[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117301-en":3,"doc-seo-117301-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},117301,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Automated Infant Pain Detection from Acoustic Features of Baby Cries - Thesis","This thesis develops an automated approach for detecting infant pain using acoustic characteristics extracted from baby cries. It covers neonatal comfort as the clinical motivation, applies audio signal processing in time and time-frequency domains, and defines clear thesis objectives. A curated dataset including COPE and Baby Chillanto is processed through scaling, re-sampling, filtering, segmentation, and cleaning. The work extracts log-Mel and MFCC features, performs augmentation with SMOTE, and evaluates machine learning classifiers such as SVM and CNNs with YAMNet, reporting prediction performance and inference results.","DIPARTIMENTO  \nDI INGEGNERIA  \nDIPARTIMENTO DI INGEGNERIA DELL’INFORMAZIONE  \nCORSO DI LAUREA MAGISTRALE IN BIOINGEGNERIA DELLA  \nRIABILITAZIONE  \n“Automated Infant Pain Detection from Acoustic Features of Baby Cries”  \nRelatore: Dott.ssa Rubega Maria  \nLaureando: Caselli Alessandro  \nCorrelatore: Dott. Passarotto Edoardo  \nANNO ACCADEMICO 2023 – 2024  \n23 Ottobre 2024  \n“Ringrazio la Dottoressa Rubega Maria per avermi proposto questo interessantissimo progetto  \ndi tesi.  \nRingrazio il Dottor Edoardo Passarotto, il mio mentore in questopercorso di tesi, che mi hainsegnato tanto, sempre con gentilezza, interesse e pazienza.  \nRingrazio mio fratello, i miei zii e i miei amici che mi hanno aiutato a crescere e maturare. Sonosempre stati per me ottimi esempi da cuiprendere spunto per migliorare come uomo,  \nlavoratore, fidanzato e persona.  \nRingrazio Giulia, da anni la mia consigliera, migliore amica, spalla su cui piangere e ora anche  \nfonte di grande aƯetto e amore.  \nRingrazio Angela, mia madre, sempre dalla mia parte. Senza di lei, probabilmente non avrei  \nscritto questi ringraziamenti.  \nInfine, dedico questo traguardo a mio padre, che mi protegge dall'alto e mi ha potuto crescere solo tramite il bene e le belle storie che ha lasciato nel cuore dei suoi conoscenti.”  \n1. Introduction .............................................................................................................. 7  \n1.1. Neonatal comfort ............................................................................................... 7  \n1.2. Audio signal processing ...................................................................................... 9  \n1.2.1. Analysis in the time domain .......................................................................... 9  \n1.2.2. Analysis in the time-frequency domain ........................................................ 10  \n1.3. Thesis objectives .............................................................................................. 11  \n2. Materials and Methods ............................................................................................ 13  \n2.1. Dataset: COPE and Baby Chillanto .................................................................... 13  \n2.2. Pre-Processing ................................................................................................. 14  \n2.2.1. Signal Scaling ............................................................................................ 16  \n2.2.2. Signal Re-Sampling .................................................................................... 17  \n2.2.3. Signal Filtering ........................................................................................... 18  \n2.2.4. Signal Segmentation .................................................................................. 20  \n2.2.5. Dataset cleaning........................................................................................ 23  \n2.3. Feature Extraction ............................................................................................ 25  \n2.3.1. Log-Mel Scale ............................................................................................ 25  \n2.3.2. MFCC: Mel Frequency Cepstral CoeƯicient ................................................. 26  \n2.3.3. Windowing and Overlapping ....................................................................... 27  \n2.4. Data Augmentation: SMOTE .............................................................................. 28  \n2.5. Classification algorithms .................................................................................. 31  \n2.5.1. Support Vector Machines ........................................................................... 31  \n2.5.1.1. SVM operating principles ..................................................................... 31  \n2.5.1.2. Application of SVM with Mel coeƯicients .............................................. 35  \n2.5.1.3. Evaluation metrics for SVM m","cbCaitlACK4s02lG","https://ap.wps.com/l/cbCaitlACK4s02lG","pdf",1752493,1,71,"English","en",105,"# Introduction\n## Neonatal comfort\n## Audio signal processing\n## Thesis objectives\n# Materials and Methods\n## Dataset: COPE and Baby Chillanto\n## Pre-Processing\n## Feature Extraction\n## Data Augmentation: SMOTE\n## Classification algorithms\n# Results\n## Features Extracted\n## Prediction Model Performances\n## YAMNet inference\n# Discussion, Conclusions and Future Developments\n## Discussion\n## Conclusion\n## Future Developments\n# Bibliography\n# Appendix","[{\"question\":\"What acoustic signals and feature types are used to detect infant pain?\",\"answer\":\"The method extracts log-Mel scale features and MFCC coefficients from baby-cry audio. It also considers windowing and overlapping to structure the analysis.\"},{\"question\":\"How is the dataset prepared before training and evaluation?\",\"answer\":\"The dataset (COPE and Baby Chillanto) undergoes scaling, re-sampling, filtering, and segmentation. It is then cleaned to improve data quality prior to modeling.\"},{\"question\":\"Which models are used and how are their performances evaluated?\",\"answer\":\"The thesis evaluates SVM and CNN-based approaches, including transfer learning with a YAMNet model. It reports prediction model performances and includes evaluation metrics for the classifiers.\"}]",1785675067,179,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"automated-infant-pain-detection-from-acoustic-features-of-baby-cries-thesis","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/automated-infant-pain-detection-from-acoustic-features-of-baby-cries-thesis/117301/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What acoustic signals and feature types are used to detect infant pain?","Question",{"text":74,"@type":75},"The method extracts log-Mel scale features and MFCC coefficients from baby-cry audio. It also considers windowing and overlapping to structure the analysis.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How is the dataset prepared before training and evaluation?",{"text":79,"@type":75},"The dataset (COPE and Baby Chillanto) undergoes scaling, re-sampling, filtering, and segmentation. It is then cleaned to improve data quality prior to modeling.",{"name":81,"@type":72,"acceptedAnswer":82},"Which models are used and how are their performances evaluated?",{"text":83,"@type":75},"The thesis evaluates SVM and CNN-based approaches, including transfer learning with a YAMNet model. It reports prediction model performances and includes evaluation metrics for the classifiers.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]