arXiv subjects

Armando J. Pinho

Publications and source records attributed to Armando J. Pinho.

13 recordsLinked to original sources

arXiv2026

Revisiting OmniAnomaly for Anomaly Detection: performance metrics and comparison with PCA-based models

Deep learning models have become the dominant approach for multivariate time series anomaly detection (MTSAD), often reporting substantial performance improvements over classical statistical methods. However, these gains are frequently evaluated under heterogeneous thresholding strategies and evaluation protocols, making fair comparisons difficult. This work revisits OmniAnomaly, a widely used stochastic recurrent model for MTSAD, and systematically compares it with a simple linear baseline based on Principal Component Analysis (PCA) on the Server Machine Dataset (SMD). Both methods are evaluated under identical thresholding and evaluation procedures, with experiments repeated across 100 runs for each of the 28 machines in the dataset. Performance is evaluated using Precision, Recall and F1-score at point-level, with and without point-adjustment, and under different aggregation strategies across machines and runs, with the corresponding standard deviations also reported. The results show large variability across machines and show that PCA can achieve performance comparable to OmniAnomaly, and even outperform it when point-adjustment is not applied. These findings question the added value of more complex architectures under current benchmarking practices and highlight the critical role of evaluation methodology in MTSAD research.

stat.ML↗

arXiv2026

The 2026 Algorithmic Information Theory Data Compression Challenge

Lossless data compression remains central to computer science, with direct impact on storage, communication bandwidth, computational cost, and energy consumption. It is also closely related to Algorithmic Information Theory, where compressibility provides an operational measure of structure and non-randomness. This paper presents the 2026 Algorithmic Information Theory Data Compression Challenge, a benchmark for evaluating general-purpose lossless compressors under realistic constraints. Submissions were encouraged to use arithmetic or range coding, limited to at most 8 GB of memory, and required to include a decompressor no larger than 1 MB. The benchmark comprised sixteen heterogeneous files, split into public training and hidden testing datasets. In total, 117 valid submitted compressors were evaluated alongside established reference compressors using compression ratio, compression and decompression time, Weissman score, and Pareto-frontier analysis. The results show that performance depends strongly on the optimization criterion: fast compressors achieved the best speed-oriented scores, whereas modelling-intensive compressors produced smaller outputs at higher computational cost. A Normalized Compression Distance analysis further revealed clusters of related submissions and distinguished incremental variants from more independent implementations. Selected submissions were described for their methodological novelty or competitive performance and further tested on four large external datasets, where several achieved competitive or superior results relative to established compressors. Overall, the challenge confirms the importance of probabilistic modelling, hidden testing, and external datasets for assessing compression performance and generalization. Benchmark resources, leaderboard data, binaries, and selected source code are publicly available at https://aitdcc.github.io.

cs.IT↗

arXiv2026

Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning

The topic of Multivariate Time Series Anomaly Detection (MTSAD) has grown rapidly over the past years, with a steady rise in publications and Deep Learning (DL) models becoming the dominant paradigm. To address the lack of systematization in the field, this study introduces a novel and unified taxonomy with eleven dimensions over three parts (Input, Output and Model) for the categorization of DL-based MTSAD methods. The dimensions were established in a two-fold approach. First, they derived from a comprehensive analysis of methodological studies. Second, insights from review papers were incorporated. Furthermore, the proposed taxonomy was validated using an additional set of recent publications, providing a clear overview of methodological trends in MTSAD. Results reveal a convergence toward Transformer-based and reconstruction and prediction models, setting the foundation for emerging adaptive and generative trends. Building on and complementing existing surveys, this unified taxonomy is designed to accommodate future developments, allowing for new categories or dimensions to be added as the field progresses. This work thus consolidates fragmented knowledge in the field and provides a reference point for future research in MTSAD.

stat.ML↗

arXiv2026

A two-step sequential approach for hyperparameter selection in finite context models

