ABSTRACT Background Intrusion Tolerant Systems (ITS) aim to maintain system security despite adversarial presence by limiting the impact of successful attacks. Current ITS risk managers rely heavily on public databases like NVD and Exploit DB, which suffer from long delays in vulnerability evaluation, reducing system responsiveness. Objective This work extends the HAL 9000 Risk Manager to integrate additional real‐time threat intelligence sources and employ machine learning techniques to automatically predict and reassess vulnerability risk scores, addressing limitations of existing solutions. Methods A custom‐built scraper collects diverse cybersecurity data from multiple Open Source Intelligence (OSINT) platforms, such as NVD, CVE, AlienVault OTX, and OSV. HAL 9000 uses machine learning models for CVE score prediction, vulnerability clustering through scalable algorithms, and reassessment incorporating exploit likelihood and patch availability to dynamically evaluate system configurations. Results Integration of newly scraped data significantly enhances the risk management capabilities, enabling faster detection and mitigation of emerging vulnerabilities with improved resilience and security. Experiments show HAL 9000 provides lower risk and more resilient configurations compared to prior methods while maintaining scalability and automation. Conclusions The proposed enhancements position HAL 9000 as a next‐generation autonomous Risk Manager capable of effectively incorporating diverse intelligence sources and machine learning to improve ITS security posture in dynamic threat environments. Future work includes expanding data sources, addressing misinformation risks, and real‐world deployments.

Convolutional Neural Networks (CNN) have been successfully applied to images, text and audio, but their performance are not so good when applied to feature-based tabular data. Exceptions are works such as TabNet and DeepInsight, which employ end-to-end approaches. In this work, we propose an alternative way of using CNNs to model tabular data where knowledge is extracted from the feature space before being introduced to the network. Our strategy, Map-Optimize-Learn (MOL), changes the shape representation of samples in order to produce suitable input data for the CNN architecture. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against baseline and state of the art Machine Learning (ML) algorithms for tabular datasets. Preliminary results suggest that the strategy has potential to improve prediction quality of tabular data over end-to-end CNN methods and classical ML methods.

This work discusses a strategy named Map, Optimize and Learn (MOL) which analyzes how to change the representation of samples of a 2D dataset to generate useful patterns for classification tasks using Convolutional Neural Networks (CNN) architectures. The strategy is applied to a real-world scenario of children and teenagers with cardiac pathology and compared against state of the art Machine Learning (ML) algorithms for 2D datasets. Preliminary results suggests that the strategy has potential to improve the prediction quality.

We implement a quantum binary classifier where given a dataset of pairs of training inputs and target outputs our goal is to predict the output of a new input. The script is based in a hybrid scheme inspired in an existing PennyLane's variational classifier and to encode the classical data we resort to PennyLane's amplitude encoding embedding template. We use the quantum binary classifier applied to the well known Iris dataset and to a car traffic dataset. Our results show that the quantum approach is capable of performing the task using as few as 2 qubits. Accuracies are similar to other quantum machine learning research studies, and as good as the ones produced by classical classifiers.

One important problem in Bioinformatics is the discovery of new interactions between cellular lines and chemical compounds. In silico methods for cell-line screening are fundamental to optimize cost and time in the drug discovery processes. In order to build these methods, we need to computationally represent cell lines. Current methods for modeling cell line interactions rely on comparing genetic expression profiles. However, these profiles are usually unknown. In this work, we present a method to characterize and represent cell lines by text processing the related scientific literature. We collect abstracts of scientific papers about cellular lines from Cellosaurus and PubMed. These documents are then represented as TF-IDF vectors. We build a data set for classification with the document vectors having the cell line identifier as the target class. We then apply a multiclass SVM classification method. We use Support Vector Domain Description to describe and characterize each cell line with its corresponding hyperplane obtained with a one-vs-rest training. We evaluated several configurations of classifiers, using micro-averaged precision as metric to choose the best classifier, and were able to differentiate cellular lines from a set of 200+.

Diabetes management is a complex and a sensible problem as each diabetic is a unique case with particular needs. The optimal solution would be a constant monitoring of the diabetic's values and automatically acting accordingly. We propose an approach that guides the user and analyses the data gathered to give individual advice. By using data mining algorithms and methods, we uncover hidden behaviour patterns that may lead to crisis situations. These patterns can then be transformed into logical rules, able to trigger in a particular context, and advise the user. We believe that this solution, is not only beneficial for the diabetic, but also for the doctor accompanying the situation. The advice and rules are useful input that the medical expert can use while prescribing a particular treatment. During the data gathering phase, when the number of records is not enough to attain useful conclusions, a base set of logical rules, defined from medical protocols, directives and/or advice, is responsible for advise and guiding the user. The proposed system will accompany the user at start with generic advice, and with constant learning, advise the user more specifically. We discuss this approach describing the architecture of the system, its base rules and data mining component. The system is to be incorporated in a currently developed diabetes management application for Android.

