Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552135
Hao Feng, C. Gomes, Casper Thule, Kenneth Lausdahl, Alexandros Iosifidis, P. Larsen
Cyber-Physical Systems (CPSs) are getting increasingly complex and generate large amounts of data. Analyzing such data provides us an insight into a given system. The digital twin concept emerges as an attempt to seamlessly integrate the data and insight in order to improve system performances. It enables applications such as visualization, monitoring, state estimation, and self-adaptation. In this paper, we demonstrate the construction of a digital twin exemplified by an incubator system, including the benefits and challenges of each application. The result is a description of the building blocks of a digital twin.
{"title":"Introduction to Digital Twin Engineering","authors":"Hao Feng, C. Gomes, Casper Thule, Kenneth Lausdahl, Alexandros Iosifidis, P. Larsen","doi":"10.23919/ANNSIM52504.2021.9552135","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552135","url":null,"abstract":"Cyber-Physical Systems (CPSs) are getting increasingly complex and generate large amounts of data. Analyzing such data provides us an insight into a given system. The digital twin concept emerges as an attempt to seamlessly integrate the data and insight in order to improve system performances. It enables applications such as visualization, monitoring, state estimation, and self-adaptation. In this paper, we demonstrate the construction of a digital twin exemplified by an incubator system, including the benefits and challenges of each application. The result is a description of the building blocks of a digital twin.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"108 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74863639","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}
Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552121
Akul Sharma, R. Garner, M. Rocca, Celina Alba, Yenlin Lee, K. Yang, Maya Brawer-Cohen, D. Duncan
Post-traumatic epilepsy (PTE) is a consequence of traumatic brain injury (TBI) and can drastically decrease quality of life. Currently, there is no method available to predict which TBI patients will develop epilepsy. The present study aims to use a machine learning model that can accurately predict the risk of developing PTE from white-matter alterations following trauma. We used diffusion weighted imaging of 39 patients from the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy to analyze fractional anisotropy from a tractography-based analysis. Next, we utilized a Random Forest model to classify seizure outcomes in TBI patients. Our model, assessed with 100 rounds of cross-validation, classified seizure outcome with 61% accuracy. The discrimination between seizure-free and seizure-affected subjects suggests that the classifier could improve characterization and diagnosis of PTE. These results may be instrumental in predicting PTE risk and may be implemented in future research of antiepileptic therapies.
{"title":"Machine Learning of Diffusion Weighted Imaging for Prediction of Seizure Susceptibility Following Traumatic Brain Injury","authors":"Akul Sharma, R. Garner, M. Rocca, Celina Alba, Yenlin Lee, K. Yang, Maya Brawer-Cohen, D. Duncan","doi":"10.23919/ANNSIM52504.2021.9552121","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552121","url":null,"abstract":"Post-traumatic epilepsy (PTE) is a consequence of traumatic brain injury (TBI) and can drastically decrease quality of life. Currently, there is no method available to predict which TBI patients will develop epilepsy. The present study aims to use a machine learning model that can accurately predict the risk of developing PTE from white-matter alterations following trauma. We used diffusion weighted imaging of 39 patients from the Epilepsy Bioinformatics Study for Antiepileptogenic Therapy to analyze fractional anisotropy from a tractography-based analysis. Next, we utilized a Random Forest model to classify seizure outcomes in TBI patients. Our model, assessed with 100 rounds of cross-validation, classified seizure outcome with 61% accuracy. The discrimination between seizure-free and seizure-affected subjects suggests that the classifier could improve characterization and diagnosis of PTE. These results may be instrumental in predicting PTE risk and may be implemented in future research of antiepileptic therapies.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"82 1","pages":"1-9"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87447998","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}
Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552130
Emin Oguz Inci, Jan Croes, W. Desmet, C. Gomes, Casper Thule, Kenneth Lausdahl, P. Larsen
In non-iterative serial co-simulation, the solution sequence of the systems is ordered either ad-hoc or based on the solution priorities. The selection of the priorities determines which systems approximate the upcoming inputs from connected systems. This input estimation causes an error on the time integration of the states. This article discusses indicators to estimate the extent of input estimation contribution on the overall state calculation error and addresses to the question if the solution sequence has an influence on the state evolution. Moreover, a temporal analysis of this effect is studied to predict when to flip the sequence at an interface between two systems on a linear numerical example. In conclusion, an adaptive algorithm which switches the co-simulation sequence run-time based on the input estimation accuracy is proposed and validated with a parameter study.
