Search

Connected and autonomous vehicles (CAVs) offload computationally intensive tasks to multi-access edge computing (MEC) servers via vehicle-to-infrastructure (V2I) communication, enabling applications within the vehicular metaverse, which transforms physical environment into the digital space enabling advanced analysis or predictive modeling. A core challenge is physical-to-virtual (P2V) synchronization through digital twins (DTs), reliant on MEC networks and ultra-reliable low-latency communication (URLLC). To address this, we introduce radiance field (RF) delta video compression (RFDVC), which uses RF-encoder and RF-decoder architecture using distributed RFs as DTs storing photorealistic 3D urban scene in compressed form. This method extracts differences between CAV-frame capturing actual traffic and RF-frame capturing empty scene from the same pose in batches encoded and transmitted over the MEC network. Experiments show data savings up to 90% against H.264 codec and 45% against H.265 codec under different conditions as lighting changes, rain and fog. RFDVC exhibits greater resilience to transmission errors, achieving a bit error rate (BER) of approximately 10^-1.6 at signal-to-noise ratio (SNR) of 10 dB, compared to 10^-1.4 for standard video coding.

Mobile systems will have to support multiple AI-based applications, each leveraging heterogeneous data sources through DNN architectures collaboratively executed within the network. To minimize the cost of the AI inference task subject to requirements on latency, quality, and - crucially - reliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To this end, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, high-quality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC matches the optimum and outperforms its alternatives by over 80%.

Speculative Decoding (SD) is a technique to accelerate the inference of Large Language Models (LLMs) by using a lower complexity draft model to propose candidate tokens verified by a larger target model. To further improve efficiency, Multi-Candidate Speculative Decoding (MCSD) improves upon this by sampling multiple candidate tokens from the draft model at each step and verifying them in parallel, thus increasing the chances of accepting a token and reducing generation time. Existing MCSD methods rely on the draft model to initialize the multi-candidate sequences and use static length and tree attention structure for draft generation. However, such an approach suffers from the draft and target model's output distribution differences, especially in a dynamic generation context. In this work, we introduce a new version of MCSD that includes a target model initialized multi-candidate generation, a dynamic sliced topology-aware causal mask for dynamic length adjustment, and decision models to optimize early stopping. We experimented with our method on Llama 2-7B and its variants and observed a maximum 27.5% speedup compared to our MCSD baseline across three benchmarks with Llama 2-7B as the target model and JackFram 68M as the draft model. Additionally, we evaluate the effects of using the target model initialized multi-candidate process with different draft models on output quality., Comment: Accepted by NeurIPS ENLSP 2024 Workshop

In today's fast-paced world, accurately monitoring stress levels is crucial. Sensor-based stress monitoring systems often need large datasets for training effective models. However, individual-specific models are necessary for personalized and interactive scenarios. Traditional methods like Ecological Momentary Assessments (EMAs) assess stress but struggle with efficient data collection without burdening users. The challenge is to timely send EMAs, especially during stress, balancing monitoring efficiency and user convenience. This paper introduces a novel context-aware active reinforcement learning (RL) algorithm for enhanced stress detection using Photoplethysmography (PPG) data from smartwatches and contextual data from smartphones. Our approach dynamically selects optimal times for deploying EMAs, utilizing the user's immediate context to maximize label accuracy and minimize intrusiveness. Initially, the study was executed in an offline environment to refine the label collection process, aiming to increase accuracy while reducing user burden. Later, we integrated a real-time label collection mechanism, transitioning to an online methodology. This shift resulted in an 11% improvement in stress detection efficiency. Incorporating contextual data improved model accuracy by 4%. Personalization studies indicated a 10% enhancement in AUC-ROC scores, demonstrating better stress level differentiation. This research marks a significant move towards personalized, context-driven real-time stress monitoring methods.

Lightweight autonomous unmanned aerial vehicles (UAV) are emerging as a central component of a broad range of applications. However, autonomous navigation necessitates the implementation of perception algorithms, often deep neural networks (DNN), that process the input of sensor observations, such as that from cameras and LiDARs, for control logic. The complexity of such algorithms clashes with the severe constraints of these devices in terms of computing power, energy, memory, and execution time. In this paper, we propose NaviSplit, the first instance of a lightweight navigation framework embedding a distributed and dynamic multi-branched neural model. At its core is a DNN split at a compression point, resulting in two model parts: (1) the head model, that is executed at the vehicle, which partially processes and compacts perception from sensors; and (2) the tail model, that is executed at an interconnected compute-capable device, which processes the remainder of the compacted perception and infers navigation commands. Different from prior work, the NaviSplit framework includes a neural gate that dynamically selects a specific head model to minimize channel usage while efficiently supporting the navigation network. In our implementation, the perception model extracts a 2D depth map from a monocular RGB image captured by the drone using the robust simulator Microsoft AirSim. Our results demonstrate that the NaviSplit depth model achieves an extraction accuracy of 72-81% while transmitting an extremely small amount of data (1.2-18 KB) to the edge server. When using the neural gate, as utilized by NaviSplit, we obtain a slightly higher navigation accuracy as compared to a larger static network by 0.3% while significantly reducing the data rate by 95%. To the best of our knowledge, this is the first exemplar of dynamic multi-branched model based on split DNNs for autonomous navigation.

