Minősített cikkek
Developing a Workflow Management System Simulation for Capturing Internal IaaS Behavioural Knowledge
Scientific workflows are becoming increasingly important for complex scientific applications. Conducting real experiments for large-scale workflows is challenging because they are very expensive and time consuming. A simulation is an alternative approach to a real experiment that can help evaluating the performance of workflow management systems (WMS) and optimise workflow management techniques. Although there are several workflow simulators available today, they are often user-oriented and treat the cloud as a black box. Unfortunately, this behaviour prevents the evaluation of the infrastructure level impact of the various decisions made by the WMSs. To address these issues, we have developed a WMS simulator (called DISSECT-CF-WMS) on DISSECT-CF that exposes the internal details of cloud infrastructures. DISSECT-CF-WMS enables better energy awareness by allowing the study of schedulers for physical machines. It also enables dynamic provisioning to meet the resource needs of the workflow application while considering the provisioning delay of a VM in the cloud. We evaluated our simulation extension by running several workflow applications on a given infrastructure. The experimental results show that we can investigate different schedulers for physical machines on different numbers of virtual machines to reduce energy consumption. The experiments also show that DISSECT-CF-WMS is up to 295× faster than WorkflowSim and still provides equivalent results. The experimental results of auto-scaling show that it can optimise makespan, energy consumption and VM utilisation in contrast to static VM provisioning.
Scientific workflows are becoming increasingly important for complex scientific applications. Conducting real experiments for large-scale workflows is challenging because they are very expensive and time consuming. A simulation is an alternative approach to a real experiment that can help evaluating the performance of workflow management systems (WMS) and optimise workflow management techniques. Although there are several workflow simulators available today, they are often user-oriented and treat the cloud as a black box. Unfortunately, this behaviour prevents the evaluation of the infrastructure level impact of the various decisions made by the WMSs. To address these issues, we have developed a WMS simulator (called DISSECT-CF-WMS) on DISSECT-CF that exposes the internal details of cloud infrastructures. DISSECT-CF-WMS enables better energy awareness by allowing the study of schedulers for physical machines. It also enables dynamic provisioning to meet the resource needs of the workflow application while considering the provisioning delay of a VM in the cloud. We evaluated our simulation extension by running several workflow applications on a given infrastructure. The experimental results show that we can investigate different schedulers for physical machines on different numbers of virtual machines to reduce energy consumption. The experiments also show that DISSECT-CF-WMS is up to 295× faster than WorkflowSim and still provides equivalent results. The experimental results of auto-scaling show that it can optimise makespan, energy consumption and VM utilisation in contrast to static VM provisioning.
Minősített cikkek
Property-Based Quality Measures in Ontology Modeling
The development of an appropriate ontology model is usually a hard task. One of the main issues is that ontology developers usually concentrate on classes and neglect the role of properties. This paper analyzes the role of an appropriate property set in providing multi-purpose ontology models with a high level of re-usability in different areas. In this paper, novel quality metrics related to property components are introduced and a conversion method is presented to map the base ontology into models for software development. The benefits of the proposed quality metrics and the usability of the proposed conversion methods are demonstrated by examples from the field of knowledge modeling.
The development of an appropriate ontology model is usually a hard task. One of the main issues is that ontology developers usually concentrate on classes and neglect the role of properties. This paper analyzes the role of an appropriate property set in providing multi-purpose ontology models with a high level of re-usability in different areas. In this paper, novel quality metrics related to property components are introduced and a conversion method is presented to map the base ontology into models for software development. The benefits of the proposed quality metrics and the usability of the proposed conversion methods are demonstrated by examples from the field of knowledge modeling.
Minősített cikkek
Mathematical Model for the Generalized VRP Model
The Vehicle Routing Problem (VRP) is a highly investigated logistics problem. VRP can model in-plant and out-plant material handling or a whole supply chain. The first Vehicle Routing Problem article was published in 1959 by Dantzig and Ramser, and many varieties of VRP have appeared since then. Transport systems are becoming more and more customized these days, so it is necessary to develop a general system that covers many transport tasks. Based on the literature, several components of VRP have appeared, but the development of an integrated system with all components has not yet been completed by the researchers. An integrated system can be useful because it is easy to configure; many transportation tasks can be easily modeled with its help. Our purpose is to present a generalized VRP model and show, in the form of case studies, how many transport tasks the system can model by including (omitting) each component. In this article, a generalized system is introduced, which covers the main VRP types that have appeared over the years. In the introduction, the basic Vehicle Routing Problem is presented, where the most important Vehicle Routing Problem components published so far are also detailed. The paper also gives the mathematical model of the generalization of the Vehicle Routing Problem and some case studies of the model are presented.
