Software effort estimation predicts resources needed for a project, including person-hours and costs, and is vital for effective planning and budgeting. This paper compares two grammar-based evolutionary algorithms: grammar-based genetic programming (GGP) and grammatical evolution (GE). Both algorithms are tested on public project datasets and compared with machine learning models such as support vector machines, artificial neural networks, and least-squares linear regression. Results demonstrate that GGP and GE outperform alternative methods across two evaluation metrics, highlighting their effectiveness in estimating software effort.

Fitness Landscape Analysis (FLA) is one of the most effective approaches to understanding how the best solutions to an optimization problem are distributed within its search space. Several studies have been conducted with the aim of investigating the fitness landscape of AutoML (Automated Machine Learning) problems, in which the search space is composed of alternative pipelines for building ML models. However, FLA in this context presents significant challenges due to the inherent complexity of AutoML problems. Moreover, previous research indicates that traditional FLA metrics used to characterize the fitness landscapes are not suitable for problems involving AutoML. In this paper, we explore the relationship between the complexity characteristics of ML datasets and FLA metrics for AutoML. In fact, there is evidence in the literature that these characteristics actually exert a significant influence on AutoML’s search space. To date, previous authors have not yet investigated how the complexity characteristics of datasets actually impact the fitness landscape in AutoML. In our analysis, we identified statistically significant correlations between them in such a way that complexity measures can serve as more cost-effective proxies for FLA metrics.

The widespread use of machine learning (ML) in software engineering (SE) encounters a notable challenge: the need for various domain-specific parameters in algorithms. The issue arises when attempting to reuse these parameters across different applications, resulting in sub-optimal outcomes. This hindrance significantly contributes to the limited migration of ML solutions from research labs to industrial settings. This paper underscores the pressing need for novel research to tackle the overarching problem of generic algorithm customisation. To address this, we propose leveraging Automated Machine Learning (AutoML) approaches. These techniques automatically select intelligible models and their corresponding hyper-parameters for forecasting software defect-proneness. More specifically, this paper adapts an AutoML approach to the field of software defect prediction, namely a hyper-heuristic evolutionary algorithm for automatically designing decision tree algorithms (HEAD-DT), originally proposed to address a generic optimisation problem. We benchmark against the popular general software defect-proneness prediction framework (GSDP) and some standard classifiers. Experimental results reveal that the proposed HEAD-DT implementation surpasses other algorithms across three distinct evaluation measures.

Agent-based models (ABM) stand as a well-established paradigm in developing computational models. ABM enable the simulation of complex systems by consolidating individual-level interactions through an underlying artificial social network. Upon the accurate construction of a model, experts can employ it as a decision support system for assessing policies in hypothetical what-if scenarios and gaining insights into the operational dynamics of the target system. However, ABM still face diverse challenges such as learning realistic agents' behavioral patterns to model real-world conducts and habits. Existing research shows that machine learning techniques, when used in ABM, can address such challenges. This work focuses on using evolutionary algorithms (EAs) to learn agents' behavior through the definition of their micro-rules, aiming to accurately model them, and thus improving the global performance of the system. To do so, we model the machine learning problem and undertake a comparative analysis of seven EAs, encompassing both classical and recent approaches, to learn agents' micro-rules with a specific focus on consumers' behavior for brand selection. Our investigation involves the assessment of the performance of each EA across problem instances derived from an ABM applied to real-world marketing domains such as dairy products and automakers. The findings of our study reveal a distinct dominance of SHADE-ILS and DECC-g over the remaining algorithms considered. Furthermore, we underline the advantages of these methods to assist modelers in selecting among the best solutions.

