Skip to main content

VIGILANCIA ACUSTICA INTELIGENTE DE INTERIORES PARA EL ANALISIS Y MODELADO DE ESCENAS PARA LA DETECCION DE COMPORTAMIENTOS ANOMALOS DE PERSONAS Y MAQUINAS

PID2021-129043OB-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2021
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE ALCALA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Enhanced acoustic monitoring for industrial predictive maintenance using semi-coprime microphone array and joint spatial-frequency filtering

  • Corral García, Gonzalo
  • Tejera Berengue, Diana|||0000-0002-7724-2476
  • Utrilla Manso, Manuel|||0000-0003-2930-6049
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • Zhu Zhou, Fang Fang|||0000-0003-2797-6073
This paper analyzes the problem of the acquisition and separation of sound sources in industrial environments that concentrate the energy in different frequency bands, using microphone arrays. Their very different spectral characteristics make the application of spatial filtering algorithms difficult, as beamformers are usually designed for specific frequency bands. Separation of sound sources is essential for the application of anomaly detection algorithms in predictive maintenance applications. The anomaly detectors must be fed with signals emitted by the machine under study, isolated from other sounds in the environment. Sound separation can be implemented in the time domain if sounds are not simultaneous, in the frequency domain if the energy appears in different bands for the different machines, or by spatial filtering if they are produced in different places. Unfortunately, the nature of signals makes this process difficult, motivating the research to obtain multiband microphone arrays with narrow main lobes and high difference between the main beam level and the highest sidelobe level. In this paper, a semi-coprime array (SCA)?based non-uniform array structure and non-uniform filter banks are combined to separate the sound sources in an industrial environment. The proposed SCA-based architecture addresses this requirement by providing a large effective aperture with fewer microphones, narrow main lobes, improved mainlobe?sidelobe contrast across multiple bands, and mitigation of grating lobes via a minimum processor. This approach can be applied with very few adaptations to any environment with many sound sources, emitting at different bands from different positions., Spanish Ministry of Science and Innovation
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Non-linear synthetic time series generation for electroencephalogram data using long short-term memory models

  • Alqaysi, Bakr Rashid
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
  • Aldujaili, Ali Abdulameer
Background/Objectives: The implementation of artificial intelligence-based systems for disease detection using biomedical signals is challenging due to the limited availability of training data. This paper deals with the generation of synthetic EEG signals using deep learning-based models, to be used in future research for training Parkinson?s disease detection systems. Methods: Linear models, such as AR, MA, and ARMA, are often inadequate due to the inherent non-linearity of time series. To overcome this drawback, long short-term memory (LSTM) networks are proposed to learn long-term dependencies in non-linear EEG time series and subsequently generate synthetic signals to enhance the training of detection systems. To learn the forward and backward time dependencies in the EEG signals, a Bidirectional LSTM model has been implemented. The LSTM model was trained on the UC San Diego Resting State EEG Dataset, which includes samples from two groups: individuals with Parkinson?s disease and a healthy control group. Results: To determine the optimal number of cells in the model, we evaluated the mean squared error (MSE) and cross-correlation between the original and synthetic signals. This method was also applied to select the length of the hidden state vector. The number of hidden cells was set to 14, and the length of the hidden state vector for each cell was fixed at 4. Increasing these values did not improve MSE or cross-correlation and unnecessarily increased computational complexity. The proposed model?s performance was evaluated using the mean-squared error (MSE), Pearson?s correlation coefficient, and the power spectra of the synthetic and original signals, demonstrating the suitability of the proposed method for this application. Conclusions: The proposed model was compared to Autoregressive Moving Average (ARMA) models, demonstrating superior performance. This confirms that deep learning-based models, such as LSTM, are strong alternatives to statistical models like ARMA for handling non-linear, multifrequency, and non-stationary signals., Agencia Estatal de Investigación
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Computationally constrained audio-based violence detection through transfer learning and data augmentation techniques

