Pub Date : 2019-10-01DOI: 10.1109/WiSEE.2019.8920353
Abigail J. Kragt Finnell, P. Schubert
Space-to-earth Wireless Power Transfer (WPT) in large scale will not be allowed unless the side lobe levels (SLL) can be reduced many orders of magnitude lower than the current technology allows. In particular, high SLL could potentially interfere with aircraft communications around the beam, while the area inside the beam would necessarily be a no-fly zone, similar as over nuclear power plants. To overcome this, the transmitting antenna must be cleverly designed and controlled. In this work, independent validation of the layout, spacing, and envelope arrangement of a design first proposed in 2016 is performed and presented. This design involves a hexagonal design with a triangular antenna element arrangement and a spacing of 0.8 wavelengths using the Dolph-Chebychev beam profile. While this has been shown to produce −240 dB SLL in the AWR Design Environment already, it will now be analyzed using the MATLAB Phased Array System Toolbox. The design will also be investigated on a smaller scale, with the potential for use in other applications, including the powering of low orbit weather balloons or unmanned aerial vehicles (UAVs). The possibility of very low SLL would be transformational in these and other WPT applications, including space solar power, and could greatly benefit humanity and the environment.
{"title":"Antenna Arrangement Verification for Low Sidelobe Levels","authors":"Abigail J. Kragt Finnell, P. Schubert","doi":"10.1109/WiSEE.2019.8920353","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920353","url":null,"abstract":"Space-to-earth Wireless Power Transfer (WPT) in large scale will not be allowed unless the side lobe levels (SLL) can be reduced many orders of magnitude lower than the current technology allows. In particular, high SLL could potentially interfere with aircraft communications around the beam, while the area inside the beam would necessarily be a no-fly zone, similar as over nuclear power plants. To overcome this, the transmitting antenna must be cleverly designed and controlled. In this work, independent validation of the layout, spacing, and envelope arrangement of a design first proposed in 2016 is performed and presented. This design involves a hexagonal design with a triangular antenna element arrangement and a spacing of 0.8 wavelengths using the Dolph-Chebychev beam profile. While this has been shown to produce −240 dB SLL in the AWR Design Environment already, it will now be analyzed using the MATLAB Phased Array System Toolbox. The design will also be investigated on a smaller scale, with the potential for use in other applications, including the powering of low orbit weather balloons or unmanned aerial vehicles (UAVs). The possibility of very low SLL would be transformational in these and other WPT applications, including space solar power, and could greatly benefit humanity and the environment.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121482957","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920366
Esmail M M Abuhduma, G. Comert, Ahmed Elqaouaq, A. Reeves, W. Kellen
This research focuses on studying the scattering phenomenon. Scattering electromagnetic waves from a rotating conducting cylinder is investigated when the material of the conducting cylinder is linear, homogeneous, isotropic, and dispersive. This study is an extension of a previous work that investigated the effect of the rotating very good conducting cylinder on the scattered phase and amplitude, when the material of the very good conducting cylinder is linear, homogeneous, isotropic, and nondispersive. One of the important result of the previous work is that the Franklin transformation is a proper and more accurate method to calculate the effect of the rotation, and gives more accurate results than Galilean transformation. In this research, the Franklin transformation will be used to investigate the effect of the rotation of the very good conducting object on the scattered phase and magnitude of the incident waves. The two types of incident waves (E-wave and H-wave) will be considered herein. The simulation results will clearly display the behavior of the scattered phase and magnitude with changes to the incident frequency, the speed of rotation, and the radius of the very good conducting cylinder. Moreover, this result is compared with the result of the previous work (non-dispersive material) to show the behavior of the scattered phase and magnitude when the incident frequency, speed of the rotation and radius of the very good conducting cylinder is changed.
