IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Copy-CAV: V2X-Enabled wireless towing for emergency transport
Get PDFAs smart connected vehicles become increasingly common and pave the way for the autonomous
vehicles of the future, their ability to provide enhanced safety and assistance services has improved.
One such service is the emergency transport of drivers in medical distress: as a positive solution
of the distress is typically more likely after timely response, an autonomous vehicle could cut on
emergency response times, and thus play a key role in saving the life of its driver.
In this paper, we show how such an autonomous emergency transport service can be run from
a wireless cellular network, and discuss the importance of having a human in the loop in order to
expedite driving. We present a Monte-Carlo-based driver assessment system that the network can
use when selecting the most suitable candidate to wirelessly tow an autonomous vehicle with an
incapacitated driver. We show that this mechanism results in a selection policy that ensures better
cohesion between the vehicles, thereby significantly improving service reliability by reducing the
chances of disruptions by intervening traffic.TRUEpu
Optimizing UAV Resupply Scheduling for Heterogeneous and Persistent Aerial Service
Get PDFWith the current advances in UAV technologies, aerial vehicles (UAVs) are becoming very attractive for many purposes. However, currently the bottleneck in the adoption of them is no longer due to architectural and protocol challenges and constraints, but rather to the limited energy that they can rely on. In this article, we design two power resupplying schemes under the assumption of a fleet of homogeneous UAVs. Such schemes are designed to minimize the size of the fleet to be devoted to a persistent service (i.e., carried out at all times) of a set of aerial locations. First, we consider the case where the aerial locations to be served are equidistant from an energy supply station. In that scenario, we design a simple scheduling, that we name HORR, which we prove to be feasible and exact, in the sense that it uses the minimum possible number of UAVs to guarantee the permanent coverage of the aerial service locations. Then, we extend that work for the case of non-evenly distributed aerial locations. In this new scenario, we demonstrate that the problem becomes NP-hard, and design a lightweight scheduling scheme, PHERR, that extends the operation of HORR to the heterogeneous case. Through numerical analysis, we show that PHERR provides near-exact resupply schedules.TRUEpu
Visible Light or Infrared? Modulating LiFi for Dual Operation in the Visible and Infrared Spectra
Get PDFLight-Fidelity (LiFi) has emerged in the last few years as a promising technology for alleviating the stringent demand of wireless data services. Prior works have considered LiFi operating either in the visible light or infrared spectrum. Each spectrum band has its own advantages: visible light allows leveraging existing infrastructure for communication, while infrared is not affected by degradation in presence of light dimming. In this work, we propose a modulation scheme that efficiently uses both spectra, and present a simple, low cost, yet efficient modulation technique that retains the benefits of both bands. We prototype our solution by creating an extended version of OpenVLC, and we experimentally show its robust performance in communication under different dimming conditions. We make the implemented system publicly available to the research community.TRUEpu
Forecasting Network Traffic: A Survey and Tutorial with Open-Source Comparative Evaluation
Get PDFThis paper presents a review of the literature on network traffic prediction, while also serving as a tutorial to the topic. We examine works based on autoregressive moving average models, like ARMA, ARIMA and SARIMA, as well as works based on Artifical Neural Networks approaches, such as RNN, LSTM, GRU, and CNN. In all cases, we provide a complete and self-contained presentation of the mathematical foundations of each technique, which allows the reader to get a full understanding of the operation of the different proposed methods. Further, we perform numerical experiments based on real data sets, which allows comparing the various approaches directly in terms of fitting quality and computational costs. We make our code publicly available, so that readers can readily access a wide range of forecasting tools, and possibly use them as benchmarks for more advanced solutions.European CommissionTRUEpu
The impact of physicochemical features of carbon electrodes on the capacitive performance of supercapacitors: a machine learning approach
Get PDFHybrid electric vehicles and portable electronic systems use supercapacitors for energy storage owing
to their fast charging/discharging rates, long life cycle, and low maintenance. Specific capacitance
is regarded as one of the most important performance-related characteristics of a supercapacitor’s
electrode. In the current study, Machine Learning (ML) algorithms were used to determine the impact
of various physicochemical properties of carbon-based materials on the capacitive performance of
electric double-layer capacitors. Published experimental datasets from 147 references (4899 data
entries) were extracted and then used to train and test the ML models, to determine the relative
importance of electrode material features on specific capacitance. These features include current
density, pore volume, pore size, presence of defects, potential window, specific surface area, oxygen,
and nitrogen content of the carbon-based electrode material. Additionally, categorical variables
as the testing method, electrolyte, and carbon structure of the electrodes are considered as well.