  • Zhu Zhou, Fang Fang|||0000-0003-2797-6073
  • Tejera Berengue, Diana|||0000-0002-7724-2476
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • Utrilla Manso, Manuel|||0000-0003-2930-6049
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
Audio-based violence detection is a critical research area for enhancing public safety and security. This paper delves into comparing machine learning models, specifically Convolutional Neural Networks and Shallow Networks in the context of audio violence detection. We evaluate these models under varying training set configurations and data augmentation techniques, analyzing their impact on model performance and robustness under varying real-world conditions. Specifically, we address the issue of domain shifts, exploring how models perform under different types of noise and reverberation. Our results highlight scenarios where Shallow Networks, despite their lower computational costs, exhibit performance nearly on par with that of high-cost CNNs. Introducing tailored data augmentation techniques significantly enhances the models? performance and stability against domain shifts, providing a promising direction for improving system robustness. Our research underscores the value of careful model selection for real-world audio-based violence detection applications, recognizing the importance of an optimal trade-off between computational cost and performance, especially in resource-constrained scenarios. This research provides valuable insights for researchers and practitioners in developing more efficient, robust and accurate audio-based violence detection systems., Ministerio de Ciencia e Innovación, Comunidad de Madrid, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Application of Deep Learning to Identify Flutter Flight Testing Signals Parameters and Analysis of Real F-18 Flutter Flight Test Data

  • Abou Kebeh, Sami
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
Aircraft envelope expansion during the installation of new underwing stores presents significant challenges, particularly due to the aeroelastic flutter phenomenon. Accurate modeling of aeroelastic behavior often necessitates flight testing, which poses risks due to the potential catastrophic consequences of reaching the flutter point. Traditional methods, like frequency sweeps, are effective but require prolonged exposure to flutter conditions, making them less suitable for transonic flight validations. This paper introduces a robust deep learning approach to process sine dwell signals from aeroelastic flutter flight tests, characterized by short data lengths (less than 5 s) and low frequencies (less than 10 Hz). We explore the preliminary viability of different deep learning networks and compare their performances to existing methods such as the PRESTO algorithm and Laplace Wavelet Matching Pursuit estimation. Deep learning algorithms demonstrate substantial accuracy and robustness, providing reliable parameter identification for flutter analysis while significantly reducing the time spent near flutter conditions. Although the results with the networks trained show less accuracy than the PRESTO algorithm, they are more accurate than the LaplaceWavelet estimation, and the results are promising enough to justify extended investigation on this area. This approach is validated using both synthetic data and real F-18 flight test signals, which highlights its potential for real-time analysis and broader applicability in aeroelastic testing., Ministerio de Ciencia e Innovación, Comunidad de Madrid, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

A Novel Generalized Beamforming Layer Set for Deep Learning Based Acoustic Cavitation Detection

  • Zhu Zhou, Fang Fang|||0000-0003-2797-6073
  • Tejera Berengue, Diana|||0000-0002-7724-2476
  • Corral García, Gonzalo
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
  • Utrilla Manso, Manuel|||0000-0003-2930-6049
Cavitation is a major issue in hydraulic machinery, causing mechanical damage, efficiency loss and potential system failure. Early detection of cavitation is crucial for predictive maintenance, yet conventional monitoring methods based on pressure and vibration sensors often lack real-time accuracy. In this study, we proposea deep learning-based approach for cavitation detection by integrating trainable beamforming techniques into a trimmed YAMNet architecture. Our method improves computational efficiency by reducing the depth of YAMNet while incorporating spatial filtering layers with learnable parameters. Specifically, we introduce the Standard Beamforming Layer Set, which embeds domain knowledge into the spatial filtering process to enhance the extraction of cavitation-related features. Additionally, we propose the Generalized Beamforming Layer Set, which extends conventional beamforming by incorporating multiple summation elements, increasing noise robustness and detection reliability in complex industrial environments. The system is trained and evaluated using a real-world cavitation noise database recorded in an operational hydraulic system. Experimental results show that a trimmed YAMNet model with beamforming integration significantly improves detection accuracy while reducing computational cost. The proposed Generalized Beamforming Layer Set approach outperforms traditional beamforming methods, achieving a relative improvement of 33.90% over the baseline single-microphone setup without beamforming. These results highlight the effectiveness of integrating adaptive beamforming with deep learning for real-time acoustic monitoring, opening the way for more efficient and robust cavitation detection systems in industrial environments., Spanish Ministry of Science and Innovation, Comunidad de Madrid, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Analysis of distance and environmental impact on UAV acoustic detection

