Search

In diluted lattices, cooperation is often enhanced at specific densities, particularly near the percolation threshold for stochastic updating rules. However, the Replicator rule, despite being probabilistic, does not follow this trend. We find that this anomalous behavior is caused by structures formed by holes and defectors, which prevent some agents from experiencing fluctuations, thereby restricting the free flow of information across the network. As a result, the system becomes trapped in a frozen state, though this can be disrupted by introducing perturbations. Finally, we provide a more quantitative analysis of the relationship between the percolation threshold and cooperation, tracking its development within clusters of varying sizes and demonstrating how the percolation threshold shapes the fundamental structures of the lattice.

In this work, we developed new mathematical methods for analyzing network topology and applied these methods to the analysis of brain networks. More specifically, we rigorously developed quantitative methods based on complexes constructed from digraphs (digraph-based complexes), such as path complexes and directed clique complexes (alternatively, we refer to these complexes as "higher-order structures," or "higher-order topologies," or "simplicial structures"), and, in the case of directed clique complexes, also methods based on the interrelations between the directed cliques, what we called "directed higher-order connectivities." This new quantitative theory for digraph-based complexes can be seen as a step towards the formalization of a "quantitative simplicial theory." Subsequently, we used these new methods, such as characterization measures and similarity measures for digraph-based complexes, to analyze the topology of digraphs derived from brain connectivity estimators, specifically the estimator known as information partial directed coherence (iPDC), which is a multivariate estimator that can be considered a representation of Granger causality in the frequency-domain, particularly estimated from electroencephalography (EEG) data from patients diagnosed with left temporal lobe epilepsy, in the delta, theta and alpha frequency bands, to try to find new biomarkers based on the higher-order structures and connectivities of these digraphs. In particular, we attempted to answer the following questions: How does the higher-order topology of the brain network change from the pre-ictal to the ictal phase, from the ictal to the post-ictal phase, at each frequency band and in each cerebral hemisphere? Does the analysis of higher-order structures provide new and better biomarkers for seizure dynamics and also for the laterality of the seizure focus than the usual graph theoretical analyses?

The purpose of the research was to build an index of informational asymmetry with market and firm proxies that reflect the analysts' perception of the level of informational asymmetry of companies. The proposed method consists of the construction of an algorithm based on the Elo rating and captures the perception of the analyst that choose, between two firms, the one they consider to have better information. After we have the informational asymmetry index, we run a regression model with our rating as dependent variable and proxies used by the literature as the independent variable to have a model that can be used for other researches that need to measure the level of informational asymmetry of a company. Our model presented a good fit between our index and the proxies used to measure informational asymmetry and we find four significant variables: coverage, volatility, Tobin q, and size.

Machine learning has significantly advanced healthcare by aiding in disease prevention and treatment identification. However, accessing patient data can be challenging due to privacy concerns and strict regulations. Generating synthetic, realistic data offers a potential solution for overcoming these limitations, and recent studies suggest that fine-tuning foundation models can produce such data effectively. In this study, we explore the potential of foundation models for generating realistic medical images, particularly chest x-rays, and assess how their performance improves with fine-tuning. We propose using a Latent Diffusion Model, starting with a pre-trained foundation model and refining it through various configurations. Additionally, we performed experiments with input from a medical professional to assess the realism of the images produced by each trained model.

Cell cortex contraction is essential for shaping cells, enabling movement, ensuring proper division, maintaining tissue integrity, guiding development, and responding to mechanical signals - all critical for the life and health of multicellular organisms. Differential contractions in cell membranes, particularly when cells of different types interact, play a crucial role in the emergence of segregation. In this study, we introduce a model where rings composed of active particles interact through differential membrane contraction within a specified cutoff distance. We demonstrate that segregation arises solely from differential contraction, with the activity of the rings functioning similarly to an effective temperature. Additionally, we observed that segregation involves cluster fusion-diffusion process. However, the decay exponent of the segregation parameter we found is close to $\lambda \sim -1/3$, which differs from the $\lambda \sim -1/4$ predicted by previous theoretical approaches and simulations.

