PAtCH: Proactive Approach to Circumvent Holes in Wireless Sensor Networks.

The occurrence of hole regions in Wireless Sensor Networks is a significant challenge when applying a greedy technique in a geographic routing approach. The local minimum phenomenon is commonly attributed to physical obstacles, energy depletion of the nodes, failures in communication between neighbors, or even the incorrect deployment of the nodes in the sensing field. To address the problem of hole regions, most approaches choose to abandon the traditional greedy forwarding mechanism to temporarily adopt the well-known perimeter routing scheme applied to nearby nodes or along the edge of a region of a hole. However, this mechanism does not satisfy the network load balance requirement, because it imposes too much traffic to the nodes in the hole's edge, making them overloaded when compared to other network nodes more distant from holes. In this work, we propose a novel location-free geographic routing technique called PAtCH (Proactive Approach to Circumvent Holes in Wireless Sensor Network) to avoid routing holes in WSNs. Our solution can circumvent hole regions and create routing paths toward the destination. We consider that our sink has a higher communication range, and the Received Signal Strength Indicator (RSSI) is used to assist the construction of the routing paths. Our results show the efficiency achieved by our proposed solution in scenarios with hole regions, also maintaining all the benefits of a classic greedy forwarding technique.

Applying Self-Supervised Representation Learning for Emotion Recognition Using Physiological Signals.

The use of machine learning (ML) techniques in affective computing applications focuses on improving the user experience in emotion recognition. The collection of input data (e.g., physiological signals), together with expert annotations are part of the established standard supervised learning methodology used to train human emotion recognition models. However, these models generally require large amounts of labeled data, which is expensive and impractical in the healthcare context, in which data annotation requires even more expert knowledge. To address this problem, this paper explores the use of the self-supervised learning (SSL) paradigm in the development of emotion recognition methods. This approach makes it possible to learn representations directly from unlabeled signals and subsequently use them to classify affective states. This paper presents the key concepts of emotions and how SSL methods can be applied to recognize affective states. We experimentally analyze and compare self-supervised and fully supervised training of a convolutional neural network designed to recognize emotions. The experimental results using three emotion datasets demonstrate that self-supervised representations can learn widely useful features that improve data efficiency, are widely transferable, are competitive when compared to their fully supervised counterparts, and do not require the data to be labeled for learning.

How Validation Methodology Influences Human Activity Recognition Mobile Systems.

In this article, we introduce explainable methods to understand how Human Activity Recognition (HAR) mobile systems perform based on the chosen validation strategies. Our results introduce a new way to discover potential bias problems that overestimate the prediction accuracy of an algorithm because of the inappropriate choice of validation methodology. We show how the SHAP (Shapley additive explanations) framework, used in literature to explain the predictions of any machine learning model, presents itself as a tool that can provide graphical insights into how human activity recognition models achieve their results. Now it is possible to analyze which features are important to a HAR system in each validation methodology in a simplified way. We not only demonstrate that the validation procedure k-folds cross-validation (k-CV), used in most works to evaluate the expected error in a HAR system, can overestimate by about 13% the prediction accuracy in three public datasets but also choose a different feature set when compared with the universal model. Combining explainable methods with machine learning algorithms has the potential to help new researchers look inside the decisions of the machine learning algorithms, avoiding most times the overestimation of prediction accuracy, understanding relations between features, and finding bias before deploying the system in real-world scenarios.