Small-scale autonomous airborne vehicles, such as micro-drones, are expected to be a central component of a broad spectrum of applications ranging from exploration to surveillance and delivery. This class of vehicles is characterized by severe constraints in computing power and energy reservoir, which impairs their ability to support the complex state-of-the-art neural models needed for autonomous operations. The main contribution of this paper is a new class of neural navigation models -- NaviSlim -- capable of adapting the amount of resources spent on computing and sensing in response to the current context (i.e., difficulty of the environment, current trajectory, and navigation goals). Specifically, NaviSlim is designed as a gated slimmable neural network architecture that, different from existing slimmable networks, can dynamically select a slimming factor to autonomously scale model complexity, which consequently optimizes execution time and energy consumption. Moreover, different from existing sensor fusion approaches, NaviSlim can dynamically select power levels of onboard sensors to autonomously reduce power and time spent during sensor acquisition, without the need to switch between different neural networks. By means of extensive training and testing on the robust simulation environment Microsoft AirSim, we evaluate our NaviSlim models on scenarios with varying difficulty and a test set that showed a dynamic reduced model complexity on average between 57-92%, and between 61-80% sensor utilization, as compared to static neural networks designed to match computing and sensing of that required by the most difficult scenario., Comment: Accepted to IoTDI 2024, part of CPS-IoT Week for 2024, Hong Kong, and pending publication in Proceedings

The increasing pervasiveness of intelligent mobile applications requires to exploit the full range of resources offered by the mobile-edge-cloud network for the execution of inference tasks. However, due to the heterogeneity of such multi-tiered networks, it is essential to make the applications' demand amenable to the available resources while minimizing energy consumption. Modern dynamic deep neural networks (DNN) achieve this goal by designing multi-branched architectures where early exits enable sample-based adaptation of the model depth. In this paper, we tackle the problem of allocating sections of DNNs with early exits to the nodes of the mobile-edge-cloud system. By envisioning a 3-stage graph-modeling approach, we represent the possible options for splitting the DNN and deploying the DNN blocks on the multi-tiered network, embedding both the system constraints and the application requirements in a convenient and efficient way. Our framework -- named Feasible Inference Graph (FIN) -- can identify the solution that minimizes the overall inference energy consumption while enabling distributed inference over the multi-tiered network with the target quality and latency. Our results, obtained for DNNs with different levels of complexity, show that FIN matches the optimum and yields over 65% energy savings relative to a state-of-the-art technique for cost minimization.

The metaverse is a virtual space that combines physical and digital elements, creating immersive and connected digital worlds. For autonomous mobility, it enables new possibilities with edge computing and digital twins (DTs) that offer virtual prototyping, prediction, and more. DTs can be created with 3D scene reconstruction methods that capture the real world's geometry, appearance, and dynamics. However, sending data for real-time DT updates in the metaverse, such as camera images and videos from connected autonomous vehicles (CAVs) to edge servers, can increase network congestion, costs, and latency, affecting metaverse services. Herein, a new method is proposed based on distributed radiance fields (RFs), multi-access edge computing (MEC) network for video compression and metaverse DT updates. RF-based encoder and decoder are used to create and restore representations of camera images. The method is evaluated on a dataset of camera images from the CARLA simulator. Data savings of up to 80% were achieved for H.264 I-frame - P-frame pairs by using RFs instead of I-frames, while maintaining high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) qualitative metrics for the reconstructed images. Possible uses and challenges for the metaverse and autonomous mobility are also discussed., Comment: 6 pages, 6 figures, conference

The existing work on the distributed training of machine learning (ML) models has consistently overlooked the distribution of the achieved learning quality, focusing instead on its average value. This leads to a poor dependability}of the resulting ML models, whose performance may be much worse than expected. We fill this gap by proposing DepL, a framework for dependable learning orchestration, able to make high-quality, efficient decisions on (i) the data to leverage for learning, (ii) the models to use and when to switch among them, and (iii) the clusters of nodes, and the resources thereof, to exploit. For concreteness, we consider as possible available models a full DNN and its compressed versions. Unlike previous studies, DepL guarantees that a target learning quality is reached with a target probability, while keeping the training cost at a minimum. We prove that DepL has constant competitive ratio and polynomial complexity, and show that it outperforms the state-of-the-art by over 27% and closely matches the optimum.

Daily monitoring of stress is a critical component of maintaining optimal physical and mental health. Physiological signals and contextual information have recently emerged as promising indicators for detecting instances of heightened stress. Nonetheless, developing a real-time monitoring system that utilizes both physiological and contextual data to anticipate stress levels in everyday settings while also gathering stress labels from participants represents a significant challenge. We present a monitoring system that objectively tracks daily stress levels by utilizing both physiological and contextual data in a daily-life environment. Additionally, we have integrated a smart labeling approach to optimize the ecological momentary assessment (EMA) collection, which is required for building machine learning models for stress detection. We propose a three-tier Internet-of-Things-based system architecture to address the challenges. We utilized a cross-validation technique to accurately estimate the performance of our stress models. We achieved the F1-score of 70\% with a Random Forest classifier using both PPG and contextual data, which is considered an acceptable score in models built for everyday settings. Whereas using PPG data alone, the highest F1-score achieved is approximately 56\%, emphasizing the significance of incorporating both PPG and contextual data in stress detection tasks.