{"title":"The Effect and Selection of Solution Sequence in Co-Simulation","authors":"Emin Oguz Inci, Jan Croes, W. Desmet, C. Gomes, Casper Thule, Kenneth Lausdahl, P. Larsen","doi":"10.23919/ANNSIM52504.2021.9552130","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552130","url":null,"abstract":"In non-iterative serial co-simulation, the solution sequence of the systems is ordered either ad-hoc or based on the solution priorities. The selection of the priorities determines which systems approximate the upcoming inputs from connected systems. This input estimation causes an error on the time integration of the states. This article discusses indicators to estimate the extent of input estimation contribution on the overall state calculation error and addresses to the question if the solution sequence has an influence on the state evolution. Moreover, a temporal analysis of this effect is studied to predict when to flip the sequence at an interface between two systems on a linear numerical example. In conclusion, an adaptive algorithm which switches the co-simulation sequence run-time based on the input estimation accuracy is proposed and validated with a parameter study.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"88 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85150705","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}
Military defense modernization initiatives often involve complex systems that must be understood to inform design, planning, implementation and acquisition decisions. To gain a basic understanding of the system and identify key initial parameters, simulation experiments can be used to generate – or farm – data efficiently and effectively over a large parametric space. While machine learning models can be used for post-simulation analysis to identify key parameters, interpretability and their black-box nature can present challenges when the intent is to provide support to decision makers. In this paper, we apply a model-agnostic method for interpreting machine learning predictions, known as SHapley Additive exPlanations (SHAP), to data farmed from an agent-based simulation that models a military operational scenario. The scenario is motivated by a Canadian Army initiative to modernize its intelligence, surveillance, and reconnaissance assets and abstracted to minimize the complexity of the modeled system and validate the findings of SHAP.
{"title":"Use of Shapley Additive Explanations in Interpreting Agent-Based Simulations of Military Operational Scenarios","authors":"Lynne Serré, Maude Amyot-Bourgeois, Brittany Astles","doi":"10.23919/ANNSIM52504.2021.9552151","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552151","url":null,"abstract":"Military defense modernization initiatives often involve complex systems that must be understood to inform design, planning, implementation and acquisition decisions. To gain a basic understanding of the system and identify key initial parameters, simulation experiments can be used to generate – or farm – data efficiently and effectively over a large parametric space. While machine learning models can be used for post-simulation analysis to identify key parameters, interpretability and their black-box nature can present challenges when the intent is to provide support to decision makers. In this paper, we apply a model-agnostic method for interpreting machine learning predictions, known as SHapley Additive exPlanations (SHAP), to data farmed from an agent-based simulation that models a military operational scenario. The scenario is motivated by a Canadian Army initiative to modernize its intelligence, surveillance, and reconnaissance assets and abstracted to minimize the complexity of the modeled system and validate the findings of SHAP.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"1 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83144123","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}
Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552106
Bernhard Schenkenfelder, Wolfgang Fenz, S. Thumfart, G. Ebenhofer, Gernot Stübl, D. Lumenta, G. Reishofer, J. Scharinger
MRI and associated contrast agent administration to visualize the vasculature prove valuable for planning surgical interventions and can reduce the operative time by helping to locate internal structures of interest for the operation. However, the visual representation of soft tissues deviates due to differences in body posture, in water and fat content, and in their gravitational displacement. In this paper, we present a novel approach for calculating deformations of abdominal fat tissue and vascular structures in MRI scans. The underlying elastic registration model is based on a current abdominal RGB-D scan as a surface-matching target. We demonstrate the pipeline on Dixon MRI and RGB-D scans acquired from ten patients with a diagnosis of breast cancer and a treatment plan including mastectomy. Results indicate that the proposed system enhances the surgeon's spatial perception of the abdominal vasculature and improves the accuracy of blood vessel locations shown in MRI scans.
