[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118781-en":3,"doc-seo-118781-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},118781,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Machine Learning methods to estimate odour intensity - Electronic nose drone for real-time odour monitoring in wastewater treatment plants","Odour is a human perception whose link to chemical composition remains insufficiently understood. Instrumental Odour Monitoring Systems, especially electronic noses, enable real-time monitoring by learning the relationship between sensor responses and odour concentration. This study presents a drone-borne e-nose system generating dynamic sensor signals for classifying and quantifying odours in wastewater treatment plants. Predictive Machine Learning models distinguish odour from non-odour samples with 93% accuracy and estimate odour concentration with agreement within a factor of four compared with dynamic olfactometry measurements.","Machine Learning methods to estimate odour intensity  \nAuthor: Ivan Casanovas Rodr´ıguez  \nFacultat de F´ısica, Universitat de Barcelona, Diagonal 645, 08028 Barcelona, Spain.  \nAdvisor: Santiago Marco Col´as  \nAbstract: Odour is a human perception whose relationship with chemical composition is unknown. Contrary to the olfactometric measurement techniques, senso-instrumental methods provide real-time odour monitoring. The study presents a drone equipped with an electronic nose that generates dynamic sensor signals for the classification and quantification of odours in wastewater treatment plants. By calibrating predictive models with Machine Learning algorithms, odour/nonodour samples are classified with 93% accuracy, and odour concentration is predicted 95% limits of agreement within a factor of four, in comparison with dynamic olfactometry measurements.  \nI. INTRODUCTION  \nOdour pollution is currently a significant environmental and human health issue. Due to advancements in society, there is a growing number of odour-emitting sources, and wastewater treatment plants (WWTPs) are one of the primary contributors. These emissions have an impact on well-being and air quality in the nearby area, and can even lead to health and psychological problems.  \nUnderstanding odour as a human perception, its characterization has become a challenge. This difficulty arises from its subjectivity nature and the complexity of its chemical composition. In recent years, the main purpose has been to estimate odour intensity via standardized methods.  \nAccording to the European standard EN13725:2022, its quantification is determined in a laboratory by dynamic olfactometry, a sensorial technique that correlates odour concentration with the human sense of smell. This measurement, carried out by trained human panels, represents the dilution factor required for a sample to reach its odour detection threshold concentration (ouE /m3 ) . Since the referenced method is a slow process and requires multiple sampling, real-time odour monitoring isnot feasible. These limitations, along with the variability in results, highlight the need for alternative techniques. Instrumental Odour Monitoring Systems (IOMS) [1], commonly known as electronic noses, are devices trained to classify and quantify odours by analyzing the dynamic electrical signals provided by poorly-selective chemical sensors. Their aim is to establish the relationship between sensors response and odour concentration, which is unknown a priori. Using algorithms that learn from samples, we are able to solve the problem and experimentally measure what is actually a human perception. There is also a necessity to study complex environments such as WWTPS, where there are numerous odour-emitting sources. A novel approach to odour monitoring in these areas is the utilization of drones equipped with e-noses, because they allow for quickly measuring different positions. In this study [2], a similar IOMS was employed to monitor odour in the WWTP of Molina de Segura (Murcia, Spain) . The drone hovers above  \nthe WWTP following a predefined navigation path and, at each point of interest, the chemical sensors continuously measure for a specific period of time. The drone is also equipped with an odour sampling device to measure the odour concentration using dynamic olfactometry. Moreover, odourless samples (blanks) are characterized through sensor measurements in the surroundings. By covering the entire area, an odour concentration map can be developed to study odour propagation and the interaction of emissions from different sources.  \nThe main goal of this TFG is to estimate the emitting odours of a WWTP by processing the sensor signals using Machine Learning methods. As the odour concentrations of the samples are known, two types of problems are addressed. On one hand, the classification aims to distinguish between odour and non-odour samples. On the other hand, the regression problem involves predicting the","cbCailV6l5jDXpy4","https://ap.wps.com/l/cbCailV6l5jDXpy4","pdf",2355210,1,5,"English","en",105,"# Introduction\n## Odour pollution and measurement challenge\n## Electronic noses and drone-based monitoring\n# Experimental Methods\n## Drone and sensor system\n## Data acquisition and sampling campaign","[{\"question\":\"Why are real-time odour monitoring techniques needed compared with standard dynamic olfactometry?\",\"answer\":\"Dynamic olfactometry relies on trained human panels and is a slow process requiring multiple sampling, making real-time monitoring difficult. Variability and limitations in the referenced method motivate alternative approaches.\"},{\"question\":\"How does the drone with an electronic nose help estimate odour intensity at wastewater treatment plants?\",\"answer\":\"The drone follows a predefined path and uses chemical sensors to record dynamic electrical signals at each point. Odour and odourless (blank) samples are also measured using dynamic olfactometry to calibrate predictive models.\"},{\"question\":\"What Machine Learning tasks are used with the collected sensor and odour data?\",\"answer\":\"Two problems are addressed: classification to distinguish odour vs non-odour samples, and regression to predict odour concentration for each sample after preprocessing the data.\"}]","Machine Learning methods to estimate odour intensity - Electronic nose drone for real-time odour monitoring in wastewater treatment plants | PDF",1785720219,13,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-methods-to-estimate-odour-intensity-electronic-nose-drone-for-real-time-odour-monitoring-in-wastewater-treatment-plants","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-methods-to-estimate-odour-intensity-electronic-nose-drone-for-real-time-odour-monitoring-in-wastewater-treatment-plants/118781/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are real-time odour monitoring techniques needed compared with standard dynamic olfactometry?","Question",{"text":76,"@type":77},"Dynamic olfactometry relies on trained human panels and is a slow process requiring multiple sampling, making real-time monitoring difficult. Variability and limitations in the referenced method motivate alternative approaches.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the drone with an electronic nose help estimate odour intensity at wastewater treatment plants?",{"text":81,"@type":77},"The drone follows a predefined path and uses chemical sensors to record dynamic electrical signals at each point. Odour and odourless (blank) samples are also measured using dynamic olfactometry to calibrate predictive models.",{"name":83,"@type":74,"acceptedAnswer":84},"What Machine Learning tasks are used with the collected sensor and odour data?",{"text":85,"@type":77},"Two problems are addressed: classification to distinguish odour vs non-odour samples, and regression to predict odour concentration for each sample after preprocessing the data.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":21,"slug":138},19,"General","general"]