The rapid evolution and widespread accessibility of non-invasive medical imaging technologies, exemplified by Magnetic Resonance Imaging (MRI) and Computerized Tomography (CT), are fundamentally reshaping medical decisionmaking paradigms. These sophisticated imaging modalities, capable of extracting high-definition medical images, have emerged as integral components of modern healthcare, facilitating precise diagnostics and treatment planning. The escalating adoption of such technologies, however, has accentuated the need for a nuanced understanding and optimization of the performance and productivity of both medical equipment and the teams operating them, mainly due to the high costs and risks caused by their misuse. This work proposes using univariate analytical models to estimate the number of exams performed per day with machine learning algorithms. For such, different energy-related sensors monitoring 25 magnetic resonance equipment from three different brands were considered. The results of the research reveal a compelling validation of the proposed approach. A notably high Pearson correlation coefficient is observed between the predictions generated by the evaluated models and the real measurements obtained through the Radiology Information System (RIS). This robust correlation emphasizes the accuracy and reliability of the estimation models, validating their potential applicability in real-world healthcare scenarios. Furthermore, the study unveils an intriguing trend that distinguishes the performance of electric current sensors. Thirteen out of the 25 evaluated MRI machines demonstrate superior results when equipped with electric current sensors compared to other sensor types. This nuanced insight not only substantiates the critical role of energy-related sensors in predicting equipment performance but also underscores the importance of tailoring monitoring strategies to the unique characteristics of each machine.

Texts produced by the Brazilian judiciary have a complex and technical vocabulary, with elaborate use of the Portuguese language and many legal terms difficult to be understood, generating a barrier in communication between the judiciary and the population. In this sense, the Automatic Text Simplification (ATS), activity of the Natural Language Processing (NLP) area, can be applied to improve the readability of these types of text using specialized algorithms, and promote scalability in simplifying them, in view of the great demand in the courts. In this context, this article presents an evaluation of four methods of state of the art in text simplification, evaluated according to readability metrics, to improve the quality of existing texts in the judicial summaries, dataset containing 100 summaries of the Federal Regional Court of the 5th Region (TRF5) and another 100 of the Federal Supreme Court (STF). The methods MUSS(EN), MUSS(PT), Transformers and NMT + Attention were tested, and the results of the simplifications exceeded the FRE readability index of the original texts, making them more readable.

Textual cohesion is an essential aspect of a formally written text, related to linguistic mechanisms that connect elements such as words, sentences, and paragraphs. Several studies have proposed approaches to estimate textual cohesion in essays automatically. There is limited research that aims to study the extent to which the use of machine learning approaches can predict the textual cohesion of essays written in different languages (not just English). This paper reports on the findings of a study that aimed to propose and evaluate approaches that automatically estimate the cohesion of essays in Portuguese and English. The study proposed regression-based models grounded in conventional feature-based machine learning methods and deep learning-based pre-trained language models. The study also examined the explainability of automated approaches to scrutinize their predictions. We analyzed two datasets composed of 4,570 (Portuguese) and 7,101 (English) essays. The results demonstrate that a deep learning-based model achieved the best performance on both datasets with a moderate Pearson correlation with human-rated cohesion scores. However, the explainability of the automatic cohesion estimations based on conventional machine learning models offered a stronger potential than that of the deep learning model.

The sequencing of sampling algorithms has shown to be a promising approach in generating balanced versions of unbalanced data. Sequencing allows different algorithms of under-sampling and/or over-sampling to be performed in sequence, producing a resulting balanced database. However, defining the most appropriate sequence of sampling algorithms is challenging. This article treats the sequencing problem as a combinatorial optimization task and proposes a multi-objective optimization method to seek promising solutions that maximize the performance of classifiers both in accuracy and in F1-score. The results showed that the proposed method was capable of finding optimized sequences that improved the performance of the classifiers, obtaining statistically better results, mainly in F1- score, when compared with competing methods, in most of the selected unbalanced problems.

Domestic violence has increased globally as the COVID-19 pandemic combines with economic and social stresses. Some works have used traditional feature extractors to identify body positions to detect physical violence. Besides, the use of Machine Learning is limited by the trade-off between collecting more data while keeping users' privacy. Federated Learning (FL) is a technique that allows the creation of client-server networks, in which anonymized training data can be uploaded to a central model, responsible for aggregating and keeping the model up to date, and then distributing the updated model to the clients' nodes. This paper proposed an FL approach to the violence detection problem in video. The framework was evaluated on AIRTLab Dataset, in which frames were extracted. It used pretrained Convolutional Neural Networks (CNN) to address the image classification problem. Inception v3, MobileNet v2, ResNet-152 v2, and VGG-16 architectures were evaluated, with the MobileNet architecture presenting the best performance, in terms of accuracy (99.4%), with a loss of 0.5% when compared to the non-FL setting.