{"title":"Scattering of EM waves from a Rotating Dispersive Very Good Conducting Cylinder","authors":"Esmail M M Abuhduma, G. Comert, Ahmed Elqaouaq, A. Reeves, W. Kellen","doi":"10.1109/WiSEE.2019.8920366","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920366","url":null,"abstract":"This research focuses on studying the scattering phenomenon. Scattering electromagnetic waves from a rotating conducting cylinder is investigated when the material of the conducting cylinder is linear, homogeneous, isotropic, and dispersive. This study is an extension of a previous work that investigated the effect of the rotating very good conducting cylinder on the scattered phase and amplitude, when the material of the very good conducting cylinder is linear, homogeneous, isotropic, and nondispersive. One of the important result of the previous work is that the Franklin transformation is a proper and more accurate method to calculate the effect of the rotation, and gives more accurate results than Galilean transformation. In this research, the Franklin transformation will be used to investigate the effect of the rotation of the very good conducting object on the scattered phase and magnitude of the incident waves. The two types of incident waves (E-wave and H-wave) will be considered herein. The simulation results will clearly display the behavior of the scattered phase and magnitude with changes to the incident frequency, the speed of rotation, and the radius of the very good conducting cylinder. Moreover, this result is compared with the result of the previous work (non-dispersive material) to show the behavior of the scattered phase and magnitude when the incident frequency, speed of the rotation and radius of the very good conducting cylinder is changed.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134000830","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920352
Carlos R. Mejias-Morillo, A. Gbaguidi, Daewon Kim, S. Namilae, E. Rojas-Nastrucci
During the last decade, the use of wireless sensor networks (WSN) has grown up exponentially for many applications because of the improvements in deployment processes and ability to sense the events in real-time. The combination of the WSN features with the direct print additive manufacturing process (DPAM), which uses fused deposition modeling (FDM) and microdispensing, enables the fabrication of complex structure with flexible features. By integrating an RFID IC sensor tag and an antenna, a low-cost passive wireless node is shown in this work. In this sense, the design, manufacturing, and testing of a 3D-printed UHF RFID passive wireless sensor that can be used to detect impacts from micrometeoroid and orbital debris are presented. The designed antenna was fabricated using Kapton wrapping and the DPAM process to achieve an antenna gain of 3.92 dBi at 915 MHz, which is dependent on the size and conductivity of the ground plane. The resistance sensing range of the passive wireless node is up 2 MΩ with a range of 1.9 m. The sensor is tested using a micrometeoroid and orbital debris impact sensing element. The manufacturing process and design presented in this work enable future in-space wireless sensor fabrication to support human space exploration.
{"title":"UHF RFID-based Additively Manufactured Passive Wireless Sensor for Detecting Micrometeoroid and Orbital Debris Impacts","authors":"Carlos R. Mejias-Morillo, A. Gbaguidi, Daewon Kim, S. Namilae, E. Rojas-Nastrucci","doi":"10.1109/WiSEE.2019.8920352","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920352","url":null,"abstract":"During the last decade, the use of wireless sensor networks (WSN) has grown up exponentially for many applications because of the improvements in deployment processes and ability to sense the events in real-time. The combination of the WSN features with the direct print additive manufacturing process (DPAM), which uses fused deposition modeling (FDM) and microdispensing, enables the fabrication of complex structure with flexible features. By integrating an RFID IC sensor tag and an antenna, a low-cost passive wireless node is shown in this work. In this sense, the design, manufacturing, and testing of a 3D-printed UHF RFID passive wireless sensor that can be used to detect impacts from micrometeoroid and orbital debris are presented. The designed antenna was fabricated using Kapton wrapping and the DPAM process to achieve an antenna gain of 3.92 dBi at 915 MHz, which is dependent on the size and conductivity of the ground plane. The resistance sensing range of the passive wireless node is up 2 MΩ with a range of 1.9 m. The sensor is tested using a micrometeoroid and orbital debris impact sensing element. The manufacturing process and design presented in this work enable future in-space wireless sensor fabrication to support human space exploration.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114153170","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 : 2019-10-01DOI: 10.1109/wisee.2019.8920289
{"title":"WiSEE 2019 Author List","authors":"","doi":"10.1109/wisee.2019.8920289","DOIUrl":"https://doi.org/10.1109/wisee.2019.8920289","url":null,"abstract":"","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"309 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116117710","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 : 2019-10-01DOI: 10.1109/wisee.2019.8920324
{"title":"WiSEE 2019 Cover Page","authors":"","doi":"10.1109/wisee.2019.8920324","DOIUrl":"https://doi.org/10.1109/wisee.2019.8920324","url":null,"abstract":"","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129039622","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920328
J. Budroweit, M. Jaksch
In this paper, the in-situ testing and characterization of an highly integrated radio frequency (RF) agile transceiver in an radiation environment is presented. The device under test (DUT) is exposed by γ-rays to evaluate the total ionizing dose effects. The advance in-situ test setup allows detailed analysis of the DUT’s RF performance. The test procedures and methods are described and particular test results are shown. The DUT has been irradiated to a total ionizing dose of ~190krad and has not shown any conspicuous degradation effects or malfunctions.
