[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124065-en":3,"doc-seo-124065-105":29,"detail-sidebar-cat-0-en-105":89},{"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":27,"seo_description":14,"update_tm":28,"read_time":11},124065,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Optimizing energy efficiency in underwater acoustic networks through machine learning classifiers","Battery and bandwidth limitations severely constrain underwater wireless sensor networks, reducing their lifetime and practical adoption. This work focuses on using edge-based machine learning to cut network resource demand in an underwater Internet of Things setting. It quantifies the potential impact by applying classifiers in an automated pipeline corrosion detection pipeline, transmitting only extracted conclusions rather than raw data. The goal is to reduce the burden on energy-powered acoustic nodes while enabling reliable risk classification.","STEWART, C., FOUGH, F., FOUGH, N. and PRABHU, R. 2024. Optimizing energy efficiency in underwater acoustic networks through machine learning classifiers. In Proceedings of the 31st IEEE (Institute of Electrical and Electronics Engineers) International conference on electronics, circuits, and systems (IEEE ICECS 2024), 18-20 November 2024, Nancy, France. Piscataway: IEEE [online], 10848718. Available from:  \n[https://doi.org/10.1109/ICECS61496.2024.10848718](https://doi.org/10.1109/ICECS61496.2024.10848718)  \nOptimizing energy efficiency in underwater acoustic networks through machine learning  \nclassifiers .  \nSTEWART, C., FOUGH, F., FOUGH, N. and PRABHU, R.  \n2024  \n© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.  \nOptimizing Energy Efficiency in Underwater Acoustic Networks Through Machine Learning Classifiers  \nCraig Stewart, Faranak Fough, Nazila Fough, Radhakrishna Prabhu  \nSchool of Computing, Engineering and Technology  \nRobert Gordon University, Aberdeen, UK  \nAbstract –Among many challenges in establishing an Underwater Wireless Sensor Network, is the challenge of resource constraints, battery and bandwidth being limited which renders acoustic networks limited in life and application. One identified application of TinyML is the potential of cutting the demand for network resources on the Internet of Things. Based on this hypothesis, this paper attempts to quantify the potential in using machine learning algorithms at the edge of the underwater network to reduce the burden on the battery powered acoustic node through an example automated of pipeline corrosion detection by transmitting only extracted conclusions from data.  \nKeywords—ML, Underwater Acoustics, Underwater Internet of Things, Underwater Wireless Sensor Networks, Pipeline Monitoring  \nI. INTRODUCTION  \nMachine Learning (ML) has been embraced across a plethora of fields such as healthcare [1], energy [2], and marine [3] etc. and has now begun to become pervasive in regular tasks. One application of ML is in the field of communications where it is being anticipated that it will have significant benefits in managing traffic [4], Enhancing Quality of Service (QoS) [5] and Network Design itself [6].Underwater Wireless Acoustic Communication (UWAC) has many characteristics that render it disadvantageous when trying to obtain low-energy and high data-rate communications that render it a channel quite unlike a terrestrial radio frequency channel. The bandwidth is limited to lower frequencies in the spectrum asthe physics tend to attenuate these frequencies less whilst requiring significant transmission powers to carry signals over vast distances of ocean wirelessly. ML classification atthe edge of the Underwater Wireless Acoustic Networks (UWAN) shows promise as it can take complex multidimensional data such as that from submerged sensor arraysand draw “meaningful data” from them through classification or regression that is useful for specific applications that would usually involve a layer of human interpretation. Thus, this work proposes taking a potential scenario in subsea pipeline corrosion and failure classification for energy efficient transmission using Machine Learning Classifiers.  \nII. METHODOLOGY  \nOn a terrestrial network, according to the OSI model, compression takes place on the Presentation Layer,  \ntraditionally, UWSN neglect this layer for energy efficiency reasons, however, computational resources are smaller and more efficient now that could enable for data to be reformatted before transmission for new energy savings to be found, compression mechanisms also use far more data than the single bit that is the aim of th","cbCaipV8lQ2wcu3j","https://ap.wps.com/l/cbCaipV8lQ2wcu3j","pdf",260114,1,3,"English","en",105,"# Introduction\n## Underwater wireless acoustic communication and ML classification\n# Methodology\n## Compression, dataset generation, and ML training\n## Risk modeling with DNV-RP-F101 and limit state equations","[{\"question\":\"Why are underwater acoustic networks challenging in energy efficiency?\",\"answer\":\"Resource constraints such as limited battery capacity and bandwidth restrict how long acoustic networks can operate, especially because underwater channels differ from terrestrial radio frequency behavior.\"},{\"question\":\"How does the paper use machine learning to reduce energy usage?\",\"answer\":\"It trains ML classifiers at the edge to classify pipeline corrosion risk and transmit only extracted conclusions instead of sending full raw data, reducing demand on network resources.\"},{\"question\":\"What dataset and standards are used for pipeline corrosion risk modeling?\",\"answer\":\"A large synthetic dataset is generated using metrics defined by DNVRP-F101, and the simulation uses equations to relate corrosion characteristics to leak or burst risk for ML training and evaluation.\"}]","Optimizing energy efficiency in underwater acoustic networks through machine learning classifiers | PDF",1785820162,{"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":84,"head_meta":86,"extra_data":88,"updated_unix":28},"optimizing-energy-efficiency-in-underwater-acoustic-networks-through-machine-learning-classifiers","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"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":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/optimizing-energy-efficiency-in-underwater-acoustic-networks-through-machine-learning-classifiers/124065/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why are underwater acoustic networks challenging in energy efficiency?","Question",{"text":73,"@type":74},"Resource constraints such as limited battery capacity and bandwidth restrict how long acoustic networks can operate, especially because underwater channels differ from terrestrial radio frequency behavior.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does the paper use machine learning to reduce energy usage?",{"text":78,"@type":74},"It trains ML classifiers at the edge to classify pipeline corrosion risk and transmit only extracted conclusions instead of sending full raw data, reducing demand on network resources.",{"name":80,"@type":71,"acceptedAnswer":81},"What dataset and standards are used for pipeline corrosion risk modeling?",{"text":82,"@type":74},"A large synthetic dataset is generated using metrics defined by DNVRP-F101, and the simulation uses equations to relate corrosion characteristics to leak or burst risk for ML training and evaluation.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"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":104,"slug":136},19,"General","general"]