Search

Mobility performance has been a key focus in cellular networks up to 5G. To enhance handover (HO) performance, 3GPP introduced Conditional Handover (CHO) and Layer 1/Layer 2 Triggered Mobility (LTM) mechanisms in 5G. While these reactive HO strategies address the trade-off between HO failures (HOF) and ping-pong effects, they often result in inefficient radio resource utilization due to additional HO preparations. To overcome these challenges, this article proposes a proactive HO framework for mobility management in O-RAN, leveraging user-cell link predictions to identify the optimal target cell for HO. We explore various categories of Graph Neural Networks (GNNs) for link prediction and analyze the complexity of applying them to the mobility management domain. Two GNN models are compared using a real-world dataset, with experimental results demonstrating their ability to capture the dynamic and graph-structured nature of cellular networks. Finally, we present key insights from our study and outline future steps to enable the integration of GNN-based link prediction for mobility management in 6G networks., Comment: 7 pages, 2 figures, 2 tables. Submitted to IEEE Vehicular Technology Magazine, Special Issue on "AI for 6G O-RAN Intelligent, Cost-Efficient and Secure Automation"

An exact analytical expression for the bending angle of light due to a non-rotating massive object, considering the actual distances from source and observer to the gravitational mass, is derived. Our novel formula generalizes Darwin well-known equation for gravitational light bending [Proc. R. Soc. London A 263, 39-50 (1961)], where both source and observer are placed at infinite distance from the lensing mass, and provides excellent results in comparison with the post Newtonian (PPN) formalism up to first order. As a result, the discrepancy between our recent expression and the PPN approach is 6.6 mas for sun-grazing beams coming from planet Mercury, with significant differences up to 2 mas for distant starlight. Our findings suggest that these considerations should not be dismissed for both solar system objects and extragalactic sources, where non-negligible errors might be present in ultraprecise astrometry calculations., Comment: Accepted for publication in Monthly Notices of the Royal Astronomical Society

Bayesian inference for inverse problems hinges critically on the choice of priors. In the absence of specific prior information, population-level distributions can serve as effective priors for parameters of interest. With the advent of machine learning, the use of data-driven population-level distributions (encoded, e.g., in a trained deep neural network) as priors is emerging as an appealing alternative to simple parametric priors in a variety of inverse problems. However, in many astrophysical applications, it is often difficult or even impossible to acquire independent and identically distributed samples from the underlying data-generating process of interest to train these models. In these cases, corrupted data or a surrogate, e.g. a simulator, is often used to produce training samples, meaning that there is a risk of obtaining misspecified priors. This, in turn, can bias the inferred posteriors in ways that are difficult to quantify, which limits the potential applicability of these models in real-world scenarios. In this work, we propose addressing this issue by iteratively updating the population-level distributions by retraining the model with posterior samples from different sets of observations, and we showcase the potential of this method on the problem of background image reconstruction in strong gravitational lensing when score-based models are used as data-driven priors. We show that, starting from a misspecified prior distribution, the updated distribution becomes progressively closer to the underlying population-level distribution, and the resulting posterior samples exhibit reduced bias after several updates., Comment: 20 pages, 15 figures. To be published in The Astrophysical Journal. Added and updated references; fixed typos; extended discussions in some sections. Results unchanged

Gravitational lensing is the deflection of light rays due to the gravity of intervening masses. This phenomenon is observed in a variety of scales and configurations, involving any non-uniform mass such as planets, stars, galaxies, clusters of galaxies, and even the large scale structure of the universe. Strong lensing occurs when the distortions are significant and multiple images of the background source are observed. The lens objects must align on the sky of order ~1 arcsecond for galaxy-galaxy lensing, or 10's of arcseonds for cluster-galaxy lensing. As the discovery of lens systems has grown to the low thousands, these systems have become pivotal for precision measurements and addressing critical questions in astrophysics. Notably, they facilitate the measurement of the Universe's expansion rate, dark matter, supernovae, quasars, and the first stars among other topics. With future surveys expected to discover hundreds of thousands of lensing systems, the modelling and simulation of such systems must occur at orders of magnitude larger scale then ever before. Here we present `caustics`, a Python package designed to handle the extensive computational demands of modeling such a vast number of lensing systems., Comment: 13 pages, 3 figures, submitted to JOSS