The Vehicle Routing Problem (VRP) is a highly investigated logistics problem. VRP can model in-plant and out-plant material handling or a whole supply chain. The first Vehicle Routing Problem article was published in 1959 by Dantzig and Ramser, and many varieties of VRP have appeared since then. Transport systems are becoming more and more customized these days, so it is necessary to develop a general system that covers many transport tasks. Based on the literature, several components of VRP have appeared, but the development of an integrated system with all components has not yet been completed by the researchers. An integrated system can be useful because it is easy to configure; many transportation tasks can be easily modeled with its help. Our purpose is to present a generalized VRP model and show, in the form of case studies, how many transport tasks the system can model by including (omitting) each component. In this article, a generalized system is introduced, which covers the main VRP types that have appeared over the years. In the introduction, the basic Vehicle Routing Problem is presented, where the most important Vehicle Routing Problem components published so far are also detailed. The paper also gives the mathematical model of the generalization of the Vehicle Routing Problem and some case studies of the model are presented.
Minősített cikkek
Analysis of the Multi-Objective Optimisation Techniques in Solving a Complex Vehicle Routing Problem
The Vehicle Routing Problem (VRP) is a common logistics problem. The problem was first published in 1959 as the Truck Dispatching Problem. In the basic problem, vehicles deliver the products from a given depot and then return to the depot. The objective function is to minimise the distance travelled by the vehicles. Since the first published paper, a number of variants have been developed that adapt to real logistics demands. This article investigates the optimisation of a complex Vehicle Routing Problem. The following multi-objective optimisation techniques are investigated in the article: weighted-sum method, weighted-exponential sum method, weighted global criterion method, exponentially weighted criterion, weighted product method, bounded objective function method, pareto ranking, Non-dominated Sorting Genetic Algorithm II, Strength Pareto Evolutionary Algorithm, Niched Pareto Genetic Algorithm. The article provides a detailed analysis with the following heuristic algorithms: Ant Colony System, Genetic Algorithm, Tabu Search, Firefly Algorithm, Simulated Annealing.
The Vehicle Routing Problem (VRP) is a common logistics problem. The problem was first published in 1959 as the Truck Dispatching Problem. In the basic problem, vehicles deliver the products from a given depot and then return to the depot. The objective function is to minimise the distance travelled by the vehicles. Since the first published paper, a number of variants have been developed that adapt to real logistics demands. This article investigates the optimisation of a complex Vehicle Routing Problem. The following multi-objective optimisation techniques are investigated in the article: weighted-sum method, weighted-exponential sum method, weighted global criterion method, exponentially weighted criterion, weighted product method, bounded objective function method, pareto ranking, Non-dominated Sorting Genetic Algorithm II, Strength Pareto Evolutionary Algorithm, Niched Pareto Genetic Algorithm. The article provides a detailed analysis with the following heuristic algorithms: Ant Colony System, Genetic Algorithm, Tabu Search, Firefly Algorithm, Simulated Annealing.
Minősített cikkek
Fitness Landscape Analysis of Population-Based Heuristics in Solving a Complex Vehicle Routing Problem
In this paper, a fitness landscape analysis of a complex Vehicle Routing Problem (VRP) is presented, and the effectiveness of population-based heuristic techniques is analyzed on this complex problem. The Vehicle Routing Problem is a common optimization task where vehicles deliver products to customers. The task is NP difficult; several heuristic algorithms have been involved in solving the problem. The objective is to select the right algorithm for the task, where the search space analysis provides an analytical answer. In this paper, the analysis of the population-based heuristics is presented. The paper presents an analysis of the following population algorithms: Ant System, Elitist Strategy of Ant System, Firefly Algorithm, Genetic Algorithm. In this paper, the results of the iterations of each population algorithm are analyzed in terms of the followings: fitness values, fitness distances, basic swap sequence distances, Hamming distances, the best solution, and filtered optima. Based on the test results, it can be concluded that the Ant System algorithm proved to be the most effective and the Firefly algorithm is not recommended to solve the presented complicated VRP.
