Pub Date : 2020-11-16DOI: 10.1109/LCN48667.2020.9314813
S. Saadatmand, S. Kanhere
Mobile Crowdsensing (MCS) systems take advantage of the ubiquity and sensing power of smartphones in data gathering. Reverse auction is a popular incentive mechanism framework for MCS wherein, the participants can determine their expected rewards for their contributions. In this paper, for the first time, we consider a multi-task location-dependent reverse auction based MCS setting wherein, each task requires a specific amount of contribution to be fulfilled, participants may need to move to the task locations in order to participate in them, and the goal is to assign each participant to at most one task in a way such that the cumulative contribution of the fulfilled tasks are maximised while not exceeding a limited budget. We show that this is an NP-hard optimization problem and propose Ant Colony Optimisation-based Multi-Task Assignment (ACOMTA) as an approximation algorithm for it. We uncover an issue with the basic instantiation of ACO and propose an approach called Valid Random Path Generator (VRPG) to avoid lack of or premature convergence of the algorithm. Through extensive experiments, we show that the proposed algorithm outperforms a greedy approach as well as a random-based solution.
{"title":"ACOMTA: An Ant Colony Optimisation based Multi-Task Assignment Algorithm for Reverse Auction based Mobile Crowdsensing","authors":"S. Saadatmand, S. Kanhere","doi":"10.1109/LCN48667.2020.9314813","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314813","url":null,"abstract":"Mobile Crowdsensing (MCS) systems take advantage of the ubiquity and sensing power of smartphones in data gathering. Reverse auction is a popular incentive mechanism framework for MCS wherein, the participants can determine their expected rewards for their contributions. In this paper, for the first time, we consider a multi-task location-dependent reverse auction based MCS setting wherein, each task requires a specific amount of contribution to be fulfilled, participants may need to move to the task locations in order to participate in them, and the goal is to assign each participant to at most one task in a way such that the cumulative contribution of the fulfilled tasks are maximised while not exceeding a limited budget. We show that this is an NP-hard optimization problem and propose Ant Colony Optimisation-based Multi-Task Assignment (ACOMTA) as an approximation algorithm for it. We uncover an issue with the basic instantiation of ACO and propose an approach called Valid Random Path Generator (VRPG) to avoid lack of or premature convergence of the algorithm. Through extensive experiments, we show that the proposed algorithm outperforms a greedy approach as well as a random-based solution.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124889108","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314772
Inaam Ilahi, M. Usama, M. Farooq, M. Janjua, Junaid Qadir
The performance of densely-deployed low-power wide-area networks (LPWANs) can significantly deteriorate due to packets collisions, and one of the main reasons for that is the rule-based PHY layer transmission parameters assignment algorithms. LoRaWAN is a leading LPWAN technology where LoRa serves as the physical layer. Here, we propose and evaluate a deep reinforcement learning (DRL)-based PHY layer transmission parameter assignment algorithm for LoRaWAN. Our algorithm ensures fewer collisions and better network performance compared to the existing state-of-the-art PHY layer transmission parameter assignment algorithms for LoRaWAN. Our algorithm outperforms the state of the art learning-based technique achieving up to 500% improvement of PDR in some cases.
{"title":"LoRaDRL: Deep Reinforcement Learning Based Adaptive PHY Layer Transmission Parameters Selection for LoRaWAN","authors":"Inaam Ilahi, M. Usama, M. Farooq, M. Janjua, Junaid Qadir","doi":"10.1109/LCN48667.2020.9314772","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314772","url":null,"abstract":"The performance of densely-deployed low-power wide-area networks (LPWANs) can significantly deteriorate due to packets collisions, and one of the main reasons for that is the rule-based PHY layer transmission parameters assignment algorithms. LoRaWAN is a leading LPWAN technology where LoRa serves as the physical layer. Here, we propose and evaluate a deep reinforcement learning (DRL)-based PHY layer transmission parameter assignment algorithm for LoRaWAN. Our algorithm ensures fewer collisions and better network performance compared to the existing state-of-the-art PHY layer transmission parameter assignment algorithms for LoRaWAN. Our algorithm outperforms the state of the art learning-based technique achieving up to 500% improvement of PDR in some cases.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125167907","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314770
Yuchen Liu, D. Blough
Millimeter-wave wireless LANs are targeted for use with bandwidth-intensive applications such as virtual/augmented reality and real-time high-definition video. To maintain high throughput while addressing mmWave signal blockages, multiple access points (APs) within one room to improve line-of-sight conditions is considered a promising approach. In a scenario with fixed and mobile (human) obstacles, we mathematically analyze LoS blockages produced by mobility, and use the analysis to develop a multi-AP association scheme. Our scheme statically assigns primary and backup APs in order to maximize blockage robustness and perform load balancing among APs. Simulation results show that: 1) our static approach can provide blockage tolerance close to that of an expensive dynamic probing approach while achieving higher throughput, 2) the use of client mobility patterns, if known, can improve our static approach even further, and 3) our approach achieves significantly better fairness and load balancing than existing approaches.
