IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
An In-Depth Analysis of COVID-19 Symptoms Considering the Co-Occurrence of Symptoms Using Clustering Algorithms
Get PDFA comprehensive analysis of the COVID-19 pandemic is necessary to prepare for future healthcare challenges. In this regard, the large number of datasets collected during the pandemic has allowed various studies on disease behavior and characteristics. For example, collected datasets can be used to extract knowledge about the symptomatic behavior of the disease. In this work, we are interested in analyzing the relationships between the different symptoms of the disease, considering various dimensions, such as countries, variants of COVID-19, and age groups. To this end, we consider the co-occurrence of symptoms as a fundamental element. More precisely, we implemented clustering techniques to discover symptomatic patterns across the various dimensions. For instance, in analyzing the dominant patterns, we observe that symptom congestion or runny nose almost always appears with the symptom muscle pain across many dimensions. Hence, the information on symptom patterns can be helpful in decision-making processes to detect and combat COVID-19 and similar diseases.SocialProbingTRUEpu
ORAN-Sense: Localizing Non-cooperative Transmitters with Spectrum Sensing and 5G O-RAN
Get PDFCrowdsensing networks for the sole purpose of performing spectrum measurements have resulted in prior initiatives that have failed primarily due to their costs for maintenance. In this paper, we take a different view and propose ORAN-Sense, a novel architecture of Internet of Things (IoT) spectrum crowdsensing devices integrated into the Next Generation of cellular networks. We use this framework to extend the capabilities of 5G networks and localize a transmitter that does not collaborate in the process of positioning. While 5G signals can not be applied to this scenario as the transmitter does not participate in the localization process through dedicated pilot symbols and data, we show how to use Time Difference of Arrival-based positioning using low-cost spectrum sensors, minimizing hardware impairments of low-cost spectrum receivers, introducing methods to address errors caused by over-the-air signal propagation, and proposing a low-cost synchronization technique. We have deployed our localization network in two major cities in Europe. Our experimental results indicate that signal localization of noncollaborative transmitters is feasible even using low-cost radio receivers with median accuracies of tens of meters with just a few sensors spanning cities, which makes it suitable for its integration in the Next Generation of cellular networks.Ministerio de Asuntos Económicos y Transformación DigitalMinisterio de UniversidadesTRUEpu
Explainable and Transferable Loss Meta-Learning for Zero-Touch Anticipatory Network Management
Get PDFZero-touch network management is one of the most ambitious yet strongly required paradigms for beyond 5G and 6G mobile communication systems. Achieving full automation requires a closed loop that combines (i) network status data collection and processing, (ii) predictive capabilities based on such data to anticipate upcoming needs, and (iii) effective decision making that best addresses such future needs through proper network control and orchestration. Recent seminal works have proposed approaches to jointly implement the last two phases above via a single deep learning model trained on past network status to directly optimize future decisions. This is achieved by designing custom loss functions that directly embed the management task objective. Experiments with real-world measurement data have demonstrated that this strategy leads to substantial performance gains across diverse network management tasks. In this paper, we go one step beyond the loss tailoring schemes above, and introduce a loss meta-learning paradigm that (i) reduces the need for human intervention at model design stage, (ii) eases explainability and transferability of trained deep learning models for network management, and (iii) outperforms custom losses across a range of controlled experiments and practical use cases.Regional Government of MadridEuropean UnionTRUEpu
Designing the Network Intelligence Stratum for 6G Networks
