The residential environment is constantly evolving technologically. With this evolution, sensors have become intelligent interconnecting home appliances, personal computers, and mobile devices. Despite the benefits of this interaction, these devices are also prone to security threats and vulnerabilities. Ensuring the security of smart homes is challenging due to the heterogeneity of applications and protocols involved in this environment. This work proposes the FamilyGuard architecture to add a new layer of security and simplify management of the home environment by detecting network traffic anomalies. Experiments are carried out to validate the main components of the architecture. An anomaly detection module is also developed by using machine learning through one-class classifiers based on the network flow. The results show that the proposed solution can offer smart home users additional and personalized security features using low-cost devices.

We have seen significant growth in adopting new protocols and intelligent devices for the residential environment in recent years. These devices provide convenience, security, and energy efficiency to users. For instance, security cameras can detect unauthorized movement, and smoke sensors can detect potential fire accidents. However, many examples have shown that such devices may generate new cyber threats causing concerns about the security of sensitive data present in the home environment. In this article, we explore the application of machine learning to identify anomalous activities that can take place in a smart-home environment. We evaluated the performance of twelve one-class algorithms in three test cases; the best models showed an AUC higher than 94%, which indicates the usefulness of adopting unsupervised learning algorithms in identifying anomalous traffic in home networks.

Coffee is a big commodity in Brazil, however it’s production is threatened by several biotic stresses. The objective of this paper is the classification of these biotic stresses that attack the leaf, such as leaf miner, rust, cercospora, and brown leaf spot, comparing several methods of image preprocessing to reach a better performance and finding the best one for this task. Using neural networks, part of artificial intelligence, we obtained good results using the networks ResNet50, MobileNetV2 and AlexNet using images with filters such as clahe, gaussian, wavelet and Graythresh. The networks achieved good result, varying from 93% to 98% using certain filters. This paper can aid farmers in the classification of these biotic stresses and can also help future researchers in this area, demonstrating the impact of each filter used in this research and it’s benefits in this type of task.

Coffee is one of the most consumed beverages worldwide, with Brazil leading exports in 2024. However, production is threatened by biotic stresses such as cercospora, phoma, rust, and leaf miner, which reduce grain quality and cause major losses. Disease identification is usually performed manually by specialists, a process that is slow, limited, and error-prone. This study proposes automating classification through Convolutional Neural Networks (CNNs) combined with various image processing techniques. The JMunBEN and JMunBEN2 datasets were used for this task, together with image preprocessing techniques such as cropping, augmentation, Gaussian, Clahe, Graythresh and Wavelet. Three CNN architectures—ResNet50, MobileNetV2, and AlexNet—were tested for multiclass classification, trained for 100 epochs with Adam optimizer and CrossEntropy loss. The article proposed wavelet filter yielded the best results, with ResNet achieving 99.07% accuracy, confirming CNNs with image pre-processing techniques to be efficient tools for rapid, reliable detection of coffee biotic stresses.