Modern IEEE 802.11 (Wi-Fi) networks extensively rely on multiple-input multiple-output (MIMO) to significantly improve throughput. To correctly beamform MIMO transmissions, the access point needs to frequently acquire a beamforming matrix (BM) from each connected station. However, the size of the matrix grows with the number of antennas and subcarriers, resulting in an increasing amount of airtime overhead and computational load at the station. Conventional approaches come with either excessive computational load or loss of beamforming precision. For this reason, we propose SplitBeam, a new framework where we train a split deep neural network (DNN) to directly output the BM given the channel state information (CSI) matrix as input. We formulate and solve a bottleneck optimization problem (BOP) to keep computation, airtime overhead, and bit error rate (BER) below application requirements. We perform extensive experimental CSI collection with off-the-shelf Wi-Fi devices in two distinct environments and compare the performance of SplitBeam with the standard IEEE 802.11 algorithm for BM feedback and the state-of-the-art DNN-based approach LB-SciFi. Our experimental results show that SplitBeam reduces the beamforming feedback size and computational complexity by respectively up to 81% and 84% while maintaining BER within about 10^-3 of existing approaches. We also implement the SplitBeam DNNs on FPGA hardware to estimate the end-to-end BM reporting delay, and show that the latter is less than 10 milliseconds in the most complex scenario, which is the target channel sounding frequency in realistic multi-user MIMO scenarios., Comment: Presented at the 43rd IEEE International Conference on Distributed Computing Systems (ICDCS 2023)

The execution of large deep neural networks (DNN) at mobile edge devices requires considerable consumption of critical resources, such as energy, while imposing demands on hardware capabilities. In approaches based on edge computing the execution of the models is offloaded to a compute-capable device positioned at the edge of 5G infrastructures. The main issue of the latter class of approaches is the need to transport information-rich signals over wireless links with limited and time-varying capacity. The recent split computing paradigm attempts to resolve this impasse by distributing the execution of DNN models across the layers of the systems to reduce the amount of data to be transmitted while imposing minimal computing load on mobile devices. In this context, we propose a novel split computing approach based on slimmable ensemble encoders. The key advantage of our design is the ability to adapt computational load and transmitted data size in real-time with minimal overhead and time. This is in contrast with existing approaches, where the same adaptation requires costly context switching and model loading. Moreover, our model outperforms existing solutions in terms of compression efficacy and execution time, especially in the context of weak mobile devices. We present a comprehensive comparison with the most advanced split computing solutions, as well as an experimental evaluation on GPU-less devices.

Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models. However, in settings where personalization is necessary at deployment time to fine-tune the model, a person-specific dataset needs to be collected online by interacting with the users. Optimizing the collection of labels in such phase is instrumental to impose a tolerable burden on the users while maximizing personal improvement. In this paper, we consider a fine-grain stress detection problem based on wearable sensors targeting everyday settings, and propose a novel context-aware active learning strategy capable of jointly maximizing the meaningfulness of the signal samples we request the user to label and the response rate. We develop a multilayered sensor-edge-cloud platform to periodically capture physiological signals and process them in real-time, as well as to collect labels and retrain the detection model. We collect a large dataset and show that the context-aware active learning technique we propose achieves a desirable detection performance using 88\% and 32\% fewer queries from users compared to a randomized strategy and a traditional active learning strategy, respectively., Comment: Accepted paper at CHASE '23

To make machine learning (ML) sustainable and apt to run on the diverse devices where relevant data is, it is essential to compress ML models as needed, while still meeting the required learning quality and time performance. However, how much and when an ML model should be compressed, and {\em where} its training should be executed, are hard decisions to make, as they depend on the model itself, the resources of the available nodes, and the data such nodes own. Existing studies focus on each of those aspects individually, however, they do not account for how such decisions can be made jointly and adapted to one another. In this work, we model the network system focusing on the training of DNNs, formalize the above multi-dimensional problem, and, given its NP-hardness, formulate an approximate dynamic programming problem that we solve through the PACT algorithmic framework. Importantly, PACT leverages a time-expanded graph representing the learning process, and a data-driven and theoretical approach for the prediction of the loss evolution to be expected as a consequence of training decisions. We prove that PACT's solutions can get as close to the optimum as desired, at the cost of an increased time complexity, and that, in any case, such complexity is polynomial. Numerical results also show that, even under the most disadvantageous settings, PACT outperforms state-of-the-art alternatives and closely matches the optimal energy cost.

