[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291124-105":59,"doc-detail-291124-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","hybrid-machine-learning-approach-towards-anomaly-detection-and-data-quality-assessment-of-iot-weather-data-msc-research-project","Hybrid Machine Learning Approach Towards Anomaly Detection and Data Quality Assessment Of IoT Weather Data - MSc Research Project","","The growing rate of climate change requires high standards of analysis of weather data. This research uses IoT weather data from nearly 1200 cities worldwide to assess data quality through clustering and anomaly detection. A hybrid approach combines PCA for dimensional reduction with Isolation Forest for initial anomaly labeling, then DBSCAN and Gaussian Mixture Model for final clustering and anomaly identification. Results show anomaly rates of about 14–15%, ROC 0.70, clear visual separation, and improved performance over individual models.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/hybrid-machine-learning-approach-towards-anomaly-detection-and-data-quality-assessment-of-iot-weather-data-msc-research-project/291124/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/hybrid-machine-learning-approach-towards-anomaly-detection-and-data-quality-assessment-of-iot-weather-data-msc-research-project/291124.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the research address?","Question",{"text":113,"@type":114},"It addresses the need for high standards in analyzing weather data under climate change by detecting anomalies and assessing data quality from IoT sources.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which algorithms are used in the hybrid model?",{"text":118,"@type":114},"The approach uses PCA for dimensional reduction, Isolation Forest for initial anomaly labeling, and a combination of DBSCAN and Gaussian Mixture Model for final clustering and anomaly detection.",{"name":120,"@type":111,"acceptedAnswer":121},"What dataset is used and what is its scale?",{"text":122,"@type":114},"The study uses “The Weather Dataset 1” from Kaggle, containing readings from approximately 1200 cities worldwide.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291124,1789643521,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","Hybrid Machine Learning Approach Towards Anomaly Detection and Data Quality Assessment Of IoT Weather Data  \nMSc Research Project  \nData Analytics  \nSaket Abhaykumar Kulkarni  \nStudent ID: 23102381  \nSchool of Computing National College of Ireland  \nSupervisor: Jaswinder Singh  \nNational College of Ireland Project Submission Sheet School of Computing  \n| Student Name: | Saket Abhaykumar Kulkarni |\n| --- | --- |\n| Student ID: | 23102381 |\n| Programme: | Data Analytics |\n| Year: | 2024 |\n| Module: | MSc Research Project |\n| Supervisor: | Jaswinder Singh |\n| Submission Due Date: | 12/08/2024 |\n| Project Title: | Hybrid Machine Learning Approach Towards Anomaly Detection and Data Quality Assessment Of IoT Weather Data |\n| Word Count: | 6471 |\n| Page Count: | 20 |\n\nI hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project.  \nALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author’s written or electronic work is illegal (plagiarism) and may result in disciplinary action.  \n\n| Signature: |  |\n| --- | --- |\n| Date: | 13th September 2024 |\n\nPLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST:  \n\n| Attach a completed copy of this sheet to each project (including multiple copies) . | □ |\n| --- | --- |\n| Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ |\n| You must ensure that you retain a HARD COPY of the project, both foryour own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ |\n\nAssignments that are submitted to the Programme Coordinator office must be placed into the assignment box located outside the office.  \n\n| Office Use Only |  |\n| --- | --- |\n| Signature: |  |\n| Date: |  |\n| Penalty Applied (if applicable): |  |\n\nHybrid Machine Learning Approach Towards Anomaly Detection and Data Quality Assessment Of  \nIoT Weather Data  \nSaket Abhaykumar Kulkarni  \n23102381  \nAbstract  \nThe growing rate of climate change requires high standards of analysis of weather data. This research focuses on climate science and its data quality assessment though clustering and anomaly detection using traditional machine learning with a combination of PCA for dimensional reduction. By using IoT weather data from almost 1200 cities around the world, the hybrid model is built to detect anomalies and classify data according to its quality. The final percentage of anomalies found in the data are between 14-15 % of the entire data with an ROC of 0.70 and the anomalies are visualised which shows clear separation between the values. The hybrid model performed better compared to individual models with evaluations metrics of Homogeneity: 0.702, Completeness: 0.527, V-Measure: 0.602, Adjusted Rand Index: 0.713 . The following model is a strong base to prove that there is space for traditional machine learning in this field rather that heavy deep learning models which require much higher computational power. The pre-trained models perform well and are a the base for future development in clustering analysis of weather data.  \nKeywords: Machine Learning, Climate Science, Clustering, Anomalies, Data Quality  \n1 Introduction  \nClimate change and its impact on weather patterns have become increasingly significant concerns in recent years. The rise of Internet of Things has improvised the ability to collect, analyze, and interpret vast amounts of weather data Gubbi et al. (2013) . This wealth of information presents both opportunities and challenges in identifying anomalies and patterns that may indicate climate shifts or extreme weather events. This research focuses on developing a hybrid machine lear","cbCaidzcY5KZd2FE","https://ap.wps.com/l/cbCaidzcY5KZd2FE","pdf",1888123,22,"English","# 1 Introduction\n## Research focus and motivation\n## Hybrid model components and methodology\n## Dataset and objective\n# Abstract\n## Problem statement and approach\n## Data source and evaluation results","[{\"question\":\"What problem does the research address?\",\"answer\":\"It addresses the need for high standards in analyzing weather data under climate change by detecting anomalies and assessing data quality from IoT sources.\"},{\"question\":\"Which algorithms are used in the hybrid model?\",\"answer\":\"The approach uses PCA for dimensional reduction, Isolation Forest for initial anomaly labeling, and a combination of DBSCAN and Gaussian Mixture Model for final clustering and anomaly detection.\"},{\"question\":\"What dataset is used and what is its scale?\",\"answer\":\"The study uses “The Weather Dataset 1” from Kaggle, containing readings from approximately 1200 cities worldwide.\"}]","Hybrid Machine Learning Approach Towards Anomaly Detection and Data Quality Assessment Of IoT Weather Data - MSc Research Project | PDF",55]