Identificación de eventos delictivos a partir de señales de audio utilizando modos de correlación wavelet

dc.contributor.advisorBolaños Martinez, Freddy
dc.contributor.advisorFletscher Bocanegra, Luis Alejandro
dc.contributor.authorÁlvarez Osorio, Carlos Andres
dc.coverage.cityMedellín (Antioquia, Colombia)
dc.date.accessioned2024-07-23T20:23:58Z
dc.date.available2024-07-23T20:23:58Z
dc.date.issued2024
dc.descriptionIlustraciones, gráficosspa
dc.description.abstractDurante muchos años, la seguridad en los entornos urbanos ha sido una preocupación para los habitantes de todas las ciudades del mundo. A causa de la inseguridad que existe en mayor o menor medida, los gobiernos en diferentes regiones del mundo buscan continuamente mecanismos para prevenir actos criminales. Este estudio presenta un método que busca prevenir delitos utilizando señales de audio que pueden capturarse en un entorno urbano. Por ello, se utiliza una técnica emergente, denominada modos de correlación wavelet, con el fin de representar señales de audio de forma compacta, tras lo cual se implementa un método basado en aprendizaje automático para clasificar las señales de audio en dos categorías: aquellas asociadas con un evento o crimen violento o aquellos asociados con un evento común (no violento o no criminal). En el estudio realizado, fue posible concluir que los modos de correlación de wavelet permiten realizar la clasificación de este tipo de señales con una precisión mayor al 80 % y con tiempos de ejecución menores a 1 segundo, utilizando un máximo de 4 características para el entrenamiento de los modelos. Las pruebas se realizaron en un computador portátil con sistema operativo de 64 bits, procesador x64, Windows 11, procesador AMD Ryzen 5 5500U, 16 Gb de RAM. (Tomado de la fuente)spa
dc.description.abstractFor many years, safety in urban environments has been a concern for inhabitants of all cities worldwide. Because of the insecurity that exists to a greater or lesser extent, governments in different regions of the world continually seeks mechanisms to prevent criminal acts. This study introduces a method to prevent crime events using audio signals that can be captured in an urban environment. For this, an emerging technique, called wavelet correlation modes, is used to represent audio signals in a compact manner, following which a machine learning based method is implemented to classify the audio signals into two categories: those associated with a violent event or crime or those associated with a common event (nonviolent or noncriminal). In the study carried out, it was possible to conclude that wavelet compression modes allow the classification of this type of signals with a precision greater than 80 % and with execution times less than 1 second, using a maximum of 4 characteristics for the model training. The tests were carried out on a laptop with a 64-bit operating system, x64 processor, Windows 11, AMD Ryzen 5 5500U processor, 16 Gb of RAM.eng
dc.description.curricularareaIngeniería Eléctrica E Ingeniería De Control.Sede Medellínspa
dc.description.degreelevelMaestríaspa
dc.description.researchareaProcesamiento Digital de Señales e Inteligencia Artificialspa
dc.description.sponsorshipEste trabajo fue apoyado por el Fondo de Ciencia, Tecnología e Innovación (FCTeI) del Sistema General de Regalías (SGR) bajo el proyecto identificado con el código BPIN 2020000100044spa
dc.format.extent54 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/86601
