arXiv subjects

Odemir M. Bruno

Publications and source records attributed to Odemir M. Bruno.

At least 19 recordsLinked to original sources

arXiv2026

Acoustic Resonance Distribution for Core-Shell Scatterers

Acoustic metamaterials can exhibit unusual effective properties through mechanisms such as energy localization and resonant behavior in their constituent building blocks. Here, we investigate the internal acoustic energy of fluid core-shell spheres and map how resonances emerge from the interplay between material contrasts and shell geometry. The resulting phase diagram reveals an organized resonant landscape across distinct impedance-contrast regimes. From this structure, we obtain two compact predictive relations: one for resonance existence and another for spectral recurrence of successive peaks. Together, they enable the rapid identification of material and geometric combinations associated with targeted resonance responses. The framework is further tested against representative systems from the literature, reproducing their observed behavior. These results provide a physics-based route for screening and tailoring resonant core-shell building blocks before full-wave numerical simulations.

physics.app-ph↗

arXiv2026

Restoring detailed balance in non-Hermitian Markov processes

Stochastic processes out-of-equilibrium often involve asymmetric contributions that break detailed balance and lead to non-monotonic entropy production, limiting thermodynamic interpretations and inference techniques. Here we use Dyson maps to restore monotonic entropy growth in those processes, allowing the use of standard tools from statistical physics, providing a general and computationally tractable method applicable to a broad class of Markovian systems.

cond-mat.stat-mech↗

arXiv2025

Trapped acoustic energy and resonances in spherical scatterers

The effectiveness of biochemical antivirals are vulnerable to mutations, motivating physical approaches. Recent experiments with ultrasound reveal viral disruption at MHz frequencies, yet the mechanism remains unclear. We model viruses as fluid-like inclusions and analyze internal acoustic fields. Exact solutions reveal that impedance mismatch induces resonances even for subwavelength scatterers. Beyond the monopole, higher-order modes trap significant energy with significant resonance peak broadening even in absence of explicit dissipation mechanisms. These findings suggest internal acoustic resonances as a mechanism for viral destabilization and acoustic metamaterial applications.

physics.app-ph↗

arXiv2025

Essential metrics for Life on graphs

We present a strong theoretical foundation that frames a well-defined family of outer-totalistic network automaton models as a topological generalisation of binary outer-totalistic cellular automata, of which the Game of Life is one notable particular case. These "Life-like network automata" are quantitatively described by expressing their genotype (the mean field curve and Derrida curve) and phenotype (the evolution of the state and defect averages). After demonstrating that the genotype and phenotype are correlated, we illustrate the utility of these essential metrics by tackling the firing squad synchronisation problem in a bottom-up fashion, with results that exceed a 90% success rate.

nlin.CG↗

arXiv2025

A Benchmarking Framework for Network Classification Methods

Network classification plays a crucial role in the study of complex systems, impacting fields like biology, sociology, and computer science. In this research, we present an innovative benchmark dataset made up of synthetic networks that are categorized into various classes and subclasses. This dataset is specifically crafted to test the effectiveness and resilience of different network classification methods. To put these methods to the test, we also introduce various types and levels of structural noise. We evaluate five feature extraction techniques: traditional structural measures, Life-Like Network Automata (LLNA), Graph2Vec, Deterministic Tourist Walk (DTW), and its improved version, the Deterministic Tourist Walk with Bifurcation (DTWB). Our experimental results reveal that DTWB surpasses the other methods in classifying both classes and subclasses, even when faced with significant noise. LLNA and DTW also perform well, while Graph2Vec lands somewhere in the middle in terms of accuracy. Interestingly, topological measures, despite their simplicity and common usage, consistently show the weakest classification performance. These findings underscore the necessity of robust feature extraction techniques for effective network classification, particularly in noisy conditions.

cs.SI↗

arXiv2025

Network classification through random walks

Network models have been widely used to study diverse systems and analyze their dynamic behaviors. Given the structural variability of networks, an intriguing question arises: Can we infer the type of system represented by a network based on its structure? This classification problem involves extracting relevant features from the network. Existing literature has proposed various methods that combine structural measurements and dynamical processes for feature extraction. In this study, we introduce a novel approach to characterize networks using statistics from random walks, which can be particularly informative about network properties. We present the employed statistical metrics and compare their performance on multiple datasets with other state-of-the-art feature extraction methods. Our results demonstrate that the proposed method is effective in many cases, often outperforming existing approaches, although some limitations are observed across certain datasets.

