[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126730-en":3,"doc-seo-126730-105":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},126730,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Clustering of clinical multivariate time-series utilizing recent advances in machine-learning - Master’s thesis","The thesis establishes a foundation for future research on a machine-learning based anomaly detection system for hospitalized patients. The initial work identifies project needs, relevant background, and literature covering similar criteria, followed by interviews with medical experts and researchers. The collected data and interview suggestions guide the exploration of clustering and analysis approaches, which are then evaluated and discussed. Results indicate that K-means combined with principle component-based clustering achieved the highest quality.","Faculty of Engineering Science and Technology  \nDepartment of Computer Science and Computational Engineering  \nClustering of clinical multivariate time-series utilizing recent advances in machine-learning  \nAsal Asgari  \nDTE-3900 Master’s thesis in Applied Computer Science May 2023  \nThis thesis document was typeset using the UiT Thesis LaTEX Template.© 2023 – [http://github.com/egraff/uit-thesis](http://github.com/egraff/uit-thesis)  \nAbstract  \nThe purpose of this thesis is to set the groundwork for future research on developing a machine-learning based anomaly detection system for hospitalized patients. Our first step was to study and analyze the project’s needs, background, and literature examining similar criteria. In the second step, we interviewed medical experts and researchers. Based on our research and the suggestions received in our interviews, we explored methods that could be utilized to approach the issue based on the data we collected. The results of these approaches were then discussed.  \nAccording to the results, the K-means algorithm, which utilizes principle components to cluster, obtained the highest quality. We then discussed how other algorithms have been influenced more by the shape of the data than by the values ofthe data. Afterward, we made some suggestions about how this research could be approached in the future as we move forward.  \nAcknowledgements  \nI would first like to thank my supervisors Helge Fredriksen and Bernt Arild Bremdal for their guidance, feedback, and resources.  \nI am also grateful to my parents for supporting me and making it possible forme to move to Norway and pursue higher education.  \nLastly, I am thankful to my classmates Håkon Berg Borhaug, Johanne Holst Klæboe and Joachim Kristensen for all their help during my master’s.  \nContents  \nAbstract i  \nAcknowledgements iii  \nList of Figures vii  \nList of Tables ix  \n1 Introduction 1  \n1.1 Background .......................... 1  \n1.2 Relevance ........................... 2  \n1.3 Objective ............................ 3  \n1.4 The State of the Art ...................... 4  \n1.5 Strategy ............................ 6  \n1.6 Theory ............................. 6  \n1.6.1 Machine Learning ................... 6  \n1.6.2 Time-series Clustering ................. 7  \n1.6.3 Clustering Evaluation Metrics ............. 9  \n1.6.4 Similarity Measures .................. 10  \n1.6.5 Dimensionality Reduction ............... 11  \n2 Tools and Methods 13  \n2.1 Tools .............................. 13  \n2.1.1 Tool Selection ..................... 13  \n2.2 Preprocessing ......................... 14  \n2.3 Non-temporal Analysis ..................... 15  \n2.4 Clustering ........................... 16  \n2.4.1 Dataset ......................... 17  \n2.4.2 K-means ........................ 17  \n2.4.3 Hierarchical Clustering ................ 20  \n2.4.4 DBSCAN ........................ 22  \n2.5 Methods pipeline ....................... 22  \n3 Results and Discussion 25  \nvi contents  \n3.1 Results ............................. 25  \n3.1.1 Non-temporal Analysis ................. 25  \n3.1.2 Clustering ....................... 32  \n3.2 Discussion ........................... 40  \n3.2.1 Non-temporal analysis ................. 40  \n3.2.2 Clustering ....................... 41  \n4 Conclusion and Future Work 43  \nBibliography 45  \nA Installation and User Guide 51  \nA.1 Installation ........................... 51  \nA.2 User Guide ........................... 52  \nB Task Description 53  \nList of Figures  \n2.1 Dataset format with patient vitals, gender, level of consciousness, and the time each record was made ........... 15  \n2.2 Table of Calculated the standard deviation(std), minimum(min), maximum(max), and mean values of systolic blood pressure for each patient’s trajectory .................. 16  \n2.3 Figure of the elbow method using the Silhouette score suggesting the optimal number of clusters for the Type 1 dataset 19  \n2.4 Figure of the elbow method using the Silhouette score","cbCailv9oTJWQ8ny","https://ap.wps.com/l/cbCailv9oTJWQ8ny","pdf",4487191,1,74,"English","en",105,"# Abstract\n# Acknowledgements\n# List of Figures\n# List of Tables\n# 1 Introduction\n## 1.1 Background\n## 1.2 Relevance\n## 1.3 Objective\n## 1.4 The State of the Art\n## 1.5 Strategy\n## 1.6 Theory\n# 2 Tools and Methods\n## 2.1 Tools\n## 2.2 Preprocessing\n## 2.3 Non-temporal Analysis\n## 2.4 Clustering\n## 2.5 Methods pipeline\n# 3 Results and Discussion\n## 3.1 Results\n## 3.2 Discussion\n# 4 Conclusion and Future Work\n# Bibliography\n# A Installation and User Guide\n## A.1 Installation\n## A.2 User Guide\n# B Task Description","[{\"question\":\"What problem does the thesis aim to support?\",\"answer\":\"It lays groundwork for a machine-learning based anomaly detection system for hospitalized patients, starting from clustering and data analysis approaches.\"},{\"question\":\"How were the requirements and approach shaped in the thesis?\",\"answer\":\"The work reviewed project needs and related literature, then interviewed medical experts and researchers. The discovered needs and suggestions informed the methods explored using the collected data.\"},{\"question\":\"Which clustering approach produced the best results and why?\",\"answer\":\"K-means, using principal components to cluster, achieved the highest quality. Other algorithms were reported to be more influenced by the shape of the data rather than the raw values.\"}]","Clustering of clinical multivariate time-series utilizing recent advances in machine-learning - Master’s thesis | PDF",1785934472,186,{"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},"clustering-of-clinical-multivariate-time-series-utilizing-recent-advances-in-machine-learning-masters-thesis","",{"@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/clustering-of-clinical-multivariate-time-series-utilizing-recent-advances-in-machine-learning-masters-thesis/126730/",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","2026-08-05",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},"What problem does the thesis aim to support?","Question",{"text":75,"@type":76},"It lays groundwork for a machine-learning based anomaly detection system for hospitalized patients, starting from clustering and data analysis approaches.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the requirements and approach shaped in the thesis?",{"text":80,"@type":76},"The work reviewed project needs and related literature, then interviewed medical experts and researchers. The discovered needs and suggestions informed the methods explored using the collected data.",{"name":82,"@type":73,"acceptedAnswer":83},"Which clustering approach produced the best results and why?",{"text":84,"@type":76},"K-means, using principal components to cluster, achieved the highest quality. Other algorithms were reported to be more influenced by the shape of the data rather than the raw values.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":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":106,"slug":138},19,"General","general"]