Pub Date : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130487
Konrad Kluwak, Teodor Niżyński
Gait analysis based on observational methods is commonly used in everyday clinical practice. It is largely subjective and has a variety of limitations. In this publication we describe application of Recurrent Neural Networks (RNN) type Long Short-Term Memory (LSTM) for classification between healthy gait and gait with disease entity. This classification is based on person single step, beginning and ending with right foot strike on ground. The classification was carried out on reference motion database from Human Motion Laboratory (HML) of the Polish-Japanese Academy of Information Technology (PJAIT) containing a large set of samples. LSTM network checked in publication is a part of motion tagging system based on the EXTag concept.
{"title":"Gait Classification using LSTM Networks for Tagging System","authors":"Konrad Kluwak, Teodor Niżyński","doi":"10.1109/SoSE50414.2020.9130487","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130487","url":null,"abstract":"Gait analysis based on observational methods is commonly used in everyday clinical practice. It is largely subjective and has a variety of limitations. In this publication we describe application of Recurrent Neural Networks (RNN) type Long Short-Term Memory (LSTM) for classification between healthy gait and gait with disease entity. This classification is based on person single step, beginning and ending with right foot strike on ground. The classification was carried out on reference motion database from Human Motion Laboratory (HML) of the Polish-Japanese Academy of Information Technology (PJAIT) containing a large set of samples. LSTM network checked in publication is a part of motion tagging system based on the EXTag concept.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126255334","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130495
Qiancheng Jin, Jichao Li, Jiang Jiang, Kewei Yang
Technological importance assessment is a fundamental problem in the field of technological innovation management research. Assessing the importance of weapon technology can help to identify the innovative and disruptive technologies, and is of considerable significance to the future development and planning of weapon technology. From the perspective of system-of-systems and the complex network theory, this paper puts forward a unified frame to evaluate the technical importance based on a technology system-of-systems network model. First of all, considering the complicated correlation between weapon technologies, the weapon technology system-of-systems is modeled as a complex network by abstracting the technical entities as nodes and the relationships between technologies as edges. Next, three classical node centrality indexes of the complex network are introduced, and the TOPSIS method is utilized to synthesize the advantages of the three indexes to measure the node importance. Finally, a case of the unmanned combat technology system-of-systems is studied to demonstrate the feasibility and effectiveness of our proposed method. The results show that our proposed method achieves excellent performance in evaluating the importance of the technical nodes, which provides useful insight into the management and development of technological innovation for the relevant decision-making departments.
{"title":"Research on Assessment of Technical Importance Based on Weapon Technology System-of-Systems Network Model","authors":"Qiancheng Jin, Jichao Li, Jiang Jiang, Kewei Yang","doi":"10.1109/SoSE50414.2020.9130495","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130495","url":null,"abstract":"Technological importance assessment is a fundamental problem in the field of technological innovation management research. Assessing the importance of weapon technology can help to identify the innovative and disruptive technologies, and is of considerable significance to the future development and planning of weapon technology. From the perspective of system-of-systems and the complex network theory, this paper puts forward a unified frame to evaluate the technical importance based on a technology system-of-systems network model. First of all, considering the complicated correlation between weapon technologies, the weapon technology system-of-systems is modeled as a complex network by abstracting the technical entities as nodes and the relationships between technologies as edges. Next, three classical node centrality indexes of the complex network are introduced, and the TOPSIS method is utilized to synthesize the advantages of the three indexes to measure the node importance. Finally, a case of the unmanned combat technology system-of-systems is studied to demonstrate the feasibility and effectiveness of our proposed method. The results show that our proposed method achieves excellent performance in evaluating the importance of the technical nodes, which provides useful insight into the management and development of technological innovation for the relevant decision-making departments.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122241059","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130511
Conor Wallace, Sean Ackels, P. Benavidez, M. Jamshidi
As the demand for mobile autonomous systems increases across various industries, fault diagnostic systems will need to become more intelligent and robust. In this paper we propose a distributed Long Short-Term Memory (LSTM)- based ensemble learning architecture for learning highly nonlinear, temporal fault classification boundaries for an Unmanned Ground Vehicle (UGV). The main goal of the architecture is to reduce classification bias by ensembling LSTM models as well as achieving near-real time processing time. This is done by parallelizing the deep learning models on Amazon Web Services (AWS) cloud instances via Apache Kafka, a real-time data pipelining infrastructure. An experiment is conducted on a UGV subjected to dislocated suspension faults and results showing the effectiveness of the approach are shown.