{"title":"Blockage Robustness in Access Point Association for mmWave Wireless LANs with Mobility","authors":"Yuchen Liu, D. Blough","doi":"10.1109/LCN48667.2020.9314770","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314770","url":null,"abstract":"Millimeter-wave wireless LANs are targeted for use with bandwidth-intensive applications such as virtual/augmented reality and real-time high-definition video. To maintain high throughput while addressing mmWave signal blockages, multiple access points (APs) within one room to improve line-of-sight conditions is considered a promising approach. In a scenario with fixed and mobile (human) obstacles, we mathematically analyze LoS blockages produced by mobility, and use the analysis to develop a multi-AP association scheme. Our scheme statically assigns primary and backup APs in order to maximize blockage robustness and perform load balancing among APs. Simulation results show that: 1) our static approach can provide blockage tolerance close to that of an expensive dynamic probing approach while achieving higher throughput, 2) the use of client mobility patterns, if known, can improve our static approach even further, and 3) our approach achieves significantly better fairness and load balancing than existing approaches.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122598306","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314823
Flavio Cirillo, Bin Cheng, Raffaele Porcellana, Marco Russo, Gürkan Solmaz, Hisashi Sakamoto, S. Romano
Data usage control is of utmost importance for federated data analytics across multiple business domains. However, the existing data usage control approaches are limited due to their complexity and inefficiency. This paper proposes an intent-oriented data usage control system for federated data analytics, called IntentKeeper. The system allows users to specify intents for data usage policies and services easily. Thus, it reduces the data sharing complexity for data providers and consumers. Moreover, IntentKeeper enforces preventive and proactive data usage control for better security and efficiency through joint decisions based on policy enforcement and service orchestration. The use case validations for the automotive industry scenario show that IntentKeeper significantly reduces the complexity of policy specification (up to 75% for moderately complex scenarios) compared to the state-of-the-art flow-based approach. Lastly, the experimental results show that the IntentKeeper system provides sufficiently short response times (less than 40ms) with minimal overhead (less than 10ms).
{"title":"IntentKeeper: Intent-oriented Data Usage Control for Federated Data Analytics","authors":"Flavio Cirillo, Bin Cheng, Raffaele Porcellana, Marco Russo, Gürkan Solmaz, Hisashi Sakamoto, S. Romano","doi":"10.1109/LCN48667.2020.9314823","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314823","url":null,"abstract":"Data usage control is of utmost importance for federated data analytics across multiple business domains. However, the existing data usage control approaches are limited due to their complexity and inefficiency. This paper proposes an intent-oriented data usage control system for federated data analytics, called IntentKeeper. The system allows users to specify intents for data usage policies and services easily. Thus, it reduces the data sharing complexity for data providers and consumers. Moreover, IntentKeeper enforces preventive and proactive data usage control for better security and efficiency through joint decisions based on policy enforcement and service orchestration. The use case validations for the automotive industry scenario show that IntentKeeper significantly reduces the complexity of policy specification (up to 75% for moderately complex scenarios) compared to the state-of-the-art flow-based approach. Lastly, the experimental results show that the IntentKeeper system provides sufficiently short response times (less than 40ms) with minimal overhead (less than 10ms).","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115036993","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314777
Mohamed Hamnache, Rahim Kacimi, A. Beylot
LoRaWAN Enabled networks are expected to have a dizzying growth. Thus, an efficient allocation of wireless resources so as to support a large number of nodes is a major concern. In this paper we propose an SF assignment approach paying attention on the traffic load both per Spreading Factor and over the channels. Indeed, our strategy consists in finding a better distribution of the nodes on the SF by orchestrating an effective load balancing. Moreover, the performance of our solution is evaluated under diverse network configurations taking into account the capture effect and the non-orthogonality of SFs. In addition, we validated some assumptions by full-scale experiments like for the 3GPP path loss model which is used for the first time in LoRa simulations. Our results suggest that Load Shifting leads to better performance in terms of DER (Date Extraction Rate) while guaranteeing good scalability on the network size and density.
