[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120964-en":3,"doc-seo-120964-105":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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120964,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Detection of Seismic Infrasonic Elephant Rumbles Using Spectrogram-Based Machine Learning","This paper introduces a method for automatically identifying elephant rumbles in infrasonic seismic recordings. Electronic circuitry is designed to amplify, filter, and digitize geophone-captured signals, and a dataset is collected in Sri Lanka from a free-ranging elephant orphanage area. Signals are converted into spectrograms, spectral features are extracted, then LasyPredict links feature sets to machine-learning classifiers for training. MFCC features combined with a Ridge classifier achieve the best accuracy, and a denoising spectrum approach further improves identification performance.","Detection of Seismic Infrasonic Elephant Rumbles Using Spectrogram-Based Machine Learning  \nA. M. J. V. Costa, C. S. Pallikkonda, H. H. R. Hiroshan, G. R. U. Y. Gamlath, S. R. Munasinghe, SMIEEE,  \nC. U. S. Edussooriya  \narXiv :2312 .0283 1v 1 [ cs .CY] 5 Dec 2023  \nAbstract—This paper presents an effective method of identifying elephant rumbles in infrasonic seismic signals. The design and implementation of electronic circuitry to amplify, filter, and digitize the seismic signals captured through geophones arepresented. A collection of seismic infrasonic elephant rumbles was collected at a free-ranging area of an elephant orphanage in Sri Lanka. The seismic rumbles were converted to spectrograms and several methods were used for spectral feature extraction. Using LasyPredict, the features extracted using different methods were fed into their corresponding machine-learning algorithms to train them for automatic seismic rumble identification. It was found that the Mel frequency cepstral coefficient (MFCC) feature extraction method and the Ridge classifier machine learning algorithm give the best performance in identifying seismic elephant rumbles. A novel method for denoising the spectrum that leads to enhanced accuracy in identifying seismic rumbles is also presented.  \nIndex Terms—Infrasonic elephant rumbles, spectrogram, CMRR, MFCCs, Hjorth parameters, Geophone, seismic waves  \nI. INTRODUCTION  \nELephants use different vocalization patterns to commu  \nnicate between herds and each other for food, water, mating, and warning. Among these patterns, the infrasonic rumbles have a very specific significance in long-range communication [1] . Elephant rumbles have acoustic and seismic components. The acoustic component is what propagates through the air as a 3D wave, and gets attenuated through the foliage fairly quickly. The seismic component on the other hand propagates through the ground as a 2D Rayleigh wave and therefore, travels a longer distance compared to the acoustic component. Elephant’s foot is believed to have the capability of a seismic transponder to facilitate long-range seismic infrasonic communication. These seismic signals can be a powerful component of an elephant’s communication system, serving crucial functions such as mate finding, prey detection, and interspecific and intraspecific warnings [2] . The attenuation of seismic waves during transmission increases monotonically with frequency, hence the range of 10Hz to 40Hz is considered the ”sweet zone” for seismic signal propagation. Elephant rumbles, which have a fundamental frequency of around 20Hz [3], fall within this sweet zone, allowing them to communicate through the ground. The elephant rumbles  \nManuscript received mm dd, yyyy. All authors are affiliated to the Department of Electronic and Telecommunication Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka  \nS. R. Munasinghe is a visiting Fellow at the Department of Global Development, CALS, Cornell University, Ithaca 14850, NY, USA (e-mail: [srm278@cornell.edu](srm278@cornell.edu))  \nthat propagate as Rayleigh waves through the ground can be captured using geophones [4] .  \nDetecting and localizing wild elephants through airborne rumbles encounter certain challenges that impede its effectiveness. Airborne signals, though easy to detect, attenuate rapidly limiting the range over which elephants can be identified. The amplitude of a Rayleigh wave during ground surface transmission is inversely proportional to the square root of the distance, with a loss of 3dB for every doubling of the distance. In airborne signals, amplitude is inversely proportional to the distance, with a loss of 6dB for every doubling of the distance. Factors such as weather, time of day, scattering, and reflections due to objects, and trees also attenuate the airborne signal [2] . The seismic wave undergoes a lower attenuation compared to the airborne wave, hence the detectable range of the seismic component of a rumble","cbCaij4uaZptybb1","https://ap.wps.com/l/cbCaij4uaZptybb1","pdf",6988388,1,"English","en",105,"# Introduction\n# Spectrogram of Infrasonic Seismic Signals\n## Overview of Signal Acquisition and Processing\n## (Further sections not shown)","[{\"question\":\"How are elephant infrasonic rumbles captured for analysis?\",\"answer\":\"Elephant rumbles are recorded using geophones that capture the seismic component propagating through the ground, followed by electronic amplification, bandpass filtering, and digitization.\"},{\"question\":\"What role do spectrograms and feature extraction play?\",\"answer\":\"The seismic signals are transformed into spectrograms, and spectral feature extraction methods are applied to generate inputs for machine-learning models.\"},{\"question\":\"Which feature extraction and classifier combination performs best?\",\"answer\":\"Mel frequency cepstral coefficient (MFCC) feature extraction paired with a Ridge classifier machine-learning algorithm provides the best performance for identifying seismic elephant rumbles.\"}]","Detection of Seismic Infrasonic Elephant Rumbles Using Spectrogram-Based Machine Learning | PDF",1785733087,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"detection-of-seismic-infrasonic-elephant-rumbles-using-spectrogram-based-machine-learning","",{"@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/detection-of-seismic-infrasonic-elephant-rumbles-using-spectrogram-based-machine-learning/120964/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"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","2026-08-03",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},"How are elephant infrasonic rumbles captured for analysis?","Question",{"text":74,"@type":75},"Elephant rumbles are recorded using geophones that capture the seismic component propagating through the ground, followed by electronic amplification, bandpass filtering, and digitization.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What role do spectrograms and feature extraction play?",{"text":79,"@type":75},"The seismic signals are transformed into spectrograms, and spectral feature extraction methods are applied to generate inputs for machine-learning models.",{"name":81,"@type":72,"acceptedAnswer":82},"Which feature extraction and classifier combination performs best?",{"text":83,"@type":75},"Mel frequency cepstral coefficient (MFCC) feature extraction paired with a Ridge classifier machine-learning algorithm provides the best performance for identifying seismic elephant rumbles.","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":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"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":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]