To process and transfer large amounts of data in emerging wireless services, it has become increasingly appealing to exploit distributed data communication and learning. Specifically, edge learning (EL) enables local model training on geographically disperse edge nodes and minimizes the need for frequent data exchange. However, the current design of separating EL deployment and communication optimization does not yet reap the promised benefits of distributed signal processing, and sometimes suffers from excessive signalling overhead, long processing delay, and unstable learning convergence. In this paper, we provide an overview on practical distributed EL techniques and their interplay with advanced communication optimization designs. In particular, typical performance metrics for dual-functional learning and communication networks are discussed. Also, recent achievements of enabling techniques for the dual-functional design are surveyed with exemplifications from the mutual perspectives of "communications for learning" and "learning for communications." The application of EL techniques within a variety of future communication systems are also envisioned for beyond 5G (B5G) wireless networks. For the application in goal-oriented semantic communication, we present a first mathematical model of the goal-oriented source entropy as an optimization problem. In addition, from the viewpoint of information theory, we identify fundamental open problems of characterizing rate regions for communication networks supporting distributed learning-and-computing tasks. We also present technical challenges as well as emerging application opportunities in this field, with the aim of inspiring future research and promoting widespread developments of EL in B5G.

With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split computing approaches often underperform compared to a naive baseline of remote computation on compressed data. Recent studies propose learning compressed representations that contain more relevant information for supervised downstream tasks, showing improved tradeoffs between compressed data size and supervised performance. However, existing evaluation metrics only provide an incomplete picture of split computing. This study introduces supervised compression for split computing (SC2) and proposes new evaluation criteria: minimizing computation on the mobile device, minimizing transmitted data size, and maximizing model accuracy. We conduct a comprehensive benchmark study using 10 baseline methods, three computer vision tasks, and over 180 trained models, and discuss various aspects of SC2. We also release sc2bench, a Python package for future research on SC2. Our proposed metrics and package will help researchers better understand the tradeoffs of supervised compression in split computing., Comment: Accepted at TMLR. Code and models are available at https://github.com/yoshitomo-matsubara/sc2-benchmark

Mobile devices increasingly rely on object detection (OD) through deep neural networks (DNNs) to perform critical tasks. Due to their high complexity, the execution of these DNNs requires excessive time and energy. Low-complexity object tracking (OT) can be used with OD, where the latter is periodically applied to generate "fresh" references for tracking. However, the frames processed with OD incur large delays, which may make the reference outdated and degrade tracking quality. Herein, we propose to use edge computing in this context, 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. 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 controlling the trade-off between resource utilization and OD performance. SmartDet takes as input 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 of a JetSon Nano as mobile device and a GTX 980 Ti as edge server, connected through a Wi-Fi link. 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-Upusage 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.

Although mission-critical applications require the use of deep neural networks (DNNs), their continuous execution at mobile devices results in a significant increase in energy consumption. While edge offloading can decrease energy consumption, erratic patterns in channel quality, network and edge server load can lead to severe disruption of the system's key operations. An alternative approach, called split computing, generates compressed representations within the model (called "bottlenecks"), to reduce bandwidth usage and energy consumption. Prior work has proposed approaches that introduce additional layers, to the detriment of energy consumption and latency. For this reason, we propose a new framework called BottleFit, which, in addition to targeted DNN architecture modifications, includes a novel training strategy to achieve high accuracy even with strong compression rates. We apply BottleFit on cutting-edge DNN models in image classification, and show that BottleFit achieves 77.1% data compression with up to 0.6% accuracy loss on ImageNet dataset, while state of the art such as SPINN loses up to 6% in accuracy. We experimentally measure the power consumption and latency of an image classification application running on an NVIDIA Jetson Nano board (GPU-based) and a Raspberry PI board (GPU-less). We show that BottleFit decreases power consumption and latency respectively by up to 49% and 89% with respect to (w.r.t.) local computing and by 37% and 55% w.r.t. edge offloading. We also compare BottleFit with state-of-the-art autoencoders-based approaches, and show that (i) BottleFit reduces power consumption and execution time respectively by up to 54% and 44% on the Jetson and 40% and 62% on Raspberry PI; (ii) the size of the head model executed on the mobile device is 83 times smaller. We publish the code repository for reproducibility of the results in this study., Comment: Accepted to IEEE WoWMoM 2022. Code and models are available at https://github.com/yoshitomo-matsubara/bottlefit-split_computing

Next Generation (NextG) networks are expected to support demanding tactile internet applications such as augmented reality and connected autonomous vehicles. Whereas recent innovations bring the promise of larger link capacity, their sensitivity to the environment and erratic performance defy traditional model-based control rationales. Zero-touch data-driven approaches can improve the ability of the network to adapt to the current operating conditions. Tools such as reinforcement learning (RL) algorithms can build optimal control policy solely based on a history of observations. Specifically, deep RL (DRL), which uses a deep neural network (DNN) as a predictor, has been shown to achieve good performance even in complex environments and with high dimensional inputs. However, the training of DRL models require a large amount of data, which may limit its adaptability to ever-evolving statistics of the underlying environment. Moreover, wireless networks are inherently distributed systems, where centralized DRL approaches would require excessive data exchange, while fully distributed approaches may result in slower convergence rates and performance degradation. In this paper, to address these challenges, we propose a federated learning (FL) approach to DRL, which we refer to federated DRL (F-DRL), where base stations (BS) collaboratively train the embedded DNN by only sharing models' weights rather than training data. We evaluate two distinct versions of F-DRL, value and policy based, and show the superior performance they achieve compared to distributed and centralized DRL., Comment: 6pages

Autonomous surveillance unmanned aerial vehicles (UAVs) are deployed to observe the streets of the city for any suspicious activities. This paper utilizes surveillance UAVs for the purpose of detecting the presence of a fire in the streets. An extensive database is collected from UAV surveillance drones. With the aid of artificial intelligence (AI), fire stations can swiftly identify the presence of a fire emerging in the neighborhood. Spatio-temporal split learning is applied to this scenario to preserve privacy and globally train a fire classification model. Fires are hazardous natural disasters that can spread very quickly. Swift identification of fire is required to deploy firefighters to the scene. In order to do this, strong communication between the UAV and the central server where the deep learning process occurs is required. Improving communication resilience is integral to enhancing a safe experience on the roads. Therefore, this paper explores the adequate number of clients and data ratios for split learning in this UAV setting, as well as the required network infrastructure.