{"title":"In-Situ TID Testing and Characterization of a Highly Integrated RF Agile Transceiver for Multi-Band Radio Applications in a Radiation Environment","authors":"J. Budroweit, M. Jaksch","doi":"10.1109/WiSEE.2019.8920328","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920328","url":null,"abstract":"In this paper, the in-situ testing and characterization of an highly integrated radio frequency (RF) agile transceiver in an radiation environment is presented. The device under test (DUT) is exposed by γ-rays to evaluate the total ionizing dose effects. The advance in-situ test setup allows detailed analysis of the DUT’s RF performance. The test procedures and methods are described and particular test results are shown. The DUT has been irradiated to a total ionizing dose of ~190krad and has not shown any conspicuous degradation effects or malfunctions.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"705 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116120725","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920310
Thomas A. V. Sattolo, Saumil Macwan, Michael J. Vezina, A. Matrawy
Software-Defined Networking (SDN) provides significant flexibility when it comes to complex network management. This makes this technology an ideal candidate for dealing with network management issues in satellite and terrestrial networks.One key innovation of SDN is the separation of the control plane from the data plane. This results in a new network element: the controller. Given the importance of the role of the logically centralised (physically distributed) controller, it becomes an important point to protect in the new SDN paradigm. It could be vulnerable to attacks that are common in traditional networks such as Distributed Denial of Service (DDoS). In this paper, we address a type of attack that could threaten the operation of SDN-based environments: poisoning attacks.To perform its function, the logically centralised controller must have an accurate view of the network state. The accuracy of this view is crucial to the operation of the network. This view is obtained by exchanging information among controllers and between controllers and network elements. Such information flow could be vulnerable to different types of poisoning attacks. The motivation for writing this paper is that (1) poisoning attacks on SDN networks could have great impact, (2) most of them are relatively recent and (3) the differences between such attacks could be subtle. Therefore, we address the issues by classifying poisoning attacks in SDN. We classify both attacks and defences. For attacks we make a distinction between direct poisoning attacks and attacks that are designed to evade a specific defence.
{"title":"Classifying Poisoning Attacks in Software Defined Networking","authors":"Thomas A. V. Sattolo, Saumil Macwan, Michael J. Vezina, A. Matrawy","doi":"10.1109/WiSEE.2019.8920310","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920310","url":null,"abstract":"Software-Defined Networking (SDN) provides significant flexibility when it comes to complex network management. This makes this technology an ideal candidate for dealing with network management issues in satellite and terrestrial networks.One key innovation of SDN is the separation of the control plane from the data plane. This results in a new network element: the controller. Given the importance of the role of the logically centralised (physically distributed) controller, it becomes an important point to protect in the new SDN paradigm. It could be vulnerable to attacks that are common in traditional networks such as Distributed Denial of Service (DDoS). In this paper, we address a type of attack that could threaten the operation of SDN-based environments: poisoning attacks.To perform its function, the logically centralised controller must have an accurate view of the network state. The accuracy of this view is crucial to the operation of the network. This view is obtained by exchanging information among controllers and between controllers and network elements. Such information flow could be vulnerable to different types of poisoning attacks. The motivation for writing this paper is that (1) poisoning attacks on SDN networks could have great impact, (2) most of them are relatively recent and (3) the differences between such attacks could be subtle. Therefore, we address the issues by classifying poisoning attacks in SDN. We classify both attacks and defences. For attacks we make a distinction between direct poisoning attacks and attacks that are designed to evade a specific defence.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130268530","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920311
N. H. Ranchagoda, S. Kandeepan, Ming Ding, A. Al-Hourani, K. Gomez
Air-to-Ground (A2G) wireless communications using Unmanned Aerial Vehicles (UAVs) as Low Altitude Platforms (LAPs) have become a hot topic in recent decades. Among all the A2G channel models that can be used for A2G channel characterization, the two-ray ground reflection path loss model can be used for environments with fewer scatterers such as over water, suburban and mountainous. In such environments, signal down-fades appear due to the destructive combination of the direct component and the ground reflected component. This paper presents a frequency diversity approach to improve the coverage in such an environment. Our results show that frequency diversity can improve coverage at least by 17% when two frequencies are used assuming the threshold to be −80 dBm. Moreover, this work analyses the coverage improvement that can be obtained through polarization diversity. Our results show that having both horizontal and vertical polarizations can improve the coverage by 10%–95%, assuming the transmission frequency to be 700MHz and UAV altitude is between 100 m–300 m.