  • Tejera Berengue, Diana|||0000-0002-7724-2476
  • Zhu Zhou, Fang Fang|||0000-0003-2797-6073
  • Utrilla Manso, Manuel|||0000-0003-2930-6049
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
This paper is an expanded paper from the IEEE Sensors Applications Symposium held on 18–20 July 2023 in Ottawa, Canada., This article explores the challenge of acoustic drone detection in real-world scenarios, with an emphasis on the impact of distance, to see how sound propagation affects drone detection. Learning machines of varying complexity are used for detection, ranging from simpler methods such as linear discriminant, multilayer perceptron, support vector machines, and random forest to more complex approaches based on deep neural networks like YAMNet. Our evaluation meticulously assesses the performance of these methods using a carefully curated database of a wide variety of drones and interference sounds. This database, processed through array signal processing and influenced by ambient noise, provides a realistic basis for our analyses. For this purpose, two different training strategies are explored. In the first approach, the learning machines are trained with unattenuated signals, aiming to preserve the inherent information of the sound sources. Subsequently, testing is then carried out under attenuated conditions at various distances, with interfering sounds. In this scenario, effective detection is achieved up to 200 m, which is particularly notable with the linear discriminant method. The second strategy involves training and testing with attenuated signals to consider different distances from the source. This strategy significantly extends the effective detection ranges, reaching up to 300 m for most methods and up to 500 m for the YAMNet-based detector. Additionally, this approach raises the possibility of having specialized detectors for specific distance ranges, significantly expanding the range of effective drone detection. Our study highlights the potential of drone acoustic detection at different distances and encourages further exploration in this research area. Unique contributions include the discovery that training with attenuated signals with a worse signal-to-noise ratio allows the improvement of the general performance of learning machine-based detectors, increasing the effective detection range achieved, and the feasibility of real-time detection, even with very complex learning machines, opening avenues for practical applications in real-world surveillance scenarios., Agencia Estatal de Investigación, Junta de Comunidades de Castilla-La Mancha, Universidad de Alcalá
e_Buah Biblioteca Digital Universidad de Alcalá
Publication Artículo científico (JournalArticle)

Initializing the weights of a multilayer perceptron for activity and emotion recognition

  • Mohíno Herranz, María Inmaculada|||0000-0002-5144-3472
  • Gil Pita, Roberto|||0000-0002-1790-3834
  • García Gómez, Joaquín
  • Alonso Diaz, Sagrario
  • Rosa Zurera, Manuel|||0000-0002-3073-3278
  • Seoane, Fernando
Conducting an analysis of human behavior is an intriguing topic for many researchers. Within this field, machine learning can be applied to classify activities and emotions by analyzing physiological signals. However, the limited size of available databases poses challenges for the generalization of classifiers. This paper proposes a method to enhance the generalization of neural network-based classifiers by intelligently initializing weights for emotion and activity recognition. The signals under consideration are electrocardiogram, thoracic electrical bioimpedance, and electrodermal activity. The database used comprises recordings from 40 subjects performing various tasks that induce emotions and activities. The performance of the proposed method is compared with several standard machine learning and deep learning classifiers typically employed in emotion and activity recognition. This study involves two primary assessments. First is the activity recognition task, encompassing classes such as neutral, emotional, mental, and physical activity, where results close to 20% accuracy are achieved using the three physiological signals. Second, the emotion recognition assessment aims to differentiate between emotions like neutral, sadness, and disgust. An error probability close to 15% is obtained using thoracic electrical bioimpedance and electrodermal activity. The proposed method yields the best results among the approaches evaluated., Agencia Estatal de Investigación, Universidad de Alcalá