H. Nguyen, Marinos Vomvas, Triet Vo Huu, G. Noubir
{"title":"Wideband, Real-time Spectro-Temporal RF Identification","authors":"H. Nguyen, Marinos Vomvas, Triet Vo Huu, G. Noubir","doi":"10.1145/3479241.3486688","DOIUrl":"https://doi.org/10.1145/3479241.3486688","url":null,"abstract":"RF emissions' detection, classification, and spectro-temporal localization are crucial not only for tasks relating to understanding, managing, and protecting the RF spectrum, but also for safety and security applications such as detecting intruding drones or jammers. Achieving this goal for wideband spectrum and in real-time is a challenging problem. Existing methods are limited to a small bandwidth, and lack the capability to detect and classify multiple RF emissions in every part of a wide spectrum with a unified detection and classification solution. We present WRIST, a Wideband, Real-time RF Identification system with Spectro-Temporal detection,framework and system. Our resulting deep learning (DL) model is capable to detect, classify, and precisely locate RF emissions in time and frequency using RF samples of 100 MHz spectrum in real-time(over 6Gbps incoming I&Q streams). Such capabilities are made feasible by leveraging a deep learning-based one-stage object detection framework, and transfer learning to a multi-channel visual-based RF signals representation. We also introduce an iterative training approach which leverages synthesized and augmented RF data to efficiently build large labelled datasets of RF emissions. WRIST's detector achieves 90 mean Average Precision even in extremely congested environment in the wild. WRIST model classifies five technologies (Bluetooth, Lightbridge, Wi-Fi, XPD, and ZigBee) and is easily extendable to others.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"342 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124229972","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}
Sebastien Boire, Tolgahan Akgün, Philip Ginzboorg, Pekka Laitinen, Sandeep Tamrakar, T. Aura
{"title":"Credential Provisioning and Device Configuration with EAP","authors":"Sebastien Boire, Tolgahan Akgün, Philip Ginzboorg, Pekka Laitinen, Sandeep Tamrakar, T. Aura","doi":"10.1145/3479241.3486705","DOIUrl":"https://doi.org/10.1145/3479241.3486705","url":null,"abstract":"The Extensible Authentication Protocol (EAP) is used for authenticating client devices to WiFi networks, and it is designed to be extensible with new authentication methods. We look at ways to extend the protocol to support credential provisioning and configuration of new client devices. As large numbers of IoT devices are deployed, the task will be simplified by combining the network connectivity, identity and certificate provisioning, and application-layer connectivity to one process. The solution will also allow the use of a one-time credential for the initial authentication, so that the long-term device certificate is issued automatically after the first connection to the network. The paper analyzes the requirements and architectural design options that implement such a user experience. We consider solutions that transfer short bootstrapping data inside the EAP session and then implement the provisioning and configuration with web APIs over HTTPS. This allows future flexibility and speed of development in the provisioning and configuration steps. We designed and implemented several architecturally different solutions and present the comparison results and also compare with previous proposals that have similar goals.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114636873","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}
Aissa Hadj Mohamed, Júlio Cesar dos Reis, L. Villas
{"title":"Forecasting Citywide Crowd Flows with Unbalanced Human Mobility Distributions","authors":"Aissa Hadj Mohamed, Júlio Cesar dos Reis, L. Villas","doi":"10.1145/3479241.3486687","DOIUrl":"https://doi.org/10.1145/3479241.3486687","url":null,"abstract":"Predicting the movement of crowd flows in the city remains an open research problem. This article proposes a framework to predict the crowd flows at the city macro-level, spatially based on unbalanced flow distributions. Compared to models in literature, our framework is simpler, less computationally heavy, and attains state-of-the-art prediction results. In our experiments, we selected four baseline models to demonstrate the effectiveness of our solution. By grouping various regions composing a city into clusters, our proposed framework decreases the error rate (measured by RMSE, Root Mean Squared Error score) by 34% from the best baseline model, for the first hour prediction. In addition, our solution demonstrates high flexibility in including other urban features such as holidays, weather and social events.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"298 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121454481","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}
Aida Ghazizadeh, Puya Ghazizadeh, R. Mukkamala, S. Olariu
