Artificial intelligence extracts key insights from legal documents to predict intimate partner femicide.

Legal documents serve as valuable repositories of information pertaining to crimes, encompassing not only legal aspects but also relevant details about criminal behaviors. To date and the best of our knowledge, no studies in the field examine legal documents for crime understanding using an Artificial Intelligence (AI) approach. The present study aims to fill this research gap by identifying relevant information available in legal documents for crime prediction using Artificial Intelligence (AI). This innovative approach will be applied to the specific crime of Intimate Partner Femicide (IPF). A total of 491 legal documents related to lethal and non-lethal violence by male-to-female intimate partners were extracted from the Vlex legal database. The information included in these documents was analyzed using AI algorithms belonging to Bayesian, functions-based, instance-based, tree-based, and rule-based classifiers. The findings demonstrate that specific information from legal documents, such as past criminal behaviors, imposed sanctions, characteristics of violence severity and frequency, as well as the environment and situation in which this crime occurs, enable the correct detection of more than three-quarters of both lethal and non-lethal violence within male-to-female intimate partner relationships. The obtained knowledge is crucial for professionals who have access to legal documents, as it can help identify high-risk IPF cases and shape strategies for preventing crime. While this study focuses on IPF, this innovative approach has the potential to be extended to other types of crimes, making it applicable and beneficial in a broader context.

A Comprehensive Analysis of Factors Associated with Intimate Partner Femicide: A Systematic Review.

There has been a growing concern about violence against women by intimate partners due to its incidence and severity. This type of violence is a severe problem that has taken the lives of thousands of women worldwide and is expected to continue in the future. A limited amount of research exclusively considers factors related only to these women's deaths. Most focus on deaths of both men and women in an intimate partnership and do not provide precise results on the phenomenon under study. The necessity for an actual synthesis of factors linked solely to women's deaths in heterosexual relationships is key to a comprehensive knowledge of that case. This could assist in identifying high-risk cases by professionals involving an interdisciplinary approach. The study's objective is to systematically review the factors associated with these deaths. Twenty-four studies found inclusion criteria extracted from seven databases (Dialnet, Web of Science, Pubmed, Criminal Justice, Psychology and Behavioral Science Collection, Academic Search Ultimate, and APA Psyarticles). The review was carried out under the PRISMA guidelines' standards. The studies' quality assessment complies with the MMAT guidelines. Findings revealed that there are specific factors of the aggressor, victim, partner's relationship, and environment associated with women's deaths. The results have implications for predicting and preventing women's deaths, providing scientific knowledge applied to develop public action programs, guidelines, and reforms.

Risk Assessment Instruments for Intimate Partner Femicide: A Systematic Review.

Intimate partner violence is a severe problem that has taken the lives of thousands of women worldwide, and it is bound to continue in the future. Numerous risk assessment instruments have been developed to identify and intervene in high-risk cases. However, a synthesis of specific instruments for severe violence against women by male partners has not been identified. This type of violence has specific characteristics compared to other forms of intimate partner violence, requiring individualized attention. A systematic review of the literature has been conducted to summarize the intimate partner homicide risk assessment instruments applied to this population. It has been carried out with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement guidelines. The search strategy yielded a total of 1,156 studies, and only 33 studies met eligibility criteria and were included in the review. The data of these studies were extracted, analyzed, and presented on study characteristics (country and year, sample, data sources, purpose of the studies) and main findings (a brief description of the instruments, risk factor items, psychometric properties). The results indicate that the Danger Assessment, the Danger Assessment for Immigrants, the Danger Assessment for Law Enforcement, the Danger Assessment-5, the Taiwan Intimate Partner Violence Danger Assessment, the Severe Intimate Partner Risk Prediction Scale, The Lethality Screen, and the H-Scale are specific risk assessment instruments for predicting homicide and attempted homicide. There are differences in the number and content of risk assessment items, but most of them include the evidence's critical factors associated with homicide. Validity and reliability scores of these instruments vary, being consistency and accuracy medium-high for estimating homicide. Finally, implications for prediction and prevention are noted, and future research directions are discussed.