{"title":"Elastic Registration of Abdominal MRI Scans and RGB-D Images to Improve Surgical Planning of Breast Reconstruction","authors":"Bernhard Schenkenfelder, Wolfgang Fenz, S. Thumfart, G. Ebenhofer, Gernot Stübl, D. Lumenta, G. Reishofer, J. Scharinger","doi":"10.23919/ANNSIM52504.2021.9552106","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552106","url":null,"abstract":"MRI and associated contrast agent administration to visualize the vasculature prove valuable for planning surgical interventions and can reduce the operative time by helping to locate internal structures of interest for the operation. However, the visual representation of soft tissues deviates due to differences in body posture, in water and fat content, and in their gravitational displacement. In this paper, we present a novel approach for calculating deformations of abdominal fat tissue and vascular structures in MRI scans. The underlying elastic registration model is based on a current abdominal RGB-D scan as a surface-matching target. We demonstrate the pipeline on Dixon MRI and RGB-D scans acquired from ten patients with a diagnosis of breast cancer and a treatment plan including mastectomy. Results indicate that the proposed system enhances the surgeon's spatial perception of the abdominal vasculature and improves the accuracy of blood vessel locations shown in MRI scans.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"36 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82187362","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}
Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552113
M. Sharifi, A. Abhari, S. Taghipour
This paper presents a model for fog computing by considering the processing nodes of both edge and cloud devices for real-time applications. We use mixed-integer linear programming (MILP) mathematical model to find the optimal task scheduling and compare it with the performance of the FIFO online scheduling strategies for a fog computing sample that consists of n edge processors (EP) and one cloud processor. The MILP mathematical dispatching strategy optimizes the jobs' scheduling on the EPs and cloud processors. Finally, solving the model and simulation of more scenarios is presented to compare the performance of the optimized job scheduling model with two FIFO scenarios for a real-time application on fog computing. The results show that the FIFO process scheduling strategy's performance is between 62.71% to 95.10% of the optimal jobs' scheduling proposed in this work for the real-time fog computing-based applications.
{"title":"Modeling Real-Time Application Processor Scheduling for Fog Computing","authors":"M. Sharifi, A. Abhari, S. Taghipour","doi":"10.23919/ANNSIM52504.2021.9552113","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552113","url":null,"abstract":"This paper presents a model for fog computing by considering the processing nodes of both edge and cloud devices for real-time applications. We use mixed-integer linear programming (MILP) mathematical model to find the optimal task scheduling and compare it with the performance of the FIFO online scheduling strategies for a fog computing sample that consists of n edge processors (EP) and one cloud processor. The MILP mathematical dispatching strategy optimizes the jobs' scheduling on the EPs and cloud processors. Finally, solving the model and simulation of more scenarios is presented to compare the performance of the optimized job scheduling model with two FIFO scenarios for a real-time application on fog computing. The results show that the FIFO process scheduling strategy's performance is between 62.71% to 95.10% of the optimal jobs' scheduling proposed in this work for the real-time fog computing-based applications.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"16 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88182093","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}
Pub Date : 2021-07-19DOI: 10.23919/ANNSIM52504.2021.9552172
Na Jiang, Hamdi Kavak, W. Kennedy, A. Crooks
Within agent-based models, agents interact with each other (e.g., social networks) and their environment, and it is through such interactions more aggregate patterns emerge (e.g., disease outbreaks, traffic jams). While the popularity of agent-based modeling has grown, one challenge remains, that of creating and sharing realistic synthetic populations which incorporate social networks. To overcome this challenge, this paper introduces a new approach that creates a reusable synthetic population using the New York Metro Area as a study area. Our method directly incorporates social networks (i.e., connections within a family or workplace) when creating a synthetic population. To demonstrate the utility and reusability of the synthetic population and to highlight the role of social networks, we show two example applications: traffic dynamics and the spread of a disease. These applications demonstrate how our synthetic population method can be easily utilized for different modeling problems.