In this paper, a fitness landscape analysis of a complex Vehicle Routing Problem (VRP) is presented, and the effectiveness of population-based heuristic techniques is analyzed on this complex problem. The Vehicle Routing Problem is a common optimization task where vehicles deliver products to customers. The task is NP difficult; several heuristic algorithms have been involved in solving the problem. The objective is to select the right algorithm for the task, where the search space analysis provides an analytical answer. In this paper, the analysis of the population-based heuristics is presented. The paper presents an analysis of the following population algorithms: Ant System, Elitist Strategy of Ant System, Firefly Algorithm, Genetic Algorithm. In this paper, the results of the iterations of each population algorithm are analyzed in terms of the followings: fitness values, fitness distances, basic swap sequence distances, Hamming distances, the best solution, and filtered optima. Based on the test results, it can be concluded that the Ant System algorithm proved to be the most effective and the Firefly algorithm is not recommended to solve the presented complicated VRP.
Minősített cikkek
An Approach to Implementation of Autoencoders in Intelligent Vehicles
We can see a rise in the number of smart vehicles in the last past few years. These types of cars are usually or, in other words, they are physically work as intelligent as robots. Intelligent vehicles have become an important part as they are equipped with intelligent agents that give services to human beings. It is approximated that over 1 billion cars travel the streets and roads of the world today. With such traffic, it is apparent that there are many situations where the driver has to react quickly. As Intelligent vehicles are connected to a large amount of data, these data may be dimensionally decreased and kept as latent data. Then, when needed, they can be reconstructed and used. The aim of the current paper is an approach to the implementation of an unsupervised autoencoder technique in intelligent vehicles. The autoencoders have significant importance as they detect and recognize unknown data. In this case, we can say the autoencoders may replace labelled supervised neural networks if they learn effective encoding (data representation).
We can see a rise in the number of smart vehicles in the last past few years. These types of cars are usually or, in other words, they are physically work as intelligent as robots. Intelligent vehicles have become an important part as they are equipped with intelligent agents that give services to human beings. It is approximated that over 1 billion cars travel the streets and roads of the world today. With such traffic, it is apparent that there are many situations where the driver has to react quickly. As Intelligent vehicles are connected to a large amount of data, these data may be dimensionally decreased and kept as latent data. Then, when needed, they can be reconstructed and used. The aim of the current paper is an approach to the implementation of an unsupervised autoencoder technique in intelligent vehicles. The autoencoders have significant importance as they detect and recognize unknown data. In this case, we can say the autoencoders may replace labelled supervised neural networks if they learn effective encoding (data representation).
Minősített cikkek
Lattices defined by multigranular rough sets
One way to view the multigranular rough set model is that the assessment of more experts are considered when determining the approximations of a set, instead of a single equivalence relation expressing the indiscernibility of the objects. There are two approaches for modeling this: the optimistic and the pessimistic multigranular rough set models. In this paper, we analyze both approaches from a lattice-theoretic point of view. We generalize existing results for two equivalence relations (two experts) to n equivalence relations, completing them with additional findings. We also characterize the order structures of optimistic and pessimistic rough sets and determine when they form complete, or even completely distributive lattices. Additionally, we examine the properties of the Dedekind-MacNeille completion of the poset of optimistic multigranular rough sets. Some applications for information tables and for recommendation theory are also presented.
One way to view the multigranular rough set model is that the assessment of more experts are considered when determining the approximations of a set, instead of a single equivalence relation expressing the indiscernibility of the objects. There are two approaches for modeling this: the optimistic and the pessimistic multigranular rough set models. In this paper, we analyze both approaches from a lattice-theoretic point of view. We generalize existing results for two equivalence relations (two experts) to n equivalence relations, completing them with additional findings. We also characterize the order structures of optimistic and pessimistic rough sets and determine when they form complete, or even completely distributive lattices. Additionally, we examine the properties of the Dedekind-MacNeille completion of the poset of optimistic multigranular rough sets. Some applications for information tables and for recommendation theory are also presented.