Finite-context models (FCMs) are widely used for compressing symbolic sequences such as DNA, where predictive performance depends critically on the context length k and smoothing parameter α. In practice, these hyperparameters are typically selected through exhaustive search, which is computationally expensive and scales poorly with model complexity. This paper proposes a statistically grounded two-step sequential approach for efficient hyperparameter selection in FCMs. The key idea is to decompose the joint optimization problem into two independent stages. First, the context length k is estimated using categorical serial dependence measures, including Cramér's ν, Cohen's \k{appa} and partial mutual information (pami). Second, the smoothing parameter α is estimated via maximum likelihood conditional on the selected context length k. Simulation experiments were conducted on synthetic symbolic sequences generated by FCMs across multiple (k, α) configurations, considering a four-letter alphabet and different sample sizes. Results show that the dependence measures are substantially more sensitive to variations in k than in α, supporting the sequential estimation strategy. As expected, the accuracy of the hyperparameter estimation improves with increasing sample size. Furthermore, the proposed method achieves compression performance comparable to exhaustive grid search in terms of average bitrate (bits per symbol), while substantially reducing computational cost. Overall, the results on simulated data show that the proposed sequential approach is a practical and computationally efficient alternative to exhaustive hyperparameter tuning in FCMs.

stat.ML↗

arXiv2026

Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation

Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a Neural Network (NN) formulation of AR estimation by embedding the autoregressive structure directly into a feedforward NN, enabling coefficient estimation through backpropagation while preserving interpretability. Simulation experiments on 125,000 synthetic AR(p) time series with short-term dependence (1 <= p <= 5) show that the proposed NN-based method consistently recovers model coefficients for all series, while Conditional Maximum Likelihood (CML) fails to converge in approximately 55% of cases. When both methods converge, estimation accuracy is comparable with negligible differences in relative error, R2 and, perplexity/likelihood. However, when CML fails, the NN-based approach still provides reliable estimates. In all cases, the NN estimator achieves substantial computational gains, reaching a median speedup of 12.6x and up to 34.2x for higher model orders. Overall, results demonstrate that gradient-descent NN optimization can provide a fast and efficient alternative for interpretable AR parameter estimation.

stat.ML↗

arXiv2025

Decoding the Past: Explainable Machine Learning Models for Dating Historical Texts

Accurately dating historical texts is essential for organizing and interpreting cultural heritage collections. This article addresses temporal text classification using interpretable, feature-engineered tree-based machine learning models. We integrate five feature categories - compression-based, lexical structure, readability, neologism detection, and distance features - to predict the temporal origin of English texts spanning five centuries. Comparative analysis shows that these feature domains provide complementary temporal signals, with combined models outperforming any individual feature set. On a large-scale corpus, we achieve 76.7% accuracy for century-scale prediction and 26.1% for decade-scale classification, substantially above random baselines (20% and 2.3%). Under relaxed temporal precision, performance increases to 96.0% top-2 accuracy for centuries and 85.8% top-10 accuracy for decades. The final model exhibits strong ranking capabilities with AUCROC up to 94.8% and AUPRC up to 83.3%, and maintains controlled errors with mean absolute deviations of 27 years and 30 years, respectively. For authentication-style tasks, binary models around key thresholds (e.g., 1850-1900) reach 85-98% accuracy. Feature importance analysis identifies distance features and lexical structure as most informative, with compression-based features providing complementary signals. SHAP explainability reveals systematic linguistic evolution patterns, with the 19th century emerging as a pivot point across feature domains. Cross-dataset evaluation on Project Gutenberg highlights domain adaptation challenges, with accuracy dropping by 26.4 percentage points, yet the computational efficiency and interpretability of tree-based models still offer a scalable, explainable alternative to neural architectures.

cs.CL↗

arXiv2024

AIDetx: a compression-based method for identification of machine-learning generated text

This paper introduces AIDetx, a novel method for detecting machine-generated text using data compression techniques. Traditional approaches, such as deep learning classifiers, often suffer from high computational costs and limited interpretability. To address these limitations, we propose a compression-based classification framework that leverages finite-context models (FCMs). AIDetx constructs distinct compression models for human-written and AI-generated text, classifying new inputs based on which model achieves a higher compression ratio. We evaluated AIDetx on two benchmark datasets, achieving F1 scores exceeding 97% and 99%, respectively, highlighting its high accuracy. Compared to current methods, such as large language models (LLMs), AIDetx offers a more interpretable and computationally efficient solution, significantly reducing both training time and hardware requirements (e.g., no GPUs needed). The full implementation is publicly available at https://github.com/AIDetx/AIDetx.

cs.CL↗

arXiv2024

An experimental sorting method for improving metagenomic data encoding

Minimizing data storage poses a significant challenge in large-scale metagenomic projects. In this paper, we present a new method for improving the encoding of FASTQ files generated by metagenomic sequencing. This method incorporates metagenomic classification followed by a recursive filter for clustering reads by DNA sequence similarity to improve the overall reference-free compression. In the results, we show an overall improvement in the compression of several datasets. As hypothesized, we show a progressive compression gain for higher coverage depth and number of identified species. Additionally, we provide an implementation that is freely available at https://github.com/cobilab/mizar and can be customized to work with other FASTQ compression tools.

