Search

This paper introduces a novel supervised classification strategy that integrates functional data analysis (FDA) with tree-based methods, addressing the challenges of high-dimensional data and enhancing the classification performance of existing functional classifiers. Specifically, we propose augmented versions of functional classification trees and functional random forests, incorporating a new tool for assessing the importance of functional principal components. This tool provides an ad-hoc method for determining unbiased permutation feature importance in functional data, particularly when dealing with correlated features derived from successive derivatives. Our study demonstrates that these additional features can significantly enhance the predictive power of functional classifiers. Experimental evaluations on both real-world and simulated datasets showcase the effectiveness of the proposed methodology, yielding promising results compared to existing methods., Comment: 33 pages

The advent of big data has raised significant challenges in analysing high-dimensional datasets across various domains such as medicine, ecology, and economics. Functional Data Analysis (FDA) has proven to be a robust framework for addressing these challenges, enabling the transformation of high-dimensional data into functional forms that capture intricate temporal and spatial patterns. However, despite advancements in functional classification methods and very high performance demonstrated by combining FDA and ensemble methods, a critical gap persists in the literature concerning the transparency and interpretability of black-box models, e.g. Functional Random Forests (FRF). In response to this need, this paper introduces a novel suite of explainability tools to illuminate the inner mechanisms of FRF. We propose using Functional Partial Dependence Plots (FPDPs), Functional Principal Component (FPC) Probability Heatmaps, various model-specific and model-agnostic FPCs' importance metrics, and the FPC Internal-External Importance and Explained Variance Bubble Plot. These tools collectively enhance the transparency of FRF models by providing a detailed analysis of how individual FPCs contribute to model predictions. By applying these methods to an ECG dataset, we demonstrate the effectiveness of these tools in revealing critical patterns and improving the explainability of FRF., Comment: 33 pages

Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition -- the use of machines to understand sounds. They feature several advantages over traditional pipelines: among others, the ability to consolidate multiple tasks in a single model, the option to leverage knowledge from other modalities, and the readily-available interaction with human users. Naturally, these promises have created substantial excitement in the audio community, and have led to a wave of early attempts to build new, general-purpose foundation models for audio. In the present contribution, we give an overview of computational audio analysis as it transitions from traditional pipelines towards auditory foundation models. Our work highlights the key operating principles that underpin those models, and showcases how they can accommodate multiple tasks that the audio community previously tackled separately.

We prove a finite-dimensional moment map property for certain canonical relatively K\"ahler metrics on holomorphic fibrations, called optimal symplectic connections. We then relate the existence of zeroes of this moment map to the stability of the fibration, where the stability property we consider is a version of K-stability that takes into account the fibration structure, first introduced by Dervan--Sektnan. In particular, we prove that a stable deformation of a fibration admitting an optimal symplectic connection still admits an optimal symplectic connection, through a new approach using the finite-dimensional moment map properties and the moment map flow. We include an appendix with a proof of a result considered by Sz\'ekelyhidi that a K-polystable deformation of a constant scalar curvature K\"ahler manifold still admits a constant scalar curvature metric, using the same technique., Comment: 27 pages

Social network analysis (SNA) helps us understand the relationships and interactions between individuals, groups, organizations, or other social entities. In the literature, ties are generally considered binary or weighted based on their strength. Nonetheless, when the actors are individuals, these relationships are often imprecise, and identifying them with simple scalars leads to information loss. Indeed, social relationships are often vague in real life, and although previous research has proposed the use of fuzzy networks, these are typically characterized by crisp ties. The use of weighted links does not align with the original philosophy of fuzzy logic, which instead aims to preserve the vagueness inherent in human language and real life. For this reason, this paper proposes a generalization of the so-called Fuzzy Social Network Analysis (FSNA) to the context of imprecise relationships among actors. Dealing with imprecise ties and introducing fuzziness in the definition of relationships requires an extension of social network analysis, defining ties as fuzzy numbers instead of crisp values and extending classical centrality indices to fuzzy centrality indexes. The article presents the theory and application of real data collected through a fascinating mouse-tracking technique to study the fuzzy relationships in a collaboration network among the members of a university department., Comment: 24 pages

In this paper, we propose a method for online domain-incremental learning of acoustic scene classification from a sequence of different locations. Simply training a deep learning model on a sequence of different locations leads to forgetting of previously learned knowledge. In this work, we only correct the statistics of the Batch Normalization layers of a model using a few samples to learn the acoustic scenes from a new location without any excessive training. Experiments are performed on acoustic scenes from 11 different locations, with an initial task containing acoustic scenes from 6 locations and the remaining 5 incremental tasks each representing the acoustic scenes from a different location. The proposed approach outperforms fine-tuning based methods and achieves an average accuracy of 48.8% after learning the last task in sequence without forgetting acoustic scenes from the previously learned locations., Comment: Accepted to EUSIPCO 2024

