{"corpus_id":6684687,"paper_sha":"f2f9c868bf74c2747ace75b1b213548026626e36","doi":"10.1109/TBME.2014.2359372","arxiv_id":"1409.5181","pmid":25252274,"pmcid":null,"mag_id":2005741801,"dblp_id":"journals/corr/ZhangPL14","acl_id":null,"title":"TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise","year":2014,"publication_date":"2014-09-17","venue":"IEEE Transactions on Biomedical Engineering","journal":{"name":"IEEE Transactions on Biomedical Engineering","pages":"522-531","volume":"62"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article"],"s2_fields_of_study":["Medicine","Computer Science","Engineering"],"reference_count":39,"citation_count":701,"influential_citation_count":145,"is_open_access":true,"arxiv_categories":["cs.CY"],"arxiv_license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","arxiv_journal_ref":"IEEE Transactions on Biomedical Engineering, vol. 62, no. 2, pp.\n  522-531, February 2015","mesh_headings":[{"d":"Adolescent","mj":false,"ui":"D000293"},{"d":"Adult","mj":false,"ui":"D000328"},{"d":"Algorithms","mj":true,"ui":"D000465"},{"d":"Artifacts","mj":true,"ui":"D016477"},{"d":"Heart Rate","mj":false,"qs":[{"q":"physiology","mj":true,"ui":"Q000502"}],"ui":"D006339"},{"d":"Humans","mj":false,"ui":"D006801"},{"d":"Male","mj":false,"ui":"D008297"},{"d":"Monitoring, Ambulatory","mj":false,"qs":[{"q":"methods","mj":true,"ui":"Q000379"}],"ui":"D018670"},{"d":"Pattern Recognition, Automated","mj":false,"qs":[{"q":"methods","mj":false,"ui":"Q000379"}],"ui":"D010363"},{"d":"Photoplethysmography","mj":false,"qs":[{"q":"methods","mj":true,"ui":"Q000379"}],"ui":"D017156"},{"d":"Physical Endurance","mj":false,"qs":[{"q":"physiology","mj":false,"ui":"Q000502"}],"ui":"D010807"},{"d":"Physical Exertion","mj":false,"qs":[{"q":"physiology","mj":false,"ui":"Q000502"}],"ui":"D005082"},{"d":"Reproducibility of Results","mj":false,"ui":"D015203"},{"d":"Running","mj":false,"qs":[{"q":"physiology","mj":true,"ui":"Q000502"}],"ui":"D012420"},{"d":"Sensitivity and Specificity","mj":false,"ui":"D012680"},{"d":"Wrist","mj":false,"qs":[{"q":"physiology","mj":false,"ui":"Q000502"}],"ui":"D014953"},{"d":"Young Adult","mj":false,"ui":"D055815"}],"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":"http://arxiv.org/pdf/1409.5181","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/f2f9c868bf74c2747ace75b1b213548026626e36","s2_open_access_license":null,"s2_open_access_status":"GREEN","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Heart rate monitoring using wrist-type photoplethysmographic signals during subjects' intensive exercise is a difficult problem, since the signals are contaminated by extremely strong motion artifacts caused by subjects' hand movements. So far few works have studied this problem. In this study, a general framework, termed TROIKA, is proposed, which consists of signal decomposiTion for denoising, sparse signal RecOnstructIon for high-resolution spectrum estimation, and spectral peaK trAcking with verification. The TROIKA framework has high estimation accuracy and is robust to strong motion artifacts. Many variants can be straightforwardly derived from this framework. Experimental results on datasets recorded from 12 subjects during fast running at the peak speed of 15 km/h showed that the average absolute error of heart rate estimation was 2.34 beat per minute, and the Pearson correlation between the estimates and the ground truth of heart rate was 0.992. This framework is of great values to wearable devices such as smartwatches which use PPG signals to monitor heart rate for fitness.","claims":[{"public_id":"cl_07ad0160ad37ccc13ae378dfd259d150","status":"active","text":"Experimental results on datasets recorded from 12 subjects during fast running at 15 km/h showed an average absolute error of heart rate estimation of 2.34 beats per minute and a Pearson correlation of 0.992 between estimates and ground truth.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_07ad0160ad37ccc13ae378dfd259d150"},{"public_id":"cl_3cb20b40f3d63a6a164c9217ae3b6493","status":"active","text":"TROIKA is a general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise, consisting of signal decomposition for denoising, sparse signal reconstruction for high-resolution spectrum estimation, and spectral peak tracking with verification.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_3cb20b40f3d63a6a164c9217ae3b6493"},{"public_id":"cl_2a34b171ac55c906fc8584453db17b6f","status":"active","text":"The TROIKA framework is robust to strong motion artifacts caused by hand movements during intensive exercise.