We report a dataset containing full-scale, 3D images of rock plugs augmented by petrophysical lab characterization data for application in digital rock and capillary network analysis. Specifically, we have acquired microscopically resolved tomography datasets of 18 cylindrical sandstone and carbonate rock samples having lengths of 25.4 mm and diameters of 9.5 mm, respectively. Based on the micro-tomography data, we have computed porosity-values for each imaged rock sample. For validating the computed porosity values with a complementary lab method, we have measured porosity for each rock sample by using standard petrophysical characterization techniques. Overall, the tomography-based porosity values agree with the measurement results obtained from the lab, with values ranging from 8% to 30%. In addition, we provide for each rock sample the experimental permeabilities, with values ranging from 0.4 mD to above 5D. This dataset will be essential for establishing, benchmarking, and referencing the relation between porosity and permeability of reservoir rock at pore scale.

Structured evolutionary algorithms have been investigated for some time. However, they have been under-explored specially in the field of multi-objective optimization. Despite their good results, the use of complex dynamics and structures make their understanding and adoption rate low. Here, we propose the general subpopulation framework that has the capability of integrating optimization algorithms without restrictions as well as aid the design of structured algorithms. The proposed framework is capable of generalizing most of the structured evolutionary algorithms, such as cellular algorithms, island models, spatial predator-prey and restricted mating based algorithms under its formalization. Moreover, we propose two algorithms based on the general subpopulation framework, demonstrating that with the simple addition of a number of single-objective differential evolution algorithms for each objective the results improve greatly, even when the combined algorithms behave poorly when evaluated alone at the tests. Most importantly, the comparison between the subpopulation algorithms and their related panmictic algorithms suggests that the competition between different strategies inside one population can have deleterious consequences for an algorithm and reveal a strong benefit of using the subpopulation framework. The code for SAN, the proposed multi-objective algorithm which has the current best results in the hardest benchmark, is available at the following this https URL

Temporal graphs are commonly used to represent complex systems and track the evolution of their constituents over time. Visualizing these graphs is crucial as it allows one to quickly identify anomalies, trends, patterns, and other properties that facilitate better decision-making. In this context, selecting an appropriate temporal resolution is essential for constructing and visually analyzing the layout. The choice of resolution is particularly important, especially when dealing with temporally sparse graphs. In such cases, changing the temporal resolution by grouping events (i.e., edges) from consecutive timestamps -- a technique known as timeslicing -- can aid in the analysis and reveal patterns that might not be discernible otherwise. However, selecting an appropriate temporal resolution is a challenging task. In this paper, we propose ZigzagNetVis, a methodology that suggests temporal resolutions potentially relevant for analyzing a given graph, i.e., resolutions that lead to substantial topological changes in the graph structure. ZigzagNetVis achieves this by leveraging zigzag persistent homology, a well-established technique from Topological Data Analysis (TDA). To improve visual graph analysis, ZigzagNetVis incorporates the colored barcode, a novel timeline-based visualization inspired by persistence barcodes commonly used in TDA. We also contribute with a web-based system prototype that implements suggestion methodology and visualization tools. Finally, we demonstrate the usefulness and effectiveness of ZigzagNetVis through a usage scenario, a user study with 27 participants, and a detailed quantitative evaluation.

Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Niño-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks which are difficult to interpret and can fail to model large-scale atmospheric patterns. In comparison, graph neural networks (GNNs) are capable of modeling large-scale spatial dependencies and are more interpretable due to the explicit modeling of information flow through edge connections. We propose the first application of graph neural networks to seasonal forecasting. We design a novel graph connectivity learning module that enables our GNN model to learn large-scale spatial interactions jointly with the actual ENSO forecasting task. Our model, \graphino, outperforms state-of-the-art deep learning-based models for forecasts up to six months ahead. Additionally, we show that our model is more interpretable as it learns sensible connectivity structures that correlate with the ENSO anomaly pattern.