There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and storage. As a result, the bulk part of the machine learning operation is therefore often carried out on an edge server, where the data is compressed and transmitted. However, compressing data (such as images) leads to transmitting information irrelevant to the supervised task. Another popular approach is to split the deep network between the device and the server while compressing intermediate features. To date, however, such split computing strategies have barely outperformed the aforementioned naive data compression baselines due to their inefficient approaches to feature compression. This paper adopts ideas from knowledge distillation and neural image compression to compress intermediate feature representations more efficiently. Our supervised compression approach uses a teacher model and a student model with a stochastic bottleneck and learnable prior for entropy coding (Entropic Student). We compare our approach to various neural image and feature compression baselines in three vision tasks and found that it achieves better supervised rate-distortion performance while maintaining smaller end-to-end latency. We furthermore show that the learned feature representations can be tuned to serve multiple downstream tasks., Comment: Accepted to WACV 2022. Code and models are available at https://github.com/yoshitomo-matsubara/supervised-compression

Real-time physiological data collection and analysis play a central role in modern well-being applications. Personalized classifiers and detectors have been shown to outperform general classifiers in many contexts. However, building effective personalized classifiers in everyday settings - as opposed to controlled settings - necessitates the online collection of a labeled dataset by interacting with the user. This need leads to several challenges, ranging from building an effective system for the collection of the signals and labels, to developing strategies to interact with the user and building a dataset that represents the many user contexts that occur in daily life. Based on a stress detection use case, this paper (1) builds a system for the real-time collection and analysis of photoplethysmogram, acceleration, gyroscope, and gravity data from a wearable sensor, as well as self-reported stress labels based on Ecological Momentary Assessment (EMA), and (2) collects and analyzes a dataset to extract statistics of users' response to queries and the quality of the collected signals as a function of the context, here defined as the user's activity and the time of the day., Comment: Accepted to ACM GoodIT'21

Since stress contributes to a broad range of mental and physical health problems, the objective assessment of stress is essential for behavioral and physiological studies. Although several studies have evaluated stress levels in controlled settings, objective stress assessment in everyday settings is still largely under-explored due to challenges arising from confounding contextual factors and limited adherence for self-reports. In this paper, we explore the objective prediction of stress levels in everyday settings based on heart rate (HR) and heart rate variability (HRV) captured via low-cost and easy-to-wear photoplethysmography (PPG) sensors that are widely available on newer smart wearable devices. We present a layered system architecture for personalized stress monitoring that supports a tunable collection of data samples for labeling, and present a method for selecting informative samples from the stream of real-time data for labeling. We captured the stress levels of fourteen volunteers through self-reported questionnaires over periods of between 1-3 months, and explored binary stress detection based on HR and HRV using Machine Learning Methods. We observe promising preliminary results given that the dataset is collected in the challenging environments of everyday settings. The binary stress detector is fairly accurate and can detect stressful vs non-stressful samples with a macro-F1 score of up to \%76. Our study lays the groundwork for more sophisticated labeling strategies that generate context-aware, personalized models that will empower health professionals to provide personalized interventions., Comment: Accepted at EMBC'21

Blood Pressure (BP) is one of the four primary vital signs indicating the status of the body's vital (life-sustaining) functions. BP is difficult to continuously monitor using a sphygmomanometer (i.e. a blood pressure cuff), especially in everyday-setting. However, other health signals which can be easily and continuously acquired, such as photoplethysmography (PPG), show some similarities with the Aortic Pressure waveform. Based on these similarities, in recent years several methods were proposed to predict BP from the PPG signal. Building on these results, we propose an advanced personalized data-driven approach that uses a three-layer deep neural network to estimate BP based on PPG signals. Different from previous work, the proposed model analyzes the PPG signal in time-domain and automatically extracts the most critical features for this specific application, then uses a variation of recurrent neural networks called Long-Short-Term-Memory (LSTM) to map the extracted features to the BP value associated with that time window. Experimental results on two separate standard hospital datasets, yielded absolute errors mean and absolute error standard deviation for systolic and diastolic BP values outperforming prior works., Comment: Accepted at EMBC'21

