More Like this

1. SmartDet: Context-Aware Dynamic Control of Edge Task Offloading for Mobile Object Detection

   https://doi.org/10.1109/WoWMoM54355.2022.00034  

   Callegaro, Davide ; Levorato, Marco ; Restuccia, Francesco ( June 2022 , IEEE WoWMoM)

   Mobile devices such as drones and autonomous vehicles increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks such as navigation, target-tracking and surveillance, just to name a few. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) is thus used along with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which does not comply with real-time applications requirements. Offloading OD to edge servers can mitigate this issue, but existing work focuses on the optimization of the offloading process in systems where the wireless channel has a very large capacity. Herein, we consider systems with constrained and erratic channel capacity, and establish parallel OT (at the mobile device) and OD (at the edge server) processes that are resilient to large OD latency. We propose Katch-Up, a novel tracking mechanism that improves the system resilience to excessive OD delay. We show that this technique greatly improves the quality of the reference available to tracking, and boosts performance up to 33%. However, while Katch-Up significantly improves performance, it also increases the computing load of the mobile device. Hence, we design SmartDet, a low-complexity controller based on deep reinforcement learning (DRL) that learns to achieve the right trade-off between resource utilization and OD performance. SmartDet takes as input highly-heterogeneous context-related information related to the current video content and the current network conditions to optimize frequency and type of OD offloading, as well as Katch-Up utilization. We extensively evaluate SmartDet on a real-world testbed composed by a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link, to collect several network-related traces, as well as energy measurements. We consider a state-of-the-art video dataset (ILSVRC 2015 - VID) and state-of-the-art OD models (EfficientDet 0, 2 and 4). Experimental results show that SmartDet achieves an optimal balance between tracking performance – mean Average Recall (mAR) and resource usage. With respect to a baseline with full Katch-Up usage and maximum channel usage, we still increase mAR by 4% while using 50% less of the channel and 30% power resources associated with Katch-Up. With respect to a fixed strategy using minimal resources, we increase mAR by 20% while using Katch-Up on 1/3 of the frames. 

   more » « less
2. Spatio-Temporal Graph Attention Embedding for Joint Crowd Flow and Transition Predictions: A Wi-Fi-based Mobility Case Study

   https://doi.org/10.1145/3495003  

   Yang, Xi ; He, Suining ; Wang, Bing ; Tabatabaie, Mahan ( December 2021 , Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies)

   Crowd mobility prediction, in particular, forecasting flows at and transitions across different locations, is essential for crowd analytics and management in spacious environments featured with large gathering. We propose GAEFT, a novel crowd mobility analytics system based on the multi-task graph attention neural network to forecast crowd flows (inflows/outflows) and transitions. Specifically, we leverage the collective and sanitized campus Wi-Fi association data provided by our university information technology service and conduct a relatable case study. Our comprehensive data analysis reveals the important challenges of sparsity and skewness, as well as the complex spatio-temporal variations within the crowd mobility data. Therefore, we design a novel spatio-temporal clustering method to group Wi-Fi access points (APs) with similar transition features, and obtain more regular mobility features for model inputs. We then propose an attention-based graph embedding design to capture the correlations among the crowd flows and transitions, and jointly predict the AP-level flows as well as transitions across buildings and clusters through a multi-task formulation. Extensive experimental studies using more than 28 million association records collected during 2020-2021 academic year validate the excellent accuracy of GAEFT in forecasting dynamic and complex crowd mobility. 

   more » « less
3. Detection Through Deep Neural Networks: A Reservoir Computing Approach for MIMO-OFDM Symbol Detection

   Kangjun Bai, Lingjia Liu ( November 2020 , IEEE International Conference on Computer-Aided Design)

   null (Ed.)