{"title":"Real-Time Distributed Ensemble Learning for Fault Detection of an Unmanned Ground Vehicle","authors":"Conor Wallace, Sean Ackels, P. Benavidez, M. Jamshidi","doi":"10.1109/SoSE50414.2020.9130511","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130511","url":null,"abstract":"As the demand for mobile autonomous systems increases across various industries, fault diagnostic systems will need to become more intelligent and robust. In this paper we propose a distributed Long Short-Term Memory (LSTM)- based ensemble learning architecture for learning highly nonlinear, temporal fault classification boundaries for an Unmanned Ground Vehicle (UGV). The main goal of the architecture is to reduce classification bias by ensembling LSTM models as well as achieving near-real time processing time. This is done by parallelizing the deep learning models on Amazon Web Services (AWS) cloud instances via Apache Kafka, a real-time data pipelining infrastructure. An experiment is conducted on a UGV subjected to dislocated suspension faults and results showing the effectiveness of the approach are shown.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116159762","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130534
J. Buisson, M. JeanLevraiMbeck, Nicolas Belloir
Since the beginning of the twenty-first century, headquarters and C2 systems of systems have largely evolved in occidental armies, enacting larger distances on the battlefield and increased heterogeneity of units. This evolution combines two related aspects that concern system of systems (SoS) engineering: organizational changes and digitalization. The use of robots and drones, as well as forthcoming next-generation weapon systems will lead to step up this evolution. In this paper, we adopt the model-based engineering perspective to review this foreseeable evolution, in order to identify open challenges.
{"title":"Digitalization in Next Generation C2: Research Agenda from Model-Based Engineering Perspective","authors":"J. Buisson, M. JeanLevraiMbeck, Nicolas Belloir","doi":"10.1109/SoSE50414.2020.9130534","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130534","url":null,"abstract":"Since the beginning of the twenty-first century, headquarters and C2 systems of systems have largely evolved in occidental armies, enacting larger distances on the battlefield and increased heterogeneity of units. This evolution combines two related aspects that concern system of systems (SoS) engineering: organizational changes and digitalization. The use of robots and drones, as well as forthcoming next-generation weapon systems will lead to step up this evolution. In this paper, we adopt the model-based engineering perspective to review this foreseeable evolution, in order to identify open challenges.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115261999","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130559
K. Tehrani, Mathieu Weber, I. Rasoanarivo
This paper presents a high voltage pulse generator using SiC-Mosfets switches. This generator has to provide a pulse burst for high frequency applications (>100KHZ) with an amplitude greater than or equal to 1KV. This design is developed by two back to back converters. First part of this prototype is based on a threelevel boost converter and second part is based on a three-level buck converter. This protype can be used in different industrial applications such as: medical treatment or physical and chemical fields. In this paper, first, we present the structure of this design then we validate this a proposed topology with simulation and experimental results.
{"title":"Design Of High Voltage Pulse Generator With Back To Back Multilevel Boost Buck Converters Using Sic-Mosfet Switches","authors":"K. Tehrani, Mathieu Weber, I. Rasoanarivo","doi":"10.1109/SoSE50414.2020.9130559","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130559","url":null,"abstract":"This paper presents a high voltage pulse generator using SiC-Mosfets switches. This generator has to provide a pulse burst for high frequency applications (>100KHZ) with an amplitude greater than or equal to 1KV. This design is developed by two back to back converters. First part of this prototype is based on a threelevel boost converter and second part is based on a three-level buck converter. This protype can be used in different industrial applications such as: medical treatment or physical and chemical fields. In this paper, first, we present the structure of this design then we validate this a proposed topology with simulation and experimental results.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127732413","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130510
Aurelijus Morkevicius, J. Bankauskaite, Nerijus Jankevicius
The ongoing transformation in the industry from a document-based systems engineering to a model-based systems engineering approach reveals a need for new methods of capturing and analyzing knowledge about the system. Moreover, complex real-life problems require the application of MBSE practices to enable evolving systems to communicate independently to achieve a common goal. This is the level of system of systems. At this level similar standardized model- based approaches are used to capture knowledge; however, most analysis is far from being standards based. Most of the tools provide proprietary approaches to analyze a system of systems. Is there a way to apply a standards-based approach to execute engineering analysis and behavioral simulation on a system of systems model? This paper describes the research used to answer this question.