Urban heat islands, defined as specific zones exhibiting substantially higher temperatures than their immediate environs, pose significant threats to environmental sustainability and public health. This study introduces a novel machine-learning model that amalgamates data from the Sentinel-3 satellite, meteorological predictions, and additional remote sensing inputs. The primary aim is to generate detailed spatiotemporal maps that forecast the peak temperatures within a 24-hour period in Turin. Experimental results validate the model's proficiency in predicting temperature patterns, achieving a Mean Absolute Error (MAE) of 2.09 degrees Celsius for the year 2023 at a resolution of 20 meters per pixel, thereby enriching our knowledge of urban climatic behavior. This investigation enhances the understanding of urban microclimates, emphasizing the importance of cross-disciplinary data integration, and laying the groundwork for informed policy-making aimed at alleviating the negative impacts of extreme urban temperatures., Comment: 4 pages, submitted to IEEE MetroLivEnv 2024 conference

Very-High Resolution (VHR) remote sensing imagery is increasingly accessible, but often lacks annotations for effective machine learning applications. Recent foundation models like GroundingDINO and Segment Anything (SAM) provide opportunities to automatically generate annotations. This study introduces FMARS (Foundation Model Annotations in Remote Sensing), a methodology leveraging VHR imagery and foundation models for fast and robust annotation. We focus on disaster management and provide a large-scale dataset with labels obtained from pre-event imagery over 19 disaster events, derived from the Maxar Open Data initiative. We train segmentation models on the generated labels, using Unsupervised Domain Adaptation (UDA) techniques to increase transferability to real-world scenarios. Our results demonstrate the effectiveness of leveraging foundation models to automatically annotate remote sensing data at scale, enabling robust downstream models for critical applications. Code and dataset are available at \url{https://github.com/links-ads/igarss-fmars}., Comment: Accepted at IGARSS 2024, 5 pages. Revised and corrected version

Rapid detection and well-timed intervention are essential to mitigate the impacts of wildfires. Leveraging remote sensed data from satellite networks and advanced AI models to automatically detect hotspots (i.e., thermal anomalies caused by active fires) is an effective way to build wildfire monitoring systems. In this work, we propose a novel dataset containing time series of remotely sensed data related to European fire events and a Self-Supervised Learning (SSL)-based model able to analyse multi-temporal data and identify hotspots in potentially near real time. We train and evaluate the performance of our model using our dataset and Thraws, a dataset of thermal anomalies including several fire events, obtaining an F1 score of 63.58.

Air pollution poses a significant threat to public health and well-being, particularly in urban areas. This study introduces a series of machine-learning models that integrate data from the Sentinel-5P satellite, meteorological conditions, and topological characteristics to forecast future levels of five major pollutants. The investigation delineates the process of data collection, detailing the combination of diverse data sources utilized in the study. Through experiments conducted in the Milan metropolitan area, the models demonstrate their efficacy in predicting pollutant levels for the forthcoming day, achieving a percentage error of around 30%. The proposed models are advantageous as they are independent of monitoring stations, facilitating their use in areas without existing infrastructure. Additionally, we have released the collected dataset to the public, aiming to stimulate further research in this field. This research contributes to advancing our understanding of urban air quality dynamics and emphasizes the importance of amalgamating satellite, meteorological, and topographical data to develop robust pollution forecasting models., Comment: 5 pages, 2 figures, submitted to IEEE MetroLivEnv 2024

