We decomposed density functional theory charge densities of 53 nitroaromatic molecules into atom-centered electric multipoles using the distributed multipole analysis that provides a detailed picture of the molecular electronic structure. Three electric multipoles, (the charge of the nitro groups), (the total dipole, i.e., polarization, of the nitro groups), (the total electron delocalization of the C ring atoms), and the number of explosophore groups (#NO₂) were selected as features for a comprehensive machine learning (ML) investigation. The target property was the impact sensitivity h₅₀ (cm) values quantified by drop-weight measurements, with a large h₅₀ (e.g., 150 cm) indicating that an explosive is insensitive and vice versa. After a preliminary screening of 42 ML algorithms, four were selected based on the lowest root mean square errors: Extra Trees, Random Forests, Gradient Boosting, and AdaBoost. Compared to experimental data, the predicted h₅₀ values of molecules having very different sensitivities for the four algorithms have differences in the range 19–28%. The most important properties for predicting h₅₀ are the electron delocalization in the ring atoms and the polarization of the nitro groups with averaged weights of 39% and 35%, followed by the charge (16%) and number (10%) of nitro groups. A significant result is how the contribution of these properties to h₅₀ depends on their actual sensitivities: for the most sensitive explosives (h₅₀ up to ∼50 cm), the four properties contribute to reducing h₅₀, and for intermediate ones (∼50 cm ≲ h₅₀ ≲ 100 cm) #NO₂ and contribute to increasing it and the other two properties to reducing it. For highly insensitive explosives (h₅₀ ≳ 200 cm), all four properties essentially contribute to increasing it. These results furnish a consistent molecular basis of the sensitivities of known explosives that also can be used for developing safer new ones.

The search for functional fluorescent organic materials can significantly benefit from the rapid and accurate predictions of photophysical properties. However, screening large numbers of potential fluorophore molecules in different solvents faces limitations of quantum mechanical calculations and experimental measurements. In this work, we develop machine learning (ML) algorithms for predicting the fluorescence of a molecule, focusing on two target properties: emission wavelengths (WLs) and quantum yields (QYs). For this purpose, we employ the Deep4Chem database which contains the optical properties of 20,236 combinations of 7,016 chromophores in 365 different solvents. Several chemical descriptors, or features, were selected as inputs for each model, and each molecule was characterized by its SMILES fingerprint. The Shapley additive explanations (SHAP) technique was used to rationalize the results, showing that the most impactful properties are chromophore-related, as expected from chemical intuition. For the best-performing model, the Random Forest, our results for the test set show a root-mean-square error (RMSE) of 28.8 nm (0.15 eV) for WLs and 0.19 for QYs. The developed ML models were used to predict, thus completing, the missing results for the WL and QY target properties in the original Deep4Chem database, resulting in two new databases: one for each property. Testing our ML models for each target property in molecules not included in the original Deep4Chem database gave good results.

With the increase in the use of the Internet to access sensitive data, intrusion detection has become an essential security measure. The evolution that took place in Artificial Intelligence in the last decades, notably in Machine Learning techniques, combined with the availability of network traffic datasets, opened a vast field for research and development in Intrusion Detection Systems based on anomalies. Published studies on this subject, nonetheless, are unanimous in stating that this type of detection is more prone to the occurrence of false positives. In order to mitigate this problem, we propose a more effective method of identifying them, compared to using only the algorithms confidence. For this, we hypothesize that the relevance given by the algorithm to certain attributes may be related to whether the detection is true or false. The method consists, therefore, in obtaining these features relevance through eXplainable Artificial Intelligence (XAI) and, together with a confidence measure, identifying detections that are more likely to be false. By using the LYCOS-IDS2017 dataset, it is possible to eliminate more than 65% of the total false positives, with a loss of only 0.38% of true positives. Conversely, by using only a confidence measure, the elimination of false positives is approximately just 50%, with a loss of 0.42% of true positives.

A chatbot or conversational agent is a software that can interact or ``chat'' with a human user using a natural language, like English, for instance. Since the first chatbot developed, many have been created but most of their problems still persist, like providing the right answer to the user and user acceptance itself. Considering such facts, in this work, we present a chatbot-building framework that considers the use of sentiment analysis and tree timelines to provide a better chatbot answer. For instance, as presented in our experiments, the user can be addressed to a human attendant when its sentiment is very negative, or even try another branch of the tree timeline, as an alternative answer, whenever the user sentiment is less negative.