2021 IEEE International Systems Conference (SysCon)最新文献_第8页

Transfer Learning on the Edge Networks 边缘网络上的迁移学习

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447110

Deepak Saggu, Akramul Azim

{"title":"Transfer Learning on the Edge Networks","authors":"Deepak Saggu, Akramul Azim","doi":"10.1109/SysCon48628.2021.9447110","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447110","url":null,"abstract":"Transfer learning focuses on using extensive labeled data samples in the source domain to resolve a different yet related task for the target domain, even when there is no similarity among the training and testing problem’s datasets and distribution of features. This paper will discourse the implementation of the transfer learning model on edge networks to improve the performance factors and communication delay times within different servers. Any extensive system working with embedded systems is considered a high-performance system. An embedded system aims to perform some specific tasks based on the microprocessors, works on low resources and have less power consumption. An embedded system has a functional mapping, and various environment states to generate significant results. For the edge networks, the description of tasks and the dynamics of outer environment is crucial. For further clarification, we developed the transfer learning model. We experimented it on the embedded system using edge device (edge networks) and the local system to compare the time latency of the transfer learning model’s execution. As a result, we concluded that the transfer learning model works effectively and gives us decent accuracy. Implementing a transfer learning model on edge networks is better than implementing on a local system in terms of cost, performance and efficiency.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115943738","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}

引用次数: 0

System Design of the Rifleman of the Future 未来步枪手的系统设计

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447053

Vikram Mittal, S. Herbert, Gene Lesinski, James R. Enos

{"title":"System Design of the Rifleman of the Future","authors":"Vikram Mittal, S. Herbert, Gene Lesinski, James R. Enos","doi":"10.1109/SysCon48628.2021.9447053","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447053","url":null,"abstract":"The rifleman will play a crucial role in future conflicts, so it is imperative that the Army outfits them with the right equipment. However, there is a tendency to provide them with every new technology as it becomes available. This results in a situation where the rifleman is overloaded with technology, only some of which is relevant to the mission. This effect can be resolved by treating the rifleman as a system, comprised of a soldier that is integrated with equipment, focused on performing a mission. This study uses model-based systems engineering to design the rifleman of the future, looking out to 2050. This analysis initially develops a functional model of the current rifleman, identifying the functions and subfunctions that they perform. They must be able to shoot, move, communicate, survive, and sustain. These functions are then allocated against the current equipment set including rifles, body-armor, and radios. The functional model is then updated to reflect the future mission set of the rifleman. The updated functional model is aligned against the current equipment set to identify gaps and needs. New technologies are then allocated against these gaps and needs. The goal of this analysis is to divest from science fiction and focus on what the future rifleman will need to win on the battlefield.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130259386","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}

引用次数: 0

Infusion Complexity: Understanding the Need to Measure Infusion Success of Advanced Technologies into Complex Systems 输液复杂性:了解需要衡量输注成功的先进技术到复杂的系统

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447120

Cinda Chullen, Roshi Rose Nilchiani

{"title":"Infusion Complexity: Understanding the Need to Measure Infusion Success of Advanced Technologies into Complex Systems","authors":"Cinda Chullen, Roshi Rose Nilchiani","doi":"10.1109/SysCon48628.2021.9447120","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447120","url":null,"abstract":"When a technology is deemed ready to be infused into a legacy or parent system, the infusion process becomes complicated and it is difficult to measure the success of that infusion. This paper concentrates on that infusion and introduces the concept of “infusion complexity.” The complexity at the interface of a new technology’s infusion into a legacy system can contribute to the success and smooth the transition of it into an integrated system. In contrast, it can create unforeseen emergent behavior and challenges in the infusion problem. Therefore, it is critical to gain deep knowledge and assess the complexity of the two complex systems’ infusion to help reveal their success or lack thereof. Because minimal written research exists involving technology infusion into complex systems, a more thorough study is needed. A literature survey was performed and sets the landscape for what has currently been accomplished. The topics researched include technology readiness and assessment, integration and system readiness, technology infusion in complex systems, engineering change, and associated research. Overall, this paper communicates the need to understand and measure the success of infusing a new or advanced technology into a complex system. This research could help project managers and system mangers integrate new technologies more effectively and efficiently.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114343792","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}

引用次数: 0

Multi Base Stations to Multi Mobile Units: Green Communication Systems via A Wavefront Multiplexing Technique 多基站到多移动单元:基于波前复用技术的绿色通信系统