cs.SI↗

arXiv2025

VORTEX: Challenging CNNs at Texture Recognition by using Vision Transformers with Orderless and Randomized Token Encodings

Texture recognition has recently been dominated by ImageNet-pre-trained deep Convolutional Neural Networks (CNNs), with specialized modifications and feature engineering required to achieve state-of-the-art (SOTA) performance. However, although Vision Transformers (ViTs) were introduced a few years ago, little is known about their texture recognition ability. Therefore, in this work, we introduce VORTEX (ViTs with Orderless and Randomized Token Encodings for Texture Recognition), a novel method that enables the effective use of ViTs for texture analysis. VORTEX extracts multi-depth token embeddings from pre-trained ViT backbones and employs a lightweight module to aggregate hierarchical features and perform orderless encoding, obtaining a better image representation for texture recognition tasks. This approach allows seamless integration with any ViT with the common transformer architecture. Moreover, no fine-tuning of the backbone is performed, since they are used only as frozen feature extractors, and the features are fed to a linear SVM. We evaluate VORTEX on nine diverse texture datasets, demonstrating its ability to achieve or surpass SOTA performance in a variety of texture analysis scenarios. By bridging the gap between texture recognition with CNNs and transformer-based architectures, VORTEX paves the way for adopting emerging transformer foundation models. Furthermore, VORTEX demonstrates robust computational efficiency when coupled with ViT backbones compared to CNNs with similar costs. The method implementation and experimental scripts are publicly available in our online repository.

cs.CV↗

arXiv2024

A Comprehensive Taxonomy of Cellular Automata

Cellular automata (CAs) are fully-discrete dynamical models that have received much attention due to the fact that their relatively simple setup can nonetheless express highly complex phenomena. Despite the model's theoretical maturity and abundant computational power, the current lack of a complete survey on the 'taxonomy' of various families of CAs impedes efficient and interdisciplinary progress. This review paper mitigates that deficiency; it provides a methodical overview of five important CA 'families': asynchronous, stochastic, multi-state, extended-neighbourhood, and non-uniform CAs. These five CA families are subsequently presented from four angles. First, a rigorous mathematical definition is given. Second, we map prominent variations within each CA family, as such highlighting mathematical equivalences with types from other families. Third, we discuss the genotype and phenotype of these CA types by means of mathematical tools, indicating when established tools break down. Fourth, we conclude each section with a brief overview of applications related to information theory and mathematical modelling.

nlin.CG↗

arXiv2024

Efficient Simulation of Non-uniform Cellular Automata with a Convolutional Neural Network

Cellular automata (CAs) and convolutional neural networks (CNNs) are closely related due to the local nature of information processing. The connection between these topics is beneficial to both related fields, for conceptual as well as practical reasons. Our contribution solidifies this connection in the case of non-uniform CAs (nuCAs), simulating a global update in the architecture of the Python package TensorFlow. Additionally, we demonstrate how the highly optimised out-of-the-box multiprocessing in TensorFlow offers interesting computational benefits, especially when simulating large numbers of nuCAs with many cells.

nlin.CG↗

arXiv2024

A Comparative Survey of Vision Transformers for Feature Extraction in Texture Analysis

Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are currently among the best texture analysis approaches. On the other hand, Vision Transformers (ViTs) have been surpassing the performance of CNNs on tasks such as object recognition, causing a paradigm shift in the field. However, ViTs have so far not been scrutinized for texture recognition, hindering a proper appreciation of their potential in this specific setting. For this reason, this work explores various pre-trained ViT architectures when transferred to tasks that rely on textures. We review 21 different ViT variants and perform an extensive evaluation and comparison with CNNs and hand-engineered models on several tasks, such as assessing robustness to changes in texture rotation, scale, and illumination, and distinguishing color textures, material textures, and texture attributes. The goal is to understand the potential and differences among these models when directly applied to texture recognition, using pre-trained ViTs primarily for feature extraction and employing linear classifiers for evaluation. We also evaluate their efficiency, which is one of the main drawbacks in contrast to other methods. Our results show that ViTs generally outperform both CNNs and hand-engineered models, especially when using stronger pre-training and tasks involving in-the-wild textures (images from the internet). We highlight the following promising models: ViT-B with DINO pre-training, BeiTv2, and the Swin architecture, as well as the EfficientFormer as a low-cost alternative. In terms of efficiency, although having a higher number of GFLOPs and parameters, ViT-B and BeiT(v2) can achieve a lower feature extraction time on GPUs compared to ResNet50.