   The Reservoir Computing, a neural computing framework suited for temporal information processing, utilizes a dynamic reservoir layer for high-dimensional encoding, enhancing the separability of the network. In this paper, we exploit a Deep Learning (DL)-based detection strategy for Multiple-input, Multiple-output Orthogonal Frequency-Division Multiplexing (MIMO-OFDM) symbol detection. To be specific, we introduce a Deep Echo State Network (DESN), a unique hierarchical processing structure with multiple time intervals, to enhance the memory capacity and accelerate the detection efficiency. The resulting hardware prototype with the hybrid memristor-CMOS co-design provides in-memory computing and parallel processing capabilities, significantly reducing the hardware and power overhead. With the standard 180nm CMOS process and memristive synapses, the introduced DESN consumes merely 105mW of power consumption, exhibiting 16.7% power reduction compared to shallow ESN designs even with more dynamic layers and associated neurons. Furthermore, numerical evaluations demonstrate the advantages of the DESN over state-of-the-art detection techniques in the literate for MIMO-OFDM systems even with a very limited training set, yielding a 47.8% improvement against conventional symbol detection techniques. 

   more » « less
4. MatchMaker: An Inter-operator Network Sharing Framework in Unlicensed Bands

   https://doi.org/10.1109/SAHCN.2019.8824920  

   Hirzallah, Mohammed ; Xiao, Yong ; Krunz, Marwan ( June 2019 , 2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON))

   In this paper, we consider the scenario in which mobile network operators (MNOs) share network infrastructure for operating 5G new radio (NR) services in unlicensed bands, whereby they reduce their deployment cost and extend their service coverage. Conserving privacy of MNOs’ users, maintaining fairness with coexisting technologies such as Wi-Fi, and reducing communication overhead between MNOs are among top challenges limiting the feasibility and success of this sharing paradigm. To resolve the above issues, we present MatchMaker, a novel framework for joint network infrastructure and unlicensed spectrum sharing among MNOs. MatchMaker extends the 3GPP’s infrastructure sharing architecture, originally introduced for licensed bands, to have privacy-conserving protocols for managing the shared infrastructure. We also propose a novel privacy-conserving algorithm for channel assignment among MNOs. Although achieving an optimal channel assignment for MNOs over unlicensed bands dictates having global knowledge about MNOs’ network conditions and their interference zones, our channel assignment algorithm does not require such global knowledge and maximizes the cross-technology fairness for the coexisting systems. We let the manager, controlling the shared infrastructure, estimate potential interference among MNOs and Wi-Fi systems by asking MNOs to propose their preferred channel assignment and monitoring their average contention delay overtime. The manager only accepts/rejects MNOs’ proposals and builds contention graph between all co-located devices. Our results show that MatchMaker achieves fairness up to 90% of the optimal alpha-fairness-based channel assignment while still preserving MNOs’ privacy. 

   more » « less
5. Evaluation of Physical Layer Secret Key Generation for IoT Devices

   https://doi.org/10.1109/WAMICON.2019.8765465  

   Jacovic, Marko ; Kraus, Martin ; Mainland, Geoffrey ; Dandekar, Kapil R. ( April 2019 , 2019 IEEE 20th Wireless and Microwave Technology Conference (WAMICON))

   As aspects of our daily lives become more interconnected with the emergence of the Internet of Things (IoT), it is imperative that our devices are reliable and secure from threats. Vulnerabilities of Wi-Fi Protected Access (WPA/WPA2) have been exposed in the past, motivating the use of multiple security techniques, even with the release of WPA3. Physical layer security leverages existing components of communication systems to enable methods of protecting devices that are well-suited for IoT applications. In this work, we provide a low-complexity technique for generating secret keys at the Physical layer to enable improved IoT security. We leverage the existing carrier frequency offset (CFO) and channel estimation components of Orthogonal Frequency Division Multiplexing (OFDM) receivers for an efficient approach. The key generation algorithm we propose focuses on the unique CFO and channel experienced between a pair of desired nodes, and to the best of our understanding, the combination of the features has not been examined previously for the purpose of secret key generation. Our techniques are appropriate for IoT devices, as they do not require extensive processing capabilities and are based on second order statistics. We obtain experimental results using USRP N210 software defined radios and analyze the performance of our methods in post-processing. Our techniques improve the capability of desired nodes to establish matching secret keys, while hindering the threat of an eavesdropper, and are useful for protecting future IoT devices. 

   more » « less