Several works in the literature use propositional (“black box”) approaches to generate prediction models. In this work we employ the Inductive Logic Programming technique, whose prediction model is based on first order rules, to the domain of breast cancer. These rules have the advantage of being interpretable and convenient to be used as a common language between the computer scientists and the medical experts. We also explore the relevance of some of variables usually collected to predict breast cancer. We compare our results with a propositional classifier that was considered best for the same dataset studied in this paper.

Mammoclass is a web tool that allows users to enter a small set of variable values that describe a finding in a mammography, and produces a probability of this finding being malignant or benign. The tool requires that the user types in every variable a value in order to perform a prediction. In this work, we present a speech-to-text interface integrated to MammoClass that allows radiologists to speak up a mammography report instead of typing it in. This new MammoClass module can take audio content, transcribe it into written words, and automatically extract the variable values by applying a parser to the recognized text. Results of spoken mammography reports show that the same variables are extracted for both types of input: typed in or dictated text.

Probabilistic Inductive Logic Programming (PILP) is a relatively unexplored area of Statistical Relational Learning which extends classic Inductive Logic Programming (ILP). Within this scope, we introduce SkILL, a Stochastic Inductive Logic Learner, which takes probabilistic annotated data and produces First Order Logic (FOL) theories. Data in several domains such as medicine and bioinformatics have an inherent degree of uncertainty, and because SkILL can handle this type of data, the models produced for these areas are closer to reality. SkILL can then use probabilistic data to extract non-trivial knowledge from databases, and also address efficiency issues by introducing an efficient search strategy for finding hypotheses in PILP environments. SkILL's capabilities are demonstrated using a real world medical dataset in the breast cancer domain.

Bayesian network structures are usually built using only the data and starting from an empty network or from a naïve Bayes structure. Very often, in some domains, like medicine, a prior structure knowledge is already known. This structure can be automatically or manually refined in search for better performance models. In this work, we take Bayesian networks built by specialists and show that minor perturbations to this original network can yield better classifiers with a very small computational cost, while maintaining most of the intended meaning of the original model.

We evaluated a population of 7199 children between 2 and 19 years old to study the relations between the observed demographic and physiological features in the occurrence of a pathological/non-pathological heart condition. The data was collected at the Real Hospital Português, Pernambuco, Brazil. We performed a feature importance study, with the aim of categorizing the most relevant variables, indicative of abnormalities. Results show that second heart sound, weight, heart rate, height and secondary reason for consultation are important features, but not nearly as decisive as the presence of heart murmurs. Quantitatively speaking, systolic murmurs and a hyperphonetic second heart sound increase the odds of having a pathology by a factor of 320 and 6, respectively.

When mammography reveals a suspicious finding, a core needle biopsy is usually recommended. In 5% to 15% of these cases, the biopsy diagnosis is non-definitive and a more invasive surgical excisional biopsy is recommended to confirm a diagnosis. The majority of these cases will ultimately be proven benign. The use of excisional biopsy for diagnosis negatively impacts patient quality of life and increases costs to the healthcare system. In this work, we employ a multi-relational machine learning approach to predict when a patient with a non-definitive core needle biopsy diagnosis need not undergo an excisional biopsy procedure because the risk of malignancy is low.

Map-Reduce is a programming model that has its roots in early functional programming. In addition to producing short and elegant code for problems involving lists or collections, this model has proven very useful for large-scale highly parallel data processing. In this work, we present the design and implementation of a high-level parallel construct that makes the Map-Reduce programming model available for Prolog programmers. To the best of our knowledge, there is no Map-Reduce framework native to Prolog, and so the aim of this work is to offer data processing features from which several applications can greatly benefit; the Inductive Logic Programming field, for instance, can take advantage of a Map-Reduce predicate when proving newly created rules against sets of examples. Our Map-Reduce model was comprehensively tested with different applications. Our experiments, using the Yap Prolog system, show that: (i) the model scales linearly up to 24 processors; (ii) a dynamic distributed scheduling strategy performs better than centralized or static scheduling strategies; and (iii) the performance varies significantly with the number of items being sent to each processor at a time. Overall, our Map-Reduce framework presents as a good alternative for both taking advantage of the currently available low cost multi-core architectures and developing scalable data processing applications, native to the Prolog programming language.

In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser's performance is comparable to the manual method.

The DigiScope project aims at developing a digitally enhanced stethoscope capable of using state of the art technology in order to help physicians in their daily medical routine. One of the main tasks of DigiScope is to build a repository of auscultations (sound and medical related data). In this work, we present a preliminary analysis and study of the first auscultations performed on children of a Brazilian hospital. Results indicate that classifiers can be obtained that distinguish reasonably well patients with cardiac pathologies from those that do not have pathologies.

