One of the fields where Artificial Intelligence (AI) must continue to innovate is computer security. The integration of Wireless Sensor Networks (WSN) with the Internet of Things (IoT) creates ecosystems of attractive surfaces for security intrusions, being vulnerable to multiple and simultaneous attacks. This research evaluates the performance of supervised ML techniques for detecting intrusions based on network traffic captures. This work presents a new balanced dataset (IDSAI) with intrusions generated in attack environments in a real scenario. This new dataset has been provided in order to contrast model generalization from different datasets. The results show that for the detection of intruders, the best supervised algorithms are XGBoost, Gradient Boosting, Decision Tree, Random Forest, and Extra Trees, which can generate predictions when trained and predicted with ten specific intrusions (such as ARP spoofing, ICMP echo request Flood, TCP Null, and others), both of binary form (intrusion and non-intrusion) with up to 94% of accuracy, as multiclass form (ten different intrusions and non-intrusion) with up to 92% of accuracy. In contrast, up to 90% of accuracy is achieved for prediction on the Bot-IoT dataset using models trained with the IDSAI dataset.

Convolutional neural networks (CNNs) have shown outstanding results in different application tasks. However, the best performance is obtained when customized CNNs architectures are designed, which is labor intensive and requires highly specialized knowledge. Over three decades, neuroevolution (NE) has studied the application of evolutionary computation to optimize artificial neural networks (ANNs) at different levels. It is well known that the encoding of ANNs highly impacts the complexity of the search space and the optimization algorithms’ performance as well. As NE has rapidly advanced toward the optimization of CNNs topologies, researchers face the challenging duty of representing these complex networks. Furthermore, a compilation of the most widely used encoding methods is nonexistent. In response, we present a comprehensive review on the state-of-the-art of encodings for CNNs.

The present study evaluated the effects of blackberry juice that is rich in different concentrations of anthocyanins and polyphenols (2.6 mg/kg anthocyanins, 14.57 mg/kg polyphenols; 5.83 mg/kg anthocyanins, 27.10 mg/kg polyphenols; 10.57 mg/kg anthocyanins, 38.40 mg/kg polyphenols) on anxiety-like behaviour in Wistar rats. The rats were treated with blackberry juice for 21 days and then tested in the elevated plus maze, locomotor activity test and forced swim test. The results were compared with a reference anxiolytic drug diazepam (2.0 mg/kg) and vehicle (8.7 ml/kg). The intermediate dose of blackberry juice exerted an anxiolytic-like effect that was similar to diazepam, without affecting locomotive activity. The low and high doses of blackberry juice exerted no significant effects on anxiety-like behaviour compared with vehicle. In the forced swim test, both the high and intermediate doses of blackberry juice reduced total immobility time, suggesting a protective effect against behavioural changes that are induced by acute stress. These findings suggest a potential therapeutic effect of blackberry juice on anxiety that is associated with a stressful event.