Edge computing enables Mobile Autonomous Systems (MASs) to execute continuous streams of heavy-duty mission-critical processing tasks, such as real-time obstacle detection and navigation. However, in practical applications, erratic patterns in channel quality, network load, and edge server load can interrupt the task flow execution, which necessarily leads to severe disruption of the system's key operations. Existing work has mostly tackled the problem with reactive approaches, which cannot guarantee task-level reliability. Conversely, in this paper we focus on learning-based predictive edge computing to achieve self-resilient task offloading. By conducting a preliminary experimental evaluation, we show that there is no dominant feature that can predict the edge-MAS system reliability, which calls for an ensemble and selection of weaker features. To tackle the complexity of the problem, we propose SeReMAS, a data-driven optimization framework. We first mathematically formulate a Redundant Task Offloading Problem (RTOP), where a MAS may connect to multiple edge servers for redundancy, and needs to select which server(s) to transmit its computing tasks in order to maximize the probability of task execution while minimizing channel and edge resource utilization. We then create a predictor based on Deep Reinforcement Learning (DRL), which produces the optimum task assignment based on application-, network- and telemetry-based features. We prototype SeReMAS on a testbed composed by a drone, mounting a PixHawk flight controller, a Jetson Nano board, and three 802.11n WiFi interfaces. We extensively evaluate SeReMAS by considering an application where one drone offloads high-resolution images for real-time analysis to three edge servers on the ground. Experimental results show that SeReMAS improves task execution probability by $17\%$ with respect to existing reactive-based approaches., Comment: Corrected typo in title

Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud/edge servers may decrease the mobile device's computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple "exits" earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the trade-off between accuracy and delay can be tuned according to the current conditions or application demands. In this paper, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the paper by providing a set of compelling research challenges., Comment: Accepted to ACM Computing Surveys (CSUR)

The prompt and accurate detection of faults and abnormalities in electric transmission lines is a critical challenge in smart grid systems. Existing methods mostly rely on model-based approaches, which may not capture all the aspects of these complex temporal series. Recently, the availability of data sets collected using advanced metering devices, such as Micro-Phasor Measurement units ($\mu$ PMU), which provide measurements at microsecond timescale, boosted the development of data-driven methodologies. In this paper, we introduce a novel deep learning-based approach for fault detection and test it on a real data set, namely, the Kaggle platform for a partial discharge detection task. Our solution adopts a Long-Short Term Memory architecture with attention mechanism to extract time series features, and uses a 1D-Convolutional Neural Network structure to exploit frequency information of the signal for prediction. Additionally, we propose an unsupervised method to cluster signals based on their frequency components, and apply multi task learning on different clusters. The method we propose outperforms the winner solutions in the Kaggle competition and other state of the art methods in many performance metrics, and improves the interpretability of analysis., Comment: This article has been accepted for publication in the IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, 2020

The edge computing paradigm places compute-capable devices - edge servers - at the network edge to assist mobile devices in executing data analysis tasks. Intuitively, offloading compute-intense tasks to edge servers can reduce their execution time. However, poor conditions of the wireless channel connecting the mobile devices to the edge servers may degrade the overall capture-to-output delay achieved by edge offloading. Herein, we focus on edge computing supporting remote object detection by means of Deep Neural Networks (DNNs), and develop a framework to reduce the amount of data transmitted over the wireless link. The core idea we propose builds on recent approaches splitting DNNs into sections - namely head and tail models - executed by the mobile device and edge server, respectively. The wireless link, then, is used to transport the output of the last layer of the head model to the edge server, instead of the DNN input. Most prior work focuses on classification tasks and leaves the DNN structure unaltered. Herein, our focus is on DNNs for three different object detection tasks, which present a much more convoluted structure, and modify the architecture of the network to: (i) achieve in-network compression by introducing a bottleneck layer in the early layers on the head model, and (ii) prefilter pictures that do not contain objects of interest using a convolutional neural network. Results show that the proposed technique represents an effective intermediate option between local and edge computing in a parameter region where these extreme point solutions fail to provide satisfactory performance. The code and trained models are available at https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors ., Comment: Accepted to ICPR 2020 in the 1st round (the 25th International Conference on Pattern Recognition)

Following the trends of mobile and edge computing for DNN models, an intermediate option, split computing, has been attracting attentions from the research community. Previous studies empirically showed that while mobile and edge computing often would be the best options in terms of total inference time, there are some scenarios where split computing methods can achieve shorter inference time. All the proposed split computing approaches, however, focus on image classification tasks, and most are assessed with small datasets that are far from the practical scenarios. In this paper, we discuss the challenges in developing split computing methods for powerful R-CNN object detectors trained on a large dataset, COCO 2017. We extensively analyze the object detectors in terms of layer-wise tensor size and model size, and show that naive split computing methods would not reduce inference time. To the best of our knowledge, this is the first study to inject small bottlenecks to such object detectors and unveil the potential of a split computing approach. The source code and trained models' weights used in this study are available at https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors ., Comment: Accepted to EMDL '20 (4th International Workshop on Embedded and Mobile Deep Learning) co-located with ACM MobiCom 2020

In this paper, we present a framework for the dynamic selection of the wireless channels used to deliver information-rich data streams to edge servers. The approach we propose is data-driven, where a predictor, whose output informs the decision making of the channel selector, is built from available data on the transformation imposed by the network on previously transmitted packets. The proposed technique is contextualized to real-time video streaming for immediate processing. The core of our framework is the notion of probes, that is, short bursts of packets transmitted over unused channels to acquire information while generating a controlled impact on other active links. Results indicate a high accuracy of the prediction output and a significant improvement in terms of received video quality when the prediction output is used to dynamically select the used channel for transmission., Comment: This article has been accepted for publication in the IEEE International Conference on Communications (ICC) Workshop on "Edge Machine Learning for 5G Mobile Networks and Beyond (EML5G)" 2020

