[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122523-en":3,"doc-seo-122523-105":30,"detail-sidebar-cat-0-en-105":91},{"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":29},122523,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Using machine learning for fault detection in lighthouse light sensors - Paper","Lighthouses support maritime safety by using photoresistor sensors to switch light operation according to time of day, but sensor malfunctions can gradually shift the light’s timing and compromise hazard warnings. The work presents a machine-learning method for automatic detection of such gradual faults, addressing the lack of verified historical failure data through fault simulation and pre-trained models. Four algorithms are evaluated, with the multi-layer perceptron achieving reliable detection of small timing discrepancies (10–15 minutes).","Using machine learning for fault detection in  \nlighthouse light sensors  \nMichael Kampouridis  \nSchool of Computer Science and Electronic Engineering University of Essex Wivenhoe Park, UK [mkampo@essex.ac.uk](mkampo@essex.ac.uk)  \nNikolaos Vastardis  \nGeneral Lighthouse Authorities of the UK and Ireland Research and Development Directorate Harwich, UK [Nikolaos.Vastardis@gla-rad.org](Nikolaos.Vastardis@gla-rad.org)  \narXiv :2409 .05495v 1 [ cs .LG] 9 Sep 2024  \nGeorge Rayment  \nSchool of Computer Science and Electronic Engineering University of Essex  \nWivenhoe Park, UK  \n[gr17754@essex.ac.uk](gr17754@essex.ac.uk)  \nAbstract—Lighthouses play a crucial role in ensuring maritime safety by signaling hazardous areas such as dangerous coastlines, shoals, reefs, and rocks, along with aiding harbor entries and aerial navigation. This is achieved through the use of photoresistor sensors that activate or deactivate based on the time of day. However, a significant issue is the potential malfunction of these sensors, leading to the gradual misalignment of the light’s operational timing. This paper introduces an innovative machine learning-based approach for automatically detecting such malfunctions. We evaluate four distinct algorithms: decision trees, random forest, extreme gradient boosting, and multi-layer perceptron. Our findings indicate that the multi-layer perceptron is the most effective, capable of detecting timing discrepancies as small as 10-15 minutes. This accuracy makes it a highly efficient tool for automating the detection of faults in lighthouse light sensors.  \nIndex Terms—machine learning, lighthouses, fault detection  \nI. INTRODUCTION  \nThe General Lighthouse Authority (GLA) of the UK and Ireland is dedicated to providing a reliable, efficient, and costeffective navigation aid service for the maritime community’s safety and benefit. The GLA Research and Development (GRAD) division, serving all three General Lighthouse Authorities in the UK and Ireland, is at the forefront of this mission. GRAD is responsible for researching and developing both physical and radio marine aids to navigation (AtoNs), as well as supporting systems and their integration, to uphold the GLA’s commitment to delivering top-notch AtoNs for the safety and benefit of mariners.  \nGRAD manages a variety of AtoNs, including lighthouses, buoys, light-vessels, beacons, and electronic navigation systems. These aids are crucial for safely guiding mariners through some of the UK’s most trafficked waters, like the Dover Strait, the world’s busiest shipping lane.  \nAmong these aids, lighthouses play a vital role in marking perilous coastlines, shoals, reefs, rocks, and assisting in both sea and aerial navigation. A critical component of a lighthouse is its photoresistor sensor, which automates the light’s  \noperation. However, sensor malfunctions pose significant risks, such as delayed activation of lights, endangering ships in the vicinity by not alerting them to nearby hazards.  \nThe challenge lies in monitoring and addressing sensor malfunctions in lighthouses, often situated in remote and hardto-access locations. Reaching these sites, sometimes requiring costly helicopter transport, drives up maintenance expenses significantly. As a result, it’s more feasible to replace unreliable components during regular maintenance visits rather than immediately upon detecting a fault.  \nTo proactively detect potential sensor faults and efficiently plan maintenance, we propose utilizing machine learning (ML) to identify early signs of malfunction in lighthouse light sensors. A major hurdle is the absence of historical data on verified sensor failures, largely due to preemptive replacements during scheduled maintenance. Sensor failures can be gradual, showing increasing delays in light activation, or abrupt, such as a total breakdown. Our focus is on the former, the more complex scenario, as abrupt failures are straightforward and don’t require ML intervention.  \nTo ","cbCaibTel8zoky86","https://ap.wps.com/l/cbCaibTel8zoky86","pdf",893645,1,7,"English","en",105,"# Introduction\n## Background information and literature review\n## Proposed approach and methodology\n## Experimental setup\n## Results and discussion\n## Conclusion and future work","[{\"question\":\"Why are lighthouse light sensor malfunctions risky?\",\"answer\":\"Malfunctions can delay or disrupt light activation, meaning nearby ships may not receive timely warnings of hazards, increasing maritime risk.\"},{\"question\":\"How does the paper handle the lack of verified historical sensor-failure data?\",\"answer\":\"It simulates gradual photoresistor sensor faults and evaluates pre-trained machine-learning models on the generated data.\"},{\"question\":\"Which algorithm performs best for detecting timing discrepancies, and what accuracy level is reported?\",\"answer\":\"The multi-layer perceptron is reported as the most effective, detecting timing discrepancies as small as 10–15 minutes.\"}]","Using machine learning for fault detection in lighthouse light sensors - Paper | PDF",1785811086,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"using-machine-learning-for-fault-detection-in-lighthouse-light-sensors-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/using-machine-learning-for-fault-detection-in-lighthouse-light-sensors-paper/122523/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are lighthouse light sensor malfunctions risky?","Question",{"text":75,"@type":76},"Malfunctions can delay or disrupt light activation, meaning nearby ships may not receive timely warnings of hazards, increasing maritime risk.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper handle the lack of verified historical sensor-failure data?",{"text":80,"@type":76},"It simulates gradual photoresistor sensor faults and evaluates pre-trained machine-learning models on the generated data.",{"name":82,"@type":73,"acceptedAnswer":83},"Which algorithm performs best for detecting timing discrepancies, and what accuracy level is reported?",{"text":84,"@type":76},"The multi-layer perceptron is reported as the most effective, detecting timing discrepancies as small as 10–15 minutes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]