{"title":"Approximating Expected Job Completion Time in Dynamic Vehicular Clouds","authors":"Aida Ghazizadeh, Puya Ghazizadeh, R. Mukkamala, S. Olariu","doi":"10.1145/3479241.3486695","DOIUrl":"https://doi.org/10.1145/3479241.3486695","url":null,"abstract":"Motivated by the success of conventional cloud computing, vehicular clouds were introduced as a group of vehicles whose corporate computing, sensing, communication and physical resources can be coordinated and dynamically allocated to authorized users. One of the attributes that set vehicular clouds apart from conventional clouds is resource volatility. As vehicles enter and leave the cloud, new compute resources become available while others depart, creating a volatile environment where the task of reasoning about fundamental performance metrics becomes very challenging. Just as in conventional clouds, job completion time ranks high among the fundamental quantitative performance figures of merit. With this in mind, the main contribution of this work is to offer easy-to-compute approximations of job completion time in a dynamic vehicular cloud model involving vehicles on a highway. We assume estimates of the first moment of the time it takes the job to execute without any overhead attributable to the working of the vehicular cloud. A comprehensive set of simulations have shown that our approximations are very accurate.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133264662","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}
Stylianos Tsanakas, Aroosa Hameed, John Violos, Aris Leivadeas
{"title":"An Innovative Neuro-Genetic Algorithm and Geometric Loss Function for Mobility Prediction","authors":"Stylianos Tsanakas, Aroosa Hameed, John Violos, Aris Leivadeas","doi":"10.1145/3479241.3486706","DOIUrl":"https://doi.org/10.1145/3479241.3486706","url":null,"abstract":"In this research we design a time series geo-location prediction model based on Long Short-Term Memory (LSTM) with a custom geometric loss function. In order to estimate a close to optimal LSTM Recurrent Neural Network (RNN) architecture we use an innovative Genetic Algorithm (GA) tailored for RNN hypertuning. The proposed Neuro-Genetic Algorithm (Neuro-GA) includes a similarity function for the selection of the RNN that will be recombined and an early stopping criterion for the worse performing RNNs. In addition, we examine the applicability of an incremental learning approach for personalized RNN modeling. Compared with auto-machine learning and deep learning models, the proposed methodology shows substantially better prediction results and the early stopping criterion improves the speed of hypertuning convergence. The experiments also show that the incremental learning approach has significant better accuracy than a generic RNN as the personalized models are retrained to new users location data.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133106458","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}
Shyam Krishnan Venkateswaran, Ching-Lun Tai, Y. Ben-Yehezkel, Yaron Alpert, Raghupathy Sivakumar
{"title":"Extending Battery Life for Wi-Fi-Based IoT Devices: Modeling, Strategies, and Algorithm","authors":"Shyam Krishnan Venkateswaran, Ching-Lun Tai, Y. Ben-Yehezkel, Yaron Alpert, Raghupathy Sivakumar","doi":"10.1145/3479241.3486699","DOIUrl":"https://doi.org/10.1145/3479241.3486699","url":null,"abstract":"Wi-Fi is one of the key wireless technologies for the Internet of things (IoT) owing to its ubiquity. Low-power operation of commercial Wi-Fi enabled IoT modules (typically powered by replaceable batteries) is critical in order to achieve a long battery life, while maintaining connectivity, and thereby reduce the cost and frequency of maintenance. In this work, we focus on commonly used sparse periodic uplink traffic scenario in IoT. Through extensive experiments with a state-of-the-art Wi-Fi enabled IoT module (Texas Instruments SimpleLink CC3235SF), we study the performance of the power save mechanism (PSM) in the IEEE 802.11 standard and show that the battery life of the module is limited, while running thin uplink traffic, to ~30% of its battery life on an idle connection, even when utilizing IEEE 802.11 PSM. Focusing on sparse uplink traffic, a prominent traffic scenario for IoT (e.g., periodic measurements, keep-alive mechanisms, etc.), we design a simulation framework for single-user sparse uplink traffic on ns-3, and develop a detailed and platform-agnostic accurate power consumption model within the framework and calibrate it to CC3235SF. Subsequently, we present five potential power optimization strategies (including standard IEEE 802.11 PSM) and analyze, with simulation results, the sensitivity of power consumption to specific network characteristics (e.g., round-trip time (RTT) and relative timing between TCP segment transmissions and beacon receptions) to present key insights. Finally, we propose a standard-compliant client-side cross-layer power saving optimization algorithm that can be implemented on client IoT modules. We show that the proposed optimization algorithm extends battery life by 24%, 26%, and 31% on average for sparse TCP uplink traffic with 5 TCP segments per second for networks with constant RTT values of 25 ms, 10 ms, and 5 ms, respectively.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130562371","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}
Natasha Zlobinsky, D. Johnson, A. Mishra, A. Lysko
{"title":"Simulation and Improved Channel Assignment by Simulated Annealing of a Wireless Mesh Network using Dynamic Spectrum Access","authors":"Natasha Zlobinsky, D. Johnson, A. Mishra, A. Lysko","doi":"10.1145/3479241.3486696","DOIUrl":"https://doi.org/10.1145/3479241.3486696","url":null,"abstract":"This work tackles a new angle to the Channel Assignment (CA) problem, which has otherwise been fairly widely studied for allocating channels optimally to access points and ad-hoc network nodes. Wireless Mesh Networks (WMNs) using Dynamic Spectrum Access (DSA), such as Television White Spaces (TVWS), create new avenues for research due to the additional constraints and complexity. For the production of controlled and repeatable experiments and design of CA algorithms without the drawbacks and difficulties of real hardware, we use Network Simulator 3 (ns3). In this paper we address the construction of an experimental setup in ns3 for evaluating CA algorithms in a DSA WMN environment. Additionally, we propose a solution to the CA problem in this scenario using Simulated Annealing. We simulate TVWS device operation by adding TVWS channels (this can be extended to include any new DSA bands), provide a framework for multi-radio multi-channel WMN experiments, and present and analyse the performance of a CA algorithm. Results show that the proposed algorithm provides channel assignments with much improved performance (120%-755% better) over random channel assignments.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126871787","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}