State-of-the-art drone technologies have severe flight time limitations due to weight constraints, which inevitably lead to a relatively small amount of available energy. Therefore, frequent battery replacement or recharging is necessary in applications such as delivery, exploration, or support to the wireless infrastructure. Mobile charging stations (i.e., mobile stations with charging equipment) for outdoor ad-hoc battery charging is one of the feasible solutions to address this issue. However, the ability of these platforms to charge the drones is limited in terms of the number and charging time. This paper designs an auction-based mechanism to control the charging schedule in multi-drone setting. In this paper, charging time slots are auctioned, and their assignment is determined by a bidding process. The main challenge in developing this framework is the lack of prior knowledge on the distribution of the number of drones participating in the auction. Based on optimal second-price-auction, the proposed formulation, then, relies on deep learning algorithms to learn such distribution online. Numerical results from extensive simulations show that the proposed deep learning-based approach provides effective battery charging control in multi-drone scenarios., Comment: 14 pages, 19 figures, IEEE Transactions on Vehicular Technology ( Volume: 68 , Issue: 5 , May 2019 )

Recent advances in the Internet of Things (IoT) technologies have enabled the use of wearables for remote patient monitoring. Wearable sensors capture the patient's vital signs, and provide alerts or diagnosis based on the collected data. Unfortunately, wearables typically have limited energy and computational capacity, making their use challenging for healthcare applications where monitoring must continue uninterrupted long time, without the need to charge or change the battery. Fog computing can alleviate this problem by offloading computationally intensive tasks from the sensor layer to higher layers, thereby not only meeting the sensors' limited computational capacity but also enabling the use of local closed-loop energy optimization algorithms to increase the battery life.

Infrastructure assistance has been proposed as a viable solution to improve the capabilities of commercial Unmanned Aerial Vehicles (UAV), especially toward fully autonomous operations. The airborne nature of these devices imposes constrains limiting the onboard available energy supply and computing power. The assistance of the surrounding communication and computing infrastructure can mitigate such limitations by extending the communication range and taking over the execution of compute-intense tasks. However, autonomous operations impose specific, and rather extreme in some cases, demands to the infrastructure. Focusing on flight assistance and task offloading to edge servers, this paper presents an in-depth evaluation of the ability of the communication infrastructure to support the necessary flow of information from the UAV to the infrastructure. The study is based on our recently proposed FlyNetSim, an open-source UAV-network simulator accurately modeling both UAV and network operations.

Unmanned Aerial Vehicle (UAV) systems are being increasingly used in a broad range of applications requiring extensive communications, either to interconnect the UAVs with each other or with ground resources. Focusing either on the modeling of UAV operations or communication and network dynamics, available simulation tools fail to capture the complex interdependencies between these two aspects of the problem. The main contribution of this paper is a flexible and scalable open source simulator -- FlyNetSim -- bridging the two domains. The overall objective is to enable simulation and evaluation of UAV swarms operating within articulated multi-layered technological ecosystems, such as the Urban Internet of Things (IoT). To this aim, FlyNetSim interfaces two open source tools, ArduPilot and ns-3, creating individual data paths between the devices operating in the system using a publish and subscribe-based middleware. The capabilities of FlyNetSim are illustrated through several case-study scenarios including UAVs interconnecting with a multi-technology communication infrastructure and intra-swarm ad-hoc communications., Comment: This article has been accepted for publication in the ACM MSWiM 2018. 21st ACM International Conference on Modelling, Analysis and Simulation of Wireless and Mobile Systems (MSWIM '18), October 28-November 2, 2018, Montreal, QC, Canada

By placing computation resources within a one-hop wireless topology, the recent edge computing paradigm is a key enabler of real-time Internet of Things (IoT) applications. In the context of IoT scenarios where the same information from a sensor is used by multiple applications at different locations, the data stream needs to be replicated. However, the transportation of parallel streams might not be feasible due to limitations in the capacity of the network transporting the data. To address this issue, a content and computation-aware communication control framework is proposed based on the Software Defined Network (SDN) paradigm. The framework supports multi-streaming using the extended Berkeley Packet Filter (eBPF), where the traffic flow and packet replication for each specific computation process is controlled by a program running inside an in-kernel Virtual Ma- chine (VM). The proposed framework is instantiated to address a case-study scenario where video streams from multiple cameras are transmitted to the edge processor for real-time analysis. Numerical results demonstrate the advantage of the proposed framework in terms of programmability, network bandwidth and system resource savings., Comment: This article has been accepted for publication in the IEEE International Conference on Computer Communications (INFOCOM Workshops), 2018

