Héctor A. Sánchez-Hevia

Indoor Blind Localization of Smartphones by Means of Sensor Data Fusion

Locating the nodes in wireless sensor networks (WSNs) is currently a very active area of research due to their increasing number of potential applications. Wireless networks composed of smartphones have gained particular interest, mainly due to the high availability of such devices. This paper presents a novel algorithm for blind localization of commercial off-the-shelf smartphones in a WSN. The algorithm uses acoustic signals and inertial sensors to estimate the sensor positions simultaneously. Estimates of range and direction-of-arrival (DOA) locally obtained in each node are combined with a maximum likelihood estimator. A tailored optimization algorithm is also proposed to solve the DOA uncertainty problem. Our proposal obtains low localization errors without considering any reference node nor any prior synchronization between nodes.

Maximum Likelihood Decision Fusion for Weapon Classification in Wireless Acoustic Sensor Networks

Gunshot acoustic analysis is a field with many practical applications, but due to the multitude of factors involved in the generation of the acoustic signature of firearms, it is not a trivial task. The main problem arises with the strong spatial dependence shown by the recorded waveforms even when dealing with the same weapon. However, this can be lessen by using a spatially diverse receiver such as a wireless acoustic sensor network. In this work, we address multichannel acoustic weapon classification using spatial information and a novel decision fusion rule based on it. We propose a fusion rule based on maximum likelihood estimation that takes advantage of diverse classifier ensembles to improve upon classic decision fusion techniques. Classifier diversity comes from a spatial segmentation that is performed locally at each node. The same segmentation is also used to improve the accuracy of the local classification by means of a divide and conquer approach.

Improving learning efficiency in multi-objective simulated annealing programming for sound environment classification

In this work, a classifier that jointly optimises the expected total classification cost and the energy consumption is presented. A numerical study is provided, where different alternatives are implemented on a hearing aid. Our proposal is capable of automatically classifying the acoustic environment that surrounds the user and choosing the parameters of the amplification that are best adapted to the users comfort, while attaining relevant improvements in both classification and learning-related energy consumptions with small to negligible loss in classification accuracy.

Indoor blind localization of smartphones by means of sensor data fusion

Locating the nodes in wireless sensor networks (WSN) is currently a very active area of research due to their increasing number of potential applications. Networks composed of smartphones have gained particular interest, mainly due to the high availability of such devices. This paper presents an algorithm for blind localization of smartphones in a WSN. Data fusion from different embedded sensors is combined to estimate the position and orientation of the nodes within the network. The algorithm uses acoustic and RF signals to estimate the angle and range between each pair of nodes. The different node position estimations are further combined. Our proposal yields location errors lower than 0.5 m., which is a valid solution for many WSN applications.

FPGA-based real-time acoustic camera using pdm mems microphones with a custom demodulation filter

Acoustic cameras are devices capable of displaying visual representation of sound waves, by means of a microphone array and various signal processing techniques. These devices typically rely on complex hardware configurations, since large number of acquisition channels and processing power are required. However the use of an all-digital signal path makes possible to simplify the hardware by eliminating the need for an analog front-end, yet the usage of 1 bit oversampled ADCs requires a proper demodulation, and may become too demanding for systems with a large number of input channels. In this paper we describe a custom designed high efficiency demodulation filter for a FPGA-based acoustic camera architecture with real-time processing capabilities using PDM MEMS microphones.

Acoustic Detection of Violence in Real and Fictional Environments

Detecting violence is an important task due to the amount of people who suffer its effects daily. There is a tendency to focus the problem either in real situations or in non real ones, but both of them are useful on its own right. Until this day there has not been clear effort to try to relate both environments. In this work we try to detect violent situations on two different acoustic databases through the use of crossed information from one of them into the other. The system has been divided into three stages: feature extraction, feature selection based on genetic algorithms and classification to take a binary decision. Results focus on comparing performance loss when a database is evaluated with features selected on itself, or selection based in the other database. In general, complex classifiers tend to suffer higher losses, whereas simple classifiers, such as linear and quadratic detectors, offers less than a 10% loss in most situations.

Indoor Self-Localization and Orientation Estimation of Smartphones Using Acoustic Signals

We propose a new acoustic self-localization and orientation estimation algorithm for smartphones networks composed of commercial off-the-shelf devices equipped with two microphones and a speaker. Each smartphone acts as an acoustic transceiver, which emits and receives acoustic signals. Node locations are found by combining estimates of the range and direction of arrival (DoA) between node pairs using a maximum likelihood (ML) estimator. A tailored optimization algorithm is proposed to simultaneously solve the DoA uncertainty problem that arises from the use of only 2 microphones per node and obtain the azimuthal orientation of each node without requiring an electronic compass.

Distributed and collaborative sound environment information extraction in binaural hearing aids

Current research in the field of Wireless Acoustic Sensor Networks (WASN) is gradually introducing the use of sound spatial techniques in the field of binaural hearing aids, in which sound environment information must be extracted in order to tune up the main hearing aid algorithms. In binaural hearing aids, computational capability, memory and data transmission are strictly constrained, which makes the use of distributed and collaborative approaches suitable. This paper proposes solutions for the collaborative and distributed sound environment information extraction through the estimation of the different noise levels, analyzing both the performance and the computational and transmission requirements. Results demonstrate that the proposed distributed solutions highly reduce the transmission rate and the computational cost, while maintaining the accuracy in the estimations.

Synchronization for classical blind source separation algorithms in wireless acoustic sensor networks

The use of wireless acoustic sensor networks is becoming very popular since they entail many advantages. However, this type of distributed sensor networks has an important drawback for many signal processing algorithms, the synchronization problem. Broadly speaking, in those networks, signals received at the different nodes are not synchronized due to two main factors, the clock problem and the important differences in propagation delays between sources and microphones. In this work we introduce a synchronization solution for mixtures of two and three speech sources in the framework of blind source separation. This proposal of synchronization has a mixture alignment stage prior to apply the separation method. Obtained results demonstrate that this synchronization method aligns speech mixtures correctly since it improves the performance of the classical separation algorithm in terms of both speech quality and speech intelligibility.

TWO-SENSOR EEG-BASED STRESS DETECTION SYSTEM

In this paper, we propose a computationally-efficient EEGbased stress detection that uses only two non-invasive electrodes. The system is designed to classify between two situations: high stress level or low stress level. A linear classifier is trained using supervised learning using a subset of features that has been selected among a larger proposed set of features, using a tailored feature selection algorithm. The proposed algorithm has been evaluated with subjects playing skill games, obtaining errors of 19.2% in the train set and 29.2% in the test set.