Video-based Automatic License Plate Recognition (ALPR) involves extracting vehicle license plate text information from video captures. Traditional systems typically rely heavily on high-end computing resources and utilize multiple frames to recognize license plates, leading to increased computational overhead. In this paper, we propose two methods capable of efficiently extracting exactly one frame per vehicle and recognizing its license plate characters from this single image, thus significantly reducing computational demands. The first method uses Visual Rhythm (VR) to generate time-spatial images from videos, while the second employs Accumulative Line Analysis (ALA), a novel algorithm based on single-line video processing for real-time operation. Both methods leverage YOLO for license plate detection within the frame and a Convolutional Neural Network (CNN) for Optical Character Recognition (OCR) to extract textual information. Experiments on real videos demonstrate that the proposed methods achieve results comparable to traditional frame-by-frame approaches, with processing speeds three times faster.

We introduce MilkQA, a question answering dataset from the dairy domain dedicated to the study of consumer questions. The dataset contains 2,657 pairs of questions and answers, written in the Portuguese language and originally collected by the Brazilian Agricultural Research Corporation (Embrapa). All questions were motivated by real situations and written by thousands of authors with very different backgrounds and levels of literacy, while answers were elaborated by specialists from Embrapa's customer service. Our dataset was filtered and anonymized by three human annotators. Consumer questions are a challenging kind of question that is usually employed as a form of seeking information. Although several question answering datasets are available, most of such resources are not suitable for research on answer selection models for consumer questions. We aim to fill this gap by making MilkQA publicly available. We study the behavior of four answer selection models on MilkQA: two baseline models and two convolutional neural network archictetures. Our results show that MilkQA poses real challenges to computational models, particularly due to linguistic characteristics of its questions and to their unusually longer lengths. Only one of the experimented models gives reasonable results, at the cost of high computational requirements.

Video-based vehicle detection and counting play a critical role in managing transport infrastructure. Traditional image-based counting methods usually involve two main steps: initial detection and subsequent tracking, which are applied to all video frames, leading to a significant increase in computational complexity. To address this issue, this work presents an alternative and more efficient method for vehicle detection and counting. The proposed approach eliminates the need for a tracking step and focuses solely on detecting vehicles in key video frames, thereby increasing its efficiency. To achieve this, we developed a system that combines YOLO, for vehicle detection, with Visual Rhythm, a way to create time-spatial images that allows us to focus on frames that contain useful information. Additionally, this method can be used for counting in any application involving unidirectional moving targets to be detected and identified. Experimental analysis using real videos shows that the proposed method achieves mean counting accuracy around 99.15% over a set of videos, with a processing speed three times faster than tracking based approaches.

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investigate different auto-encoder (AE) architectures, which require no labels, and explore training strategies to learn representations from images. The models are evaluated considering both the reconstruction error of the images and the feature spaces in terms of their discriminative power. We study the role of dense and convolutional layers on the results, as well as the depth and capacity of the networks, since those are shown to affect both the dimensionality reduction and the capability of generalising for different visual domains. Classification results with AE features were as discriminative as pre-trained CNN features. Our findings can be used as guidelines for the design of unsupervised representation learning methods within and across domains.

In this paper, we show how a Portuguese BERT model can be combined with structured data in order to deploy a chatbot based on a finite state machine to create a conversational AI system that helps a real-estate company to predict its client's contact motivation. The model achieves human level results in a dataset that contains 235 unbalanced labels. Then, we also show its benefits considering the business impact comparing it against classical NLP methods.

Continual Object Detection is essential for enabling intelligent agents to interact proactively with humans in real-world settings. While parameter-isolation strategies have been extensively explored in the context of continual learning for classification, they have yet to be fully harnessed for incremental object detection scenarios. Drawing inspiration from prior research that focused on mining individual neuron responses and integrating insights from recent developments in neural pruning, we proposed efficient ways to identify which layers are the most important for a network to maintain the performance of a detector across sequential updates. The presented findings highlight the substantial advantages of layer-level parameter isolation in facilitating incremental learning within object detection models, offering promising avenues for future research and application in real-world scenarios.

