{"title":"Improving support vector machine classification accuracy based on kernel parameters optimization","authors":"Lubna B. Mohammed, K. Raahemifar","doi":"10.22360/springsim.2018.cns.013","DOIUrl":"https://doi.org/10.22360/springsim.2018.cns.013","url":null,"abstract":"Support Vector Machine (SVM) learning algorithm is considered as the most popular classification algorithm. It is a supervised learning technique that is mainly based on the conception of decision planes. These decision planes define decision boundaries which are used to separate a set of objects. It is important to extract the main features of the training datasets. These features can be used to define the separation boundaries. The separation boundaries can also be improved by tuning the parameters of the separation hyperplane. In literature, there are different techniques for feature selection and SVM parameters optimization that can be used to improve classification accuracy. There are a wide variety of applications that use SVM classification algorithm, such as text classification, disease diagnosis, gene analysis, and many others. The aim of this paper is to investigate the techniques that can be used to improve the classification accuracy of SVM based on kernel parameters optimization. The datasets are collected from different applications; having different number of classes and different number of features. The analysis and comparison among different kernel parameters were implemented on different datasets to study the effect of the number of features, the number of classes, and kernel parameters on the performance of the classification process.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114443775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Enabling design-space exploration for domain-specific modelling","authors":"B. Meyers, J. Denil, Ken Vanherpen, H. Vangheluwe","doi":"10.22360/springsim.2018.mod4sim.006","DOIUrl":"https://doi.org/10.22360/springsim.2018.mod4sim.006","url":null,"abstract":"Design-Space Exploration (DSE) looks for a suitable candidate solution to a problem, with respect to a set of criteria, by searching through a space of possible solution designs. Domain-Specific Modelling (DSM) allows language engineers to create Domain-Specific Languages (DSLs) for a particular domain, allowing non-technical domain experts to use the DSL to model a system, analyse, optimise or transform the model, generate code or documentation, etc. This paper presents a framework to enable DSE for DSM, so that non-technical domain experts can define DSE input using DSL syntax, and obtain DSL instances as a result of execution the DSE. The contribution of our framework is twofold: (1) automatic generation of a family of related DSLs (to describe structural constraints as well as constraints on simulation results) for modelling a DSE problem at the DSL level from a given DSL definition, and (2) generic support for executing a DSE algorithm, which searches the design space and generates suitable DSL instances. The framework can be applied to any explicitly defined DSL with an explicitly defined semantic domain. We evaluate this claim by applying our framework to a user-defined Simulink library. The approach is explained using a DSL for modelling electronic filters.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121098396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Mierlo, Yentl Van Tendeloo, István Dávid, B. Meyers, Addis Gebremichael, H. Vangheluwe
{"title":"A multi-paradigm approach for modelling service interactions in model-driven engineering processes","authors":"S. Mierlo, Yentl Van Tendeloo, István Dávid, B. Meyers, Addis Gebremichael, H. Vangheluwe","doi":"10.5555/3213214.3213220","DOIUrl":"https://doi.org/10.5555/3213214.3213220","url":null,"abstract":"To tackle the growing complexity of engineered systems, Model-Driven Engineering (MDE) proposes to promote models to first-class citizens in the development process. Within MDE, Multi-Paradigm Modelling (MPM) advocates modelling every relevant aspect of a system explicitly, using the most appropriate formalism(s), at the most appropriate level(s) of abstraction, while explicitly modelling the underlying process. Often, activities of the process require interaction with (domain-specific) engineering and modelling tools. These interactions are, however, typically captured in scripts and program code, which is ill-suited for describing the timed, reactive, and concurrent behaviour of these protocols. Additionally, formal analysis of the overall process is limited due to the incorporation of black-box activities. In this paper, we propose an approach for the explicit modelling of service interaction protocols in the activities of MDE processes. We also explicitly model the execution semantics of our process model, to promote reuse and allow for future analysability. For both purposes, we propose to use SCCD, a Statecharts variant, resulting in a unified and concise formalism.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121169299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Patrolling task planning for the multi-layer multi-agent system based on sequential allocation method","authors":"Xin Zhou, Weiping Wang, Tao Wang, Xiaobo Li","doi":"10.22360/springsim.2018.msciaas.001","DOIUrl":"https://doi.org/10.22360/springsim.2018.msciaas.001","url":null,"abstract":"The unmanned aerial vehicle (UAV) swarm has developed rapidly in recent years, especially the UAV swarm with sensors which is becoming common means of achieving situational awareness. In this paper, we develop a scalable, online and myopic algorithm for the multi-layer multi-agent system continuously patrolling problem. The main goal of the multi-agent system is to collect information as much as possible. We formulate this problem as Partially Observable Markov Decision Process (POMDP). The algorithm includes information dimensionality reduction representation, inter-layer information interaction, online heuristic function and sequential allocation method, which effectively improve the collected information and reduces the computational complexity. In addition, as the layer increases, this algorithm can guarantee the patrolling performance of the multi-agent system without increasing the computational complexity for each sub-leader. Finally, the empirical analysis shows that our algorithm has many advantages, which has theoretical and practical significance.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129172265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Software architecture for parallel particle tracking with the distribution of large amount of data","authors":"Florent Bonnier, N. Emad, X. Juvigny","doi":"10.22360/springsim.2018.hpc.015","DOIUrl":"https://doi.org/10.22360/springsim.2018.hpc.015","url":null,"abstract":"This study is about the architecture of a library designed for particle tracking. This library exposes common features used to track particles in large meshes using parallel algorithms to localize, manage, distribute and move particles over computing units. The proposed library design ables particles to be tracked using multiple heterogeneous parallel paradigms with component reusability. A customized algorithm to distribute particles over processes has been developed that uses different features of this architecture and shows a high impact on particle localization and movement execution time.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132207089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Laura Pérez-Vilarelle, J. L. Risco-Martín, J. Ayala