Among five applied regression models, an extreme gradient boosting model was found to best
correlate those features with the capacitive performance, highlighting that the specific surface area,
the presence of nitrogen doping, and the potential window are the most significant descriptors for
the specific capacitance. These findings are summarized in a modular and open-source application
for estimating the capacitance of supercapacitors given, as only inputs, the features of their carbon-
based electrodes, the electrolyte and testing method. In perspective, this work introduces a new wide
dataset of carbon electrodes for supercapacitors extracted from the experimental literature, also
giving an instance of how electrochemical technology can benefit from ML models.TRUEpu
From Experiments to Insights: A Journey in 5G New Radio Localization
Get PDFThe 3GPP has recently made the inclusion of positioning services a priority in future generations of cellular networks, thus providing an opportunity for these networks to serve as fertile ground for the emergence of new service-based applications. With the release of 3GPP Release 16 there has been an extensive standardization effort aimed at improving positioning capabilities in 5G networks, particularly
in terms of physical layer signals, measurement techniques, and network architecture. Despite these advances, the experimental evaluation of 5G positioning in real-world scenarios is still lagging behind, due to factors such as the slow integration of positioning technologies into open-source 5G frameworks,
the complexity of setting up a testbed for 5G positioning with multiple base stations (BSs), and the high cost associated with such a deployment. This article offers a comprehensive review of these factors and provides a state-of-the-art overview of 5G positioning and its support in SDR-based platforms. In addition,
we present guidance on the proper setup and configuration of a testbed for SDR-based multi-BS synchronized 5G positioning, the lessons we have learnt in the process, and through a series of time-based real-over-the-air measurements, we demonstrate how localization design choices can be effectively evaluated even with limited-size and low-cost SDR-based testbed.TRUEpu
Analysis of the Behavior Pattern of Energy Consumption through Online Clustering Techniques
Get PDFAnalyzing energy consumption is currently of great interest to define efficient energy management strategies. In particular, studying the evolution of the behavior of the consumption pattern can allow energy policies to be defined according to the time of year. In this sense, this work proposes to study the evolution of energy behavior patterns using online clustering techniques. In particular, the centroids of the groups constructed by the techniques will represent their consumption patterns. Specifically, two unsupervised online machine learning techniques ideal for the stated objective will be analyzed, X-Means and LAMDA, since they are capable of varying and adapting the number of clusters at runtime. These techniques are applied to energy consumption data in commercial buildings, making groupings on previous groups, in our case, monthly and quarterly. We compare their performance, to finish by analyzing the evolution of the patterns over time. The results are very promising since the quality of the consumption patterns obtained is very good according to the performance metrics. Thus, the three main contributions of this article are to propose an approach to determine energy consumption patterns using online non -supervised learning approaches, a methodology to analyze and explain the evolution of energy consumption using centroids of clusters, and a comparison strategy of online learning techniques. The online clustering techniques have qualities of the order of 0.59 and 0.41 for Silhouette and Davies-Boulding, respectively, for X-Means, and of the order of 0.71 and 0.24 for Silhouette and Davies-Boulding, respectively, for LAMDA, in different datasets of energy. The results are motivating, since very good results are obtained in terms of the quality of the clusters, particularly with LAMDA, therefore, analyzing its centroids as the patterns of user behaviors makes a lot of sense.TRUEpu
Mules and Permission Laundering in Android: Dissecting Custom Permissios in the Wild
Get PDFAndroid implements a permission system to regulate apps' access to system resources and sensitive user data. One salient feature of this system is its extensibility: apps can define their own custom permissions to expose features and data to other apps. However, little is known about how widespread the usage of custom permissions is, and what is the impact that these permissions can have on users' privacy and security. In this paper, we empirically study the usage of custom permissions at large scale, using a dataset of 2.2M pre-installed and app-store-downloaded apps. We find the usage of custom permissions to be widespread, and seemingly growing over time. Despite this prevalence, we find that custom permissions are virtually invisible to end users, and their purpose mostly undocumented. This lack of transparency can lead to serious security and privacy problems: we show that custom permissions can facilitate access to permission-protected system resources to apps that lack those permissions without user awareness. To detect this practice, we design and implement two static analysis tools, and highlight multiple concerning cases spotted in the wild. We conclude this study with a discussion of potential solutions to mitigate the privacy and security risks of custom permissions.Horizon EuropeSpanish Ministry of ScienceTRUEpu
Delirium detection using wearable sensors and machine learning in patients with intracerebral hemorrhage
Get PDFObjective: Delirium is associated with worse outcomes in patients with stroke and neurocritical illness, but delirium detection in these patients can be challenging with existing screening tools. To address this gap, we aimed to develop and evaluate machine learning models that detect episodes of post-stroke delirium based on data from wearable activity monitors in conjunction with stroke-related clinical features.
Design: Prospective observational cohort study.
Setting: Neurocritical Care and Stroke Units at an academic medical center.
Patients: We recruited 39 patients with moderate-to-severe acute intracerebral hemorrhage (ICH) and hemiparesis over a 1-year period [mean (SD) age 71.3 (12.20), 54% male, median (IQR) initial NIH Stroke Scale 14.5 (6), median (IQR) ICH score 2 (1)].
Measurements and main results: Each patient received daily assessments for delirium by an attending neurologist, while activity data were recorded throughout each patient’s hospitalization using wrist-worn actigraph devices (on both paretic and non-paretic arms). We compared the predictive accuracy of Random Forest, SVM and XGBoost machine learning methods in classifying daily delirium status using clinical information alone and combined with actigraph data. Among our study cohort, 85% of patients (n = 33) had at least one delirium episode, while 71% of monitoring days (n = 209) were rated as days with delirium. Clinical information alone had a low accuracy in detecting delirium on a day-to-day basis [accuracy mean (SD) 62% (18%), F1 score mean (SD) 50% (17%)]. Prediction performance improved significantly (p < 0.001) with the addition of actigraph data [accuracy mean (SD) 74% (10%), F1 score 65% (10%)]. Among actigraphy features, night-time actigraph data were especially relevant for classification accuracy.
Conclusions: We found that actigraphy in conjunction with machine learning models improves clinical detection of delirium in patients with stroke, thus paving the way to make actigraph-assisted predictions clinically actionable.Global Individual Fellowship Marie Skłodowska- Curie Action H2020-MSCA-IF-2020Rhode Island Foundation, Brown University’s Office of the Vice President for Research (OVPR)TRUEpu
PassiveLiFi Demonstration: Rethinking LiFi for Low-Power and Long-Range RF Backscatter
Get PDFPassiveLiFi Demonstration: Rethinking LiFi for Low-Power and Long-Range RF BackscatterEuropean UnionTRUEpu