Minősített cikkek
Identification of online harassment using ensemble fine-tuned pre-trained Bert
Identification of online hate is the prime concern for natural language processing researchers; social media has augmented this menace by providing a virtual platform for online harassment. This study identifies online harassment using the trolling aggression and cyber-bullying dataset from shared tasks workshop. This work concentrates on extreme pre-processing and ensemble approach for model building; this study also considers the existing algorithms like the random forest, logistic regression, multinomial Naïve Bayes. Logistic regression proves to be more efficient with the highest accuracy of 57.91%. Ensemble bidirectional encoder representation from transformers showed promising results with 62% precision, which is better than most existing models.
Identification of online hate is the prime concern for natural language processing researchers; social media has augmented this menace by providing a virtual platform for online harassment. This study identifies online harassment using the trolling aggression and cyber-bullying dataset from shared tasks workshop. This work concentrates on extreme pre-processing and ensemble approach for model building; this study also considers the existing algorithms like the random forest, logistic regression, multinomial Naïve Bayes. Logistic regression proves to be more efficient with the highest accuracy of 57.91%. Ensemble bidirectional encoder representation from transformers showed promising results with 62% precision, which is better than most existing models.
Minősített cikkek
Deep convolutional neural network model for bad code smells detection based on oversampling method
Code smells refers to any symptoms or anomalies in the source code that shows violation of design principles or implementation. Early detection of bad code smells improves software quality. Nowadays several artificial neural network (ANN) models have been used for different topics in software engineering: software defect prediction, software vulnerability detection, and code clone detection. It is not necessary to know the source of the data when using ANN models but require large training sets. Data imbalance is the main challenge of artificial intelligence techniques in detecting the code smells. To overcome these challenges, the objective of this study is to presents deep convolutional neural network (D-CNN) model with synthetic minority over-sampling technique (SMOTE) to detect bad code smells based on a set of Java projects. We considered four code-smell datasets which are God class, data class, feature envy and long method and the results were compared based on different performance measures. Experimental results show that the proposed model with oversampling techniques can provide better performance for code smells detection and prediction results can be further improved when the model is trained with more datasets. Moreover, more epochs and hidden layers help increase the accuracy of the model.
Code smells refers to any symptoms or anomalies in the source code that shows violation of design principles or implementation. Early detection of bad code smells improves software quality. Nowadays several artificial neural network (ANN) models have been used for different topics in software engineering: software defect prediction, software vulnerability detection, and code clone detection. It is not necessary to know the source of the data when using ANN models but require large training sets. Data imbalance is the main challenge of artificial intelligence techniques in detecting the code smells. To overcome these challenges, the objective of this study is to presents deep convolutional neural network (D-CNN) model with synthetic minority over-sampling technique (SMOTE) to detect bad code smells based on a set of Java projects. We considered four code-smell datasets which are God class, data class, feature envy and long method and the results were compared based on different performance measures. Experimental results show that the proposed model with oversampling techniques can provide better performance for code smells detection and prediction results can be further improved when the model is trained with more datasets. Moreover, more epochs and hidden layers help increase the accuracy of the model.
Minősített cikkek
Automated Assessment Generation in Intelligent Tutoring Systems
Intelligent Tutoring Systems have a huge potential to improve the efficiency of learning and teaching, especially for personalized adaptive self-learning. The investigation presented in this paper focuses on the implementation of a sub-module, the Automated Question Generation for Assessment unit, using a combined rule based and machine learning based methods. The proposed module is based on a proposed background domain ontology, and it works in two phases. A generator automaton is used to construct the answer templates in the first phase. In the next phase, an encoder-decoder neural network translator unit was used to generate the question sentence templates for the selected answer templates. According to the tests with the implemented prototype assessment generator application on the SQL domain, the proposed framework is suitable to generate assessment tasks in a very efficient way.
Intelligent Tutoring Systems have a huge potential to improve the efficiency of learning and teaching, especially for personalized adaptive self-learning. The investigation presented in this paper focuses on the implementation of a sub-module, the Automated Question Generation for Assessment unit, using a combined rule based and machine learning based methods. The proposed module is based on a proposed background domain ontology, and it works in two phases. A generator automaton is used to construct the answer templates in the first phase. In the next phase, an encoder-decoder neural network translator unit was used to generate the question sentence templates for the selected answer templates. According to the tests with the implemented prototype assessment generator application on the SQL domain, the proposed framework is suitable to generate assessment tasks in a very efficient way.