cs.CV↗

arXiv2024

Advanced wood species identification based on multiple anatomical sections and using deep feature transfer and fusion

In recent years, we have seen many advancements in wood species identification. Methods like DNA analysis, Near Infrared (NIR) spectroscopy, and Direct Analysis in Real Time (DART) mass spectrometry complement the long-established wood anatomical assessment of cell and tissue morphology. However, most of these methods have some limitations such as high costs, the need for skilled experts for data interpretation, and the lack of good datasets for professional reference. Therefore, most of these methods, and certainly the wood anatomical assessment, may benefit from tools based on Artificial Intelligence. In this paper, we apply two transfer learning techniques with Convolutional Neural Networks (CNNs) to a multi-view Congolese wood species dataset including sections from different orientations and viewed at different microscopic magnifications. We explore two feature extraction methods in detail, namely Global Average Pooling (GAP) and Random Encoding of Aggregated Deep Activation Maps (RADAM), for efficient and accurate wood species identification. Our results indicate superior accuracy on diverse datasets and anatomical sections, surpassing the results of other methods. Our proposal represents a significant advancement in wood species identification, offering a robust tool to support the conservation of forest ecosystems and promote sustainable forestry practices.

cs.CV↗

arXiv2023

RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

Texture analysis is a classical yet challenging task in computer vision for which deep neural networks are actively being applied. Most approaches are based on building feature aggregation modules around a pre-trained backbone and then fine-tuning the new architecture on specific texture recognition tasks. Here we propose a new method named \textbf{R}andom encoding of \textbf{A}ggregated \textbf{D}eep \textbf{A}ctivation \textbf{M}aps (RADAM) which extracts rich texture representations without ever changing the backbone. The technique consists of encoding the output at different depths of a pre-trained deep convolutional network using a Randomized Autoencoder (RAE). The RAE is trained locally to each image using a closed-form solution, and its decoder weights are used to compose a 1-dimensional texture representation that is fed into a linear SVM. This means that no fine-tuning or backpropagation is needed. We explore RADAM on several texture benchmarks and achieve state-of-the-art results with different computational budgets. Our results suggest that pre-trained backbones may not require additional fine-tuning for texture recognition if their learned representations are better encoded.

cs.CV↗

arXiv2023

Using deterministic tourist walk as a small-world metric on Watts-Strogatz networks

The Watts-Strogatz model (WS) has been demonstrated to effectively describe real-world networks due to its ability to reproduce the small-world properties commonly observed in a variety of systems, including social networks, computer networks, biochemical reactions, and neural networks. As the presence of small-world properties is a prevalent characteristic in many real-world networks, the measurement of "small-worldness" has become a crucial metric in the field of network science, leading to the development of various methods for its assessment over the past two decades. In contrast, the deterministic tourist walk (DTW) method has emerged as a prominent technique for texture analysis and network classification. In this paper, we propose the use of a modified version of the DTW method to classify networks into three categories: regular networks, random networks, and small-world networks. Additionally, we construct a small-world metric, denoted by the coefficient $χ$, from the DTW method. Results indicate that the proposed method demonstrates excellent performance in the task of network classification, achieving over $90\%$ accuracy. Furthermore, the results obtained using the coefficient $χ$ on real-world networks provide evidence that the proposed method effectively serves as a satisfactory small-world metric.

cs.SI↗

arXiv2023

Exploring ordered patterns in the adjacency matrix for improving machine learning on complex networks

The use of complex networks as a modern approach to understanding the world and its dynamics is well-established in literature. The adjacency matrix, which provides a one-to-one representation of a complex network, can also yield several metrics of the graph. However, it is not always clear that this representation is unique, as the permutation of lines and rows in the matrix can represent the same graph. To address this issue, the proposed methodology employs a sorting algorithm to rearrange the elements of the adjacency matrix of a complex graph in a specific order. The resulting sorted adjacency matrix is then used as input for feature extraction and machine learning algorithms to classify the networks. The results indicate that the proposed methodology outperforms previous literature results on synthetic and real-world data.