Unmanned Aerial Vehicle (UAV) systems are being increasingly used in a broad range of scenarios and applications. However, their deployment in urban areas poses important technical challenges. One of the most prominent concerns is the robustness of communications between the ground stations and the UAVs in a highly dynamic and crowded spectrum. Indeed, competing data streams may create local or temporary congestion impairing the ground stations to control the UAVs. The main contribution of this paper is a robust multi-path communication framework for UAV systems. The framework continuously probes the performance of multiple wireless multi-hop paths from the ground stations to each UAV, and dynamically selects the path providing the best performance to support timely control. Numerical results, based on a real-world implementation and extensive field experimentation, demonstrate the ability of the proposed framework to provide robust control against exogenous interference and network congestion., Comment: This article has been accepted for publication in the IEEE International Conference on Sensing, Communication and Networking (SECON Workshops), 2018

A novel semantic approach to data selection and compression is presented for the dynamic adaptation of IoT data processing and transmission within "wireless islands", where a set of sensing devices (sensors) are interconnected through one-hop wireless links to a computational resource via a local access point. The core of the proposed technique is a cooperative framework where local classifiers at the mobile nodes are dynamically crafted and updated based on the current state of the observed system, the global processing objective and the characteristics of the sensors and data streams. The edge processor plays a key role by establishing a link between content and operations within the distributed system. The local classifiers are designed to filter the data streams and provide only the needed information to the global classifier at the edge processor, thus minimizing bandwidth usage. However, the better the accuracy of these local classifiers, the larger the energy necessary to run them at the individual sensors. A formulation of the optimization problem for the dynamic construction of the classifiers under bandwidth and energy constraints is proposed and demonstrated on a synthetic example., Comment: Presented at the Information Theory and Applications Workshop (ITA), February 17, 2017

This paper develops a control framework for a network of energy harvesting nodes connected to a Base Station (BS) over a multiple access channel. The objective is to adapt their transmission strategy to the state of the network, including the energy available to the individual nodes. In order to reduce the complexity of control, an optimization framework is proposed where energy storage dynamics are replaced by dynamic average power constraints induced by the time correlated energy supply, thus enabling lightweight and flexible network control. Specifically, the BS adapts the packet transmission probability of the "active" nodes (those currently under a favorable energy harvesting state) so as to maximize the average long-term throughput, under these dynamic average power constraints. The resulting policy takes the form of the packet transmission probability as a function of the energy harvesting state and number of active nodes. The structure of the throughput-optimal genie-aided policy, in which the number of active nodes is known non-causally at the BS, is proved. Inspired by the genie-aided policy, a Bayesian estimation approach is presented to address the case where the BS estimates the number of active nodes based on the observed network transmission pattern. It is shown that the proposed scheme outperforms by 20% a scheme in which the nodes operate based on local state information only, and performs well even when energy storage dynamics are taken into account., Comment: Submitted to IEEE ISIT 2017

In the Urban Internet of Things devices and systems are interconnected at the city scale to provide innovative services to the citizens.However, the traffic generated by the sensing and processing systems may overload local access networks. A coexistence problem arises where concurrent applications mutually interfere and compete for available resources. This effect is further aggravated by the multiple scales involved and heterogeneity of the networks supporting the urban IoT. One of the main contributions of this paper is the introduction of the notion of content-oriented cognitive interference control in heterogeneous local access networks supporting computing and data processing in the urban IoT. A network scenario where multiple communication technologies, such as Device-to-Device and Long Term Evolution (LTE), is considered. The focus of the present paper is on city monitoring applications, where a video data stream generated by a camera system is remotely processed to detect objects. The cognitive network paradigm is extended to dynamically shape the interference pattern generated by concurrent data streams and induce a packet loss trajectory compatible with video processing algorithms. Numerical results show that the proposed cognitive transmission strategy enables a significant throughput increase of interfering applications for a target accuracy of the monitoring application., Comment: Submitted to IEEE Globecom 2016

A novel interference management approach is proposed for modern communication scenarios, where multiple applications and networks coexist on the same channel resource. The leading principle behind the proposed approach is that the interference level should be adapted to the content being transmitted by the data links to maximize the amount of delivered information. A network setting is considered where Device-to-Device (D2D) communications underlay a Long Term Evolution (LTE) link uploading video content to the network infrastructure. For this scenario, an optimization problem is formulated aiming at the maximization of the D2D throughput under a constraint on the Peak Signal-to-Noise-Ratio of the video data stream. The resulting optimal policy focuses interference on specific packets within the video stream, and significantly increases the throughput achieved by the D2D link compared to an undifferentiated interference strategy. The optimal strategy is applied to a real-world video streaming application to further demonstrate the performance gain., Comment: submitted to IEEE Globecom 2016

Energy storage is a fundamental component for the development of sustainable and environment-aware technologies. One of the critical challenges that needs to be overcome is preserving the State of Health (SoH) in energy harvesting systems, where bursty arrival of energy and load may severely degrade the battery. Tools from Markov process and Dynamic Programming theory are becoming an increasingly popular choice to control dynamics of these systems due to their ability to seamlessly incorporate heterogeneous components and support a wide range of applications. Mapping aging rate measures to fit within the boundaries of these tools is non-trivial. In this paper, a framework for modeling and controlling the aging rate of batteries based on Markov process theory is presented. Numerical results illustrate the tradeoff between battery degradation and task completion delay enabled by the proposed framework.