Pub Date : 2018-07-01DOI: 10.1109/ICUFN.2018.8436950
Hyunjun Han, Jusung Kang, M. A. Raza, Heung-no Lee
We introduce a deep learning based collision avoidance based on learning events accompanied by an online, semi-supervised learning algorithm that allows the learning agent to gain experiences and learn by itself without any preacquired training dataset through online trial-and-error approach. Using distance sequences as inputs, two procedures are performed in the proposed algorithm; data gathering procedure and learning procedure. Simulation results show that our system can achieve minimum of 99.86% up to 99.99% accuracy in classifying collision event from all possible events, allowing autonomous agent to navigate within simulated environments without collision.
{"title":"Learning Through Adverse Event for Collision Avoidance: A Self-Learning Approach","authors":"Hyunjun Han, Jusung Kang, M. A. Raza, Heung-no Lee","doi":"10.1109/ICUFN.2018.8436950","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436950","url":null,"abstract":"We introduce a deep learning based collision avoidance based on learning events accompanied by an online, semi-supervised learning algorithm that allows the learning agent to gain experiences and learn by itself without any preacquired training dataset through online trial-and-error approach. Using distance sequences as inputs, two procedures are performed in the proposed algorithm; data gathering procedure and learning procedure. Simulation results show that our system can achieve minimum of 99.86% up to 99.99% accuracy in classifying collision event from all possible events, allowing autonomous agent to navigate within simulated environments without collision.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122686215","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8436787
Sunghoon Lee, J. Heo
Information reconciliation is a critical process of any Quantum Key Distribution (QKD) protocol, where two legitimate parties agree on a secret key. Two parties attempt to eliminate the discrepancies between their correlated keys in the presence of an adversary, while revealing a minimum amount of information. In this paper, we propose a reconciliation protocol using polar codes with a soft-output decoder. We demonstrate that our method is better than a conventional protocol using polar codes in the view of reconciliation efficiency.
{"title":"Efficient Reconciliation Protocol with Polar Codes for Quantum Key Distribution","authors":"Sunghoon Lee, J. Heo","doi":"10.1109/ICUFN.2018.8436787","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436787","url":null,"abstract":"Information reconciliation is a critical process of any Quantum Key Distribution (QKD) protocol, where two legitimate parties agree on a secret key. Two parties attempt to eliminate the discrepancies between their correlated keys in the presence of an adversary, while revealing a minimum amount of information. In this paper, we propose a reconciliation protocol using polar codes with a soft-output decoder. We demonstrate that our method is better than a conventional protocol using polar codes in the view of reconciliation efficiency.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128316160","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8437006
A. Alshra’a, Parag Sewalkar, J. Seitz
In Software Defined Networking (SDN), link failure situations require switches to make optimized rerouting decisions locally i.e. without controller intervention. However, such optimized rerouting decisions must be made after the link failure situation has been confirmed. The mechanisms that confirm such link failure situations require a certain amount of processing time which may introduce a bottleneck in the performance. This paper proposes an enhanced approach that employs a mechanism to make the rerouting decision without the confirmation of link failure. The approach uses the OpenState Pipeline to manage the network in failure situations, and the experiment results show notable enhancements in packets loss rate and usage of Ternary Content Addressable Memory (TCAM).
{"title":"Enhanced Failure Recovery Mechanism Using OpenState Pipeline in SDN","authors":"A. Alshra’a, Parag Sewalkar, J. Seitz","doi":"10.1109/ICUFN.2018.8437006","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8437006","url":null,"abstract":"In Software Defined Networking (SDN), link failure situations require switches to make optimized rerouting decisions locally i.e. without controller intervention. However, such optimized rerouting decisions must be made after the link failure situation has been confirmed. The mechanisms that confirm such link failure situations require a certain amount of processing time which may introduce a bottleneck in the performance. This paper proposes an enhanced approach that employs a mechanism to make the rerouting decision without the confirmation of link failure. The approach uses the OpenState Pipeline to manage the network in failure situations, and the experiment results show notable enhancements in packets loss rate and usage of Ternary Content Addressable Memory (TCAM).","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128756339","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8436806
Young-Il Choi, N. Park
Networks beyond 2020 are required to support diverse use cases. Among the emerging services, support of delay critical mobile applications require network enhancements to natively offer low latency and high mobility. In this regard, the 5G network needs to be flexible for new service scenarios, and MEC can be supported to reduce the latency. In this paper, we present the feature of support for MEC in the 5G network and explain working mechanisms for application allocation, user plain selection, traffic local routing and steering.
