When employing neural networks in the real world, we often encounter challenges related to dataset size, data imbalance and model selection. In this paper, we investigate the benefits of incorporating information obtained from causal structures or Qualitative Models for Data Generation Processes (QM-DGP) into neural network design and training, by leveraging causal reasoning principles such as d-separation and the Markov blanket to determine relevant input variables. Through empirical analysis, we compare networks which exploit causal structures and those that do not, focusing on aspects related to dataset efficiency. Our findings show that networks which exploit causal structures require fewer samples to achieve (near-)optimal performance on average, making them more suitable in frugal learning scenarios. We also propose a causally-decomposed neural network architecture based on causal structural information and show that it is more data efficient than its fully-connected counterpart. Our results highlight the practical advantage of using causal reasoning in neural network design, particularly in settings where data efficiency plays a crucial role.

Modern technologies have enabled illicit firearms trafficking to partially merge with cybercrime, while also allowing its off-line aspects to become increasingly complex. The online trade of firearms, their components, 3D blueprints and illicit substances carried out by criminals on both the surface Web and dark Web is increasingly difficult to address as a consequence of the exponential growth in the amount of information disseminated on the Internet. On the other hand, law enforcement agencies are confronted with significant challenges that require the development of sophisticated technological solutions capable of processing large volumes of data, identifying relevant information in a timely manner and creating networks of connections between potential criminal groups. This article presents a real-world practical system, namely the CEASEFIRE one, powered by advanced artificial intelligence technologies that can assist law enforcement personnel in addressing the above described challenges.

Observing events that require attention triggers the generation of a case and the start of an investigation process. An important part of such a process implies studying similar cases, aiming to improve situation awareness. However, identifying relevant cases, which are typically stored in a database, is work-intensive unless the investigator is supported by a smart Information Retrieval (IR) tool. We propose the development of IR tools that are able to leverage application domain knowledge to increase the relevance of the results. We suggest that formal models that explicitly represent the real-world phenomenon under investigation can be used to compute such relevance while also providing an explanation to the investigator. Our research is primarily motivated by the objective of supporting law enforcement officers in criminal investigation, but we show how our vision is applicable across multiple domains by providing simple application examples for both criminal investigation and cybersecurity incident investigation.

This paper proposes an improved analysis of the Qualitative Models of Data Generating Processes (QM-DGP). The approach supports (i) determination of the complexity of a Machine Learning problem and (ii) a coarse determination of the quantities of training data that are needed to train good quality models. Compared to the previously published approach to the QM-DGP analysis, this paper introduces a more thorough and theoretically sound treatment of the learning complexity. Firstly, the approach provides more rigorous determination of the complexity of the data generating processes (DGP). Secondly, the determination of the learning complexity and the required training data volumes is based on sound statistical principles for the estimation of the distributions over categorical variables. The effectiveness of the proposed method was experimentally confirmed in controlled settings. Different ground truth models were used to sample test and training data. The approach correctly predicts the size of the training data sets for which machine learning yields models supporting classification close to Bayes Error. While the majority of the experiments were carried out on probabilistic graphical models (PGM), the experiments with Neural Networks confirmed that the QM-DGP approach is not limited to PGMs.

AI-based decision support solutions require life cycles that adequately address critical steps, such as (i) finding suitable machine learning (ML) methods for the problem at hand, (ii) preparing and executing adequate data acquisition processes and (iii) tractable evaluation of the overall solution. Understanding the data generating processes is key in achieving this. Training and test data can be seen as a result of a causal data generation process, a sampling process in which the data is collected from different sources that are influenced by multiple interdependent phenomena. This is represented by a Qualitative Model of Data Generation Processes (QM-DGP), a causal graphical model. QM-DGP facilitates analysis of the complexity of the underlying data generating processes that can inform the development of trustable ML-based solutions in multiple ways. Firstly, this analysis is the basis for the determination of the required complexity of the ML models. Secondly, it facilitates the determination of the quantities of training data supporting good learning results. Thirdly, it can provide guidance for a systematic simplification of the models, supporting tractable solutions without significantly reduced performance. The construction of QM-DGP and the analysis benefit from sound theoretical concepts, such as d-separation and I-Maps. Experimental results with simulated data indicate that the approach can be effective in predicting the required quantities of training data and the determination of the modelling complexity using different types of models.

This paper introduces a probabilistic approach for forecasting vessel trajectories. It combines a Dynamic Bayesian Network (DBN) and an auxiliary position determination process to iteratively sample future vessel positions in a scalable and computationally efficient manner. The DBN is a discrete probabilistic model of typical vessel behaviors. It is used for ancestral sampling to predict the speed and orientation of a vessel which, in turn, are used by the auxiliary process to predict the vessel's position in a discretized representation of the space. The DBN is event based and uses latent variables that efficiently encode the context influencing the dynamics of different types of vessels. The parameters of the DBN are learned in an unsupervised fashion by using the Expectation Maximization (EM) algorithm. The experiments with real world data confirm the accuracy and effectiveness of the proposed approach.