In classification, when there is a disproportion in the number of observations in each class, the data is said to be class imbalance. Class imbalance is pervasive in real world applications of data classification and has been the focus of much research. The minority class contributes too little to the decision boundary because the learning process learns from each observation in isolation. In this paper, we discuss the application of learning pairwise rankers as a solution to class imbalance. We compare ranking models to alternatives from the literature.

Phishing attacks aims to steal sensitive information and, unfortunately, are becoming a common practice on the web. Email phishing is one of the most common types of attacks on the web and can have a big impact on individuals and enterprises. There is still a gap in prevention when it comes to detecting phishing emails, as new attacks are usually not detected. The goal of this work was to develop a model capable of identifying phishing emails based on machine learning approaches. The work was performed in collaboration with E-goi, a multi-channel marketing automation company. The data consisted of emails collected from the E-goi servers in the electronic mail format. The problem consisted of a classification problem with unbalanced classes, with the minority class corresponding to the phishing emails and having less than 1% of the total emails. Several models were evaluated after careful data selection and feature extraction based on the email content and the literature regarding these types of problems. Due to the imbalance present in the data, several sampling methods based on under-sampling techniques were tested to see their impact on the model’s ability to detect phishing emails. The final model consisted of a neural network able to detect more than 80% of phishing emails without compromising the remaining emails sent by E-goi clients.

Weather and meteorological optical range (MOR) perception is crucial for smooth and safe autonomous driving (AD). This article introduces two deep learning-based architectures, employing early and intermediate sensor fusion and multi-task strategies, designed for concurrent weather and MOR classification in AD. Extensive experiments employing the publicly available FogChamber dataset demonstrate that the proposed early fusion architecture, characterized by its lightweight design and simplicity, achieves an accuracy of 98.88% in weather classification and 89.77% in MOR classification, with a competitive memory allocation of 5.33 megabytes (MB) and an inference time of 2.50 milliseconds (ms). In contrast, the proposed intermediate fusion architecture prioritizes performance, achieving higher accuracies of 99.38% in weather classification and 91.88% in MOR classification. However, it requires a more substantial memory allocation of 54.06 MB and exhibits a longer inference time of 15.55 ms. Compared to other state-of-the-art architectures, the proposed methods present a competitive balance between accuracy performance, inference time, and memory allocation, which are crucial parameters for enabling autonomous driving. The code presented in this research is available at https://github.com/CelsoPereira1/AutoWeatherPerception .

In many real-world prediction tasks, the class labels contain information about the relative order between the labels that are not captured by commonly used loss functions such as multicategory cross-entropy. In ordinal regression, many works have incorporated ordinality into models and loss functions by promoting unimodality of the probability output. However, current approaches are based on heuristics, particularly non-parametric ones, which are still insufficiently explored in the literature. We analyze the set of unimodal distributions in the probability simplex, establishing fundamental properties and giving new perspectives to understand the ordinal regression problem. Two contributions are then proposed to incorporate the preference for unimodal distributions into the predictive model: 1) UnimodalNet, a new architecture that by construction ensures the output is a unimodal distribution, and 2) Wasserstein Regularization, a new loss term that relies on the notion of projection in a set to promote unimodality. Experiments show that the new architecture achieves top performance, while the proposed new loss term is very competitive while maintaining high unimodality.

Ordinal classification tasks are present in a large number of different domains. However, common losses for deep neural networks, such as cross-entropy, do not properly weight the relative ordering between classes. For that reason, many losses have been proposed in the literature, which model the output probabilities as following a unimodal distribution. This manuscript reviews many of these losses on three different datasets and suggests a potential improvement that focuses the unimodal constraint on the neighborhood around the true class, allowing for a more flexible distribution, aptly called quasi-unimodal loss. For this purpose, two constraints are proposed: A first constraint concerns the relative order of the top-three probabilities, and a second constraint ensures that the remaining output probabilities are not higher than the top three. Therefore, gradient descent focuses on improving the decision boundary around the true class in detriment to the more distant classes. The proposed loss is found to be competitive in several cases.