Minősített cikkek
B-Morpher: Automated Learning of Morphological Language Characteristics for Inflection and Morphological Analysis
The automated induction of inflection rules is an important research area for computational linguistics. In this paper, we present a novel morphological rule induction model called B-Morpher that can be used for both inflection analysis and morphological analysis. The core element of the engine is a modified Bayes classifier in which class categories correspond to general string transformation rules. Beside the core classification module, the engine contains a neural network module and verification unit to improve classification accuracy. For the evaluation, beside the large Hungarian dataset the tests include smaller non-Hungarian datasets from the SIGMORPHON shared task pools. Our evaluation shows that the efficiency of B-Morpher is comparable with the best results, and it outperforms the state-of-the-art base models for some languages. The proposed system can be characterized by not only high accuracy, but also short training time and small knowledge base size.
The automated induction of inflection rules is an important research area for computational linguistics. In this paper, we present a novel morphological rule induction model called B-Morpher that can be used for both inflection analysis and morphological analysis. The core element of the engine is a modified Bayes classifier in which class categories correspond to general string transformation rules. Beside the core classification module, the engine contains a neural network module and verification unit to improve classification accuracy. For the evaluation, beside the large Hungarian dataset the tests include smaller non-Hungarian datasets from the SIGMORPHON shared task pools. Our evaluation shows that the efficiency of B-Morpher is comparable with the best results, and it outperforms the state-of-the-art base models for some languages. The proposed system can be characterized by not only high accuracy, but also short training time and small knowledge base size.
Minősített cikkek
Advanced Methods to Solve Multi-project Scheduling Problems Taking into Account Multiple Objective Functions
Project-based planning and execution have an important role in the product lifecycle. Medium and large-sized companies are executing more than one project simultaneously, usually sharing common resources. Each project has its individual goals to achieve. Creating a company-wide optimal or near-optimal schedule in this complex environment is very difficult. Our paper presents a model to define the problem and a concept of a possible solver. A proof-of-concept of an advanced solver with experimental results is presented.
Project-based planning and execution have an important role in the product lifecycle. Medium and large-sized companies are executing more than one project simultaneously, usually sharing common resources. Each project has its individual goals to achieve. Creating a company-wide optimal or near-optimal schedule in this complex environment is very difficult. Our paper presents a model to define the problem and a concept of a possible solver. A proof-of-concept of an advanced solver with experimental results is presented.
Minősített cikkek
Fuzzy formal concept analysis: approaches, applications and issues
Formal concept analysis (FCA) is today regarded as a significant technique for knowledge extraction, representation, and analysis for applications in a variety of fields. Significant progress has been made in recent years to extend FCA theory to deal with uncertain and imperfect data. The computational complexity associated with the enormous number of formal concepts generated has been identified as an issue in various applications. In general, the generation of a concept lattice of sufficient complexity and size is one of the most fundamental challenges in FCA. The goal of this work is to provide an overview of research articles that assess and compare numerous fuzzy formal concept analysis techniques which have been suggested, as well as to explore the key techniques for reducing concept lattice size. as well as we'll present a review of research articles on using fuzzy formal concept analysis in ontology engineering, knowledge discovery in databases and data mining, and information retrieval.
Formal concept analysis (FCA) is today regarded as a significant technique for knowledge extraction, representation, and analysis for applications in a variety of fields. Significant progress has been made in recent years to extend FCA theory to deal with uncertain and imperfect data. The computational complexity associated with the enormous number of formal concepts generated has been identified as an issue in various applications. In general, the generation of a concept lattice of sufficient complexity and size is one of the most fundamental challenges in FCA. The goal of this work is to provide an overview of research articles that assess and compare numerous fuzzy formal concept analysis techniques which have been suggested, as well as to explore the key techniques for reducing concept lattice size. as well as we'll present a review of research articles on using fuzzy formal concept analysis in ontology engineering, knowledge discovery in databases and data mining, and information retrieval.