{"title":"Support for Edge Computing in the 5G Network","authors":"Young-Il Choi, N. Park","doi":"10.1109/ICUFN.2018.8436806","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436806","url":null,"abstract":"Networks beyond 2020 are required to support diverse use cases. Among the emerging services, support of delay critical mobile applications require network enhancements to natively offer low latency and high mobility. In this regard, the 5G network needs to be flexible for new service scenarios, and MEC can be supported to reduce the latency. In this paper, we present the feature of support for MEC in the 5G network and explain working mechanisms for application allocation, user plain selection, traffic local routing and steering.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128610671","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8437027
Kyu-Min Lee, S. Han, Hyungbin Yun
Network models can be classified into two large groups: undirected and directed. Directed network graphs that can represent causal relationships are likely more appropriate in bio-medical data. There have been many studies to estimate DAGs(Directed Acyclic Graphs), of which the two-stage approach using lasso effectively. Find the edges between the nodes in the first step and find the direction in the second step. In this paper, we try to compare which penalized regression is better to find neighborhoods through simulations. We present the result of the simulations that shows which penalized regression is the best.
{"title":"A Comparison of Penalized Regressions for Estimating Directed Acyclic Networks","authors":"Kyu-Min Lee, S. Han, Hyungbin Yun","doi":"10.1109/ICUFN.2018.8437027","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8437027","url":null,"abstract":"Network models can be classified into two large groups: undirected and directed. Directed network graphs that can represent causal relationships are likely more appropriate in bio-medical data. There have been many studies to estimate DAGs(Directed Acyclic Graphs), of which the two-stage approach using lasso effectively. Find the edges between the nodes in the first step and find the direction in the second step. In this paper, we try to compare which penalized regression is better to find neighborhoods through simulations. We present the result of the simulations that shows which penalized regression is the best.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129002194","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8437011
Jianping Li, Man Hu, Zhiyuan Cheng
Polar code is widely accepted due to its excellent error correction performance, low complexity coding and decoding structure. However, the imperfect performance in the short code length of polar codes limits its further application. A significant way to improve the performance of short polar code is to choose fit subchannels for information bits accurately and effectively. After analyzing some construction algorithms for polar codes under Gaussian channel, comparing their complexity and their BER performance, this paper proposes an improved polarization weight (PW) algorithm, which can reduce the bit error rate.
{"title":"Research on Polar Code Construction Algorithms Under Gaussian Channel","authors":"Jianping Li, Man Hu, Zhiyuan Cheng","doi":"10.1109/ICUFN.2018.8437011","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8437011","url":null,"abstract":"Polar code is widely accepted due to its excellent error correction performance, low complexity coding and decoding structure. However, the imperfect performance in the short code length of polar codes limits its further application. A significant way to improve the performance of short polar code is to choose fit subchannels for information bits accurately and effectively. After analyzing some construction algorithms for polar codes under Gaussian channel, comparing their complexity and their BER performance, this paper proposes an improved polarization weight (PW) algorithm, which can reduce the bit error rate.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130316886","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8436968
Qinghua Wang, Xin Huang, D. Mengistu
Time synchronization is important for many network applications. This paper utilizes the fact that time service is a standard service in almost all kinds of computer networks, and proposes a new session key agreement protocol by building sessions keys based on the locally available time information. A prototype system has been tested in the simulation environment and the results are promising.
{"title":"Session Key Agreement for End-to-End Security in Time-Synchronized Networks","authors":"Qinghua Wang, Xin Huang, D. Mengistu","doi":"10.1109/ICUFN.2018.8436968","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436968","url":null,"abstract":"Time synchronization is important for many network applications. This paper utilizes the fact that time service is a standard service in almost all kinds of computer networks, and proposes a new session key agreement protocol by building sessions keys based on the locally available time information. A prototype system has been tested in the simulation environment and the results are promising.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123954943","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8437013
Batbayar Khandish, Eunsik Lee, Hyun Park, Jung-Bong Suk
The IEEE 802.15.4 protocol is designed to provide for connecting low data rate devices with low-power in wireless personal area network (LR-WPAN). In IEEE 802.15.4, a slotted carrier sensing multiple access with collision avoidance (CSMA/CA) algorithm is employed to coordinate a large number of sensor devices. Energy consumption requirements make it to use fewer number of backoffs, which adversely increases collisions, resulting in degradation of energy consumption. In this paper, we present a novel scheme to improve both network throughput and energy efficiency. We develop a Markov model for the proposed scheme with the provision of mathematical analysis, which is validated via experiments using ns- 2 simulator. It is shown that the proposed scheme significantly enhances the performance in respect of both network throughput and energy efficiency.