A locally conformally product (LCP) structure on a compact conformal manifold is a closed non-exact Weyl connection (i.e.~a linear connection which is locally but not globally the Levi-Civita connection of Riemannian metrics in the conformal class), with reducible holonomy. A left-invariant LCP structure on a compact quotient $\Gamma\backslash G$ of a simply connected Riemannian Lie group $(G,g)$ with Lie algebra $\mathfrak{g}$ can be characterized in terms of a closed 1-form $\theta\in\mathfrak{g}^*$ and a non-zero subspace $\mathfrak{u}\subset \mathfrak{g}$ satisfying some algebraic conditions. We show that these conditions are equivalent to the fact that $\mathfrak{g}$ is isomorphic to a semidirect product of a non-unimodular Lie algebra acting on an abelian one by a conformal representation. This extends to the general case previous results holding for solvmanifolds. In addition, we construct explicit examples of compact LCP manifolds which are not solvmanifolds., Comment: 23 pages

Deep learning based approaches have been used to improve image quality in cone-beam computed tomography (CBCT), a medical imaging technique often used in applications such as image-guided radiation therapy, implant dentistry or orthopaedics. In particular, while deep learning methods have been applied to reduce various types of CBCT image artifacts arising from motion, metal objects, or low-dose acquisition, a comprehensive review summarizing the successes and shortcomings of these approaches, with a primary focus on the type of artifacts rather than the architecture of neural networks, is lacking in the literature. In this review, the data generation and simulation pipelines, and artifact reduction techniques are specifically investigated for each type of artifact. We provide an overview of deep learning techniques that have successfully been shown to reduce artifacts in 3D, as well as in time-resolved (4D) CBCT through the use of projection- and/or volume-domain optimizations, or by introducing neural networks directly within the CBCT reconstruction algorithms. Research gaps are identified to suggest avenues for future exploration. One of the key findings of this work is an observed trend towards the use of generative models including GANs and score-based or diffusion models, accompanied with the need for more diverse and open training datasets and simulations., Comment: 16 pages, 4 figures, 1 Table, published in IEEE Access Journal

Thanks to evolving cellular telecommunication networks, providers can deploy a wide range of services. Soon, 5G mobile networks will be available to handle all types of services and applications for vast numbers of users through their mobile equipment. To effectively manage new 5G systems, end-to-end (E2E) performance analysis and optimization will be key features. However, estimating the end-user experience is not an easy task for network operators. The amount of end-user performance information operators can measure from the network is limited, complicating this approach. Here we explore the calculation of service metrics [known as key quality indicators (KQIs)] from classic low-layer measurements and parameters. We propose a complete machine-learning (ML) modeling framework. This system's low-layer metrics can be applied to measure service-layer performance. To assess the approach, we implemented and evaluated the proposed system on a real cellular network testbed.

Aircraft are composed of many electronic systems: sensors, displays, navigation equipment and communication elements. These elements require a reliable interconnection, which is a major challenge for communication networks as high reliability and predictability requirements must be verified for safe operation. In addition, their verification via hardware deployments is limited because these are costly and make difficult to try different architectures and configurations, thus delaying the design and development in this area. Therefore, verification at early stages in the design process is of great importance and must be supported by simulation. In this context, this work presents an event-driven link level framework and simulator for the validation of avionics networks. The presented tool supports communication protocols such as Avionics Full-Duplex Switched Ethernet (AFDX), which is a common protocol in avionics, as well as Ethernet, used with static routing. Alsa, accurate results are facilitated by the simulator through the utilization of realistic models for the different devices. The proposed platform is evaluated in Clean Sky's Disruptive Cockpit for Large Passenger Aircraft architecture scenario showing capabilities of the simulator. The speed of the verification is a key factor in its application, so the computational cost is analysed, proving that the execution time is linearly dependent on the number of messages sent.

