Indoor environment dataset based on RSSI collected with bluetooth devices.

This paper describes a data collection experiment focused on researching indoor positioning systems using Bluetooth Low Energy (BLE) devices. The study was conducted in a real-world scenario with 150 test points and collected signals from 11 mobile devices. The dataset contains RSSI values from the mobile devices in relation to 15 fixed anchor nodes in the experimentation scenario. The dataset includes data on device identification, labels and coordinates of test points, and the room where the data was collected. The data is organized as CSV files and offers valuable information for researchers developing and assessing location models. By sharing this dataset, we aim to support the creation of robust and precise indoor localization models.

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.

A Small World Graph Approach for an Efficient Indoor Positioning System.

The main goal of an Indoor Positioning System (IPS) is to estimate the position of mobile devices in indoor environments. For this purpose, the primary source of information is the signal strength of packets received by a set of routers. The fingerprint technique is one of the most used techniques for IPSs. By using supervised machine learning techniques, it trains a model with the received signal intensity information so it can be used to estimate the positions of the devices later in an online phase. Although the k-Nearest Neighbors (kNN) is one of the most widely used classification methods due to its accuracy, it has no scalability since a sample that needs to be classified must be compared to all other samples in the training database. In this work, we use a novel hierarchical navigable small world graph technique to build a search structure so the location of a sample can be efficiently found, allowing the IPSs to be used in large-scale scenarios or run on devices with limited resources. To carry out our performance evaluation, we proposed a synthetic IPS dataset generator as well as implemented a complete real-world, large-scale IPS testbed. We compared the performance of our graph-based solution with other known kNN variants, such as Kd-Tree and Ball-Tree. Our results clearly show the performance gains of the proposed solution at 98% when compared to the classic kNN and at least 80% when compared to tree-based approaches.

Routing with Renewable Energy Management in Wireless Sensor Networks.

In wireless sensor networks (WSNs), power consumption is an important aspect when designing routing protocols. When compared to other components of a sensor node, the power required by radio transmitters is responsible for most of the consumption. One way to optimize energy consumption is by using energy-aware protocols. Such protocols take into consideration the residual energy information (i.e., remaining battery power) when making decisions, providing energy efficiency through the careful management of energy consumption. In this work, we go further and propose a new routing protocol that uses not only the residual energy information, but also the available renewable energy information from renewable energy sources such as solar cells. We then present the Renewable Energy-Based Routing (REBORN) algorithm, an energy-aware geographic routing algorithm, capable of managing both the residual and the available energy. Our results clearly show the advantages and the efficiency achieved by our REBORN algorithm when compared to other proposed energy-aware approaches.

Indoor Positioning System Using Dynamic Model Estimation.

Indoor Positioning Systems (IPSs) are used to locate mobile devices in indoor environments. Model-based IPSs have the advantage of not having an exhausting training and signal characterization of the environment, as required by the fingerprint technique. However, most model-based IPSs are done using fixed model parameters, treating the whole scenario as having a uniform signal propagation. This might work for most small scale experiments, but not for larger scenarios. In this paper, we propose PoDME (Positioning using Dynamic Model Estimation), a model-based IPS that uses dynamic parameters that are estimated based on the location the signal was sent. More specifically, we use the set of anchor nodes that received the signal sent by the mobile node and their signal strengths, to estimate the best local values for the log-distance model parameters. Also, since our solution depends highly on the selected anchor nodes to use on the position computation, we propose a novel method for choosing the three best anchor nodes. Our method is based on several data analysis executed on a large-scale, Bluetooth-based, real-world experiment and it chooses not only the nearest anchor but also the ones that benefit our least-square-based position computation. Our solution achieves a position estimation error of 3 m, which is 17% better than a fixed-parameters model from the literature.

Cooperative Localization Improvement Using Distance Information in Vehicular Ad Hoc Networks.

In vehicular ad hoc networks (VANets), a precise localization system is a crucial factor for several critical safety applications. The global positioning system (GPS) is commonly used to determine the vehicles' position estimation. However, it has unwanted errors yet that can be worse in some areas, such as urban street canyons and indoor parking lots, making it inaccurate for most critical safety applications. In this work, we present a new position estimation method called cooperative vehicle localization improvement using distance information (CoVaLID), which improves GPS positions of nearby vehicles and minimize their errors through an extended Kalman filter to execute Data Fusion using GPS and distance information. Our solution also uses distance information to assess the position accuracy related to three different aspects: the number of vehicles, vehicle trajectory, and distance information error. For that purpose, we use a weighted average method to put more confidence in distance information given by neighbors closer to the target. We implement and evaluate the performance of CoVaLID using real-world data, as well as discuss the impact of different distance sensors in our proposed solution. Our results clearly show that CoVaLID is capable of reducing the GPS error by 63%, and 53% when compared to the state-of-the-art VANet location improve (VLOCI) algorithm.