{"title":"An Efficient Backoff Scheme in Wireless Sensor Networks","authors":"Batbayar Khandish, Eunsik Lee, Hyun Park, Jung-Bong Suk","doi":"10.1109/ICUFN.2018.8437013","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8437013","url":null,"abstract":"The IEEE 802.15.4 protocol is designed to provide for connecting low data rate devices with low-power in wireless personal area network (LR-WPAN). In IEEE 802.15.4, a slotted carrier sensing multiple access with collision avoidance (CSMA/CA) algorithm is employed to coordinate a large number of sensor devices. Energy consumption requirements make it to use fewer number of backoffs, which adversely increases collisions, resulting in degradation of energy consumption. In this paper, we present a novel scheme to improve both network throughput and energy efficiency. We develop a Markov model for the proposed scheme with the provision of mathematical analysis, which is validated via experiments using ns- 2 simulator. It is shown that the proposed scheme significantly enhances the performance in respect of both network throughput and energy efficiency.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"246 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134505893","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8436754
Eunmi Chu, Hyuk Ju Jang, B. Jung
This paper proposes a machine learning (ML)-based exponential effective signal-to-noise ratio (SNR) mapping (EESM) method for simulating the system-level performance of cellular networks, which utilizes a deep neural network (DNN) regression algorithm. We first explain overall procedure of the link-to-system (L2S) mapping algorithm which has been used in commercial standardization organizations such as IEEE 802.16 and 3GPP LTE. Then, we apply the proposed ML-based EESM method to the existing L2S mapping procedure. The processing time of the L2S mapping becomes significantly reduced through the proposed method while the mean squared errors (MSE) between the actual block-error rate (BLER) from the link-level simulator and the estimated BLER from the L2S mapping technique is also decreased, compared with the conventional L2S mapping method.
{"title":"Machine Learning Based Link-to-System Mapping for System-Level Simulation of Cellular Networks","authors":"Eunmi Chu, Hyuk Ju Jang, B. Jung","doi":"10.1109/ICUFN.2018.8436754","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436754","url":null,"abstract":"This paper proposes a machine learning (ML)-based exponential effective signal-to-noise ratio (SNR) mapping (EESM) method for simulating the system-level performance of cellular networks, which utilizes a deep neural network (DNN) regression algorithm. We first explain overall procedure of the link-to-system (L2S) mapping algorithm which has been used in commercial standardization organizations such as IEEE 802.16 and 3GPP LTE. Then, we apply the proposed ML-based EESM method to the existing L2S mapping procedure. The processing time of the L2S mapping becomes significantly reduced through the proposed method while the mean squared errors (MSE) between the actual block-error rate (BLER) from the link-level simulator and the estimated BLER from the L2S mapping technique is also decreased, compared with the conventional L2S mapping method.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131466419","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 : 2018-07-01DOI: 10.1109/ICUFN.2018.8436811
Jaemin Yu, Byeong-Moon Cho, Kyung-Joon Park, Hwangnam Kim
Recently, drones are widely used in the commercial fields. Here, we explain how we can neutralize malicious drones and ground control systems (GCSs). The proposed method simultaneously attacks the drone and the GCS. We carry out simulation as well as experimental studies to validate the proposed attack.
{"title":"Simultaneous Attack on Drone and GCS in UAV Systems","authors":"Jaemin Yu, Byeong-Moon Cho, Kyung-Joon Park, Hwangnam Kim","doi":"10.1109/ICUFN.2018.8436811","DOIUrl":"https://doi.org/10.1109/ICUFN.2018.8436811","url":null,"abstract":"Recently, drones are widely used in the commercial fields. Here, we explain how we can neutralize malicious drones and ground control systems (GCSs). The proposed method simultaneously attacks the drone and the GCS. We carry out simulation as well as experimental studies to validate the proposed attack.","PeriodicalId":224367,"journal":{"name":"2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133415186","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：