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.publisher.facultyFacultad de Minasspa
dc.publisher.placeMedellín, Colombiaspa
dc.publisher.programMedellín - Minas - Maestría en Ingeniería - Automatización Industrialspa
dc.relation.indexedLaReferenciaspa
dc.relation.referencesA. Gholamy, V. Kreinovich, and O. Kosheleva, ‘‘Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation,’’ 2018.spa
dc.relation.referencesG. T. S. R. R. R. Axton Pitt, Digl Dixon, ‘‘Litmaps,’’ 2023 Litmaps Ltd., 2023spa
dc.relation.referencesS. Waldekar and G. Saha, ‘‘Analysis and classification of acoustic scenes with wavelet transform-based mel-scaled features,’’ Multimedia Tools and Applications, vol. 79, pp. 7911--7926, 3 2020.spa
dc.relation.referencesG. Shen and B. Liu, ‘‘The visions, technologies, applications and security issues of internet of things,’’ pp. 1--4, IEEE, 5 2011spa
dc.relation.referencesMarkets and Markets, ‘‘Research and markets, internet of things (iot) market global forecast to 2021,’’ 2022.spa
dc.relation.referencesJ. . T. J. . T. H. . W. U. H. R. Bowerman, B. Braverman, ‘‘The vision of a smart city. 2nd int. life ..,’’ 2000spa
dc.relation.referencesA. Gobernación, ‘‘Plan de desarrollo unidos por la vida,’’ 2020spa
dc.relation.referencesCEJ, ‘‘En 2021 aumentó el hurto a personas y otros delitos, advierte el reloj de la criminalidad de la cej,’’ 2021spa
dc.relation.referencesM. cómo vamos, ‘‘Informe de calidad de vida de medellÍn, 2020. seguridad ciudadana y convivencia,’’ 2020.spa
dc.relation.referencesJ. D. Rodriguez-Ortega, Y. A. A. Duarte-VelÃ!‘squez, C. GÃ-Toro, and J. A. Cadavid-Carmona, ‘‘Seguridad ciudadana, violencia y criminalidad: una visiÃholÃstica y criminolÃde las cifras estadÃsticas del 2018,’’ Revista Criminalidad, vol. 61, pp. 9 -- 58, 12 2019spa
dc.relation.referencesF. L. A. Tamayo-Arboleda and E. Norza, ‘‘Midiendo el crimen: cifras de criminalidad y operatividad policial en Colombia, aÃ2017,’’ Revista Criminalidad, vol. 60, pp. 49 -- 71, 12 2018.spa
dc.relation.referencesS. Mondal and A. Das Barman, ‘‘Deep learning technique based real-time audio event detection experiment in a distributed system architecture,’’ Computers and Electrical Engineering, vol. 102, p. 108252, 2022.spa
dc.relation.referencesY. Yamamoto, J. Nam, H. Terasawa, and Y. Hiraga, ‘‘Investigating time-frequency representations for audio feature extraction in singing technique classification,’’ in 2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 890--896, 2021spa
dc.relation.referencesM. Esmaeilpour, P. Cardinal, and A. L. Koerich, ‘‘Unsupervised feature learning for environmental sound classification using weighted cycle-consistent generative adversarial network,’’ Applied Soft Computing, vol. 86, p. 105912, 1 2020.spa
dc.relation.referencesI. D. Ilyashenko, R. S. Nasretdinov, Y. A. Filin, and A. A. Lependin, ‘‘Trainable wavelet-like transform for feature extraction to audio classification,’’ Journal of Physics: Conference Series, vol. 1333, p. 32029, 10 2019.spa
dc.relation.referencesD. Guillén, H. Esponda, E. Vázquez, and G. Idárraga-Ospina, ‘‘Algorithm for transformer differential protection based on wavelet correlation modes,’’ IET Generation, Transmission & Distribution, vol. 10, no. 12, pp. 2871--2879, 2016.spa
dc.relation.referencesA. Rabaoui, M. Davy, S. Rossignol, and N. Ellouze, ‘‘Using one-class svms and wavelets for audio surveillance,’’ IEEE Transactions on Information Forensics and Security, vol. 3, pp. 763--775, 12 2008spa