{"title":"L3SFA: Load Shifting Strategy for Spreading Factor Allocation in LoRaWAN Systems","authors":"Mohamed Hamnache, Rahim Kacimi, A. Beylot","doi":"10.1109/LCN48667.2020.9314777","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314777","url":null,"abstract":"LoRaWAN Enabled networks are expected to have a dizzying growth. Thus, an efficient allocation of wireless resources so as to support a large number of nodes is a major concern. In this paper we propose an SF assignment approach paying attention on the traffic load both per Spreading Factor and over the channels. Indeed, our strategy consists in finding a better distribution of the nodes on the SF by orchestrating an effective load balancing. Moreover, the performance of our solution is evaluated under diverse network configurations taking into account the capture effect and the non-orthogonality of SFs. In addition, we validated some assumptions by full-scale experiments like for the 3GPP path loss model which is used for the first time in LoRa simulations. Our results suggest that Load Shifting leads to better performance in terms of DER (Date Extraction Rate) while guaranteeing good scalability on the network size and density.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114684804","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314794
Imran Makhdoom, F. Tofigh, Ian Zhou, M. Abolhasan, J. Lipman
The existing lottery-based consensus algorithms, such as Proof-of-Work, and Proof-of-Stake, are mostly used for blockchain-based financial technology applications. Similarly, the Byzantine Fault Tolerance algorithms do provide consensus finality, yet they are either communications intensive, vulnerable to Denial-of-Service attacks, poorly scalable, or have a low faulty node tolerance level. Moreover, these algorithms are not designed for the Internet of Things systems that require near-real-time transaction confirmation, maximum fault tolerance, and appropriate transaction validation rules. Hence, we propose "Pledge," a unique Proof-of-Honesty based consensus protocol to reduce the possibility of malicious behavior during blockchain consensus. Pledge also introduces the Internet of Things centric transaction validation rules. Initial experimentation shows that Pledge is economical and secure with low communications complexity and low latency in transaction confirmation.
{"title":"PLEDGE: An IoT-oriented Proof-of-Honesty based Blockchain Consensus Protocol","authors":"Imran Makhdoom, F. Tofigh, Ian Zhou, M. Abolhasan, J. Lipman","doi":"10.1109/LCN48667.2020.9314794","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314794","url":null,"abstract":"The existing lottery-based consensus algorithms, such as Proof-of-Work, and Proof-of-Stake, are mostly used for blockchain-based financial technology applications. Similarly, the Byzantine Fault Tolerance algorithms do provide consensus finality, yet they are either communications intensive, vulnerable to Denial-of-Service attacks, poorly scalable, or have a low faulty node tolerance level. Moreover, these algorithms are not designed for the Internet of Things systems that require near-real-time transaction confirmation, maximum fault tolerance, and appropriate transaction validation rules. Hence, we propose \"Pledge,\" a unique Proof-of-Honesty based consensus protocol to reduce the possibility of malicious behavior during blockchain consensus. Pledge also introduces the Internet of Things centric transaction validation rules. Initial experimentation shows that Pledge is economical and secure with low communications complexity and low latency in transaction confirmation.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114747565","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314833
P. Willis, N. Shenoy, Yin Pan, John F. Hamilton
Switched networks require loop-avoidance protocols to avoid looping of broadcast and multicast Loop-avoidance protocols use a tree algorithm to construct a logical tree from one root such as rapid spanning tree protocol (RSTP). RSTP results in high convergence latency and heavily impaired network performance on root switch failures. Some protocols construct a logical tree from every switch resulting in high operational overhead. We propose the Meshed Tree Protocol (MTP) to designate the number of roots based on desired network uptime and computational overhead, where a meshed tree conceptually maintains multiple tree branches from a root. MTP based on multi meshed tree algorithm (MMTA), constructs and maintains multiple meshed trees from multiple designated roots. We compare a prototype of MTP based on MMTA against RSTP using switched networks in the Global Environment for Network Innovation (GENI) testbed. MTP's root failure recovery response is several magnitudes superior to RSTP.