Breast screening is the regular examination of a woman's breasts to find breast cancer earlier. The sole exam approved for this purpose is mammography. Usually, findings are annotated through the Breast Imaging Reporting and Data System (BIRADS) created by the American College of Radiology. The BIRADS system determines a standard lexicon to be used by radiologists when studying each finding. Although the lexicon is standard, the annotation accuracy of the findings depends on the experience of the radiologist. Moreover, the accuracy of the classification of a mammography is also highly dependent on the expertise of the radiologist. A correct classification is paramount due to economical and humanitarian reasons. The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a data set consisting of 348 consecutive breast masses that underwent image guided or surgical biopsy performed between October 2005 and December 2007 on 328 female subjects. The main conclusions are threefold: (1) automatic classification of a mammography, independent on information about mass density, can reach equal or better results than the classification performed by a physician; (2) mass density seems to be a good indicator of malignancy, as previous studies suggested; (3) a machine learning model can predict mass density with a quality as good as the specialist blind to biopsy, which is one of our main contributions. Our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.

Abstract One of the main advantages of Logic Programming (LP) is that it provides an excellent framework for the parallel execution of programs. In this work we investigate novel techniques to efficiently exploit parallelism from real-world applications in low cost multi-core architectures. To achieve these goals, we revive and redesign the YapOr system to exploit or-parallelism based on a multi-threaded implementation. Our new approach takes full advantage of the state-of-the-art fast and optimized YAP Prolog engine and shares the underlying execution environment, scheduler and most of the data structures used to support YapOr's model. Initial experiments with our new approach consistently achieve almost linear speedups for most of the applications, proving itself as a good alternative for exploiting implicit parallelism in the currently available low cost multi-core architectures.

In this work, we study the behaviour of different resource scheduling strategies when doing job orchestration in grid environments. We empirically demonstrate that scheduling strategies based on reinforcement learning are a good choice to improve the overall performance of grid applications and resource utilization.

Speedup in distributed executions of Constraint Logic Programming (CLP) applications are directed related to a good constraint partitioning algorithm. In this work we study different mechanisms to distribute constraints to processors based on straightforward mechanisms such as Round-Robin and Block distribution, and on a more sophisticated automatic distribution method, Grouping-Sink, that takes into account the connectivity of the constraint network graph. This aims at reducing the communication overhead in distributed environments. Our results show that Grouping-Sink is, in general, the best alternative for partitioning constraints as it produces results as good or better than Round-Robin or Blocks with low communication rate.

Abstract One of the challenges in Grid computing research is to provide a means to automatically submit, manage, and monitor applications whose main characteristic is to be composed of a large number of tasks. The large number of explicit tasks, generally placed on a centralized job queue, can cause several problems: (1) they can quickly exhaust the memory of the submission machine; (2) they can deteriorate the response time of the submission machine due to these demanding too many open ports to manage remote execution of each of the tasks; (3) they may cause network traffic congestion if all tasks try to transfer input and/or output files across the network at the same time; (4) they make it impossible for the user to follow execution progress without an automatic tool or interface; (5) they may depend on fault‐tolerance mechanisms implemented at application level to ensure that all tasks terminate successfully. In this work we present and validate a novel architectural model, GRAND (Grid Robust ApplicatioN Deployment), whose main objective is to deal with the submission of a large numbers of tasks. Copyright © 2006 John Wiley & Sons, Ltd.

Grid environments are ideal for executing applications that require a huge amount of computational work, both due to the big number of tasks to execute and to the large amount of data to be analysed. Unfortunately, current tools may require that users deal themselves with corrupted outputs or early termination of tasks. This becomes inconvenient as the number of parallel runs grows to easily exceed the thousands. ReGS is a user-level software designed to provide automatic detection and restart of corrupted or early terminated tasks. ReGS uses a Web interface to allow the setup and control of grid execution, and provides automatic input data setup. ReGS allows the automatic detection of job dependencies, through the GRID-ADL task management language. Our results show that besides automatically and effectively managing a huge number of tasks in grid environments, ReGS is also a good monitoring tool to spot grid nodes pitfalls.

Scheduling by edge reversal (SER) is a fully distributed scheduling mechanism based on the manipulation of acyclic orientations of a graph. This work uses SER to perform constraint partitioning of constraint satisfaction problems (CSP). In order to apply the SER mechanism, the graph representing the constraints must receive an acyclic orientation. Since obtaining an optimal acyclic orientation is an NP-hard problem, we study three nondeterministic strategies known in the literature: Alg-Neigh, Alg-Edges, and Alg-Colour. We implemented the three algorithms and the SER scheduling mechanism, applying them to the CSP constraint networks generated from 3 applications. Our results show that SER has a great potential to perform a good partitioning of the constraint graphs.