dc.relation.referencesA. I. Middya, B. Nag, and S. Roy, ‘‘Deep learning based multimodal emotion recognition using model-level fusion of audio–visual modalities,’’ Knowledge-Based Systems, vol. 244, p. 108580, 5 2022spa
dc.relation.referencesY. Xu, J. Yang, and K. Mao, ‘‘Semantic-filtered soft-split-aware video captioning with audio-augmented feature,’’ Neurocomputing, vol. 357, pp. 24--35, 9 2019spa
dc.relation.referencesS. Durai, ‘‘Wavelet based feature vector formation for audio signal classification,’’ 10 2007spa
dc.relation.referencesT. Düzenli and N. Ozkurt, ‘‘Comparison of wavelet based feature extraction methods for speech/music discrimination,’’ Istanbul University - Journal of Electrical and Electronics Engineering, vol. 11, pp. 617- -621, 10 2011.spa
dc.relation.referencesG. Tzanetakis, G. Essl, and P. Cook, ‘‘Audio analysis using the discrete wavelet transform,’’ pp. 318--323, 10 2001spa
dc.relation.referencesC.-C. Lin, S.-H. Chen, T.-K. Truong, and Y. Chang, ‘‘Audio classification and categorization based on wavelets and support vector machine,’’ IEEE Transactions on Speech and Audio Processing, vol. 13, pp. 644--651, 2005.spa
dc.relation.referencesK. Kim, D. H. Youn, and C. Lee, ‘‘Evaluation of wavelet filters for speech recognition,’’ SMC 2000 Confe- rence Proceedings. 2000 IEEE International Conference on Systems, Man and Cybernetics. ’Cybernetics Evolving to Systems, Humans, Organizations, and their Complex Interactions’ (Cat. No.00CH37166), pp. 2891--2894, 2000.spa
dc.relation.referencesJ. Gowdy and Z. Tufekci, ‘‘Mel-scaled discrete wavelet coefficients for speech recognition,’’ pp. 1351--1354, IEEE, 2000.spa
dc.relation.referencesS. K. Kopparapu and M. Laxminarayana, ‘‘Choice of mel filter bank in computing mfcc of a resampled speech,’’ pp. 121--124, IEEE, 5 2010.spa
dc.relation.referencesK. V. K. Kishore and P. K. Satish, ‘‘Emotion recognition in speech using mfcc and wavelet features,’’ pp. 842--847, 2013.spa
dc.relation.referencesJ. Salamon, C. Jacoby, and J. P. Bello, ‘‘A dataset and taxonomy for urban sound research,’’ pp. 1041-- 1044, ACM, 11 2014.spa
dc.relation.referencesA. Rakotomamonjy and G. Gasso, ‘‘Histogram of gradients of time-frequency representations for audio scene detection,’’ IEEE/ACM Transactions on Audio, Speech, and Language Processing, pp. 1--1, 2014.spa
dc.relation.referencesS. R. Kadiri and P. Alku, ‘‘Subjective evaluation of basic emotions from audio–visual data,’’ Sensors, vol. 22, p. 4931, 6 2022.spa
dc.relation.referencesK. Umapathy, S. Krishnan, and R. K. Rao, ‘‘Audio signal feature extraction and classification using local discriminant bases,’’ IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, pp. 1236--1246, 2007spa
dc.relation.referencesF. Weninger, F. Eyben, B. W. Schuller, M. Mortillaro, and K. R. Scherer, ‘‘On the acoustics of emotion in audio: What speech, music, and sound have in common,’’ Frontiers in Psychology, vol. 4, 2013spa
dc.relation.referencesP. Wu, J. Liu, Y. Shi, Y. Sun, F. Shao, Z. Wu, and Z. Yang, ‘‘Not only look, but also listen: Learning multimodal violence detection under weak supervision,’’ pp. 322--339, 10 2020spa
dc.relation.referencesJ. Liu, Y. Zhang, D. Lv, J. Lu, H. Xu, S. Xie, and Y. Xiong, ‘‘Classification method of birdsong based on gaborwt feature image and convolutional neural network,’’ pp. 134--140, 2021spa
dc.relation.referencesW. Dai, C. Dai, S. Qu, J. Li, and S. Das, ‘‘Very deep convolutional neural networks for raw waveforms,’’ pp. 421--425, IEEE, 3 2017.spa