{"title":"Modeling and simulation of wind energy production in the smart-grid scenario","authors":"Laura Pérez-Vilarelle, J. L. Risco-Martín, J. Ayala","doi":"10.22360/springsim.2018.msciaas.002","DOIUrl":"https://doi.org/10.22360/springsim.2018.msciaas.002","url":null,"abstract":"Renewable energies, in particular wind energy, are characterized as highly variable and unpredictable in terms of production, and they are increasingly more important in the context of the smart grid energy production. In this scenario, accurate prediction models and techniques are desirable to optimize the renewable energy production and reduce the environmental impact. In this article, we propose the development of predictive techniques based on mathematical models, and the integration in a simulation framework that enables the simulation of variable conditions in wind energy production. The system also offers the possibility to automatically select the most reliable model for the current conditions. Our results show an accuracy of prediction (model fit) of up to 84%. The proposed simulation framework has been stressed with real data acquired from wind turbines in the area of Spain, providing efficient model selection and tuning of optimization parameters.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124537994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kamrul Hasan, S. Shetty, John A. Sokolowski, Deepak K. Tosh
{"title":"Security game for cyber physical systems","authors":"Kamrul Hasan, S. Shetty, John A. Sokolowski, Deepak K. Tosh","doi":"10.22360/springsim.2018.cns.015","DOIUrl":"https://doi.org/10.22360/springsim.2018.cns.015","url":null,"abstract":"The extensive use of information and communication technologies (ICT) in cyber physical systems (CPSs) make them vulnerable to cyber-attacks. One class of cyber-attack is advanced persistent threats where highly skilled attackers can steal user authentication information and then move laterally in the network, from host to host in a hidden manner until they reach an attractive target. The security modeling process of CPSs is divided into two phases of intrusion and disruption. In each phase, a game-theoretic paradigm with different parameters predicts the interactions between the attacker and the system. By solving the model, the security of CPSs is estimated in terms of probability of attack and probability of defend. After getting those the attackers and defenders can take optimized actions to maximize their gains. Most importantly, defender/systems can tune the system parameters to mitigate the attack.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128194773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Caleb Robinson, J. Crittenden, Zhongming Lu, R. Fujimoto
{"title":"Toward a common object model for integrated transportation and land use models","authors":"Caleb Robinson, J. Crittenden, Zhongming Lu, R. Fujimoto","doi":"10.22360/springsim.2018.anss.011","DOIUrl":"https://doi.org/10.22360/springsim.2018.anss.011","url":null,"abstract":"Evaluating the effects of a change to one aspect of the modern urban environment requires knowledge about other parts and how they are interconnected. Thus, integrated simulations of many parts of the entire urban ecosystem are needed to create and evaluate the effects of policies. Many existing models target a single urban system - land use models, transportation models, water system models, etc. - however coupling them to create interconnected systems often requires great effort and resources. In this work we propose a common object model for integrated transportation and land use models (ITLUMs) using the High Level Architecture Standard (IEEE 1516) (IEEE 2010). This object model is the first step in a longer term effort to develop new simulation models that can be readily integrated through common data abstractions. Finally, the proposed object model is designed to be extendable to capture the elements from other models of the urban environment.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126352464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hurst parameter as a correlation measure for brain signal","authors":"A. Ahmad, J. Holst","doi":"10.22360/springsim.2018.cns.016","DOIUrl":"https://doi.org/10.22360/springsim.2018.cns.016","url":null,"abstract":"Correlation in brain is generally considered an evidence of physical connectivity of the neuron network. However, the way neuron clusters cooperate varies from mental function to function. In this work, we used Hurst parameter as a measure of brain signal correlation and analyzed the EEG data made fungible available by USC. We found striking results showing significant self-similarity in the analyzed EEG signal in the form of high values for the Hurst's parameter. This raises the question whether neurons communicate using common control signals very similar to the control protocols in Internet devices, also resulting in high self-similarity.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123775600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A system dynamics simulation modeling for managing the inventory in multi-echelon multi-product pharmaceutical supply chain","authors":"M. Abidi, Abdallah Lattouf, S. Altarazi","doi":"10.22360/springsim.2018.anss.007","DOIUrl":"https://doi.org/10.22360/springsim.2018.anss.007","url":null,"abstract":"This paper presents a System Dynamics simulation inventory management modeling for a multi-echelon multi-product pharmaceutical supply chain (PSC). The (R, s, S) inventory control method is adopted for all PSC entities while considering stochastic products' demand. The model aims to support the PSC entities managers selecting their operational service levels in light of the total inventory cost. Two models are proposed; the first consists of a distributor, a health care facility, and a manufacturer; while the second model introduces more complicated scenario with local and regional distributors, two healthcare facilities, and a manufacturer. The models implementation established its ability to illustrate the trade-off between the inventory cost and the service level.","PeriodicalId":413389,"journal":{"name":"Spring Simulation Multiconference","volume":"677 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132452128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}