Global Negative Correlation Learning: A Unified Framework for Global Optimization of Ensemble Models.

Ensembles are a widely implemented approach in the machine learning community and their success is traditionally attributed to the diversity within the ensemble. Most of these approaches foster diversity in the ensemble by data sampling or by modifying the structure of the constituent models. Despite this, there is a family of ensemble models in which diversity is explicitly promoted in the error function of the individuals. The negative correlation learning (NCL) ensemble framework is probably the most well-known algorithm within this group of methods. This article analyzes NCL and reveals that the framework actually minimizes the combination of errors of the individuals of the ensemble instead of minimizing the residuals of the final ensemble. We propose a novel ensemble framework, named global negative correlation learning (GNCL), which focuses on the optimization of the global ensemble instead of the individual fitness of its components. An analytical solution for the parameters of base regressors based on the NCL framework and the global error function proposed is also provided under the assumption of fixed basis functions (although the general framework could also be instantiated for neural networks with nonfixed basis functions). The proposed ensemble framework is evaluated by extensive experiments with regression and classification data sets. Comparisons with other state-of-the-art ensemble methods confirm that GNCL yields the best overall performance.

Optimisation of Non-Pharmaceutical Measures in COVID-19 Growth via Neural Networks.

On [Formula: see text] March, the World Health Organisation declared a pandemic. Through this global spread, many nations have witnessed exponential growth of confirmed cases brought under control by severe mass quarantine or lockdown measures. However, some have, through a different timeline of actions, prevented this exponential growth. Currently as some continue to tackle growth, others attempt to safely lift restrictions whilst avoiding a resurgence. This study seeks to quantify the impact of government actions in mitigating viral transmission of SARS-CoV-2 by a novel soft computing approach that makes concurrent use of a neural network model, to predict the daily slope increase of cumulative infected, and an optimiser, with a parametrisation of the government restriction time series, to understand the best set of mitigating actions. Data for two territories, Italy and Taiwan, have been gathered to model government restrictions in travelling, testing and enforcement of social distance measures as well as people connectivity and adherence to government actions. It is found that a larger and earlier testing campaign with tighter entry restrictions benefit both regions, resulting in significantly less confirmed cases. Interestingly, this scenario couples with an earlier but milder implementation of nationwide restrictions for Italy, thus supporting Taiwan's lack of nationwide lockdown, i.e. earlier government actions could have contained the growth to a degree that a widespread lockdown would have been avoided, or at least delayed. The results, found with a purely data-driven approach, are in line with the main findings of mathematical epidemiological models, proving that the proposed approach has value and that the data alone contains valuable knowledge to inform decision makers.

Effect of a Job Demand-Control-Social Support Model on Accounting Professionals' Health Perception.

The Job Demand-Control and Job Demand-Control-Support (JDCS) models constitute the theoretical approaches used to analyze the relationship between the characteristics of labor and occupational health. Few studies have investigated the main effects and multiplicative model in relation to the perceived occupational health of professional accountants. Accountants are subject to various types of pressure in performing their work; this pressure influences their health and, ultimately, their ability to perform a job well. The objective of this study is to investigate the effects of job demands on the occupational health of 739 accountants, as well as the role of the moderator that internal resources (locus of control) and external resources (social support) have in occupational health. The proposed hypotheses are tested by applying different models of neural networks using the algorithm of the Extreme Learning Machine. The results confirm the relationship between certain stress factors that affect the health of the accountants, as well as the direct effect that the recognition of superiors in occupational health has. Additionally, the results highlight the moderating effect of professional development and the support of superiors on the job's demands.

Global Sensitivity Estimates for Neural Network Classifiers.