Objective. A detailed analysis of the corneal retardation time $\tau$ as a highly related parameter to the intraocular pressure (IOP), and its plausible role as an indicator of ocular hypertension disease. Approach. A simple theoretical expression for $\tau$ is derived within the corneal viscoelastic model of Kelvin-Voigt with 3 elements. This retardation time can be easily calculated from the well-known signal and pressure amplitudes of non-contact tonometers like the Ocular Response Analyzer (ORA). Then, a population-based study was performed where 100 subjects aged from 18 to 30 were analyzed (within this group, about 10% had an elevated IOP with more than 21 mmHg). Main results. A clear relationship between the corneal retardation time and the corneal-compensated intraocular pressure was found, underlying the risk for ocular hypertensive (OHT) subjects with lower $\tau$ values to develop hypertension illnesses (due to the inability of poorly viscoelastic corneas to absorb IOP fluctuations, resulting in probable optic nerve damage). Significance. Our results might provide an useful tool to systematically discern which OHT patients (and even those with normal IOP values) are more likely to suffer glaucoma progression and, consequently, ensure an early diagnosis., Comment: Accepted for publication in Biomedical Physics and Engineering Express

This comprehensive study delves into the realm of indoor positioning technologies within the domain of Smart Education (SE). Focusing on typical techniques and technologies in educational settings, the research emphasizes the importance and potential services of localization in SE. Moreover, this work explores the feasibility and limitations of these technologies, providing a detailed account of their role in educational settings. The paper also contains in an innovative Proof of Concept (PoC), demonstrating an automatic attendance control (AAC) system that integrates 5G and WiFi technologies. This PoC effectively showcases the possibilities and effectiveness of location-based services in educational surroundings even with a limited budget, setting the stage for optimizing teaching time, enhancing the quality of education., Comment: 14 pages, 11 figures, 2 tables

The spin-reversal in dilute Li$_2$(Li$_{1-x}$Fe$_{x}$)N with $x < 1$ % is dominated by resonant quantum tunneling of spatially well-separated states. We report on the effect of finite couplings between those states that give rise to cooperative, simultaneous quantum tunneling of two spins. This phenomenon, known as spin-spin cross relaxation, effectively elucidates the fine-structure observed in isothermal magnetization loops, a previously unresolved aspect. Temperature and field-dependent magnetization measurements were conducted over a range from T = 2 K to 300 K in applied fields of up to $\mu_0H$ = 7 T. Magnetic dipole fields are computed numerically. Our findings affirm the absence of stoichiometric defects in Li$_2$(Li$_{1-x}$Fe$_{x}$)N and underscore its exemplary suitability as a model system for investigating spin-reversal processes at the microscopic level. This is attributed to its comparatively simple crystal structure, the availability of large single crystals, elevated characteristic energies, and well-defined energy levels, Comment: 9 pages, 7 figures

In recent years, wildfires have posed a significant challenge due to their increasing frequency and severity. For this reason, accurate delineation of burned areas is crucial for environmental monitoring and post-fire assessment. However, traditional approaches relying on binary segmentation models often struggle to achieve robust and accurate results, especially when trained from scratch, due to limited resources and the inherent imbalance of this segmentation task. We propose to address these limitations in two ways: first, we construct an ad-hoc dataset to cope with the limited resources, combining information from Sentinel-2 feeds with Copernicus activations and other data sources. In this dataset, we provide annotations for multiple tasks, including burned area delineation and land cover segmentation. Second, we propose a multitask learning framework that incorporates land cover classification as an auxiliary task to enhance the robustness and performance of the burned area segmentation models. We compare the performance of different models, including UPerNet and SegFormer, demonstrating the effectiveness of our approach in comparison to standard binary segmentation., Comment: Accepted at ECML PKDD 2023 - MACLEAN Workshop (11 pages, 3 figures)

The increasing frequency of catastrophic natural events, such as wildfires, calls for the development of rapid and automated wildfire detection systems. In this paper, we propose a wildfire identification solution to improve the accuracy of automated satellite-based hotspot detection systems by leveraging multiple information sources. We cross-reference the thermal anomalies detected by the Moderate-resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS) hotspot services with the European Forest Fire Information System (EFFIS) database to construct a large-scale hotspot dataset for wildfire-related studies in Europe. Then, we propose a novel multimodal supervised machine learning approach to disambiguate hotspot detections, distinguishing between wildfires and other events. Our methodology includes the use of multimodal data sources, such as the ERSI annual Land Use Land Cover (LULC) and the Copernicus Sentinel-3 data. Experimental results demonstrate the effectiveness of our approach in the task of wildfire identification., Comment: Accepted at IGARSS 2023, short paper (4 pages)