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_2a34b171ac55c906fc8584453db17b6f"}],"concepts":[{"public_id":"co_1e0d743834eb10a83803e66caeb7b820","status":"active","name":"average absolute error","description":"The mean absolute difference between estimated heart rate and ground truth, reported as 2.34 beats per minute.","types":["metric","performance measure"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1e0d743834eb10a83803e66caeb7b820"},{"public_id":"co_24063c57c559fb8f586b516199364b53","status":"active","name":"motion artifacts","description":"Strong signal contamination caused by hand movements during intensive exercise, which TROIKA is robust to.","types":["artifact","noise source"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_24063c57c559fb8f586b516199364b53"},{"public_id":"co_4a8712174e9b7f150c267b73f9e0c6b3","status":"active","name":"wrist-type photoplethysmographic signals","description":"Photoplethysmographic signals acquired from a wrist-worn device, used for heart rate monitoring.","types":["signal type"],"aliases":["wrist-type PPG signals"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4a8712174e9b7f150c267b73f9e0c6b3"},{"public_id":"co_4c79b22031ab15b5c9716dc96f0e7c10","status":"active","name":"TROIKA framework","description":"A general framework for heart rate monitoring from wrist-type PPG signals during intensive exercise, comprising signal decomposition, sparse reconstruction, and spectral peak tracking.","types":["method","framework"],"aliases":["TROIKA"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4c79b22031ab15b5c9716dc96f0e7c10"},{"public_id":"co_6259137da013973a49083e4c7d2ebe2a","status":"active","name":"Pearson correlation","description":"Correlation coefficient between estimated heart rate and ground truth, reported as 0.992.","types":["metric","performance measure"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6259137da013973a49083e4c7d2ebe2a"},{"public_id":"co_73d2cdc01447a61044b323595062cbb7","status":"active","name":"spectral peak tracking","description":"A step in TROIKA that tracks and verifies spectral peaks corresponding to heart rate.","types":["method","processing step"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_73d2cdc01447a61044b323595062cbb7"},{"public_id":"co_879e7ec81fa26b776edb695adfe872aa","status":"active","name":"signal decomposition","description":"A step in TROIKA that decomposes the PPG signal for denoising to reduce motion artifacts.","types":["method","processing step"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_879e7ec81fa26b776edb695adfe872aa"},{"public_id":"co_cbe377d6e702fb6f78e870638dc602b4","status":"active","name":"fast running at 15 km/h","description":"The peak speed of intensive exercise during which PPG signals were recorded for evaluation.","types":["experimental condition"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_cbe377d6e702fb6f78e870638dc602b4"},{"public_id":"co_dc78c83c717dc7b0567d52efd81ef854","status":"active","name":"sparse signal reconstruction","description":"A step in TROIKA that reconstructs a high-resolution spectrum from the denoised signal.","types":["method","processing step"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_dc78c83c717dc7b0567d52efd81ef854"},{"public_id":"co_f9aab41da0f1b3f0e022acf784bb4465","status":"active","name":"12 subjects","description":"The number of participants from whom datasets were recorded during fast running at 15 km/h.","types":["study population"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_f9aab41da0f1b3f0e022acf784bb4465"}],"external_ids":{"DOI":"10.1109/TBME.2014.2359372","ArXiv":"1409.5181","PubMed":25252274,"PubMedCentral":null,"MAG":2005741801,"DBLP":"journals/corr/ZhangPL14","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"http://arxiv.org/pdf/1409.5181","landing_url":"https://www.semanticscholar.org/paper/f2f9c868bf74c2747ace75b1b213548026626e36","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":null,"status":"GREEN","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":true,"full_text_source":"arxiv","count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":635945,"paper_uid":"00490856-3602-4431-86a0-4edead058331","canonical_identity":{"paper_id":635945,"paper_uid":"00490856-3602-4431-86a0-4edead058331","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/6684687"}