We give a necessary and sufficient condition for the projectivisation of a slope semistable vector bundle to admit constant scalar curvature K\"ahler (cscK) metrics in adiabatic classes, when the base admits a constant scalar curvature metric. More precisely, we introduce a stability condition on vector bundles, which we call adiabatic slope stability, which is a weaker version of K-stability and involves only test configurations arising from subsheaves of the bundle. We prove that, for a simple vector bundle with locally free graded object, adiabatic slope stability is equivalent to the existence of cscK metrics on the projectivisation, which solves a problem that has been open since work of Ross--Thomas. In particular, this shows that the existence of cscK metrics is equivalent to K-stability in this setting. We provide a numerical criterion for the Donaldson-Futaki invariant associated to said test configurations in terms of Chern classes of the vector bundle. This criterion is computable in practice and we present an explicit example satisfying our assumptions which is coming from a vector bundle that does not admit a Hermite-Einstein metric., Comment: 43 pages

The Detection and Classification of Acoustic Scenes and Events Challenge Task 4 aims to advance sound event detection (SED) systems in domestic environments by leveraging training data with different supervision uncertainty. Participants are challenged in exploring how to best use training data from different domains and with varying annotation granularity (strong/weak temporal resolution, soft/hard labels), to obtain a robust SED system that can generalize across different scenarios. Crucially, annotation across available training datasets can be inconsistent and hence sound labels of one dataset may be present but not annotated in the other one and vice-versa. As such, systems will have to cope with potentially missing target labels during training. Moreover, as an additional novelty, systems will also be evaluated on labels with different granularity in order to assess their robustness for different applications. To lower the entry barrier for participants, we developed an updated baseline system with several caveats to address these aforementioned problems. Results with our baseline system indicate that this research direction is promising and is possible to obtain a stronger SED system by using diverse domain training data with missing labels compared to training a SED system for each domain separately.

This article describes the Data-Efficient Low-Complexity Acoustic Scene Classification Task in the DCASE 2024 Challenge and the corresponding baseline system. The task setup is a continuation of previous editions (2022 and 2023), which focused on recording device mismatches and low-complexity constraints. This year's edition introduces an additional real-world problem: participants must develop data-efficient systems for five scenarios, which progressively limit the available training data. The provided baseline system is based on an efficient, factorized CNN architecture constructed from inverted residual blocks and uses Freq-MixStyle to tackle the device mismatch problem. The task received 37 submissions from 17 teams, with the large majority of systems outperforming the baseline. The top-ranked system's accuracy ranges from 54.3% on the smallest to 61.8% on the largest subset, corresponding to relative improvements of approximately 23% and 9% over the baseline system on the evaluation set., Comment: Task Description Page: https://dcase.community/challenge2024/task-data-efficient-low-complexity-acoustic-scene-classification

Sound Event Detection and Localization (SELD) is a combined task of identifying sound events and their corresponding direction-of-arrival (DOA). While this task has numerous applications and has been extensively researched in recent years, it fails to provide full information about the sound source position. In this paper, we overcome this problem by extending the task to Sound Event Detection, Localization with Distance Estimation (3D SELD). We study two ways of integrating distance estimation within the SELD core - a multi-task approach, in which the problem is tackled by a separate model output, and a single-task approach obtained by extending the multi-ACCDOA method to include distance information. We investigate both methods for the Ambisonic and binaural versions of STARSS23: Sony-TAU Realistic Spatial Soundscapes 2023. Moreover, our study involves experiments on the loss function related to the distance estimation part. Our results show that it is possible to perform 3D SELD without any degradation of performance in sound event detection and DOA estimation., Comment: This paper has been accepted for the 32nd European Signal Processing Conference EUSIPCO 2024 in Lyon

Patient triage plays a crucial role in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. Recently, a growing interest has been focused on leveraging artificial intelligence (AI) to develop algorithms able to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI based module to manage patients emergency code assignments in emergency departments. It uses emergency department historical data to train the medical decision process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, are used to accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

The Spectrometer/Telescope for Imaging X-rays (STIX) is a hard X-ray imaging spectrometer on board the ESA and NASA heliospheric mission Solar Orbiter. STIX has been operational for three years and has observed X-ray emission from ~35,000 solar flares. Throughout its lifetime, Solar Orbiter has been frequently struck by a high flux of energetic particles usually of flare origin, or from coronal mass ejection shocks. These Solar Energetic Particles (SEPs) are detected on board by the purpose-built energetic particle detector instrument suite. During SEP events, the X-ray signal is also contaminated in STIX. This work investigates the effect of these particles on the STIX instrument for two events. The first event occurred during an interplanetary shock crossing and the second event occurred when Solar Orbiter passed through Earth's radiation belts while performing a gravity assist maneuver. The induced spectra consist of tungsten fluorescence emission lines and secondary Bremsstrahlung emission produced by incident particles interacting with spacecraft components. For these two events, we identify > 100 keV electrons as significant contributors to the contamination via Bremsstrahlung emission and tungsten fluorescence., Comment: 8 pages, 11 figures, accepted by IEEE TNS