Minősített cikkek
Optimized Ad-hoc Multi-hop Broadcast Protocol for Emergency Message Dissemination in Vehicular Ad-hoc Networks
Intelligent Transportation Systems and particularly vehicular adhoc networks (VANETs) play a key role in enabling Smart Cities as well as improving and maintaining road safety. VANETs are distributed networks built from moving vehicles on the road. Each vehicle of the network has an embedded IEEE 802.11p interface to support the interaction between the vehicles and their environment (V2X) and enable Inter Vehicular Communication (IVC). However, due to the instable nature of these networks caused by the high-speed mobility of the vehicles as well as frequent fragmentation and disconnection of the network, it is necessary to design and implement robust and fault tolerant communication protocols especially in the case of emergency situations on the road to rapidly alert the environment and the competent authorities. Moreover, the communication in these networks suffers from limited bandwidth spectrum making information dissemination time critical to achieve fairness toward all the nodes of the network. This paper proposes an optimization of the Ad-hoc Multi-hop Broadcast (AMB) protocol for the dissemination of information and particularly Emergency messages in vehicular ad-hoc networks (VANETs). The proposed solution aims to reduce the network traffic while optimizing the communication time and achieving high reliability for the emergency messages. The performance of the proposed protocol is evaluated on theoretical considerations and numerical calculations
Intelligent Transportation Systems and particularly vehicular adhoc networks (VANETs) play a key role in enabling Smart Cities as well as improving and maintaining road safety. VANETs are distributed networks built from moving vehicles on the road. Each vehicle of the network has an embedded IEEE 802.11p interface to support the interaction between the vehicles and their environment (V2X) and enable Inter Vehicular Communication (IVC). However, due to the instable nature of these networks caused by the high-speed mobility of the vehicles as well as frequent fragmentation and disconnection of the network, it is necessary to design and implement robust and fault tolerant communication protocols especially in the case of emergency situations on the road to rapidly alert the environment and the competent authorities. Moreover, the communication in these networks suffers from limited bandwidth spectrum making information dissemination time critical to achieve fairness toward all the nodes of the network. This paper proposes an optimization of the Ad-hoc Multi-hop Broadcast (AMB) protocol for the dissemination of information and particularly Emergency messages in vehicular ad-hoc networks (VANETs). The proposed solution aims to reduce the network traffic while optimizing the communication time and achieving high reliability for the emergency messages. The performance of the proposed protocol is evaluated on theoretical considerations and numerical calculations
Minősített cikkek
Comparision of the walk techniques for fitness state space analysis in vehicle routing problem
The Vehicle Routing Problem (VRP) is a highly researched discrete optimization task. The first article dealing with this problem was published by Dantzig and Ramster in 1959 under the name Truck Dispatching Problem. Since then, several versions of VRP have been developed. The task is NP difficult, it can be solved only in the foreseeable future, relying on different heuristic algorithms. The geometrical property of the state space influences the efficiency of the optimization method. In this paper, we present an analysis of the following state space methods: adaptive, reverse adaptive and uphill-downhill walk. In our paper, the efficiency of four operators are analysed on a complex Vehicle Routing Problem. These operators are the 2-opt, Partially Matched Crossover, Cycle Crossover and Order Crossover. Based on the test results, the 2-opt and Partially Matched Crossover are superior to the other two methods.
The Vehicle Routing Problem (VRP) is a highly researched discrete optimization task. The first article dealing with this problem was published by Dantzig and Ramster in 1959 under the name Truck Dispatching Problem. Since then, several versions of VRP have been developed. The task is NP difficult, it can be solved only in the foreseeable future, relying on different heuristic algorithms. The geometrical property of the state space influences the efficiency of the optimization method. In this paper, we present an analysis of the following state space methods: adaptive, reverse adaptive and uphill-downhill walk. In our paper, the efficiency of four operators are analysed on a complex Vehicle Routing Problem. These operators are the 2-opt, Partially Matched Crossover, Cycle Crossover and Order Crossover. Based on the test results, the 2-opt and Partially Matched Crossover are superior to the other two methods.
Minősített cikkek
Comparison of template-based and multilayer perceptron-based approach for automatic question generation system
Intelligent tutoring systems are computer-assisted learning systems with adaption to students using artificial intelligence tools. An intelligent tutoring system can drastically improve education efficiency as it provides solutions to many issues that now plague the educational industry. One important component in education is questioning learners to assess and reinforce learning. This research compares two approaches for automatic question generation, a template-based question generation strategy and the phrase-Level automatic question generation system utilizing the Multilayer perceptron model. A template-based technique is a baseline for automatic question generation that uses templates taken from the training set to generate questions by filling certain templates with specific topic items. We utilize question-answer sentence composition datasets and manually constructed datasets for our experiments and comparison of the Multilayer perceptron training model. We used both human and automatic evaluation metrics to assess the efficiency of our suggested methods. Regarding automatic metrics, we selected the BLEU-n gram and ROUGE-N methodologies. The evaluation results demonstrate that the phrase-level Multilayer perceptron-based strategy dominates the template-based approach and has a promising score in both ROUGE automatic and human evaluation metrics.