Brazilian universities have included essay writing assignments in the entrance examination procedure to select prospective students. The essay scorers manually look for the presence of required Rhetorical Structure Theory (RST) categories and evaluate essay coherence. However, identifying RST categories is a time-consuming task. The literature reported several attempts to automate the identification of RST categories in essays with machine learning. Still, previous studies have focused on using machine learning algorithms trained on content-dependent features that can diminish classification performance, leading to over-fitting and hindering model generalisability. Therefore, this paper proposes: (i) the analysis of state-of-the-art classifiers and content-independent features to the task of RST rhetorical moves; (ii) a new approach that considers the sequence of the text to extract features – i.e. sequential content-independent features; (iii) an empirical study about the generalisability of the machine learning models and sequential content-independent features for this context; (iv) the identification of the most predictive features for automated identification of RST categories in essays written in Portuguese. The best performing classifier, XGBoost, based on sequential content-independent features, outperformed the classifiers used in the literature and are based on traditional content-dependent features. The XGBoost classifier based on sequential content-independent features also reached promising accuracy when tested for generalisability.

Deep Convolutional Neural Networks (CNNs) have reached the attention in the last decade due to their successful application to many computer vision domains. Several handcrafted architectures have been proposed in the literature, with increasing depth and millions of parameters. However, the optimal architecture size and parameters setup are dataset-dependent and challenging to find. For addressing this problem, this work proposes a Multi-Objective Grammatical Evolution framework to automatically generate suitable CNN architectures (layers and parameters) for a given classification problem. For this, a Context-free Grammar is developed, representing the search space of possible CNN architectures. The proposed method seeks to find suitable network architectures considering two objectives: accuracy and F1-score. We evaluated our method on CIFAR-10, and the results obtained show that our method generates simpler CNN architectures and overcomes the results achieved by larger (more complex) state-of-the-art CNN approaches and other grammars.

According to the World Health Organization, an estimated one billion people live with a disability. Millions of them are non-verbal and also experience motor-skill challenges. The restrictions on participation and communication caused by such disabilities often lead to discrimination and social exclusion, including the lack of access to formal education. Augmentative and Alternative Communication (AAC) is a method to afford communication for people with speech impairment. Software applications that implement AAC bring benefits of adaptability and personalization over traditional paper-based methods, but their usability needs improvement, particularly to increase user autonomy. This paper presents an interface redesign of the Livox AAC application, and a new user onboarding process based on user research to adjust the interface to user needs, contributing to user autonomy on AAC use.

The assessment of machine learning algorithms in a particular task is usually done by means of empirical evaluation on real world observational data. However, sometimes there is no previously annotated data available. Synthetic datasets have gained attention as an alternative for efficient classifier evaluation, since they are accessible and high parameterizable for a given learning task. The characterization of such databases can be done by means of descriptors on the learning object at hand, e.g., complexity measures, which extract statistical and geometric characteristics from the data sets, for a given classification problem, in order to estimate their complexity. Such complexity measures can be used to guide the production of synthetic datasets, so it reinforces one or more dataset features. The present work proposes the use of a many-objective algorithm for the generation of synthetic data considering four measures of complexity that will be balanced at the same time. The results showed that the proposal is able to optimize conflicting objectives, generating datasets of specific complexities.

Selecting the best architecture for a Deep Neural Network (DNN) is a non-trivial task since there is a massive amount of possible configurations (layers and parameters) and great difficulty in how to choose them. To make this task more independent of human interaction, this work addresses the DNN architecture selection problem as a multi-objective optimization task with different criteria in a combinatorial context. For this, we defined a new way to represent the architecture of DNN (layer sequence) as a solution in the optimization process. The proposed method attempts to find the best composition and sequence of layers for the DNN architecture satisfying two criteria: accuracy and F1score. The method was evaluated for performance and compared to the exhaustive and random approaches and state-of-the-art DNN algorithms. The results obtained showed that the proposed method is capable of achieving results close to the optimum, and competitive when compared to those results reached by state of the art algorithms.