{"title":"Towards Standards-based Execution of System of Systems Models","authors":"Aurelijus Morkevicius, J. Bankauskaite, Nerijus Jankevicius","doi":"10.1109/SoSE50414.2020.9130510","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130510","url":null,"abstract":"The ongoing transformation in the industry from a document-based systems engineering to a model-based systems engineering approach reveals a need for new methods of capturing and analyzing knowledge about the system. Moreover, complex real-life problems require the application of MBSE practices to enable evolving systems to communicate independently to achieve a common goal. This is the level of system of systems. At this level similar standardized model- based approaches are used to capture knowledge; however, most analysis is far from being standards based. Most of the tools provide proprietary approaches to analyze a system of systems. Is there a way to apply a standards-based approach to execute engineering analysis and behavioral simulation on a system of systems model? This paper describes the research used to answer this question.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133827167","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130465
Charaf Eddine Dridi, Zakaria Benzadri, F. Belala
Systems-of-Systems (SoS) have emerged as a special type of large-scale complex systems and have been widely used in various fields. An SoS is a result of the integration of a number of pre-existing, independent complex software systems called Constituent Systems (CS). During the SoS Engineering process, the specific characteristics of CSs such as the operational and managerial independence, distribution and the emergent behaviour make the modelling of their structure, relationships and interactions a complex task.On the other hand, Model-Driven-Architecture (MDA) is still one of the most promising software architecture approaches, it provides a method which simplifies SoSs complexity by increasing their abstraction level. The aim of this study is to introduce a software description meta-model that can be used for modelling SoSs. The meta-model highlights the importance of Goals, Roles, Capabilities and CSs concepts for SoS design. These concepts will be translated into an abstract architecture where their composition and relationships are well-defined. The main contributions of this paper are: (1) a Meta-Model for System-of-systems called MeMSoS, (2) its supporting tool and (3) an illustrative case study of an Aircraft-Emergency-Response-SoS (AERSoS).
{"title":"System of Systems Engineering: Meta-Modelling Perspective","authors":"Charaf Eddine Dridi, Zakaria Benzadri, F. Belala","doi":"10.1109/SoSE50414.2020.9130465","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130465","url":null,"abstract":"Systems-of-Systems (SoS) have emerged as a special type of large-scale complex systems and have been widely used in various fields. An SoS is a result of the integration of a number of pre-existing, independent complex software systems called Constituent Systems (CS). During the SoS Engineering process, the specific characteristics of CSs such as the operational and managerial independence, distribution and the emergent behaviour make the modelling of their structure, relationships and interactions a complex task.On the other hand, Model-Driven-Architecture (MDA) is still one of the most promising software architecture approaches, it provides a method which simplifies SoSs complexity by increasing their abstraction level. The aim of this study is to introduce a software description meta-model that can be used for modelling SoSs. The meta-model highlights the importance of Goals, Roles, Capabilities and CSs concepts for SoS design. These concepts will be translated into an abstract architecture where their composition and relationships are well-defined. The main contributions of this paper are: (1) a Meta-Model for System-of-systems called MeMSoS, (2) its supporting tool and (3) an illustrative case study of an Aircraft-Emergency-Response-SoS (AERSoS).","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115892959","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}
As manufacturing and service operations have been increasingly becoming complicated, planning and scheduling which directly relate to manufacturing cost, production quality, level of services are becoming more challenging and promising. To date, a variety of planning and scheduling methods have been developed to support decision making in planning and scheduling. In most manufacturing and service operations, however, planning and scheduling are still heavily relying on high-skilled planners. According to our experiences, the reason is that, real planning and scheduling problems are partly fuzzy and dynamically changing, which make them impossible to be concretely defined by mathematical models and to be solved by conventional methods. To automating planning and scheduling, in our opinion, effectively taking advantage of high-skilled planners’ know-hows plays an important role. To this end, we develop a framework, MLCP, which integrates machine learning and optimization for real planning and scheduling problems. Since the machine learning module and optimization module in the framework are independently operable but working cooperatively, MLCP can be an useful tool for constructing large-scaled system of systems with complex planning and scheduling tasks. Through a case study, we show that, implicit know-hows of high-skilled planners such as preference for schedules can be extracted from historical schedules and imported into new schedules by employing the framework.