cs.SI↗

arXiv2022

Patterns on logistic map: back to front

Recently patterns were found in the least significant digits in the logistic map orbits in the chaotic regime. However, the dynamic of these digits was not explored in deep. We propose a new interpretation of the patterns found in the least significant digits of the logistic map in a chaotic regime, based on exploring the digits' dynamics. We explored these digits by the dynamic iteration method for low positions. When the dynamic of the least significant digits was explored, periodic and fixed digits were found with dynamic analogs to fixed and periodic points of discrete systems. Periodic digits designated well-established period sizes, which are independent of parameter control or initial condition. Fixed digits have attraction and stability characteristics, such as fixed points. This analysis demonstrates that the logistic map's least significant digits have characteristic dynamics.

nlin.CD↗

arXiv2022

A Network Classification Method based on Density Time Evolution Patterns Extracted from Network Automata

Network modeling has proven to be an efficient tool for many interdisciplinary areas, including social, biological, transport, and many other real world complex systems. In addition, cellular automata (CA) are a formalism that has been studied in the last decades as a model for exploring patterns in the dynamic spatio-temporal behavior of these systems based on local rules. Some studies explore the use of cellular automata to analyze the dynamic behavior of networks, denominating them as network automata (NA). Recently, NA proved to be efficient for network classification, since it uses a time-evolution pattern (TEP) for the feature extraction. However, the TEPs explored by previous studies are composed of binary values, which does not represent detailed information on the network analyzed. Therefore, in this paper, we propose alternate sources of information to use as descriptor for the classification task, which we denominate as density time-evolution pattern (D-TEP) and state density time-evolution pattern (SD-TEP). We explore the density of alive neighbors of each node, which is a continuous value, and compute feature vectors based on histograms of the TEPs. Our results show a significant improvement compared to previous studies at five synthetic network databases and also seven real world databases. Our proposed method demonstrates not only a good approach for pattern recognition in networks, but also shows great potential for other kinds of data, such as images.

cs.SI↗

arXiv2022

Improving Deep Neural Network Random Initialization Through Neuronal Rewiring

The deep learning literature is continuously updated with new architectures and training techniques. However, weight initialization is overlooked by most recent research, despite some intriguing findings regarding random weights. On the other hand, recent works have been approaching Network Science to understand the structure and dynamics of Artificial Neural Networks (ANNs) after training. Therefore, in this work, we analyze the centrality of neurons in randomly initialized networks. We show that a higher neuronal strength variance may decrease performance, while a lower neuronal strength variance usually improves it. A new method is then proposed to rewire neuronal connections according to a preferential attachment (PA) rule based on their strength, which significantly reduces the strength variance of layers initialized by common methods. In this sense, PA rewiring only reorganizes connections, while preserving the magnitude and distribution of the weights. We show through an extensive statistical analysis in image classification that performance is improved in most cases, both during training and testing, when using both simple and complex architectures and learning schedules. Our results show that, aside from the magnitude, the organization of the weights is also relevant for better initialization of deep ANNs.

cs.NE↗

arXiv2021

Structure and Performance of Fully Connected Neural Networks: Emerging Complex Network Properties

Understanding the behavior of Artificial Neural Networks is one of the main topics in the field recently, as black-box approaches have become usual since the widespread of deep learning. Such high-dimensional models may manifest instabilities and weird properties that resemble complex systems. Therefore, we propose Complex Network (CN) techniques to analyze the structure and performance of fully connected neural networks. For that, we build a dataset with 4 thousand models and their respective CN properties. They are employed in a supervised classification setup considering four vision benchmarks. Each neural network is approached as a weighted and undirected graph of neurons and synapses, and centrality measures are computed after training. Results show that these measures are highly related to the network classification performance. We also propose the concept of Bag-Of-Neurons (BoN), a CN-based approach for finding topological signatures linking similar neurons. Results suggest that six neuronal types emerge in such networks, independently of the target domain, and are distributed differently according to classification accuracy. We also tackle specific CN properties related to performance, such as higher subgraph centrality on lower-performing models. Our findings suggest that CN properties play a critical role in the performance of fully connected neural networks, with topological patterns emerging independently on a wide range of models.

cs.LG↗