules without eliminating any measures. Experiments conducted on reference data sets show a significant improvement in the performance of the proposed strategy.
The future of Open Distributed Processing systems (ODP) will see an increasing of components number, these components are sharing resources. In general, these resources are offering some kind of services. Due to the huge number of components, it is very difficult to offer the optimum Quality of service (QoS). This encourages us to develop a model for QoS negotiation process to optimize the QoS in an ODP system. In such system, there is a High risk of software or hardware failure. To ensure good performance of a system based on our model, we develop it using a formal method. In our case, we will use Event-B to get in the end of our development a system correct by construction. Keyword: INTRODUCTIONThe evolution of telecommunications technology and the structure of organizations have led to the emergence of complex distributed systems. These systems are distributed structures whose components, both hardware and software, are of different types. In some systems, these components are developed by different actors acting independently of each other. The assembly of such components gives rise to highly heterogeneous systems. The applications that support these systems are themselves composed of distributed components. The interaction between these application components is one of the aspects of the distributed treatment. Specifically, the distributed processing correspond to different aspects of information processing in which specific components can be located in different places, during this process the communication between components may be delays or failures. This means that this kind of systems needs to be developed carefully due to its complexity [1]. This motivates us to model it using a formal method to ensure the correctness of our system and obtain a very strong assurance of bug's absence. Formal methods are a particular kind of mathematically based techniques for the specification [2], [3], development and verification of software and hardware systems [4]. There are a variety of formal methods such as language Z, a specification in Z is a predicate, the specification of invariants and the specification of operations have the form of a predicate. There is also B-method which is a method of software development based on B, a toolsupported formal method based on an abstract machine notation, used in the development of computer software. It was originally developed by Jean-Raymond Abrial [5].In this paper, we will use Event-B [6] since it allows us to prove that our system is correct by construction basing on proofs obligations. These proofs are done automatically by a tool called Rodin [7]. Event-B is also based on refinement which means creating an abstract model and enriching it in a multiple steps by adding more details to get a more concrete model [8]. In every refinement, we prove that the system is correct and it does not contradict with the previous one, whereby the resulting system is correct by
In the last few years, Model Driven Architecture (MDA), introduced by the Object Management Group (OMG), has become an important approach that uses models throughout the life cycle of software design and development. It distinguishes four levels: Computation Independent Model (CIM), Platform Independent Model (PIM), Platform Specific Model (PSM) and the code level. Transformations between PIMs and PSMs and code generation from the PIMs are well studied by various researchers.This research focuses on an important part of the transformation from the high level CIM to a PIM level. In this paper we derive the PIM Static Model, which is represented by the Domain Class Model, from a BPMN which is a key artifact of the CIM, using a set of transformation rules. Finally, we will apply our proposal to a case study, to further illustrate how to use these rules.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.