IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Characterizing 5G Adoption and its Impact on Network Traffic and Mobile Service Consumption
Get PDFThe roll out of 5G, coupled with the traffic monitoring capabilities of modern industry-grade networks, offers an unprecedented opportunity to closely observe the impact that the introduction of a new major wireless technology has on the end users.
In this paper, we seize such a unique chance, and carry out a first-of-its-kind in-depth analysis of 5G adoption along spatial, temporal and service dimensions. Leveraging massive measurement data about application-level demands collected in a nationwide 4G/5G network, we characterize the impact of the new technology on when, where and how mobile subscribers consume 5G traffic both in aggregate and for individual types of services.
This lets us unveil the overall incidence of 5G in the total mobile network traffic, its spatial and temporal fluctuations, its effect on the way 5G services are consumed, the way individual services and geographical locations contribute to fluctuations in the 5G demand, as well as surprising connections between socioeconomic status of local populations and the way the 5G technology is presently consumed.TRUEinpres
An explainable analysis of diabetes mellitus using statistical and artificial intelligence techniques
No full textBackground
Diabetes mellitus (DM) is a chronic disease prevalent worldwide, requiring a multifaceted analytical approach to improve early detection and subsequent mitigation of morbidity and mortality rates. This research aimed to develop an explainable analysis of DM by combining sociodemographic and clinical data with statistical and artificial intelligence (AI) techniques.
Methods
Leveraging a small dataset that includes sociodemographic and clinical profiles of diabetic and non-diabetic individuals, we employed a diverse set of statistical and AI models for predictive purposes and assessment of DM risk factors. The statistical tests used were Student’s t-test and Chi-square, while the AI techniques were fuzzy cognitive maps (FCM), artificial neural networks (ANN), support vector machines (SVM), and XGBoost.
Results
Our statistical models facilitated an in-depth exploration of variable associations, while the resulting AI models demonstrated exceptional efficacy in DM classification. In particular, the XGBoost model showed superior performance in accuracy, sensitivity and specificity with values of 1 for each of these metrics. On the other hand, the FCM stood out for its explainability capabilities by allowing an analysis of the variables involved in the prediction using scenario-based simulations.
Conclusions
An integrated analysis of DM using a variety of methodologies is critical for timely detection of the disease and informed clinical decision-making.TRUEpu
A Low-Complexity Standard-Compliant PAPR Reduction Scheme for OTFS Modulation
Get PDFOrthogonal Time Frequency Space (OTFS) modulation is widely recognized as a modulation scheme with advantageous properties for both radar and communication waveform designs. In OTFS, information symbols are mapped in the DelayDoppler (DD) domain leading to reliable communication in high Doppler channels. However, the presence of inverse-discrete Fourier Transform operation in OTFS architecture results in a high Peak-to-Average Power Ratio (PAPR) in the transmit OTFS frames. This paper introduces a novel metric-based symbol pre-distortion algorithm constrained by Error Vector Magnitude (EVM) limits to reduce the PAPR in OTFS modulation. The imposed constraint in the form of EVM limits establishes it
as a pragmatic method that adds no side-channel information rather exploits the available EVM limit usually kept in wireless standards. The pre-distortion applied to each symbol/sample in an OTFS frame is determined by the proposed metrics, representing the contribution of each symbol to peak values in the output. The proposed method is simple, flexible, and does not require additional complexity for symbol detection on the receiver end. Our simulation results demonstrate a significant reduction in the PAPR of OTFS blocks for both QPSK and 16-QAM modulation schemes. Furthermore, our proposed Constrained
Constellation Shaping scheme exhibits enhanced performance in PAPR reduction as the number of Doppler bins increases for an OTFS frame size.Ministerio de Asuntos Económicos y Transformación DigitalEuropean UnionTRUEpu
I love pineapple on pizza != I hate pineapple on pizza: Stance-Aware Sentence Transformers for Opinion Mining
Get PDFSentence transformers excel at grouping topically similar texts, but struggle to differentiate opposing viewpoints on the same topic. This shortcoming hinders their utility in applications where understanding nuanced differences in opinion is essential, such as those related to social and political discourse analysis. This paper addresses this issue by fine-tuning sentence transformers with arguments for and against human-generated controversial claims. We demonstrate how our fine-tuned model enhances the utility of sentence transformers for social computing tasks such as opinion mining and stance detection. We elaborate that applying stance-aware sentence transformers to opinion mining is a more computationally efficient approach in comparison to the classic classification-based approaches.UK's Research centre on Privacy, Harm Reduction & Adversarial Influence onlineSpanish Ministry of Science and InnovationESF Investing in your futureTRUEinpres
Encrypted Traffic Classification at Line Rate in Programmable Switches with Machine Learning
Get PDFEncrypted Traffic Classification (ETC) has become an important area of research with Machine Learning (ML) methods being the state-of-the-art. However, most existing solutions either rely on offline ETC based on collected network data or on online ETC with models running in the control plane of Software-Defined Networks (SDN), all of which do not run at line rate and would not meet latency requirements of time-sensitive applications in modern networks. This work leverages recent advances in data plane programmability to achieve real-time ETC in programmable switches at line rate, with high throughput and low latency. The proposed solution comprises (i) an ETC-aware Random Forest (RF) modelling process where only features based on packet size and packet arrival times are used, and (ii) an encoding of the trained RF model into production-grade P4-programmable switches. The performance of the proposed in-switch ETC framework is evaluated using 3 encrypted traffic datasets with experiments in a real-world testbed with Intel Tofino switches, in the presence of background traffic at 40 Gbps. Results show how the solution achieves high classification accuracy of up to 95%, with sub-microsecond delay, while consuming on average less than 10% of total available switch hardware resources.Smart Networks and Services Joint Undertaking (SNS JU) under the European Union’s Horizon Europe research and innovation programme under grant agreement no. 101139270European Union’s Horizon Europe research and innovation programme under Marie Skłodowska-Curie grant agreement no. 860239TRUEpu
Information-Theoretical Bounds on Privacy Leakage in Pruned Federated Learning
No full textModel pruning has been proposed as a technique for reducing the size and complexity of Federated learning (FL) models. By making local models coarser, pruning is intuitively expected to improve protection against privacy attacks. However, the level of this expected privacy protection has not been previously characterized, or optimised jointly with utility. In this paper, we investigate for the first time the privacy impact of model pruning in FL. We establish information-theoretic upper bounds on the information leakage from pruned FL and we experimentally validate them under state-of-the-art privacy attacks across different FL pruning schemes.