Artificial neural networks (ANNs) have traditionally been seen as black-box models, because, although they are able to find ``hidden'' relations between inputs and outputs with a high approximation capacity, their structure seldom provides any insights on the structure of the functions being approximated. Several research papers have tried to debunk the black-box nature of ANNs, since it limits the potential use of ANNs in many research areas. This paper is framed in this context and proposes a methodology to determine the individual and collective effects of the input variables on the outputs for classification problems based on the ANOVA-functional decomposition. The method is applied after the training phase of the ANN and allows researchers to rank the input variables according to their importance in the variance of the ANN output. The computation of the sensitivity indices for product unit neural networks is straightforward as those indices can be calculated analytically by evaluating the integrals in the ANOVA decomposition. Unfortunately, the sensitivity indices associated with ANNs based on sigmoidal basis functions or radial basis functions cannot be calculated analytically. In this paper, the indices for those kinds of ANNs are proposed to be estimated by the (quasi-) Monte Carlo method.

Ordinal regression by a generalized force-based model.

This paper introduces a new instance-based algorithm for multiclass classification problems where the classes have a natural order. The proposed algorithm extends the state-of-the-art gravitational models by generalizing the scaling behavior of the class-pattern interaction force. Like the other gravitational models, the proposed algorithm classifies new patterns by comparing the magnitude of the force that each class exerts on a given pattern. To address ordinal problems, the algorithm assumes that, given a pattern, the forces associated to each class follow a unimodal distribution. For this reason, a weight matrix that allows to modify the metric in the attributes space and a vector of parameters that allows to modify the force law for each class have been introduced in the model definition. Furthermore, a probabilistic formulation of the error function allows the estimation of the model parameters using global and local optimization procedures toward minimization of the errors and penalization of the non unimodal outputs. One of the strengths of the model is its competitive grade of interpretability which is a requisite in most of real applications. The proposed algorithm is compared to other well-known ordinal regression algorithms on discretized regression datasets and real ordinal regression datasets. Experimental results demonstrate that the proposed algorithm can achieve competitive generalization performance and it is validated using nonparametric statistical tests.

Ordinal neural networks without iterative tuning.

Ordinal regression (OR) is an important branch of supervised learning in between the multiclass classification and regression. In this paper, the traditional classification scheme of neural network is adapted to learn ordinal ranks. The model proposed imposes monotonicity constraints on the weights connecting the hidden layer with the output layer. To do so, the weights are transcribed using padding variables. This reformulation leads to the so-called inequality constrained least squares (ICLS) problem. Its numerical solution can be obtained by several iterative methods, for example, trust region or line search algorithms. In this proposal, the optimum is determined analytically according to the closed-form solution of the ICLS problem estimated from the Karush-Kuhn-Tucker conditions. Furthermore, following the guidelines of the extreme learning machine framework, the weights connecting the input and the hidden layers are randomly generated, so the final model estimates all its parameters without iterative tuning. The model proposed achieves competitive performance compared with the state-of-the-art neural networks methods for OR.

Cost-sensitive AdaBoost algorithm for ordinal regression based on extreme learning machine.

In this paper, the well known stagewise additive modeling using a multiclass exponential (SAMME) boosting algorithm is extended to address problems where there exists a natural order in the targets using a cost-sensitive approach. The proposed ensemble model uses an extreme learning machine (ELM) model as a base classifier (with the Gaussian kernel and the additional regularization parameter). The closed form of the derived weighted least squares problem is provided, and it is employed to estimate analytically the parameters connecting the hidden layer to the output layer at each iteration of the boosting algorithm. Compared to the state-of-the-art boosting algorithms, in particular those using ELM as base classifier, the suggested technique does not require the generation of a new training dataset at each iteration. The adoption of the weighted least squares formulation of the problem has been presented as an unbiased and alternative approach to the already existing ELM boosting techniques. Moreover, the addition of a cost model for weighting the patterns, according to the order of the targets, enables the classifier to tackle ordinal regression problems further. The proposed method has been validated by an experimental study by comparing it with already existing ensemble methods and ELM techniques for ordinal regression, showing competitive results.

Addressing the EU sovereign ratings using an ordinal regression approach.