dc.relation.referencesL. Deng, G. Hinton, and B. Kingsbury, ‘‘New types of deep neural network learning for speech recognition and related applications: an overview,’’ pp. 8599--8603, IEEE, 5 2013spa
dc.relation.referencesJ. Sharma, O.-C. Granmo, and M. Goodwin, ‘‘Environment sound classification using multiple feature channels and deep convolutional neural networks,’’ 10 2019spa
dc.relation.referencesS. Lee and H.-S. Pang, ‘‘Feature extraction based on the non-negative matrix factorization of convolu- tional neural networks for monitoring domestic activity with acoustic signals,’’ IEEE Access, vol. 8, pp. 122384--122395, 2020spa
dc.relation.referencesJ. Salamon and J. P. Bello, ‘‘Deep convolutional neural networks and data augmentation for environ- mental sound classification,’’ IEEE Signal Processing Letters, vol. 24, pp. 279--283, 3 2017.spa
dc.relation.referencesT. Lv, H. yong Zhang, and C. hui Yan, ‘‘Double mode surveillance system based on remote audio/video signals acquisition,’’ Applied Acoustics, vol. 129, pp. 316--321, 1 2018.spa
dc.relation.referencesG. Parascandolo, H. Huttunen, and T. Virtanen, ‘‘Recurrent neural networks for polyphonic sound event detection in real life recordings,’’ pp. 6440--6444, IEEE, 3 2016spa
dc.relation.referencesY. Tokozume and T. Harada, ‘‘Learning environmental sounds with end-to-end convolutional neural network,’’ pp. 2721--2725, IEEE, 3 2017.spa
dc.relation.referencesD. Burgund, S. Nikolovski, D. Galić, and N. Maravić, ‘‘Pearson correlation in determination of quality of current transformers,’’ Sensors, vol. 23, no. 5, 2023spa
dc.relation.referencesG. S. Shuhe Han, ‘‘Protection algorithm based on deep convolution neural network algorithm,’’ Compu- tational Intelligence and Neuroscience, 2022.spa
dc.relation.referencesA. Roy, D. Singh, R. K. Misra, and A. Singh, ‘‘Differential protection scheme for power transformers using matched wavelets,’’ IET Generation, Transmission &amp Distribution, vol. 13, pp. 2423--2437, May 2019.spa
dc.relation.referencesS. Jena and B. R. Bhalja, ‘‘Initial travelling wavefront-based bus zone protection scheme,’’ IET Generation, Transmission &amp Distribution, vol. 13, pp. 3216--3229, July 2019.spa
dc.relation.referencesR. C. Hendriks and T. Gerkmann, ‘‘Noise correlation matrix estimation for multi-microphone speech enhancement,’’ IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 223- -233, 2012.spa
dc.relation.referencesH. Hu, Z. He, Y. Zhang, and S. Gao, ‘‘Modal frequency sensitivity analysis and application using complex nodal matrix,’’ IEEE Transactions on Power Delivery, vol. 29, no. 2, pp. 969--971, 2014spa
dc.relation.referencesP. S. Addison, The Illustrated Wavelet Transform Handbook. CRC Press, Jan. 2017spa
dc.relation.referencesE. Johansson, ‘‘Wavelet theory and some of its applications,’’ Luleå University of Technology Department of Mathematics, vol. 48, 10 2005.spa
dc.relation.referencesR. R. Merry, ‘‘Wavelet theory and applications : a literature study,’’ 2005.spa
dc.relation.referencesA. Hadd and J. L. Rodgers, Understanding correlation matrices, vol. 186. SAGE Publications, Inc, 1 2021.spa
dc.relation.referencesB. Kröse, B. Krose, P. van der Smagt, and P. Smagt, ‘‘An introduction to neural networks,’’ J Comput Sci, vol. 48, 01 1996.spa
dc.relation.referencesM. Awad and R. Khanna, ‘‘Support vector machines for classification,’’ pp. 39--66, 04 2015spa
dc.relation.referencesN. Shreyas, M. Venkatraman, S. Malini, and S. Chandrakala, ‘‘Trends of sound event recognition in audio surveillance: A recent review and study,’’ The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems, pp. 95--106, 2020spa