This paper introduces a group of novel datasets representing real-time time-series and streaming data of energy prices in New Zealand, sourced from the Electricity Market Information (EMI) website maintained by the New Zealand government. The datasets are intended to address the scarcity of proper datasets for streaming regression learning tasks. We conduct extensive analyses and experiments on these datasets, covering preprocessing techniques, regression tasks, prediction intervals, concept drift detection, and anomaly detection. Our experiments demonstrate the datasets' utility and highlight the challenges and opportunities for future research in energy price forecasting., Comment: 12 Pages, 8 figures, short version accepted by PRICAI

To enhance the field of continuous motor health monitoring, we present FAN-COIL-I, an extensive vibration sensor dataset derived from a Fan Coil motor. This dataset is uniquely positioned to facilitate the detection and prediction of motor health issues, enabling a more efficient maintenance scheduling process that can potentially obviate the need for regular checks. Unlike existing datasets, often created under controlled conditions or through simulations, FAN-COIL-I is compiled from real-world operational data, providing an invaluable resource for authentic motor diagnosis and predictive maintenance research. Gathered using a high-resolution 32KHz sampling rate, the dataset encompasses comprehensive vibration readings from both the forward and rear sides of the Fan Coil motor over a continuous two-week period, offering a rare glimpse into the dynamic operational patterns of these systems in a corporate setting. FAN-COIL-I stands out not only for its real-world applicability but also for its potential to serve as a reliable benchmark for researchers and practitioners seeking to validate their models against genuine engine conditions.

This work reports an extensive study of three-dimensional topological ordered phases that, in one of the directions behave like usual topological order concerning mobility of excitations, but in the perpendicular plane manifest type-II fracton physics dictated by a fractal subsystem symmetry. We obtain an expression for the ground state degeneracy, which depends intricately on the sizes of the plane, signaling a strong manifestation of ultraviolet/infrared (UV/IR) mixing. The ground state degeneracy can be interpreted in terms of spontaneous/explicit breaking of fractal subsystem symmetries. We also study the boundary physics, which in turn is useful to understand the connection with certain two-dimensional phases. Finally, we derive a low-energy but not long-distance effective field theory, by Higgsing a fractal $U(1)$ symmetry and taking the deep IR limit. This description embodies in a natural way several aspects of the phases, such as the content of generalized global symmetries, the role of fractal symmetries on the mobility of excitations, the anomalies, and the boundary physics., Comment: 56 pages, 29 figures

In this paper, we present a multimodal dataset obtained from a honey bee colony in Montr\'eal, Quebec, Canada, spanning the years of 2021 to 2022. This apiary comprised 10 beehives, with microphones recording more than 2000 hours of high quality raw audio, and also sensors capturing temperature, and humidity. Periodic hive inspections involved monitoring colony honey bee population changes, assessing queen-related conditions, and documenting overall hive health. Additionally, health metrics, such as Varroa mite infestation rates and winter mortality assessments were recorded, offering valuable insights into factors affecting hive health status and resilience. In this study, we first outline the data collection process, sensor data description, and dataset structure. Furthermore, we demonstrate a practical application of this dataset by extracting various features from the raw audio to predict colony population using the number of frames of bees as a proxy.

In real-world scenarios, using multiple modalities like visible (RGB) and infrared (IR) can greatly improve the performance of a predictive task such as object detection (OD). Multimodal learning is a common way to leverage these modalities, where multiple modality-specific encoders and a fusion module are used to improve performance. In this paper, we tackle a different way to employ RGB and IR modalities, where only one modality or the other is observed by a single shared vision encoder. This realistic setting requires a lower memory footprint and is more suitable for applications such as autonomous driving and surveillance, which commonly rely on RGB and IR data. However, when learning a single encoder on multiple modalities, one modality can dominate the other, producing uneven recognition results. This work investigates how to efficiently leverage RGB and IR modalities to train a common transformer-based OD vision encoder, while countering the effects of modality imbalance. For this, we introduce a novel training technique to Mix Patches (MiPa) from the two modalities, in conjunction with a patch-wise modality agnostic module, for learning a common representation of both modalities. Our experiments show that MiPa can learn a representation to reach competitive results on traditional RGB/IR benchmarks while only requiring a single modality during inference. Our code is available at: https://github.com/heitorrapela/MiPa.

Algorithms developed to solve many-body quantum problems, like tensor networks, can turn into powerful quantum-inspired tools to tackle problems in the classical domain. In this work, we focus on matrix product operators, a prominent numerical technique to study many-body quantum systems, especially in one dimension. It has been previously shown that such a tool can be used for classification, learning of deterministic sequence-to-sequence processes and of generic quantum processes. We further develop a matrix product operator algorithm to learn probabilistic sequence-to-sequence processes and apply this algorithm to probabilistic cellular automata. This new approach can accurately learn probabilistic cellular automata processes in different conditions, even when the process is a probabilistic mixture of different chaotic rules. In addition, we find that the ability to learn these dynamics is a function of the bit-wise difference between the rules and whether one is much more likely than the other., Comment: 9 pages, 7 figures

A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domains and tasks. While this approach works well in many application areas, it often fails drastically when processing data from a new modality with a significant distribution shift from the data used to pre-train the model. This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift. We propose Modality Translator (ModTr) as an alternative to the common approach of fine-tuning a large model to the new modality. ModTr adapts the IR input image with a small transformation network trained to directly minimize the detection loss. The original RGB model can then work on the translated inputs without any further changes or fine-tuning to its parameters. Experimental results on translating from IR to RGB images on two well-known datasets show that our simple approach provides detectors that perform comparably or better than standard fine-tuning, without forgetting the knowledge of the original model. This opens the door to a more flexible and efficient service-based detection pipeline, where a unique and unaltered server, such as an RGB detector, runs constantly while being queried by different modalities, such as IR with the corresponding translations model. Our code is available at: https://github.com/heitorrapela/ModTr., Comment: ECCV 2024: European Conference on Computer Vision, Milan Italy

Self-supervised speech representation learning enables the extraction of meaningful features from raw waveforms. These features can then be efficiently used across multiple downstream tasks. However, two significant issues arise when considering the deployment of such methods ``in-the-wild": (i) Their large size, which can be prohibitive for edge applications; and (ii) their robustness to detrimental factors, such as noise and/or reverberation, that can heavily degrade the performance of such systems. In this work, we propose RobustDistiller, a novel knowledge distillation mechanism that tackles both problems jointly. Simultaneously to the distillation recipe, we apply a multi-task learning objective to encourage the network to learn noise-invariant representations by denoising the input. The proposed mechanism is evaluated on twelve different downstream tasks. It outperforms several benchmarks regardless of noise type, or noise and reverberation levels. Experimental results show that the new Student model with 23M parameters can achieve results comparable to the Teacher model with 95M parameters. Lastly, we show that the proposed recipe can be applied to other distillation methodologies, such as the recent DPWavLM. For reproducibility, code and model checkpoints will be made available at \mbox{\url{https://github.com/Hguimaraes/robustdistiller}}., Comment: Under review on IEEE Transactions on Audio, Speech, and Language Processing (2024)

The emergence of neural networks constrained by physical governing equations has sparked a new trend in deep learning research, which is known as Physics-Informed Neural Networks (PINNs). However, solving high-dimensional problems with PINNs is still a substantial challenge, the space complexity brings difficulty to solving large multidirectional problems. In this paper, a novel PINN framework to quickly predict several three-dimensional Terzaghi consolidation cases under different conditions is proposed. Meanwhile, the loss functions for different cases are introduced, and their differences in three-dimensional consolidation problems are highlighted. The tuning strategies for the PINNs framework for three-dimensional consolidation problems are introduced. Then, the performance of PINNs is tested and compared with traditional numerical methods adopted in forward problems, and the coefficients of consolidation and the impact of noisy data in inverse problems are identified. Finally, the results are summarized and presented from three-dimensional simulations of PINNs, which show an accuracy rate of over 99% compared with ground truth for both forward and inverse problems. These results are desirable with good accuracy and can be used for soil settlement prediction, which demonstrates that the proposed PINNs framework can learn the three-dimensional consolidation PDE well. Keywords: Three-dimensional Terzaghi consolidation; Physics-informed neural networks (PINNs); Forward problems; Inverse problems; soil settlement, Comment: 30 pages, 11 figures, 6 tables, 23 equations

We present a longitudinal multi-sensor dataset collected from honey bee colonies (Apis mellifera) with rich phenotypic measurements. Data were continuously collected between May-2020 and April-2021 from 53 hives located at two apiaries in Qu\'ebec, Canada. The sensor data included audio features, temperature, and relative humidity. The phenotypic measurements contained beehive population, number of brood cells (eggs, larva and pupa), Varroa destructor infestation levels, defensive and hygienic behaviors, honey yield, and winter mortality. Our study is amongst the first to provide a wide variety of phenotypic trait measurements annotated by apicultural science experts, which facilitate a broader scope of analysis. We first summarize the data collection procedure, sensor data pre-processing steps, and data composition. We then provide an overview of the phenotypic data distribution as well as a visualization of the sensor data patterns. Lastly, we showcase several hive monitoring applications based on sensor data analysis and machine learning, such as winter mortality prediction, hive population estimation, and the presence of an active and laying queen., Comment: Under review; project webpage: https://zhu00121.github.io/MSPB-webpage/

Power line maintenance and inspection are essential to avoid power supply interruptions, reducing its high social and financial impacts yearly. Automating power line visual inspections remains a relevant open problem for the industry due to the lack of public real-world datasets of power line components and their various defects to foster new research. This paper introduces InsPLAD, a Power Line Asset Inspection Dataset and Benchmark containing 10,607 high-resolution Unmanned Aerial Vehicles colour images. The dataset contains seventeen unique power line assets captured from real-world operating power lines. Additionally, five of those assets present six defects: four of which are corrosion, one is a broken component, and one is a bird's nest presence. All assets were labelled according to their condition, whether normal or the defect name found on an image level. We thoroughly evaluate state-of-the-art and popular methods for three image-level computer vision tasks covered by InsPLAD: object detection, through the AP metric; defect classification, through Balanced Accuracy; and anomaly detection, through the AUROC metric. InsPLAD offers various vision challenges from uncontrolled environments, such as multi-scale objects, multi-size class instances, multiple objects per image, intra-class variation, cluttered background, distinct point-of-views, perspective distortion, occlusion, and varied lighting conditions. To the best of our knowledge, InsPLAD is the first large real-world dataset and benchmark for power line asset inspection with multiple components and defects for various computer vision tasks, with a potential impact to improve state-of-the-art methods in the field. It will be publicly available in its integrity on a repository with a thorough description. It can be found at https://github.com/andreluizbvs/InsPLAD., Comment: This is an original manuscript of an article published by Taylor & Francis in the International Journal of Remote Sensing on 29 Nov 2023, available online: https://doi.org/10.1080/01431161.2023.2283900

Continual learning aims to create artificial neural networks capable of accumulating knowledge and skills through incremental training on a sequence of tasks. The main challenge of continual learning is catastrophic interference, wherein new knowledge overrides or interferes with past knowledge, leading to forgetting. An associated issue is the problem of learning "cross-task knowledge," where models fail to acquire and retain knowledge that helps differentiate classes across task boundaries. A common solution to both problems is "replay," where a limited buffer of past instances is utilized to learn cross-task knowledge and mitigate catastrophic interference. However, a notable drawback of these methods is their tendency to overfit the limited replay buffer. In contrast, our proposed solution, SurpriseNet, addresses catastrophic interference by employing a parameter isolation method and learning cross-task knowledge using an auto-encoder inspired by anomaly detection. SurpriseNet is applicable to both structured and unstructured data, as it does not rely on image-specific inductive biases. We have conducted empirical experiments demonstrating the strengths of SurpriseNet on various traditional vision continual-learning benchmarks, as well as on structured data datasets. Source code made available at https://doi.org/10.5281/zenodo.8247906 and https://github.com/tachyonicClock/SurpriseNet-CIKM-23

In this work, we study unconventional anisotropic topologically ordered phases in $3d$ that manifest type-II fractonic physics along submanifolds. While they behave as usual topological order along a preferred spatial direction, their physics along perpendicular planes is dictated by the presence of fractal subsystem symmetries, completely restricting the mobility of anyonic excitations and their bound states. We consider an explicit lattice model realization of such phases and proceed to study their properties under periodic boundary conditions and, later, in the presence of boundaries. We find that for specific lattice sizes, the system possesses line and fractal membrane symmetries that are mutually anomalous, resulting in a nontrivially gapped ground state space. This amounts to the spontaneous breaking of the fractal symmetries, implying a subextensive ground state degeneracy. For the remaining system sizes the fractal symmetries are explicitly broken by the periodic boundary conditions, which is intrinsically related to the uniqueness of the ground state. Despite that, the system is still topologically ordered since locally created quasiparticles have nontrivial mutual statistics and, in the presence of boundaries, it still presents anomalous edge modes. The intricate symmetry interplay dictated by the lattice size is a wild manifestation of ultraviolet/infrared (UV/IR) mixing., Comment: 8+6 pages, 5+6 figures, clarifications added, typos fixed, refs. added, v2 matches published version

This work investigates the impact of feeder bidirectional active power flow on the operation of two cascaded step voltage regulators (SVRs) located at a 34.5 kV rural distribution feeder. It shows that, when active power flow reversal is possible both by network reconfiguration and by high penetration levels of distributed generation (DG), typical SVR control mode settings are unable to prevent the occurrence of runaway condition, a phenomenon characterized by loss of SVR voltage control capabilities. Such developments are the basis for a DG pre-dispatch control strategy that aims to avoid the adverse effects of the described power flow reversal scenarios, as well as to ensure reliable operation of the utility distribution network., Comment: 8 pages, 11 figures, submitted to XXV SNPTEE 2019