Get PDFAs network complexity escalates, there is an increasing need for more sophisticated methods to manage and operate these networks, focusing on enhancing efficiency, reliability, and security. A wide range of Artificial Intelligence (AI)/Machine Learning (ML) models are being developed in response. These models are pivotal in automating decision-making, conducting predictive analyses, managing networks proactively, enhancing security, and optimizing network performance. They are foundational in shaping the future of networks, collectively forming what is known as Network Intelligence (NI). Prominent Standard-Defining Organizations (SDOs) are integrating NI into future network architectures, particularly emphasizing the closed-loop approach. However, existing methods for seamlessly integrating NI into network architectures are not yet fully effective. This paper introduces an in-depth architectural design for a Network Intelligence Stratum (NI Stratum). This stratum is supported by a novel end-to-end NI orchestrator that supports closed-loop NI operations across various network domains. The primary goal of this design is to streamline the deployment and coordination of NI throughout the entire network infrastructure, tackling issues related to scalability, conflict resolution, and effective data management. We detail exhaustive workflows for managing the NI lifecycle and demonstrate a reference implementation of the NI Stratum, focusing on its compatibility and integration with current network systems and open-source platforms such as Kubernetes and Kubeflow, as well as on its validation on real-world environments. The paper also outlines major challenges and open issues in deploying and managing NI.European Union’s Horizon 2020TRUEpu
Setchain Algorithms for Blockchain Scalability
Get PDFThis paper introduces algorithms to implement Setchain, a reliable distributed object that relaxes strict transaction ordering by grouping transactions into epochs, significantly improving throughput and latency. It presents three implementations — Vanilla, Compresschain, and Hashchain — with Hashchain achieving the highest efficiency by using hash-based batch validation to reduce storage overhead and improve processing speed. An extensive empirical evaluation shows that Setchain outperforms traditional approaches, making it a promising solution for high-performance blockchain applications.TRUEinpres
Performance Analysis of NSUM Estimators in Social-Network Topologies
Get PDFThe Network Scale-up Methods (NSUM) are methods to estimate unknown populations based on indirect surveys in which the participants provide information about aggregated data of their acquaintances. This preserves the privacy and may lead to higher participation. During the last thirty years, new NSUM estimators have emerged. However, conditions related to the design of the experiments and the robustness of the estimators have not been studied in depth, especially in a realistic simulation environment. This study aims to compare nine NSUM estimators under relevant conditions in the literature through simulation experiments. We have analyzed how the NSUM is affected by the network topology, transmission and recall errors, the distribution of the unknown subpopulation, the number and sizes of subpopulations, and sample size. This article shows that some NSUM estimators barely used are better and more robust to some conditions, especially when the network is scale-free or under barrier effects. In addition, some methods are very sensitive to recall errors. In terms of the subpopulations configuration, we observe that the number of known subpopulations usually employed is quite large and that the most common NSUM is robust to the number and sizes of the subpopulations.TRUEpu
Deformity Removal from Handwritten Text Documents using Variable CycleGAN
Get PDFText recognition systems typically work well for printed documents but struggle with handwritten documents due to different writing styles, background complexities, added noise of image acquisition methods, and deformed text images such as strikeoffs and underlines. These deformities change the structural information, making it difficult to restore the deformed images while maintaining the structural information and preserving the semantic dependencies of the local pixels. Current adversarial networks are unable to preserve the structural and semantic dependencies as they focus on individual pixel-to-pixel variation and encourage non-meaningful aspects of the images. To address this, we propose a Variable Cycle Generative Adversarial Network (VCGAN) that considers the perceptual quality of the images. By using a variable Content Loss (Top-k Variable Loss (TVk) ), VCGAN preserves the inter-dependence of spatially close pixels while removing the strike-off strokes. The similarity of the images is computed with TVk considering the intensity variations that do not interfere with the semantic structures of the image. Our results show that VCGAN can remove most deformities with an elevated F1 score of 97.40% and outperforms current state-of-the-art algorithms with a character error rate of 7.64% and word accuracy of 81.53% when tested on the handwritten text recognition system.TRUEpu
A few-shot learning method based on knowledge graph in large language models