In Self-Supervised Learning (SSL), Audio-Visual Correspondence (AVC) is a popular task to learn deep audio and video features from large unlabeled datasets. The key step in AVC is to randomly sample audio and video clips from the dataset and learn to minimize the feature distance between the positive pairs (corresponding audio-video pair) while maximizing the distance between the negative pairs (non-corresponding audio-video pairs). The learnt features are shown to be effective on various downstream tasks. However, these methods achieve subpar performance when the size of the dataset is rather small. In this paper, we investigate the effect of utilizing class label information in the AVC feature learning task. We modified various positive and negative data sampling techniques of SSL based on class label information to investigate the effect on the feature quality. We propose a new sampling approach which we call soft-positive sampling, where the positive pair for one audio sample is not from the exact corresponding video, but from a video of the same class. Experimental results suggest that when the dataset size is small in SSL setup, features learnt through the soft-positive sampling method significantly outperform those from the traditional SSL sampling approaches. This trend holds in both in-domain and out-of-domain downstream tasks, and even outperforms supervised classification. Finally, experiments show that class label information can easily be obtained using a publicly available classifier network and then can be used to boost the SSL performance without adding extra data annotation burden.

In this paper, we propose a method for class-incremental learning of potentially overlapping sounds for solving a sequence of multi-label audio classification tasks. We design an incremental learner that learns new classes independently of the old classes. To preserve knowledge about the old classes, we propose a cosine similarity-based distillation loss that minimizes discrepancy in the feature representations of subsequent learners, and use it along with a Kullback-Leibler divergence-based distillation loss that minimizes discrepancy in their respective outputs. Experiments are performed on a dataset with 50 sound classes, with an initial classification task containing 30 base classes and 4 incremental phases of 5 classes each. After each phase, the system is tested for multi-label classification with the entire set of classes learned so far. The proposed method obtains an average F1-score of 40.9% over the five phases, ranging from 45.2% in phase 0 on 30 classes, to 36.3% in phase 4 on 50 classes. Average performance degradation over incremental phases is only 0.7 percentage points from the initial F1-score of 45.2%., Comment: Accepted to ICASSP 2024

The measurement of deep water gravity wave elevations using in-situ devices, such as wave gauges, typically yields spatially sparse data. This sparsity arises from the deployment of a limited number of gauges due to their installation effort and high operational costs. The reconstruction of the spatio-temporal extent of surface elevation poses an ill-posed data assimilation problem, challenging to solve with conventional numerical techniques. To address this issue, we propose the application of a physics-informed neural network (PINN), aiming to reconstruct physically consistent wave fields between two designated measurement locations several meters apart. Our method ensures this physical consistency by integrating residuals of the hydrodynamic nonlinear Schr\"{o}dinger equation (NLSE) into the PINN's loss function. Using synthetic wave elevation time series from distinct locations within a wave tank, we initially achieve successful reconstruction quality by employing constant, predetermined NLSE coefficients. However, the reconstruction quality is further improved by introducing NLSE coefficients as additional identifiable variables during PINN training. The results not only showcase a technically relevant application of the PINN method but also represent a pioneering step towards improving the initialization of deterministic wave prediction methods., Comment: 16 pages with 11 figures

We study the subRiemannian cut time and cut locus of a given point in a class of step-2 Carnot groups of Reiter-Heisenberg type. Following the Hamiltonian point of view, we write and analyze extremal curves, getting the cut time of any of them, and a precise description of the set of cut points., Comment: Accepted version (to appear on ESAIM: Control, Optimisation and Calculus of Variations)

Collisionless shock waves have long been considered amongst the most prolific particle accelerators in the universe. Shocks alter the plasma they propagate through and often exhibit complex evolution across multiple scales. Interplanetary (IP) traveling shocks have been recorded in-situ for over half a century and act as a natural laboratory for experimentally verifying various aspects of large-scale collisionless shocks. A fundamentally interesting problem in both helio and astrophysics is the acceleration of electrons to relativistic energies (more than 300 keV) by traveling shocks. This letter presents first observations of field-aligned beams of relativistic electrons upstream of an IP shock observed thanks to the instrumental capabilities of Solar Orbiter. This study aims to present the characteristics of the electron beams close to the source and contribute towards understanding their acceleration mechanism. On 25 July 2022, Solar Orbiter encountered an IP shock at 0.98 AU. The shock was associated with an energetic storm particle event which also featured upstream field-aligned relativistic electron beams observed 14 minutes prior to the actual shock crossing. The distance of the beam's origin was investigated using a velocity dispersion analysis (VDA). Peak-intensity energy spectra were anaylzed and compared with those obtained from a semi-analytical fast-Fermi acceleration model. By leveraging Solar Orbiter's high-time resolution Energetic Particle Detector (EPD), we have successfully showcased an IP shock's ability to accelerate relativistic electron beams. Our proposed acceleration mechanism offers an explanation for the observed electron beam and its characteristics, while we also explore the potential contributions of more complex mechanisms., Comment: Main text: 6 pages, 2 figures. Supplementary material: 6 pages, 7 figures