Jaykumar Sheth, Vikram C. Ramanna, Behnam Dezfouli
{"title":"FLIP: A Framework for Leveraging eBPF to Augment WiFi Access Points and Investigate Network Performance","authors":"Jaykumar Sheth, Vikram C. Ramanna, Behnam Dezfouli","doi":"10.1145/3479241.3486700","DOIUrl":"https://doi.org/10.1145/3479241.3486700","url":null,"abstract":"Monitoring WiFi networks is essential to gain insight into the network operation and develop methods capable of reacting to network dynamics. However, research and development in this field are hindered because there is a lack of a framework that can be easily extended to collect various types of monitoring data from the WiFi stack. In this paper, we propose FLIP, a framework for leveraging eBPF to augment WiFi access points and investigate the performance of WiFi networks. Using this framework, we focus on two important aspects of monitoring the WiFi stack. First, considering the high delay experienced by packets at access points, we show how switching packets from the wired interface to the wireless interface can be monitored and timestamped accurately at each step. We build a testbed using FLIP access points and investigate the factors affecting packet delay experienced in access points. Second, we present a novel approach that allows access points to track the duty-cycling pattern and energy consumption of their associated stations accurately and without the need for any external energy measurement tools. We validate the high energy measurement accuracy of FLIP by empirical experiments and comparisons against a commercial tool.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126580930","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}
{"title":"Generating Synthetic Datasets for Mobile Wireless Networks with SUMO","authors":"Afonso Oliveira, T. Vazão","doi":"10.1145/3479241.3486704","DOIUrl":"https://doi.org/10.1145/3479241.3486704","url":null,"abstract":"With the softwarization of mobile wireless networks comes automated control and management of network infrastructure. Machine learning solutions come as critical enablers to achieve efficient network control and management. However, these machine learning solutions need data to train. In some applications, as is the resource allocation in the edge, large datasets, including User Equipment (UE) mobility between cells and traffic activity, are required. These may be difficult to obtain due to privacy concerns. This work presents a synthetic dataset generator that aims at supporting research activities in these areas. The introduced dataset generator uses traces from a known urban mobility simulator, Simulation of Urban MObility (SUMO). It matches them with empirical radio signal quality and diverse traffic models to obtain large datasets that can validate machine learning solutions. From the introduced generator, we created a dataset in an urban scenario in the city of Berlin with more than 6h of duration, containing more than 40000 UEs served by 21 cells.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128980441","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}
Lars Almon, Arno Manfred Krause, Oliver Fietze, M. Hollick
{"title":"Desynchronization and MitM Attacks Against Neighbor Awareness Networking Using OpenNAN","authors":"Lars Almon, Arno Manfred Krause, Oliver Fietze, M. Hollick","doi":"10.1145/3479241.3486689","DOIUrl":"https://doi.org/10.1145/3479241.3486689","url":null,"abstract":"The Neighbor Awareness Networking (NAN) specification, also known as Wi-Fi Aware, offers a quick and energy efficient way of forming wireless ad-hoc networks. It includes ranging capabilities based on Fine Timing Measurements (FTM) and can sustain connectivity to a Wi-Fi network while participating in a NAN cluster. Android is currently the only operating system to support it, offering a limited and proprietary interface. NAN shares many fundamental properties with Apple's Wireless Direct Link protocol, which is used by millions of devices today. To facilitate research in this area, we present OpenNAN: the first open source NAN stack. It supports Linux and requires just common and cheap off-the-shelf Wi-Fi hardware. Using OpenNAN we perform a security analysis of NAN and identify three attacks. First, any malicious node can manipulate the Anchor Master Selection to become the Anchor Master. Second, a malicious Anchor Master can desynchronize individual nodes by sending synchronization beacons as unicast. And finally, we show a Machine-in-the-Middle (MitM) on the NAN Service Discovery Protocol. We successfully perform all attacks against different Android versions and NAN stacks.","PeriodicalId":349943,"journal":{"name":"Proceedings of the 19th ACM International Symposium on Mobility Management and Wireless Access","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124769369","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}