交换网络需要避免环路的协议来避免广播和组播的环路。避免环路协议使用树算法从一个根开始构造一个逻辑树，如快速生成树协议RSTP (rapid spanning tree protocol)。当根交换机发生故障时，RSTP会导致较高的收敛延迟，严重影响网络性能。一些协议从每个交换机构建逻辑树，导致高操作开销。我们提出了网状树协议(MTP)，根据期望的网络正常运行时间和计算开销来指定根的数量，其中网状树在概念上从根维护多个分支。MTP基于多网格树算法(MMTA)，从多个指定根构建和维护多个网格树。我们在全球网络创新环境(GENI)测试平台上比较了基于MMTA的MTP原型和使用交换网络的RSTP。MTP的根故障恢复响应比RSTP好几个数量级。
{"title":"Root Redundancy in Meshed Tree Bridged Networks","authors":"P. Willis, N. Shenoy, Yin Pan, John F. Hamilton","doi":"10.1109/LCN48667.2020.9314833","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314833","url":null,"abstract":"Switched networks require loop-avoidance protocols to avoid looping of broadcast and multicast Loop-avoidance protocols use a tree algorithm to construct a logical tree from one root such as rapid spanning tree protocol (RSTP). RSTP results in high convergence latency and heavily impaired network performance on root switch failures. Some protocols construct a logical tree from every switch resulting in high operational overhead. We propose the Meshed Tree Protocol (MTP) to designate the number of roots based on desired network uptime and computational overhead, where a meshed tree conceptually maintains multiple tree branches from a root. MTP based on multi meshed tree algorithm (MMTA), constructs and maintains multiple meshed trees from multiple designated roots. We compare a prototype of MTP based on MMTA against RSTP using switched networks in the Global Environment for Network Innovation (GENI) testbed. MTP's root failure recovery response is several magnitudes superior to RSTP.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129339065","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314809
Martin Langer, Kai Heine, D. Sibold, R. Bermbach
The PTPv2.1 standard provides new protection mechanisms to ensure the authenticity and integrity of PTP messages. However, the distribution of the necessary security parameters is not part of the specification. This paper proposes a simple and practical approach for the automated distribution of these parameters by using a key management system that enables the Immediate Security Processing in PTP. It is based on the Network Time Security protocol and offers functions for group management, parameter updating and monitoring mechanisms. A Proof-of-Concept implementation provides initial results of the resources required for the key management system and its use.
{"title":"A Network Time Security Based Automatic Key Management for PTPv2.1","authors":"Martin Langer, Kai Heine, D. Sibold, R. Bermbach","doi":"10.1109/LCN48667.2020.9314809","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314809","url":null,"abstract":"The PTPv2.1 standard provides new protection mechanisms to ensure the authenticity and integrity of PTP messages. However, the distribution of the necessary security parameters is not part of the specification. This paper proposes a simple and practical approach for the automated distribution of these parameters by using a key management system that enables the Immediate Security Processing in PTP. It is based on the Network Time Security protocol and offers functions for group management, parameter updating and monitoring mechanisms. A Proof-of-Concept implementation provides initial results of the resources required for the key management system and its use.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"365 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125825035","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314835
Minglu Yan, Jiankun Wang, Z. Zhao
In Wi-Fi fingerprinting indoor localization, since signals of Wi-Fi APs vary over time, to retain high localization accuracy, the fingerprint database has to be updated periodically, which is labor-intensive and time-consuming. In this paper, we consider how to detect Wi-Fi fingerprint alteration accurately on line so as to update fingerprint database efficiently. To this end, we propose a deep learning model, AReAE (Alteration Reducing AutoEncoder), to reconstruct fingerprints from altered ones by learning alteration distribution. Based on AReAE, we further develop a FADet (Fingerprint Alteration Detection) system, which constructs a fingerprint ASmap (Alteration Strength map) with crowd-sourced Wi-Fi RSS (Received Signal Strength) measurements. The ASmap indicates how strong fingerprints change anywhere in the area of interest. FADet is verified through extensive experiments in real-world indoor scenarios. Results show that FADet yields accurate ASmaps for all scenarios tested, which can facilitate fingerprint database updating in time.
{"title":"Online Detection of Wi-Fi Fingerprint Alteration Strength via Deep Learning","authors":"Minglu Yan, Jiankun Wang, Z. Zhao","doi":"10.1109/LCN48667.2020.9314835","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314835","url":null,"abstract":"In Wi-Fi fingerprinting indoor localization, since signals of Wi-Fi APs vary over time, to retain high localization accuracy, the fingerprint database has to be updated periodically, which is labor-intensive and time-consuming. In this paper, we consider how to detect Wi-Fi fingerprint alteration accurately on line so as to update fingerprint database efficiently. To this end, we propose a deep learning model, AReAE (Alteration Reducing AutoEncoder), to reconstruct fingerprints from altered ones by learning alteration distribution. Based on AReAE, we further develop a FADet (Fingerprint Alteration Detection) system, which constructs a fingerprint ASmap (Alteration Strength map) with crowd-sourced Wi-Fi RSS (Received Signal Strength) measurements. The ASmap indicates how strong fingerprints change anywhere in the area of interest. FADet is verified through extensive experiments in real-world indoor scenarios. Results show that FADet yields accurate ASmaps for all scenarios tested, which can facilitate fingerprint database updating in time.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128959978","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：