No full textThe emergence of large language models has significantly transformed natural language processing and text generation. Fine-tuning these models for specific domains enables them to generate answers tailored to the unique requirements of those fields, such as in legal or medical domains. However, these models often perform poorly in few-shot scenarios. Herein, the challenges of data scarcity in fine-tuning large language models in low-sample scenarios were addressed by proposing three different KDGI (Knowledge-Driven Dialog Generation Instances) generation strategies, including entity-based KDGI generation, relation-based KDGI generation, and semantic-based multi-level KDGI generation. These strategies aimed to enhance few-shot datasets to address the issue of low fine-tuning metrics caused by insufficient data. Specifically, knowledge graphs were utilized to define the distinct KDGI generation strategies for enhancing few-shot data. Subsequently, these KDGI data were employed to fine-tune the large language model using the P-tuning v2 approach. Through multiple experiments, the effectiveness of the three KDGI generation strategies was validated using BLEU and ROUGE metrics, and the fine-tuning benefits of few-shot learning on large language models were confirmed. To further evaluate the effectiveness of KDGI, additional experiments were conducted, including LoRA-based fine-tuning in the medical domain and comparative studies leveraging Mask Language Model augmentation, back-translation, and noise injection methods. Consequently, the paper proposes a reference method for leveraging knowledge graphs in prompt data engineering, which shows potential in facilitating few-shot learning for fine-tuning large language models.TRUEpu
Nowcasting Temporal Trends Using Indirect Surveys
Get PDFIndirect surveys, in which respondents provide information about other people they know, have been proposed for estimating (nowcasting) the size of a \emph{hidden population} where privacy is important or the hidden population is hard to reach.
Examples include estimating casualties in an earthquake, conditions among female sex workers, and the prevalence of drug use and infectious diseases.
The Network Scale-up Method (NSUM) is the classical approach to developing estimates from indirect surveys, but it was designed for one-shot surveys. Further, it requires certain assumptions and asking for or estimating the number of individuals in each respondent's network.
In recent years, surveys have been increasingly deployed online and can collect data continuously (e.g., COVID-19 surveys on Facebook during much of the pandemic). Conventional NSUM can be applied to these scenarios by analyzing the data independently at each point in time, but this misses the opportunity of leveraging the temporal dimension.
We propose to use the responses from indirect surveys collected over time and develop analytical tools (i) to prove that indirect surveys can provide better estimates for the trends of the hidden population over time, as compared to direct surveys and (ii) to identify appropriate temporal aggregations to improve the estimates. We demonstrate through extensive simulations that our approach outperforms traditional NSUM and direct surveying methods.
We also empirically demonstrate the superiority of our approach on a real indirect survey dataset of COVID-19 cases.Spanish State Research Agency - Spanish Ministry of Science and InnovationTRUEinpres
COVID-19 seroprevalence estimation and forecasting in the USA from ensemble machine learning models using a stacking strategy
No full textThe COVID-19 pandemic exposed the importance of research on the spread of epidemic diseases. In this paper, we apply Artificial Intelligence and statistics techniques to build prediction models to estimate the SARS-CoV-2 seroprevalence in the United States, using multiple estimates of COVID-19 prevalence and other explanatory variables. We propose the use of stacking techniques based on multiple model building techniques (Linear and Beta Regression, Genetic Programming and Neural Networks) to obtain Predictive Ensemble Models. There has been extensive research on this field, but there has not been in-depth research on the application of stacking methods to estimate and forecast seroprevalence in the USA specifically. This paper provides a novel comparison of the behaviour and performance of different building techniques for stacking ensemble models and presents which methods are better for different scenarios. We find that Genetic Programming and Neural Networks are the best models with trained data within single states, and when multiple states are considered Genetic Programming is still better than the Regression models, but Neural Networks fail to estimate the seroprevalence accurately. Another novelty of our work is the use of cross-state validation to evaluate the models with new data, as well as temporal forecasting. Depending on how the data is processed, Linear Regression performs very well with cross-state validation and temporal forecasting, and Genetic Programming is very accurate with the former while Neural Networks work better with the latter.TRUEpu