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the training and test data follow the same distribution. For the out-of-domain case, where the test data follow a different and unknown distribution, the best recipe for data augmentation is unclear. In this paper, we show that for out-of-domain and domain generalization settings, data augmentation can provide a conspicuous and robust improvement in performance. To do that, we propose a simple training procedure: (i) use uniform sampling on standard data augmentation transformations; (ii) increase the strength transformations to account for the higher data variance expected when working out-of-domain, and (iii) devise a new reward function to reject extreme transformations that can harm the training. With this procedure, our data augmentation scheme achieves a level of accuracy that is comparable to or better than state-of-the-art methods on benchmark domain generalization datasets. Code: \url{https://github.com/Masseeh/DCAug}

A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution as the target domain. Given a cross-modal application, such as pedestrian detection from aerial images, with a considerable shift in data distribution between infrared (IR) to visible (RGB) images, a translation focused on generation might lead to poor performance as the loss focuses on irrelevant details for the task. In this paper, we propose HalluciDet, an IR-RGB image translation model for object detection. Instead of focusing on reconstructing the original image on the IR modality, it seeks to reduce the detection loss of an RGB detector, and therefore avoids the need to access RGB data. This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance. We empirically compare our approach against state-of-the-art methods for image translation and for fine-tuning on IR, and show that our HalluciDet improves detection accuracy in most cases by exploiting the privileged information encoded in a pre-trained RGB detector. Code: https://github.com/heitorrapela/HalluciDet, Comment: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors. Notwithstanding, while such models achieve SOTA performance in matched train/test conditions, their performance degrades substantially when tested in unseen conditions. To overcome this problem, strategies such as data augmentation and/or domain shift training have been explored. Available models, however, are still too large to be considered for edge speech applications on resource-constrained devices, thus model compression tools are needed. In this paper, we explore the effects that train/test mismatch conditions have on speech recognition accuracy based on compressed self-supervised speech models. In particular, we report on the effects that parameter quantization and model pruning have on speech recognition accuracy based on the so-called robust wav2vec 2.0 model under noisy, reverberant, and noise-plus-reverberation conditions.

Keyword spotting (KWS) refers to the task of identifying a set of predefined words in audio streams. With the advances seen recently with deep neural networks, it has become a popular technology to activate and control small devices, such as voice assistants. Relying on such models for edge devices, however, can be challenging due to hardware constraints. Moreover, as adversarial attacks have increased against voice-based technologies, developing solutions robust to such attacks has become crucial. In this work, we propose VIC-KD, a robust distillation recipe for model compression and adversarial robustness. Using self-supervised speech representations, we show that imposing geometric priors to the latent representations of both Teacher and Student models leads to more robust target models. Experiments on the Google Speech Commands datasets show that the proposed methodology improves upon current state-of-the-art robust distillation methods, such as ARD and RSLAD, by 12% and 8% in robust accuracy, respectively., Comment: Submitted to ICASSP 2024

In modern communication systems operating with Orthogonal Frequency-Division Multiplexing (OFDM), channel estimation requires minimal complexity with one-tap equalizers. However, this depends on cyclic prefixes, which must be sufficiently large to cover the channel impulse response. Conversely, the use of cyclic prefix (CP) decreases the useful information that can be conveyed in an OFDM frame, thereby degrading the spectral efficiency of the system. In this context, we study the impact of CPs on channel estimation with complex-valued neural networks (CVNNs). We show that the phase-transmittance radial basis function neural network offers superior results, in terms of required energy per bit, compared to classical minimum mean-squared error and least squares algorithms in scenarios without CP., Comment: XLI Simp\'osio Brasileiro de Telecomunica\c{c}\~oes e Processamento Digital de Sinais - SBrT 2023

Context. Refactoring has been widely investigated in the past in relation to production code quality, yet still little is known on how developers apply refactoring on test code. Specifically, there is still a lack of investigation into how developers typically refactor test code and its effects on test code quality and effectiveness. Objective. This paper presents a research agenda aimed to bridge this gap of knowledge by investigating (1) whether test refactoring actually targets test classes affected by quality and effectiveness concerns and (2) the extent to which refactoring contributes to the improvement of test code quality and effectiveness. Method. We plan to conduct an exploratory mining software repository study to collect test refactoring data of open-source Java projects from GitHub and statistically analyze them in combination with quality metrics, test smells, and code/mutation coverage indicators. Furthermore, we will measure how refactoring operations impact the quality and effectiveness of test code., Comment: 9 pages, 39th IEEE International Conference on Software Maintenance and Evolution (ICSME) - Registered Report