{"title":"Generation of Reusable Synthetic Population and Social Networks for Agent-Based Modeling","authors":"Na Jiang, Hamdi Kavak, W. Kennedy, A. Crooks","doi":"10.23919/ANNSIM52504.2021.9552172","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552172","url":null,"abstract":"Within agent-based models, agents interact with each other (e.g., social networks) and their environment, and it is through such interactions more aggregate patterns emerge (e.g., disease outbreaks, traffic jams). While the popularity of agent-based modeling has grown, one challenge remains, that of creating and sharing realistic synthetic populations which incorporate social networks. To overcome this challenge, this paper introduces a new approach that creates a reusable synthetic population using the New York Metro Area as a study area. Our method directly incorporates social networks (i.e., connections within a family or workplace) when creating a synthetic population. To demonstrate the utility and reusability of the synthetic population and to highlight the role of social networks, we show two example applications: traffic dynamics and the spread of a disease. These applications demonstrate how our synthetic population method can be easily utilized for different modeling problems.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"11 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84643603","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}
Pub Date : 2021-07-14DOI: 10.23919/ANNSIM52504.2021.9552126
Luca Serena, Mirko Zichichi, Gabriele D’angelo, S. Ferretti
In distributed environments, such as distributed ledgers technologies and other peer-to-peer architectures, communication represents a crucial topic. The ability to efficiently disseminate contents is strongly influenced by the type of system architecture, the protocol used to spread such contents over the network and the actual dynamicity of the communication links (i.e. static vs. temporal nets). In particular, the dissemination strategies either focus on achieving an optimal coverage, minimizing the network traffic or providing assurances on anonymity (that is a fundamental requirement of many cryptocurrencies). In this work, the behaviour of multiple dissemination protocols is discussed and studied through simulation. The performance evaluation has been carried out on temporal networks with the help of LUNES-temporal, a discrete event simulator that allows to test algorithms running on a distributed environment. The experiments show that some gossip protocols allow to either save a considerable number of messages or to provide better anonymity guarantees, at the cost of a little lower coverage achieved and/or a little increase of the delivery time.
{"title":"Simulation of Dissemination Strategies on Temporal Networks","authors":"Luca Serena, Mirko Zichichi, Gabriele D’angelo, S. Ferretti","doi":"10.23919/ANNSIM52504.2021.9552126","DOIUrl":"https://doi.org/10.23919/ANNSIM52504.2021.9552126","url":null,"abstract":"In distributed environments, such as distributed ledgers technologies and other peer-to-peer architectures, communication represents a crucial topic. The ability to efficiently disseminate contents is strongly influenced by the type of system architecture, the protocol used to spread such contents over the network and the actual dynamicity of the communication links (i.e. static vs. temporal nets). In particular, the dissemination strategies either focus on achieving an optimal coverage, minimizing the network traffic or providing assurances on anonymity (that is a fundamental requirement of many cryptocurrencies). In this work, the behaviour of multiple dissemination protocols is discussed and studied through simulation. The performance evaluation has been carried out on temporal networks with the help of LUNES-temporal, a discrete event simulator that allows to test algorithms running on a distributed environment. The experiments show that some gossip protocols allow to either save a considerable number of messages or to provide better anonymity guarantees, at the cost of a little lower coverage achieved and/or a little increase of the delivery time.","PeriodicalId":6782,"journal":{"name":"2021 Annual Modeling and Simulation Conference (ANNSIM)","volume":"1 1","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2021-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89664573","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：