{"title":"MLCP: A Framework Integrating with Machine Learning and Optimization for Planning and Scheduling in Manufacturing and Services","authors":"Jian Zheng, Yuichi Kobayashi, Yoshiyasu Takahashi, Takashi Yanagida, Tatsuhiro Sato, Daiji Hitaka","doi":"10.1109/SoSE50414.2020.9130560","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130560","url":null,"abstract":"As manufacturing and service operations have been increasingly becoming complicated, planning and scheduling which directly relate to manufacturing cost, production quality, level of services are becoming more challenging and promising. To date, a variety of planning and scheduling methods have been developed to support decision making in planning and scheduling. In most manufacturing and service operations, however, planning and scheduling are still heavily relying on high-skilled planners. According to our experiences, the reason is that, real planning and scheduling problems are partly fuzzy and dynamically changing, which make them impossible to be concretely defined by mathematical models and to be solved by conventional methods. To automating planning and scheduling, in our opinion, effectively taking advantage of high-skilled planners’ know-hows plays an important role. To this end, we develop a framework, MLCP, which integrates machine learning and optimization for real planning and scheduling problems. Since the machine learning module and optimization module in the framework are independently operable but working cooperatively, MLCP can be an useful tool for constructing large-scaled system of systems with complex planning and scheduling tasks. Through a case study, we show that, implicit know-hows of high-skilled planners such as preference for schedules can be extracted from historical schedules and imported into new schedules by employing the framework.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129823906","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 : 2020-06-01DOI: 10.1109/SoSE50414.2020.9130545
Á. Varga, G. Eigner, J. Tar
Contemporarily, numerous software packages are available to simulate the performance and reliability of new control methods and algorithms in research and development state. However, it is still advantageous to test these methods on real physical hardware to prove their real practical usability. During the several passed years, different versions of low cost aero-dynamical test beds was built at Óbuda University for this purpose and also for engineering education. In this paper, the details of latest improved version is presented, mainly concentrating on the assumptions and validation measurements concerning the test bed system model. Besides that, computed torque control (CTC) method was implemented and tested on the improved test bed for position regulation. The performance of CTC algorithm is also presented and evaluated in case of different experimental scenarios.
{"title":"Model Based Computed Torque Control for an Experimental Test Bed","authors":"Á. Varga, G. Eigner, J. Tar","doi":"10.1109/SoSE50414.2020.9130545","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130545","url":null,"abstract":"Contemporarily, numerous software packages are available to simulate the performance and reliability of new control methods and algorithms in research and development state. However, it is still advantageous to test these methods on real physical hardware to prove their real practical usability. During the several passed years, different versions of low cost aero-dynamical test beds was built at Óbuda University for this purpose and also for engineering education. In this paper, the details of latest improved version is presented, mainly concentrating on the assumptions and validation measurements concerning the test bed system model. Besides that, computed torque control (CTC) method was implemented and tested on the improved test bed for position regulation. The performance of CTC algorithm is also presented and evaluated in case of different experimental scenarios.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116040974","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}
Technical infrastructure such as bridges and tunnels are critical in economic activities, but in recent years, aging of them has progressed, and demand for checking the soundness of them is expanding. There are several technologies to inspect the aging process of the structures to find cracks on a wall or flacking inside of concrete. Among the technologies to diagnose a structure, the hammering test is a traditional, easy, simple, and effective method. We developed an AI hammering checker by using the k-mean method. However, accuracy is not good in some tasks. So, we started to develop the new version of the AI hammering checker by using deep learning. We explain the outline of the new system in this paper. As a result, the accuracy was increased up to 93.9%.
{"title":"A Study on Hammering Test using Deep Learning","authors":"Tsubasa Fukumura, Hayato Aratame, Atsushi Ito, Masafumi Koike, Katsuhiko Hibino, Yoshihisa Kawamura","doi":"10.1109/SoSE50414.2020.9130517","DOIUrl":"https://doi.org/10.1109/SoSE50414.2020.9130517","url":null,"abstract":"Technical infrastructure such as bridges and tunnels are critical in economic activities, but in recent years, aging of them has progressed, and demand for checking the soundness of them is expanding. There are several technologies to inspect the aging process of the structures to find cracks on a wall or flacking inside of concrete. Among the technologies to diagnose a structure, the hammering test is a traditional, easy, simple, and effective method. We developed an AI hammering checker by using the k-mean method. However, accuracy is not good in some tasks. So, we started to develop the new version of the AI hammering checker by using deep learning. We explain the outline of the new system in this paper. As a result, the accuracy was increased up to 93.9%.","PeriodicalId":121664,"journal":{"name":"2020 IEEE 15th International Conference of System of Systems Engineering (SoSE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122275131","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：