The human brain is the substrate for human intelligence. By simulating the human brain, artificial intelligence builds computational models that have learning capabilities and perform intelligent tasks approaching the human level. Deep neural networks consist of multiple computation layers to learn representations of data and improve the state-of-the-art in many recognition domains. However, the essence of intelligence commonly represented by both humans and AI is unknown. Here, we show that the nature of intelligence is a series of mathematically functional processes that minimize system entropy by establishing functional relationships between datasets over the space and time. Humans and AI have achieved intelligence by implementing these entropy-reducing processes in a reinforced manner that consumes energy. With this hypothesis, we establish mathematical models of language, unconsciousness and consciousness, predicting the evidence to be found by neuroscience and achieved by AI engineering. Furthermore, a conclusion is made that the total entropy of the universe is conservative, and the intelligence counters the spontaneous processes to decrease entropy by physically or informationally connecting datasets that originally exist in the universe but are separated across the space and time. This essay should be a starting point for a deeper understanding of the universe and us as human beings and for achieving sophisticated AI models that are tantamount to human intelligence or even superior. Furthermore, this essay argues that more advanced intelligence than humans should exist if only it reduces entropy in a more efficient energy-consuming way.

Land cover (LC) segmentation plays a critical role in various applications, including environmental analysis and natural disaster management. However, generating accurate LC maps is a complex and time-consuming task that requires the expertise of multiple annotators and regular updates to account for environmental changes. In this work, we introduce SPADA, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation. Performance evaluations using reliable ground truths, such as LUCAS and Urban Atlas, demonstrate the technique's effectiveness. SPADA outperforms state-of-the-art semantic segmentation approaches as well as third-party products, achieving a mean Intersection over Union (IoU) score of 42.86 and an F1 score of 67.93 on Urban Atlas and LUCAS, respectively., Comment: 4 pages, short paper. Accepted to IGARSS 2023

We study the G$_2$-instanton condition for a family of metric connections arisen from the characteristic connection, on $7$-dimensional $2$-step nilpotent Lie groups with left-invariant coclosed G$_2$-structures. According to the dimension of the commutator subgroup, we establish necessary and sufficient conditions for the connection to be an instanton, in terms of the torsion of the G$_2$-structure, the torsion of the connection and the Lie group structure.Moreover, we show that in our setup, G$_2$-instantons define a naturally reductive structure on the simply connected $2$-step nilpotent Lie group with left-invariant Riemannian metric. Taking quotient by lattices, one obtains G$_2$-instantons on compact nilmanifolds., Comment: 37 pages. Comments are welcome. v2: Minor changes, references added

In this paper, we present a pilot study aiming to investigate the challenges of teaching AI and Robotics to children in low- and middle-income countries. Challenges such as the little to none experts and the limited resources in a Mexican town to teach AI and Robotics were addressed with the creation of inclusive learning activities with Montessori method and open-source educational robots. For the pilot study, we invited 14 participants of which 10 were able to attend, 6 male and 4 female of (age in years: mean=8 and std=$\pm$1.61) and four instructors of different teaching experience levels to young audiences. We reported results of a four-lesson curriculum that is both inclusive and engaging. We showed the impact on the increase of general agreement of participants on the understanding of what engineers and scientists do in their jobs, with engineering attitudes surveys and Likert scale charts from the first and the last lesson. We concluded that this pilot study helped children coming from low- to mid-income families to learn fundamental concepts of AI and Robotics and aware them of the potential of AI and Robotics applications which might rule their adult lives. Future work might lead (a) to have better understanding on the financial and logistical challenges to organise a workshop with a major number of participants for reliable and representative data and (b) to improve pretest-posttest survey design and its statistical analysis. The resources to reproduce this work are available at \url{https://github.com/air4children/dei-hri2023}.