This paper presents a study that examined automated cross-language classification of online discussion messages for the levels of cognitive presence, a key construct from the widely used Community of Inquiry (CoI) model of online learning. Specifically, we examined the classification of 1,500 Portuguese language discussion messages using a classifier trained on a corpus of the 1,747 English language discussion messages. In the study, a random forest classifier was developed using a small set of 108 validated indicators of psychological processes, linguistic coherence, and online discussion structure. The classifier obtained 67% accuracy and Cohen's κ of 0.32, showing a moderate level of inter-rater agreement above chance and the general viability of the proposed approach. Most importantly, the findings suggest that certain aspects of cognitive presence construct are highly generalizable and transfer across different languages. Finally, the paper also presents a novel method for addressing class imbalance problem using a generic algorithm heuristic technique, which provided substantial improvements over the use of imbalanced dataset. Results and practical implications are further discussed.

Imbalanced datasets are pervasive and comprise many real-world applications, such as medical diagnosis and software fault detection. As common classifiers assume a balanced distribution of examples in the data, learning from imbalanced datasets presents its own challenges. Sampling techniques play an essential role in aiding classifiers which learn from imbalanced datasets, as these techniques return a more balanced version of the imbalanced dataset. Given the current number of sampling techniques available, selecting a technique together with a set of values for its hyper-parameters is a time-consuming task. In this work, we treat the mentioned problem as a many-objective optimization problem. An evolutionary algorithm was applied to select sampling algorithms and their parameters to imbalanced datasets considering multiple performance criteria. In the experiments, we compared the proposed method against the brute-force, the default (all sampling algorithms with their default hyper-parameters' values), and the random approaches. The experiments revealed that the proposal reached results comparable to those achieved by the brute-force approach, overcame the techniques with their default parameters most of the time, and surpassed the random search approach in the majority of the problems.

The aim of this paper is to present a taxonomy for security threats on the Web ecosystem. We proposes a classification model based on 21 vectors divided into 8 distinct security threats, making use of levels of abstraction and criteria for discrimination which consider propagation and similarity in vulnerabilities. We also propose to estimate the risk factor and impacts on assets, considering data breaches, human aspects and service reliability. In addition, we validate the taxonomic model proposed through the catalogues of attacks facing the public. Thus, it was possible to observe its applicability for most of the attacks which appear before the public.

In this work, we propose a framework to automatically generate effective PSO designs by adopting Grammatical Evolution (GE). In the proposed framework, GE searches for adequate structures and parameter values (e.g., acceleration constants, velocity equations and different particles' topology) in order to evolve the PSO design. For this, a high-level Backus--Naur Form (BNF) grammar was developed, representing the search space of possible PSO designs. In order to verify the performance of the proposed method, we performed experiments using 16 diverse continuous optimization problems, with different levels of difficulty. In the performed experiments, we identified the parameters and components that most affected the PSO performance, as well as identified designs that could be reused across different problems. We also demonstrated that the proposed method generates useful designs which achieved competitive solutions when compared to well succeeded algorithms from the literature.

The Support Vector Machine algorithm is sensitive to the choice of parameter settings. If these are not set correctly, the algorithm may have a substandard performance. It has been shown that meta-learning can be used to support the selection of SVM parameters. However, it is very dependent on the quality of the dataset and the meta-features used to characterize the dataset. As alternative for this problem, a recent technique called Active Testing characterized a dataset based on the pairwise performance differences between possible solutions. This approach selects the most useful cross-validation tests. Each new cross-validation test will contribute information to a better estimate of dataset similarity, and thus better predict which algorithms are most promising on the new dataset. In this paper we propose the application of Active Testing for the SVM parameter problem. We test it on the problem of setting the RBF kernel parameters for classification problems and we compare its similarity strategy with based on data characteristics. The results showed the variants of Active Testing that rely on cross-validation tests to estimate dataset similarity provides better solutions than those that rely on data characteristics.

