Advanced Search

Show simple item record

dc.contributor.authorGençdoğmuş, Ayşenur
dc.contributor.authorKeskin, S.R.
dc.contributor.authorDogan, G.
dc.contributor.authorOzturk, Y.
dc.date.accessioned2020-12-20T06:50:03Z
dc.date.available2020-12-20T06:50:03Z
dc.date.issued2019
dc.identifier.isbn9781728108582
dc.identifier.urihttps://doi.org/10.1109/BigData47090.2019.9006164
dc.identifier.urihttps://hdl.handle.net/20.500.12436/1904
dc.descriptionAnkura;Baidu;IEEE;IEEE Computer Society;Veryen_US
dc.description2019 IEEE International Conference on Big Data, Big Data 2019 -- 9 December 2019 through 12 December 2019 -- -- 157991en_US
dc.description.abstractA common reason for low back pain can be attributed to postural stress. While seated or walking, bad posture can put strain on the spine. Increased stress on the spine may induce tightness and spasms in the lower back muscles and may lead to low back pain. Recognition of unstructured daily activities becomes a more difficult and essential task, as monitoring of daily activities becomes more important, especially for helping sick and elderly people. In this study, we employ deep learning and machine learning methods to study spine motion and postural stress using two sensors attached to lower back of a healthy subject while the subject is performing regular daily activities. A comparison of the accuracy of deep learning and supervised machine learning approaches (Decision Tree, Random Forest, Gradient Boosting, AdaBoost, KNN, Naive Bayes) in identification and labeling of daily activities is provided. In addition, the effective values for hyper parameters of LSTM neural networks have been determined. LSTM neural networks achieved highest accuracy. © 2019 IEEE.en_US
dc.description.sponsorshipBritish Association for Psychopharmacologyen_US
dc.description.sponsorshipWe would like to thank Merve Kayhan, Lara Yener and Alyssa Yesilyurt for proofreading the article. This study is supported by the Yildiz Technical University Scientific Research Project (BAP) numbered 3539 named Motion Kinematics Data Analysis.en_US
dc.language.isoengen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofProceedings - 2019 IEEE International Conference on Big Data, Big Data 2019en_US
dc.identifier.doi10.1109/BigData47090.2019.9006164en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectBig Data Analyticsen_US
dc.subjectData Miningen_US
dc.subjectDeep Learningen_US
dc.subjectLSTM Neural Networksen_US
dc.subjectMachine Learningen_US
dc.titleA data-driven approach to kinematic analytics of spinal motionen_US
dc.typeconferenceObjecten_US
dc.departmentMühendislik ve Doğa Bilimleri Fakültesien_US
dc.identifier.startpage2222en_US
dc.identifier.endpage2229en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.institutionauthorGençdoğmuş, Ayşenur
dc.institutionauthorAyşenur Gençdoğmuş |0000-0002-6289-9985
dc.department-tempGencdogmus, A., Sabahattin Zaim University, Department of Computer Engineering, Istanbul, Turkey; Keskin, S.R., Gazi University, Department of Computer Engineering, Ankara, Turkey; Dogan, G., Sabahattin Zaim University, Department of Computer Engineering, Istanbul, Turkey; Ozturk, Y., San Diego University, Department of Electrical and Computer Engineering, San Diego, United Statesen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record