K Foysal Haque

Emerging applications require mobile devices to continuously execute complex deep neural networks (DNNs). While mobile edge computing (MEC) may reduce the computation burden of mobile devices, it exhibits excessive latency as it relies on encapsulating and decapsulating frames through the network protocol stack. To address this issue, we propose PhyDNNs, an approach where DNNs are modified to operate directly at the physical layer (PHY), thus significantly decreasing latency, energy consumption, and network overhead. Conversely from recent work in Joint Source and Channel Coding (JSCC), PhyDNNs adapt already trained DNNs to work at the PHY. To this end, we developed a novel information-theoretical framework to fine-tune PhyDNNs based on the trade-off between commu-nication efficiency and task performance. We have prototyped PhyDNNs with an experimental testbed using a Jetson Orin Nano as the mobile device and two USRP software-defined radios (SDRs) for wireless communication. We evaluated PhyDNNs performance considering various channel conditions, DNN models, and datasets. We also tested PhyDNNs on the Colosseum net-work emulator considering two different propagation scenarios. Experimental results show that PhyDNNs can reduce the end-to-end inference latency, amount of transmitted data, and power consumption by up to 48×, 1385×, and 13 × while keeping the accuracy within 7 % of the state-of-the-art approaches. Moreover, we show that PhyDNNs experience 4.3 times less latency than the most recent JSCC method while incurring in only 1.79% performance loss. For replicability, we shared the source code for the PhyDNNs implementation.

The performance of multiple-input, multiple-output (MIMO) systems highly depends on the precision of channel estimates provided by the mobile users. However, the current Wi-Fi standard requires an update interval of 10 ms, irrespective of the channel dynamics. This imposes a substantial overhead for the MIMO channel estimation. Recent work mainly targets different compression strategies, potentially compromising precoding accuracy and, in turn, the network performance. In stark opposition, we propose SHRINK, a framework to dynamically adapt the feedback transmission rate to the propagation environments and performance requirements. SHRINK determines whether the users should send back their channel estimates by predicting network performance through a data-driven analysis of prior and current channel estimates. We have experimentally evaluated SHRINK using off-the-shelf Wi-Fi devices in multiple environments, including an anechoic chamber, and benchmarked its performance against several state-of-the-art approaches. Experimental results show that SHRINK reduces airtime and data overhead by 81% on average compared to the IEEE 802.11 standard without impacting the precoding performance. Moreover, SHRINK outperforms state-of-the-art approaches by an average gain of 33.6% in airtime and data overhead reduction, corresponding to an increase in throughput of 24.5%.

A fundamental challenge in covert routing is that meeting both covertness and throughput requirements often leads to increased transmit power, which can significantly elevate the overall energy consumption of the network. Therefore, it is important to achieve higher throughput and better energy efficiency while maintaining the required covertness. To this end, we propose a novel simultaneous multi-modal Decentralized Energy- Efficient covert Routing approach - DEER for a multi-hop heterogeneous network (HetNet). Unlike the prevailing single-modal approaches, DEER leverages the diversity of the available wireless communication technologies for simultaneous multi-modal routing. DEER aims to minimize the end-to-end total transmit power of the whole route in a decentralized fashion while maintaining the constraints on required throughput and covertness. DEER stems into two main steps: node-level optimization followed by network-level optimization using the proposed custom-tailored Dijkstra’s based link state routing protocol to meet the constraints while minimizing the end-to-end total transmit power. We demonstrate by numerical analysis that DEER improves the energy efficiency by 23.5x and 2.9x times in comparison to the baseline single-modal and naive simultaneous multimodal approaches respectively.

In this paper, we propose BeamSense, a completely novel approach to implement standard-compliant Wi-Fi sensing applications. Existing work leverages the manual extraction of the uncompressed channel state information (CSI) from Wi-Fi chips, which is not supported by the 802.11 standards and hence requires the usage of specialized equipment. On the contrary, BeamSense leverages the standard-compliant compressed beamforming feedback information (BFI) (beamforming feedback angles (BFAs)) to characterize the propagation environment. Conversely from the uncompressed CSI, the compressed BFAs (i) can be recorded without any firmware modification, and (ii) simultaneously captures the channels between the access point and all the stations, thus providing much better sensitivity. BeamSense features a novel cross-domain few-shot learning (FSL) algorithm for human activity recognition to handle unseen environments and subjects with a few additional data samples. We evaluate BeamSense through an extensive data collection campaign with three subjects performing twenty different activities in three different environments. We show that our BFAs-based approach achieves about 10% more accuracy when compared to CSI-based prior work, while our FSL strategy improves accuracy by up to 30% when compared with state-of-the-art cross-domain algorithms. Additionally, to demonstrate its versatility, we apply BeamSense to another smart home application – gesture recognition – achieving over 98% accuracy across various orientations and subjects. We share the collected datasets and BeamSense implementation code for reproducibility – https://github.com/kfoysalhaque/BeamSense.

In this letter, we propose SCOPE—a novel, entropy-weighted ensembling approach for material classification at sub-Terahertz (THz) frequencies. Unlike existing methods that primarily use dedicated radars, SCOPE builds upon an integrated communication and sensing system and leverages information from both penetrating and reflected signals to enhance spatial resolution and detection accuracy across environments. We adopted spatial variability augmentation (SVA) to address the challenge of generalization across varying transmission distances and antenna gains. While most prior works are limited to radar systems or simulations, SCOPE is implemented and validated in a real sub-THz system working with a 10 GHz bandwidth. Our assessments across different sensing distances, antenna gains, and channel conditions demonstrate the efficacy of SCOPE, which reaches up to 99% accuracy in detecting five materials—glass, wood, metal, air, and plastic—outperforming existing techniques. To facilitate reproducibility, our dataset and code are available at: https://github.com/kfoysalhaque/SCOPE.