The current European debt crisis has drawn considerable attention to credit-rating agencies' news about sovereign ratings. From a technical point of view, credit rating constitutes a typical ordinal regression problem because credit-rating agencies generally present a scale of risk composed of several categories. This fact motivated the use of an ordinal regression approach to address the problem of sovereign credit rating in this paper. Therefore, the ranking of different classes will be taken into account for the design of the classifier. To do so, a novel model is introduced in order to replicate sovereign rating, based on the negative correlation learning framework. The methodology is fully described in this paper and applied to the classification of the 27 European countries' sovereign rating during the 2007-2010 period based on Standard and Poor's reports. The proposed technique seems to be competitive and robust enough to classify the sovereign ratings reported by this agency when compared with other existing well-known ordinal and nominal methods.

Negative correlation ensemble learning for ordinal regression.

In this paper, two neural network threshold ensemble models are proposed for ordinal regression problems. For the first ensemble method, the thresholds are fixed a priori and are not modified during training. The second one considers the thresholds of each member of the ensemble as free parameters, allowing their modification during the training process. This is achieved through a reformulation of these tunable thresholds, which avoids the constraints they must fulfill for the ordinal regression problem. During training, diversity exists in different projections generated by each member is taken into account for the parameter updating. This diversity is promoted in an explicit way using a diversity-encouraging error function, extending the well-known negative correlation learning framework to the area of ordinal regression, and inheriting many of its good properties. Experimental results demonstrate that the proposed algorithms can achieve competitive generalization performance when considering four ordinal regression metrics.

Evolutionary q-Gaussian radial basis function neural networks for multiclassification.

This paper proposes a radial basis function neural network (RBFNN), called the q-Gaussian RBFNN, that reproduces different radial basis functions (RBFs) by means of a real parameter q. The architecture, weights and node topology are learnt through a hybrid algorithm (HA). In order to test the overall performance, an experimental study with sixteen data sets taken from the UCI repository is presented. The q-Gaussian RBFNN was compared to RBFNNs with Gaussian, Cauchy and inverse multiquadratic RBFs in the hidden layer and to other probabilistic classifiers, including different RBFNN design methods, support vector machines (SVMs), a sparse classifier (sparse multinomial logistic regression, SMLR) and a non-sparse classifier (regularized multinomial logistic regression, RMLR). The results show that the q-Gaussian model can be considered very competitive with the other classification methods.

Development of a multi-classification neural network model to determine the microbial growth/no growth interface.

Boundary models have been recognized as useful tools to predict the ability of microorganisms to grow at limiting conditions. However, at these conditions, microbial behaviour can vary, being difficult to distinguish between growth or no growth. In this paper, the data from the study of Valero et al. [Valero, A., Pérez-Rodríguez, F., Carrasco, E., Fuentes-Alventosa, J.M., García-Gimeno, R.M., Zurera, G., 2009. Modelling the growth boundaries of Staphylococcus aureus: Effect of temperature, pH and water activity. International Journal of Food Microbiology 133 (1-2), 186-194] belonging to growth/no growth conditions of Staphylococcus aureus against temperature, pH and a(w) were divided into three categorical classes: growth (G), growth transition (GT) and no growth (NG). Subsequently, they were modelled by using a Radial Basis Function Neural Network (RBFNN) in order to create a multi-classification model that was able to predict the probability of belonging at one of the three mentioned classes. The model was developed through an over sampling procedure using a memetic algorithm (MA) in order to balance in part the size of the classes and to improve the accuracy of the classifier. The multi-classification model, named Smote Memetic Radial Basis Function (SMRBF) provided a quite good adjustment to data observed, being able to correctly classify the 86.30% of training data and the 82.26% of generalization data for the three observed classes in the best model. Besides, the high number of replicates per condition tested (n=30) produced a smooth transition between growth and no growth. At the most stringent conditions, the probability of belonging to class GT was higher, thus justifying the inclusion of the class in the new model. The SMRBF model presented in this study can be used to better define microbial growth/no growth interface and the variability associated to these conditions so as to apply this knowledge to a food safety in a decision-making process.