As more data are produced each day, and faster, data stream mining is growing in importance, making clear the need for algorithms able to fast process these data. Data stream mining algorithms are meant to be solutions to extract knowledge online, specially tailored from continuous data problem. Many of the current algorithms for data stream mining have high processing and memory costs. Often, the higher the predictive performance, the higher these costs. To increase predictive performance without largely increasing memory and time costs, this paper introduces a novel algorithm, named Online Local Boosting (OLBoost), which can be combined into online decision tree algorithms to improve their predictive performance without modifying the structure of the induced decision trees. For such, OLBoost applies a boosting to small separate regions of the instances space. Experimental results presented in this paper show that by using OLBoost the online learning decision tree algorithms can significantly improve their predictive performance. Additionally, it can make smaller trees perform as good or better than larger trees.

In Astronomy, a huge amount of image data is generated daily by photometric surveys, which scan the sky to collect data from stars, galaxies and other celestial objects. In this paper, we propose a technique to leverage unlabeled astronomical images to pre-train deep convolutional neural networks, in order to learn a domain-specific feature extractor which improves the results of machine learning techniques in setups with small amounts of labeled data available. We show that our technique produces results which are in many cases better than using ImageNet pre-training.

During the last decade, Peruvian government started to invest and promote Science and Technology through Concytec(National Council of Science and Technology). Many programs are oriented to support research projects, expenses for paper presentation, organization of conferences/ events and more. Concytec created a National Directory of Researchers(DINA) where professionals can create and add curriculum vitae, Concytec can provide official title of Researcher following some criterion for the evaluation. The actual paper aims to conduct an exploratory analysis over the curriculum vitae of Peruvian Professionals using Data Mining Approach to understand Peruvian context.

This paper studies parameter estimation using L-moments, an alternative to traditional moments with attractive statistical properties. The estimation of model parameters by matching sample L-moments is known to outperform maximum likelihood estimation (MLE) in small samples from popular distributions. The choice of the number of L-moments used in estimation remains ad-hoc, though: researchers typically set the number of L-moments equal to the number of parameters, which is inefficient in larger samples. In this paper, we show that, by properly choosing the number of L-moments and weighting these accordingly, one is able to construct an estimator that outperforms MLE in finite samples, and yet retains asymptotic efficiency. We do so by introducing a generalised method of L-moments estimator and deriving its properties in an asymptotic framework where the number of L-moments varies with sample size. We then propose methods to automatically select the number of L-moments in a sample. Monte Carlo evidence shows our approach can provide mean-squared-error improvements over MLE in smaller samples, whilst working as well as it in larger samples. We consider extensions of our approach to the estimation of conditional models and a class semiparametric models. We apply the latter to study expenditure patterns in a ridesharing platform in Brazil.

We innovate in stereo vision by explicitly providing analytical 3D surface models as viewed by a cyclopean eye model that incorporate depth discontinuities and occlusions. This geometrical foundation combined with learned stereo features allows our system to benefit from the strengths of both approaches. We also invoke a prior monocular model of surfaces to fill in occlusion regions or texture-less regions where data matching is not sufficient. Our results already are on par with the state-of-the-art purely data-driven methods and are of much better visual quality, emphasizing the importance of the 3D geometrical model to capture critical visual information. Such qualitative improvements may find applicability in virtual reality, for a better human experience, as well as in robotics, for reducing critical errors. Our approach aims to demonstrate that understanding and modeling geometrical properties of 3D surfaces is beneficial to computer vision research.

Soybean and cotton are major drivers of many countries' agricultural sectors, offering substantial economic returns but also facing persistent challenges from volunteer plants and weeds that hamper sustainable management. Effectively controlling volunteer plants and weeds demands advanced recognition strategies that can identify these amidst complex crop canopies. While deep learning methods have demonstrated promising results for leaf-level detection and segmentation, existing datasets often fail to capture the complexity of real-world agricultural fields. To address this, we collected 640 high-resolution images from a commercial farm spanning multiple growth stages, weed pressures, and lighting variations. Each image is annotated at the leaf-instance level, with 7,221 soybean and 5,190 cotton leaves labeled via bounding boxes and segmentation masks, capturing overlapping foliage, small leaf size, and morphological similarities. We validate this dataset using YOLOv11, demonstrating state-of-the-art performance in accurately identifying and segmenting overlapping foliage. Our publicly available dataset supports advanced applications such as selective herbicide spraying and pest monitoring and can foster more robust, data-driven strategies for soybean-cotton management.