This evaluation provides valuable insights into the choices and parameters that can affect the privacy protection provided by pruning.TRUEpu
Mean-Field Multi-Agent Contextual Bandit for Energy-Efficient Resource Allocation in vRANs
Get PDFRadio Access Network (RAN) virtualization, key for new-generation mobile networks, requires Hardware Accelerators (HAs) that swiftly process wireless signals from Base Stations (BSs) to meet stringent reliability targets. However, HAs are expensive and energy-hungry, which increases costs and has serious environmental implications. To address this problem, we gather data from our experimental platform and compare the performance and energy consumption of a HA (NVIDIA GPU V100) vs. a CPU (Intel Xeon Gold 6240R, 16 cores) for energy-friendly software processing. Based on the insights obtained from
this data, we devise a strategy to offload workloads to HAs opportunistically to save energy while preserving reliability. This offloading strategy, however, needs to be configured in near-real-time for every BS sharing common computational resources. This renders a challenging multi-agent collaborative problem in which the number of involved agents (BSs) can be arbitrarily large and can change over time. Thus, we propose an efficient multi-agent contextual bandit algorithm called ECORAN, which applies concepts from mean field theory to be fully scalable. Using a real platform and traces from a production mobile network, we show that ECORAN can provide up to 40% energy savings with respect to the approach used today by the industry.European Commission through Grant No. SNS-JU-101097083 (BeGREEN), 101139270 (ORIGAMI), and 101017109 (DAEMON)TRUEinpres
SPRING+: Smartphone Positioning from a Single WiFi Access Point
Get PDFIndoor positioning is a major challenge for location-based
services. WiFi deployments are often used to address indoor positioning.
Yet, they require multiple access points, which may not be available
or accessible for localization in all scenarios, or they make unrealistic
assumptions for practical deployments. In this paper we present
SPRING+, a positioning system that extracts and processes Channel
State Information (CSI) and Fine Time Measurements (FTM) from a
single Access Point (AP) to localize commercial smartphones. First, we
propose an adaptive method for estimating the Angle of Arrival (AOA)
from CSI that works on single packets and leverages information from
the estimated number of paths. Second, we present a new method
to detect the first path using FTM measurements, robust to multipath
scenarios. We evaluate SPRING+ in an extensive experimental campaign
consisting of four different testbeds: i) generic indoor spaces, ii)
generic indoor spaces with obstacles, iii) office environments and iv)
home environments. Our results show that SPRING+ is able to achieve
a median 2D positioning error between 1 and 1.8 meters with a single
WiFi AP.TRUEpu
Mobile App Consumption and Political Orientation
Get PDFElections are a cornerstone of democratic societies, and their outcome has important implications on the lives of citizens and on the interior and foreign politics of a country.
Understanding biases in the political orientation of the electorate plays a key role in assessing the health of the voting process and the reasons underlying the preferences of voters.
Traditionally, political orientation has been studied through the lenses of the socioeconomic status of voters, i.e., their education level, type of occupation, wealth, or age.
In this work, we take an original perspective and factor in mobile app usage as a different yet primary indicator of the vote decision. To this end, we explore the relationship between the 2019 European parliamentary election results in approximately 4,000 urban communes in France and the associated consumption of a wide range of mobile services.
Our results show how app usage provides complementary information to the socioeconomic status and can feed a Dirichlet regression that is up to 21% more accurate in predicting the multiparty election outcome.Comunidad de MadridFrench National Research AgencyTRUEinpres
Regret Bounds for Online Learning for Hierarchical Inference
Get PDFHierarchical Inference (HI) has emerged as a promising approach for efficient distributed inference between end devices deployed with small pre-trained Deep Learning (DL) models and edge/cloud servers running large DL models. Under HI, a device uses the local DL model to perform inference on the data samples it collects, and only the data samples on which this inference is likely to be incorrect are offloaded to a remote DL model running on the server. Thus, gauging the likelihood of incorrect local inference is key to implementing HI. A natural approach is to compute a confidence metric for the local DL inference and then use a threshold on this confidence metric to determine whether to offload or not. Recently, the HI online learning problem was studied to learn an optimal threshold for the confidence metric over a sequence of data samples collected over time. However, existing algorithms have computation complexity that grows with the number of rounds and do not exhibit a sub-linear regret bound. In this work, we propose the Hedge-HI algorithm and prove that it has O\left(T^\frac{2}{3}\E_\Z[N_T]^\frac{1}{3}\right) regret, where is the number of rounds, and is the number of distinct confidence metric values observed till round . Further, under a mild assumption, we propose Hedge-HI-Restart, which has an O\left(T^\frac{2}{3}\log (\E_\Z[ N_T])^\frac{1}{3}\right) regret bound with high probability and has a much lower computation complexity that grows sub-linearly in the number of rounds. Using runtime measurements on Raspberry Pi, we demonstrate that Hedge-HI-Restart has a runtime lower by order of magnitude and achieves cumulative loss close to that of the alternatives.TRUEpu