Support Vector Machines (SVMs) have become a well succeed technique due to the good performance it achieves on different learning problems. However, the performance depends on adjustments on its model. The automatic SVM parameter selection is a way to deal with this. This approach is considered an optimization problem whose goal is to find suitable configuration of parameters which attends some learning problem. This work proposes the use of Particle Swarm Optimization (PSO) to treat the SVM parameter selection problem. As the design of learning systems is inherently a multi-objective optimization problem, a multi-objective PSO (MOPSO) was used to maximize the success rate and minimize the number of support vectors of the model. Moreover, we propose the combination of Meta-Learning (ML) with MOPSO to the cited problem. ML is used to recommend SVM parameters, to a given input problem, based on well-succeeded parameters adopted in previous similar problems. In this combination, initial solutions provided by ML are possibly located in good regions in the search space. Hence, using a reduced number of candidate search points, the search process, to find an adequate solution, would be less expensive. We highlight that, the combination of search algorithms with ML was just studied in the single objective field and the use of MOPSO in this context has not been investigated. In our work, we implemented a prototype in which MOPSO was used to select the values of two SVM parameters for classification problems. In the performed experiments, the proposed solution (MOPSO using ML or Hybrid MOPSO) was compared to a MOPSO with random initialization, obtaining paretos with higher quality on a set of 40 classification problems.

Support Vector Machine (SVM) is a supervised technique, which achieves good performance on different learning problems. However, adjustments on its model are essentials to the SVM work well. Optimization techniques have been used to automatize this process finding suitable configurations of parameters which attends some learning problems. This work utilizes Particle Swarm Optimization (PSO) applied to the SVM parameter selection problem. As the learning systems are essentially a multi-objective problem, a multi-objective PSO (MOPSO) was used to maximize the success rate and minimize the number of support vectors of the model. Nevertheless, we propose the combination of Meta-Learning (ML) with a modified MOPSO which uses the crowding distance mechanism (MOPSO-CDR). In this combination, solutions provided by ML are possibly located in good regions in the search space. Hence, using a reduced number of successful candidates, the search process would converge faster and be less expensive. In our work, we implemented a prototype in which MOPSO-CDR was used to select the values of two SVM parameters for classification problems. In the performed experiments, the proposed solution (MOPSO-CDR using ML) was compared to the MOPSO-CDR with random initialization, obtaining pareto fronts with higher quality on a set of 40 classification problems.

Although software testing is a central task in the software lifecycle, it is sometimes neglected due to its high costs. Tools to automate the testing process minor its costs, however they generate large test suites with redundant Test Cases (TC). Automatic TC Selection aims to reduce a test suite based on some selection criterion. This process can be treated as an optimization problem, aiming to find a subset of TCs which optimizes one or more objective functions (i.e., selection criteria). The majority of search-based works focus on single-objective selection. In this light, we developed a mechanism for functional TC selection which considers two objectives simultaneously: maximize requirements' coverage while minimizing cost in terms of TC execution effort. This mechanism was implemented as a multi-objective optimization process based on Particle Swarm Optimization (PSO). We implemented two multi-objective versions of PSO (BMOPSO and BMOPSO-CDR). The experiments were performed on two real test suites, revealing very satisfactory results (attesting the feasibility of the proposed approach). We highlight that execution effort is an important aspect in the testing process, and it has not been used in a multi-objective way together with requirements coverage for functional TC selection.

Particle Swarm Optimization (PSO) has been widely used to solve many different real world optimization problems. Many novel PSO approaches have been proposed to improve the PSO performance. Recently, a communication topology based on clans was proposed. In this paper, we propose the dynamic clan PSO topology. In this approach, a novel ability is included in the clan topology, named migration process. The goal is to improve the PSO degree of convergence focusing on the distribution of the particles in the search space. A comparison with the original clan topology and other well known topologies was performed and our results in five benchmark functions have shown that the changes can provide better results, except for the Rastrigin function.

Particle swarm optimization (PSO) has been widely used to solve unconstrained optimization problems. However, problems in hyper dimensional spaces require the development of enhanced issues. For this, some variations of the original PSO form have been proposed, mainly concerning on the velocity update equation and sophisticated communication topologies of the swarm. In this paper, we propose a PSO topology based on multiples rings. In this approach, the acceleration coefficients and the communication inside each ring are adjusted based on a grade, which is calculated by evaluating a fitness comparison. The diversity of the system is provided by the ring rotations. The neighborhood of each particle is defined according its grade as defined in the dispersed PSO. A comparison with star, ring and simple multi-ring topologies was performed. Our simulation results showed that the proposed topology always achieve good results when compared to other approaches.