{"title":"Diversity Based Coverage Improvement for Air-to-Ground Wireless Channels","authors":"N. H. Ranchagoda, S. Kandeepan, Ming Ding, A. Al-Hourani, K. Gomez","doi":"10.1109/WiSEE.2019.8920311","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920311","url":null,"abstract":"Air-to-Ground (A2G) wireless communications using Unmanned Aerial Vehicles (UAVs) as Low Altitude Platforms (LAPs) have become a hot topic in recent decades. Among all the A2G channel models that can be used for A2G channel characterization, the two-ray ground reflection path loss model can be used for environments with fewer scatterers such as over water, suburban and mountainous. In such environments, signal down-fades appear due to the destructive combination of the direct component and the ground reflected component. This paper presents a frequency diversity approach to improve the coverage in such an environment. Our results show that frequency diversity can improve coverage at least by 17% when two frequencies are used assuming the threshold to be −80 dBm. Moreover, this work analyses the coverage improvement that can be obtained through polarization diversity. Our results show that having both horizontal and vertical polarizations can improve the coverage by 10%–95%, assuming the transmission frequency to be 700MHz and UAV altitude is between 100 m–300 m.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129601465","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920388
Kedjar Khaled, L. Talbi
Many propagation channel models are emerging to study the behavior of the signal in specific environments for future 5G cellular networks. However, the vertiginous growth and popularization of indoor wireless systems require a suitable design before its implementation and the propagation channel models won’t be enough. In this paper, we will discuss the first part of implementation of a suitable technique to improve the coverage and high channel capacity in complex indoor environments, where maximum of coverage and high data rate will be claimed. These implementations are to detect the weak spots within the environments and improve the accuracy of propagation channel modeling in any complex indoor environments.
{"title":"Case study of radio coverage in complex indoor environments for 5G communications","authors":"Kedjar Khaled, L. Talbi","doi":"10.1109/WiSEE.2019.8920388","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920388","url":null,"abstract":"Many propagation channel models are emerging to study the behavior of the signal in specific environments for future 5G cellular networks. However, the vertiginous growth and popularization of indoor wireless systems require a suitable design before its implementation and the propagation channel models won’t be enough. In this paper, we will discuss the first part of implementation of a suitable technique to improve the coverage and high channel capacity in complex indoor environments, where maximum of coverage and high data rate will be claimed. These implementations are to detect the weak spots within the environments and improve the accuracy of propagation channel modeling in any complex indoor environments.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124388663","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 : 2019-10-01DOI: 10.1109/WiSEE.2019.8920301
A. Mammeri, Yiheng Zhao, A. Boukerche, Abdul Jabbar Siddiqui, B. Pekilis
Among state-of-the-art vehicle maneuver classification algorithms, Hidden Markov Models are commonly applied for predicting maneuver probability. To generate a model, a sufficient number of labeled samples is necessary for training. However, annotations that contain information such as class and bounding box are not always available. Manually labeling data is tedious, inaccurate, and time consuming, especially when the dataset is extremely large. Besides, there exists lots of redundant data that negatively influences model training. In this paper, we explore the possibility of using only a few manually labeled samples to train a Convolutional Neural Network (CNN) model for vehicle maneuver classification with relatively high accuracy. We define three maneuver classification groups: motion, velocity, and turning. Each group has subclasses, reflecting different aspects of the vehicle movement. Based on the defined maneuver classes, we design a simple CNN model to distinguish vehicle maneuvers. We also propose a learning strategy that requires only a few samples for training, while maintaining high recognition precision. Comprehensive experiments were performed to demonstrate the capability of our model and performance of our training strategy. In result, our model achieves an overall of 93.48% precision for maneuver recognition with only 3.5% Controller Area Network (CAN) bus data for training.
{"title":"Design of a Semi-Supervised Learning Strategy based on Convolutional Neural Network for Vehicle Maneuver Classification","authors":"A. Mammeri, Yiheng Zhao, A. Boukerche, Abdul Jabbar Siddiqui, B. Pekilis","doi":"10.1109/WiSEE.2019.8920301","DOIUrl":"https://doi.org/10.1109/WiSEE.2019.8920301","url":null,"abstract":"Among state-of-the-art vehicle maneuver classification algorithms, Hidden Markov Models are commonly applied for predicting maneuver probability. To generate a model, a sufficient number of labeled samples is necessary for training. However, annotations that contain information such as class and bounding box are not always available. Manually labeling data is tedious, inaccurate, and time consuming, especially when the dataset is extremely large. Besides, there exists lots of redundant data that negatively influences model training. In this paper, we explore the possibility of using only a few manually labeled samples to train a Convolutional Neural Network (CNN) model for vehicle maneuver classification with relatively high accuracy. We define three maneuver classification groups: motion, velocity, and turning. Each group has subclasses, reflecting different aspects of the vehicle movement. Based on the defined maneuver classes, we design a simple CNN model to distinguish vehicle maneuvers. We also propose a learning strategy that requires only a few samples for training, while maintaining high recognition precision. Comprehensive experiments were performed to demonstrate the capability of our model and performance of our training strategy. In result, our model achieves an overall of 93.48% precision for maneuver recognition with only 3.5% Controller Area Network (CAN) bus data for training.","PeriodicalId":167663,"journal":{"name":"2019 IEEE International Conference on Wireless for Space and Extreme Environments (WiSEE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117071826","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：