Intelligent tutoring systems are computer-assisted learning systems with adaption to students using artificial intelligence tools. An intelligent tutoring system can drastically improve education efficiency as it provides solutions to many issues that now plague the educational industry. One important component in education is questioning learners to assess and reinforce learning. This research compares two approaches for automatic question generation, a template-based question generation strategy and the phrase-Level automatic question generation system utilizing the Multilayer perceptron model. A template-based technique is a baseline for automatic question generation that uses templates taken from the training set to generate questions by filling certain templates with specific topic items. We utilize question-answer sentence composition datasets and manually constructed datasets for our experiments and comparison of the Multilayer perceptron training model. We used both human and automatic evaluation metrics to assess the efficiency of our suggested methods. Regarding automatic metrics, we selected the BLEU-n gram and ROUGE-N methodologies. The evaluation results demonstrate that the phrase-level Multilayer perceptron-based strategy dominates the template-based approach and has a promising score in both ROUGE automatic and human evaluation metrics.
Minősített cikkek
The Unrelated Parallel Machines Scheduling Problem with Machine and Job Dependent Setup Times, Availability Constraints, Time Windows and Maintenance Times
Unrelated Parallel Machines Scheduling Problem (U-PMSP) is a category of discrete optimization problems in which various manufacturing jobs are assigned to identical parallel machines at particular times. In this paper, a specific production scheduling task the U-PMSP with Machine and Job Dependent Setup Times, Availability Constraint, Time Windows and Maintenance Times is introduced. Machines with different capacity limits and maintenance times are available to perform the tasks. After that our problem, the U-PMSP with Machine and Job Dependent Setup Times, Availability Constraints, Time Windows and Maintenance Times is detailed. After that, the applied optimization algorithm and their operators are introduced. The proposed algorithm is the genetic algorithm (GA), and proposed operators are the order crossover, partially matched crossover, cycle crossover and the 2-opt as a mutation operator. Then we prove the efficiency of our algorithm with test results. We also prove the efficiency of the algorithm on our own data set and benchmark data set. The authors conclude that this GA is effective for solving high complexity parallel machine problems.
Unrelated Parallel Machines Scheduling Problem (U-PMSP) is a category of discrete optimization problems in which various manufacturing jobs are assigned to identical parallel machines at particular times. In this paper, a specific production scheduling task the U-PMSP with Machine and Job Dependent Setup Times, Availability Constraint, Time Windows and Maintenance Times is introduced. Machines with different capacity limits and maintenance times are available to perform the tasks. After that our problem, the U-PMSP with Machine and Job Dependent Setup Times, Availability Constraints, Time Windows and Maintenance Times is detailed. After that, the applied optimization algorithm and their operators are introduced. The proposed algorithm is the genetic algorithm (GA), and proposed operators are the order crossover, partially matched crossover, cycle crossover and the 2-opt as a mutation operator. Then we prove the efficiency of our algorithm with test results. We also prove the efficiency of the algorithm on our own data set and benchmark data set. The authors conclude that this GA is effective for solving high complexity parallel machine problems.
Minősített cikkek
Ant Colony Algorithms For The Vehicle Routing Problem With Time Window, Period And Multiple Depots
Vehicle Routing Problem is a common problem in logistics, which can simulate in-plant and out-plant material handling. In the article, we demonstrate a Vehicle Routing Problem, which contains period, time window and multiple depots. In this case, customers must be served from several depots. The position of the nodes (depots and customers), the demand and time window of the customers are known in advance. The number and capacity constraint of vehicles are predefined. The vehicles leave from one depot, visit some customers and then return to the depot. The above-described vehicle routing is solved with construction algorithms and Ant Colony algorithms. The Ant Colony algorithms are used to improve random solutions and solutions generated with construction algorithms. According to the test results the Elitist Strategy Ant System and the Rank-Based Version of Ant System algorithms gave the best solutions.