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/syscon48628.2021.9695301

H. Yeh, D. Chang

{"title":"Multi Base Stations to Multi Mobile Units: Green Communication Systems via A Wavefront Multiplexing Technique","authors":"H. Yeh, D. Chang","doi":"10.1109/syscon48628.2021.9695301","DOIUrl":"https://doi.org/10.1109/syscon48628.2021.9695301","url":null,"abstract":"A green communication scheme using anorthogonal wavefront (WF) multiplexing scheme spatially combined with orthogonal frequency-division multiplexing (OFDM) techniques is proposed. It forms a spatial WF OFDM transceiver. The WF multiplexing technique serves as the preprocessing and postprocessing method of the WF OFDM transceiver. With coordinated multiple point forward transmission, this spatial WF OFDM system establishes a communication network. It can be applied to multiple base stations (BSs) with down links to a single or multiple mobile units (MUs). Although signals received are non-coherently due to different distances between BSs and MUs, they can be compensated and coherently combined via adaptive equalizers at MUs. This is achieved by using pilot signals with an optimization method at the receiver of MUs. Simulation results demonstrate that the WF OFDM scheme obtains the same bit error rate (BER) as predicted by theory in an additive white Gaussian noise (AWGN) channel. Moreover, the required effective equivalent isotropically radiated power (EIRP) from BSs to the MUs is significantly reduced due to multiple non-coherent transmission. Accordingly, the interference to adjacent frequency bands’ signals will be low. This green communication network is achieved via the combination of WF multiplexing, OFDM, and optimization at the receiver together. More investigations are needed to show that this WF OFDM transceiver can be applied to frequency selective mobile fading channels.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126468080","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}

引用次数: 0

K-Shell Decomposition of AS Level Multigraphs AS级多图的k壳分解

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447067

A. Nur

{"title":"K-Shell Decomposition of AS Level Multigraphs","authors":"A. Nur","doi":"10.1109/SysCon48628.2021.9447067","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447067","url":null,"abstract":"The Internet is one of the immense human-engineered systems and understanding of the topology can be helpful for network engineers and researchers. Categorization of Autonomous Systems (ASes) plays an essential role in understanding the structure and evolution of the Internet. However, the traditional categorization exhibits variation in different studies, contains ambiguity, involves subjectiveness, and sometimes does not match the reality. A better approach to classify ASes is defining the AS level topology maps as graphs and taking advantage of the graph properties through k-shell decomposition. However, the proposed solutions neither capture the parallel connections nor incorporate the varying business relations among the ASes. Abstracting ASes without any internal structure is an oversimplification since the ASes in the Internet span over various geographic regions and often cover the same regions in part or whole. In this work, we introduce k-shell decomposition on AS level multigraphs and comparison with AS level graphs. The decomposition is based on pruning the graphs according to the nodes’ connectivity pattern to generate a layered structure of the Internet. In our experiments, we analyze the structure of the shells and the connectivity structure of the Internet. Additionally, we compare top-20 ASes to understand the central core of the Internet. Our comparative results help us to understand the structure of the Internet better.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126524313","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}

引用次数: 0

A Model-Driven Framework for Security Labs using Blockchain Methodology 使用区块链方法的安全实验室模型驱动框架

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447125

Moneeb Abbas, M. Rashid, F. Azam, Yawar Rasheed, Muhammad Waseem Anwar, Maryum Humdani

{"title":"A Model-Driven Framework for Security Labs using Blockchain Methodology","authors":"Moneeb Abbas, M. Rashid, F. Azam, Yawar Rasheed, Muhammad Waseem Anwar, Maryum Humdani","doi":"10.1109/SysCon48628.2021.9447125","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447125","url":null,"abstract":"Blockchain technology is the need of an hour for ensuring security and data privacy. However, very limited tools and documentation are available, therefore, the traditional code-centric implementation of Blockchain is challenging for programmers and developers due to inherent complexities. To overcome these challenges, in this article, a novel and efficient framework is proposed that is based on the Model-Driven Architecture. Particularly, a Meta-model (M2 level Ecore Model) is defined that contains the concepts of Blockchain technology. As a part of tool support, a tree editor (developed using Eclipse Modeling Framework) and a Sirius based graphical modeling tool with a drag-drop palette have been provided to allow modeling and visualization of simple and complex Blockchain-based scenarios for security labs in a very user-friendly manner. A Model to Text (M2T) transformation code has also been written using Acceleo language that transforms the modeled scenarios into java code for Blockchain application in the security lab. The validity of the proposed framework has been demonstrated via a case study. The results prove that our framework can be reliably used and further extended for automation and development of Blockchain-based application for security labs with simplicity.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132598693","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}

引用次数: 1

Design Strategies for Integrating Artificial Intelligence into Systems Engineering Environment 人工智能与系统工程环境集成的设计策略