cs.IT↗

arXiv2021

Automatic analysis of artistic paintings using information-based measures

The artistic community is increasingly relying on automatic computational analysis for authentication and classification of artistic paintings. In this paper, we identify hidden patterns and relationships present in artistic paintings by analysing their complexity, a measure that quantifies the sum of characteristics of an object. Specifically, we apply Normalized Compression (NC) and the Block Decomposition Method (BDM) to a dataset of 4,266 paintings from 91 authors and examine the potential of these information-based measures as descriptors of artistic paintings. Both measures consistently described the equivalent types of paintings, authors, and artistic movements. Moreover, combining the NC with a measure of the roughness of the paintings creates an efficient stylistic descriptor. Furthermore, by quantifying the local information of each painting, we define a fingerprint that describes critical information regarding the artists' style, their artistic influences, and shared techniques. More fundamentally, this information describes how each author typically composes and distributes the elements across the canvas and, therefore, how their work is perceived. Finally, we demonstrate that regional complexity and two-point height difference correlation function are useful auxiliary features that improve current methodologies in style and author classification of artistic paintings. The whole study is supported by an extensive website (http://panther.web.ua.pt) for fast author characterization and authentication.

cs.CV↗

arXiv2018

Compression-Based ECG Biometric Identification Using a Non-fiducial Approach

Due to its characteristics, there is a trend in biometrics to use the ECG signal for personal identification. Recent works based on compression models have shown that these approaches are suitable to ECG biometric identification. However, the best results are usually achieved by the methods that, at least, rely on one point of interest of the ECG. In this work, we propose a compression-based non-fiducial method, that uses a measure of similarity, called the Normalized Relative Compression -- a measure related to the Kolmogorov complexity of strings. Our method uses extended-alphabet finite-context models (xaFCMs) on the quantized first-order derivative of the signal, instead of using directly the original signal, as other methods do. We were able to achieve state-of-the-art results on a database collected at the University of Aveiro, which was used on previous works, making it a good preliminary benchmark for the method.

eess.SP↗

arXiv2018

Extended-Alphabet Finite-Context Models

The Normalized Relative Compression (NRC) is a recent dissimilarity measure, related to the Kolmogorov Complexity. It has been successfully used in different applications, like DNA sequences, images or even ECG (electrocardiographic) signal. It uses a compressor that compresses a target string using exclusively the information contained in a reference string. One possible approach is to use finite-context models (FCMs) to represent the strings. A finite-context model calculates the probability distribution of the next symbol, given the previous $k$ symbols. In this paper, we introduce a generalization of the FCMs, called extended-alphabet finite-context models (xaFCM), that calculates the probability of occurrence of the next $d$ symbols, given the previous $k$ symbols. We perform experiments on two different sample applications using the xaFCMs and the NRC measure: ECG biometric identification, using a publicly available database; estimation of the similarity between DNA sequences of two different, but related, species -- chromosome by chromosome. In both applications, we compare the results against those obtained by the FCMs. The results show that the xaFCMs use less memory and computational time to achieve the same or, in some cases, even more accurate results.

cs.IT↗

arXiv2014

Information profiles for DNA pattern discovery

Finite-context modeling is a powerful tool for compressing and hence for representing DNA sequences. We describe an algorithm to detect genomic regularities, within a blind discovery strategy. The algorithm uses information profiles built using suitable combinations of finite-context models. We used the genome of the fission yeast Schizosaccharomyces pombe strain 972 h- for illustration, unveilling locations of low information content, which are usually associated with DNA regions of potential biological interest.

q-bio.GN↗

arXiv2014

A conditional compression distance that unveils insights of the genomic evolution

We describe a compression-based distance for genomic sequences. Instead of using the usual conjoint information content, as in the classical Normalized Compression Distance (NCD), it uses the conditional information content. To compute this Normalized Conditional Compression Distance (NCCD), we need a normal conditional compressor, that we built using a mixture of static and dynamic finite-context models. Using this approach, we measured chromosomal distances between Hominidae primates and also between Muroidea (rat and mouse), observing several insights of evolution that so far have not been reported in the literature.

q-bio.GN↗