Vehicle Routing Problem is a common problem in logistics, which can simulate in-plant and out-plant material handling. In the article, we demonstrate a Vehicle Routing Problem, which contains period, time window and multiple depots. In this case, customers must be served from several depots. The position of the nodes (depots and customers), the demand and time window of the customers are known in advance. The number and capacity constraint of vehicles are predefined. The vehicles leave from one depot, visit some customers and then return to the depot. The above-described vehicle routing is solved with construction algorithms and Ant Colony algorithms. The Ant Colony algorithms are used to improve random solutions and solutions generated with construction algorithms. According to the test results the Elitist Strategy Ant System and the Rank-Based Version of Ant System algorithms gave the best solutions.
Minősített cikkek
A Hybrid Discrete Bacterial Memetic Algorithm with Simulated Annealing for Optimization of the Flow Shop Scheduling Problem
This paper deals with the flow shop scheduling problem. To find the optimal solution is an NP-hard problem. The paper reviews some algorithms from the literature and applies a benchmark dataset to evaluate their efficiency. In this research work, the discrete bacterial memetic evolutionary algorithm (DBMEA) as a global searcher was investigated. The proposed algorithm improves the local search by applying the simulated annealing algorithm (SA). This paper presents the experimental results of solving the no-idle flow shop scheduling problem. To compare the proposed algorithm with other researchers’ work, a benchmark problem set was used. The calculated makespan times were compared against the best-known solutions in the literature. The proposed hybrid algorithm has provided better results than methods using genetic algorithm variants, thus it is a major improvement for the memetic algorithm family solving production scheduling problems.
This paper deals with the flow shop scheduling problem. To find the optimal solution is an NP-hard problem. The paper reviews some algorithms from the literature and applies a benchmark dataset to evaluate their efficiency. In this research work, the discrete bacterial memetic evolutionary algorithm (DBMEA) as a global searcher was investigated. The proposed algorithm improves the local search by applying the simulated annealing algorithm (SA). This paper presents the experimental results of solving the no-idle flow shop scheduling problem. To compare the proposed algorithm with other researchers’ work, a benchmark problem set was used. The calculated makespan times were compared against the best-known solutions in the literature. The proposed hybrid algorithm has provided better results than methods using genetic algorithm variants, thus it is a major improvement for the memetic algorithm family solving production scheduling problems.
Minősített cikkek
An Attraction Map Framework of a Complex Multi-Echelon Vehicle Routing Problem with Random Walk Analysis
The paper aims to investigate the basin of attraction map of a complex Vehicle Routing Problem with random walk analysis. The Vehicle Routing Problem (VRP) is a common discrete optimization problem in field of logistics. In the case of the base VRP, the positions of one single depot and many customers (which have product demands) are given. The vehicles and their capacity limits are also fixed in the system and the objective function is the minimization of the length of the route. In the literature, many approaches have appeared to simulate the transportation demands. Most of the approaches are using some kind of metaheuristics. Solving the problems with metaheuristics requires exploring the fitness landscape of the optimization problem. The fitness landscape analysis consists of the investigation of the following elements: the set of the possible states, the fitness function and the neighborhood relationship. We use also metaheuristics are used to perform neighborhood discovery depending on the neighborhood interpretation. In this article, the following neighborhood operators are used for the basin of attraction map: 2-opt, Order Crossover (OX), Partially Matched Crossover (PMX), Cycle Crossover (CX). Based on our test results, the 2-opt and Partially Matched Crossover operators are more efficient than the Order Crossover and Cycle Crossovers.
The paper aims to investigate the basin of attraction map of a complex Vehicle Routing Problem with random walk analysis. The Vehicle Routing Problem (VRP) is a common discrete optimization problem in field of logistics. In the case of the base VRP, the positions of one single depot and many customers (which have product demands) are given. The vehicles and their capacity limits are also fixed in the system and the objective function is the minimization of the length of the route. In the literature, many approaches have appeared to simulate the transportation demands. Most of the approaches are using some kind of metaheuristics. Solving the problems with metaheuristics requires exploring the fitness landscape of the optimization problem. The fitness landscape analysis consists of the investigation of the following elements: the set of the possible states, the fitness function and the neighborhood relationship. We use also metaheuristics are used to perform neighborhood discovery depending on the neighborhood interpretation. In this article, the following neighborhood operators are used for the basin of attraction map: 2-opt, Order Crossover (OX), Partially Matched Crossover (PMX), Cycle Crossover (CX). Based on our test results, the 2-opt and Partially Matched Crossover operators are more efficient than the Order Crossover and Cycle Crossovers.