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447069

Leandro Batista, B. Monsuez

引用次数: 0

Efficient Traffic Classification Using Hybrid Deep Learning 基于混合深度学习的高效流量分类

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447072

Farnaz Sarhangian, R. Kashef, M. Jaseemuddin

{"title":"Efficient Traffic Classification Using Hybrid Deep Learning","authors":"Farnaz Sarhangian, R. Kashef, M. Jaseemuddin","doi":"10.1109/SysCon48628.2021.9447072","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447072","url":null,"abstract":"Network traffic classification provides an essential contribution in network administration functions and network management such as QoS, security, and billing. Those functions need a timely and accurate detection of specific traffics. Current network traffic classification methods offer supervised and unsupervised learning capabilities for network traffic prediction or classification. Classical machine learning classifiers that use a single classification model suffer from low prediction and classification accuracy, especially for high dimensional datasets with a high sparsity level. These challenges in individual-based learning models have created a need for hybrid learning. Recently, hybriddeep learning has shown a significant role in traffic forecasting and classification due to its efficiency. However, a tradeoff between the aggregate models and the classification accuracy presents a substantial challenge in network traffic classification problems. In this paper, we have suggested two hybrid models that combine the Convolutional Neural Network (CNN) along with the Recurrent Neural Network (RNN) models, inclusive of the Gated recurrent unit (GRU) and Long Short-Term Memory (LSTM), to improve traffic classification accuracy. The efficiency of the suggested models has been evaluated by comparing them with various individual-based models using real network traffic traces. The hybrid CNN-LSTM and CNN-GRU have achieved an accuracy of up to 99.23% and 93.92%, respectively, for binary classification and 67.16% for multiclass classification.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129077296","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}

引用次数: 7

Using AHP to Choose Optimal Nuclear Power Plant Design 用层次分析法选择核电站最优设计

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447095

L. Kiser, L. D. Otero

{"title":"Using AHP to Choose Optimal Nuclear Power Plant Design","authors":"L. Kiser, L. D. Otero","doi":"10.1109/SysCon48628.2021.9447095","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447095","url":null,"abstract":"Emerging technologies in nuclear power plant (NPP) design offer decision makers the chance to explore innovative options in the nuclear power industry. Because there are more options available when it comes to NPP design selection than in past decades, having a tool to compare NPP parameters to decision maker priorities could prove useful in business strategy. The operational and safety features of Small Modular Reactors and Molten Salt Reactors address decision criteria differently than the common and traditional Light Water Reactors (LWR). This paper uses the Analytic Hierarchy Process (AHP) to explore and compare the financial, operational, and risk attributes of three nuclear power plant designs and presents a decision-making tool for choosing the optimal design. A pairwise comparison of defined criteria to establish priorities and criteria weights was based on a literature review effort and domain experience with the goals of reducing cost, optimizing plant characteristics, and minimizing risk. Results from the AHP model show the LWR design as optimal. LWRs are the most common type of NPP in operation and expected to have the most favorable public opinion, proven safety features, and lowest licensing costs. Overall, the AHP model presented in this paper reflects some challenges that the emerging NPP designs and technologies must overcome before fully breaking into the mainstream nuclear power industry.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115771444","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}

引用次数: 2

Offensive Cyber Security Trainer for Platform Management Systems 平台管理系统进攻性网络安全培训师

2021 IEEE International Systems Conference (SysCon) Pub Date : 2021-04-15 DOI: 10.1109/SysCon48628.2021.9447060

J. Timmins, S. Knight, Brian Lachine

{"title":"Offensive Cyber Security Trainer for Platform Management Systems","authors":"J. Timmins, S. Knight, Brian Lachine","doi":"10.1109/SysCon48628.2021.9447060","DOIUrl":"https://doi.org/10.1109/SysCon48628.2021.9447060","url":null,"abstract":"To protect its platforms against cyber attacks, the Royal Canadian Navy (RCN) must train specialists in platform cyber security. These specialists will need to understand the offensive capabilities of their adversaries in order to defend these platforms and to develop more secure systems. As a result, these specialists will require an environment which can facilitate training in offensive cyber security techniques. Currently, no cyber security trainer exists for the RCN’s Platform Management Systems (PMS), nor does one exist for any of the RCN’s other platform systems.The aim of this research is to develop a PMS environment based on effective training techniques and capable of training RCN personnel in offensive cyber techniques. Effective training techniques in this context will reflect best practices from pedagogical literature. The training environment in this case is an offensive cyber security trainer which facilitates the training of personnel to execute cyber kill chains mapped from real attacker tactics, techniques, and procedures. Training cyber defenders to perform these kill chains will provide them with a greater understanding of how attacks can be executed against RCN platform systems. This in turn will enable the RCN to better defend against such kill chains.In order to accomplish this aim, an offensive cyber security trainer for a PMS is developed which utilizes a combination of simulation, emulation, and virtualization to provide an effective level of control and flexibility while also maintaining a high level of realism. This training also specifically leverages a Capture the Flag (CTF) framework to enhance personnel engagement within the environment. The functionality of this trainer is demonstrated by its ability to facilitate the training program and the execution of multiple kill chains against the PMS. The effectiveness of the trainer is validated on its application of current research methodology in effective gamified training environment design.","PeriodicalId":384949,"journal":{"name":"2021 IEEE International Systems Conference (SysCon)","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116206309","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}

引用次数: 0