Identifying \textit{Anastrepha} species from the \textit{pseudoparallela} group is problematic due to morphological similarities among species and a broad geographic variation. This group comprises $31$ species of fruit flies and pests affecting passion fruit crops. Identifying these species utilises the morphological characteristics of the specimens' wings and aculeus tips. Considering the importance of identifying these species of this group and challenges due to the low data availability and class imbalance, this paper contributes to automating the classification of the species \textit{Anastrepha chiclayae} Greene, \textit{Anastrepha consobrina} (Loew), \textit{Anastrepha curitibana} Ara\'ujo, Norrbom \& Savaris, \textit{Anastrepha curitis} Stone, and \textit{Anastrepha pseudoparallela} (Loew) using deep Learning methods and designing new features based on wing structures. We explored transfer learning solutions and proposed a new set of features based on each wing's structure. We used the dual annealing algorithm to optimise the hyperparameters of Deep Neural Networks, Random Forests, Decision Trees, and Support Vector Machines combined with autoencoders and SMOTE algorithms to account for class imbalance. We tested our approach with a dataset of $127$ high-quality images belonging to a total of $5$ species and used three-fold cross validation for training, tuning and testing, encompassing six permutations of those to assess the performance of the learning algorithms. Our findings demonstrate that our novel approach, which combines feature extraction and machine learning techniques, can improve the species classification accuracy for rare \textit{Anastrepha pseudoparallela} group specimens, with the SMOTE and Random Forests algorithms leading to the average performance of $0.72$ in terms of the mean of the individual accuracies considering all species.

Mild Cognitive Impairment (MCI) is a mental disorder difficult to diagnose. Linguistic features, mainly from parsers, have been used to detect MCI, but this is not suitable for large-scale assessments. MCI disfluencies produce non-grammatical speech that requires manual or high precision automatic correction of transcripts. In this paper, we modeled transcripts into complex networks and enriched them with word embedding (CNE) to better represent short texts produced in neuropsychological assessments. The network measurements were applied with well-known classifiers to automatically identify MCI in transcripts, in a binary classification task. A comparison was made with the performance of traditional approaches using Bag of Words (BoW) and linguistic features for three datasets: DementiaBank in English, and Cinderella and Arizona-Battery in Portuguese. Overall, CNE provided higher accuracy than using only complex networks, while Support Vector Machine was superior to other classifiers. CNE provided the highest accuracies for DementiaBank and Cinderella, but BoW was more efficient for the Arizona-Battery dataset probably owing to its short narratives. The approach using linguistic features yielded higher accuracy if the transcriptions of the Cinderella dataset were manually revised. Taken together, the results indicate that complex networks enriched with embedding is promising for detecting MCI in large-scale assessments

Autonomous Vehicles (AVs) aim to improve traffic safety and efficiency by reducing human error. However, ensuring AVs reliability and safety is a challenging task when rare, high-risk traffic scenarios are considered. These 'Corner Cases' (CC) scenarios, such as unexpected vehicle maneuvers or sudden pedestrian crossings, must be safely and reliable dealt by AVs during their operations. But they arehard to be efficiently generated. Traditional CC generation relies on costly and risky real-world data acquisition, limiting scalability, and slowing research and development progress. Simulation-based techniques also face challenges, as modeling diverse scenarios and capturing all possible CCs is complex and time-consuming. To address these limitations in CC generation, this research introduces CORTEX-AVD, CORner Case Testing & EXploration for Autonomous Vehicles Development, an open-source framework that integrates the CARLA Simulator and Scenic to automatically generate CC from textual descriptions, increasing the diversity and automation of scenario modeling. Genetic Algorithms (GA) are used to optimize the scenario parameters in six case study scenarios, increasing the occurrence of high-risk events. Unlike previous methods, CORTEX-AVD incorporates a multi-factor fitness function that considers variables such as distance, time, speed, and collision likelihood. Additionally, the study provides a benchmark for comparing GA-based CC generation methods, contributing to a more standardized evaluation of synthetic data generation and scenario assessment. Experimental results demonstrate that the CORTEX-AVD framework significantly increases CC incidence while reducing the proportion of wasted simulations.