dc.relation.referencesM. A. E. M. Mohamed Elesawy, Mohamad Hussein, ‘‘Real life violence situations dataset,’’ Kaggle, 2019.spa
dc.relation.referencesT. S. (2019), ‘‘Sound events for surveillance applications (1.0.0) [data set],’’ 2019.spa
dc.relation.referencesS. R. Livingstone and F. A. Russo, ‘‘Ravdess emotional speech audio,’’ 2019.spa
dc.relation.referencesB. McFee, M. McVicar, D. Faronbi, I. Roman, M. Gover, S. Balke, S. Seyfarth, A. Malek, C. Raffel, V. Lostanlen, B. van Niekirk, D. Lee, F. Cwitkowitz, F. Zalkow, O. Nieto, D. Ellis, J. Mason, K. Lee, B. Steers, E. Halvachs, C. Thomé, F. Robert-Stöter, R. Bittner, Z. Wei, A. Weiss, E. Battenberg, K. Choi, R. Yamamoto, C. Carr, A. Metsai, S. Sullivan, P. Friesch, A. Krishnakumar, S. Hidaka, S. Kowalik, F. Keller, D. Mazur, A. Chabot-Leclerc, C. Hawthorne, C. Ramaprasad, M. Keum, J. Gomez, W. Monroe, V. A. Morozov, K. Eliasi, nullmightybofo, P. Biberstein, N. D. Sergin, R. Hennequin, R. Naktinis, beantowel, T. Kim, J. P. Åsen, J. Lim, A. Malins, D. Hereñú, S. van der Struijk, L. Nickel, J. Wu, Z. Wang, T. Gates, M. Vollrath, A. Sarroff, Xiao-Ming, A. Porter, S. Kranzler, Voodoohop, M. D. Gangi, H. Jinoz, C. Guerrero, A. Mazhar, toddrme2178, Z. Baratz, A. Kostin, X. Zhuang, C. T. Lo, P. Campr, E. Semeniuc, M. Biswal, S. Moura, P. Brossier, H. Lee, and W. Pimenta, ‘‘librosa/librosa: 0.10.1,’’ Aug. 2023.spa
dc.relation.referencesG. R. Lee, R. Gommers, F. Waselewski, K. Wohlfahrt, and A. O8217;Leary, ‘‘Pywavelets: A python package for wavelet analysis,’’ Journal of Open Source Software, vol. 4, no. 36, p. 1237, 2019spa
dc.relation.referencesF. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenho- fer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, ‘‘Scikit-learn: Machine learning in Python,’’ Journal of Machine Learning Research, vol. 12, pp. 2825--2830, 2011.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/spa
dc.subject.ddc620 - Ingeniería y operaciones afinesspa
dc.subject.lembSeguridad ciudadana - Medellín (Antioquia, Colombia)
dc.subject.lembPrevención del delito - Medellín (Antioquia, Colombia)
dc.subject.lembInnovaciones tecnológicas - Medellín (Antioquia, Colombia)
dc.subject.proposalSeguridad Ciudadanaspa
dc.subject.proposalTransformada Waveletspa
dc.subject.proposalSeñal de Audiospa
dc.subject.proposalModos de Correlación Waveletspa
dc.subject.proposalAprendizaje de Máquinaspa
dc.subject.proposalCitizen securityeng
dc.subject.proposalWavelet Transformeng
dc.subject.proposalAudio signaleng
dc.subject.proposalWavelet Correlation Modeseng
dc.subject.proposalMachine Learningeng
dc.titleIdentificación de eventos delictivos a partir de señales de audio utilizando modos de correlación waveletspa
dc.title.translatedIdentification of crime events from audio signals using wavelet correlation modeseng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentPúblico generalspa
dcterms.audience.professionaldevelopmentResponsables políticosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa
oaire.awardtitleIdentificación de eventos delictivos a partir de señales de audio utilizando modos de correlación waveletspa
oaire.fundernameFondo de Ciencia, Tecnología e Innovación (FCTeI)spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1152199519.2024.pdf
Tamaño:
1.31 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Automatización Industrial

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: