@article{heActivityRecognitionAcceleration2009,
  title = {Activity Recognition from Acceleration Data Based on Discrete Consine Transform and {{SVM}}},
  issn = {1062922X},
  doi = {10.1109/ICSMC.2009.5346042},
  abstract = {This paper developed a high-accuracy human activity recognition system based on single tri-axis accelerometer for use in a naturalistic environment. This system exploits the discrete cosine transform (DCT), the Principal Component Analysis (PCA) and Support Vector Machine (SVM) for classification human different activity. First, the effective features are extracted from accelerometer data using DCT. Next, feature dimension is reduced by PCA in DCT domain. After implementing the PCA, the most invariant and discriminating information for recognition is maintained. As a consequence, Multi-class Support Vector Machines is adopted to distinguish different human activities. Experiment results show that the proposed system achieves the best accuracy is 97.51\%, which is better than other approaches.},
  issue = {October},
  journaltitle = {Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics},
  date = {2009},
  pages = {5041--5044},
  keywords = {SVM,Activity recognition,Discrete cosine transform,Principal component analysis,Tri-axial accelerometer},
  author = {He, Zhenyu and Jin, Lianwen},
  file = {/home/dimitri/Nextcloud/Zotero/storage/IIUPVJQK/He, Jin - 2009 - Activity recognition from acceleration data based on discrete consine transform and SVM.pdf}
}

{"_id":"MfrGKHwiFcQsCcnpY","bibbaseid":"he-jin-activityrecognitionfromaccelerationdatabasedondiscreteconsinetransformandsvm","authorIDs":[],"author_short":["He, Z.","Jin, L."],"bibdata":{"bibtype":"article","type":"article","title":"Activity Recognition from Acceleration Data Based on Discrete Consine Transform and SVM","issn":"1062922X","doi":"10.1109/ICSMC.2009.5346042","abstract":"This paper developed a high-accuracy human activity recognition system based on single tri-axis accelerometer for use in a naturalistic environment. This system exploits the discrete cosine transform (DCT), the Principal Component Analysis (PCA) and Support Vector Machine (SVM) for classification human different activity. First, the effective features are extracted from accelerometer data using DCT. Next, feature dimension is reduced by PCA in DCT domain. After implementing the PCA, the most invariant and discriminating information for recognition is maintained. As a consequence, Multi-class Support Vector Machines is adopted to distinguish different human activities. Experiment results show that the proposed system achieves the best accuracy is 97.51%, which is better than other approaches.","issue":"October","journaltitle":"Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics","date":"2009","pages":"5041–5044","keywords":"SVM,Activity recognition,Discrete cosine transform,Principal component analysis,Tri-axial accelerometer","author":[{"propositions":[],"lastnames":["He"],"firstnames":["Zhenyu"],"suffixes":[]},{"propositions":[],"lastnames":["Jin"],"firstnames":["Lianwen"],"suffixes":[]}],"file":"/home/dimitri/Nextcloud/Zotero/storage/IIUPVJQK/He, Jin - 2009 - Activity recognition from acceleration data based on discrete consine transform and SVM.pdf","bibtex":"@article{heActivityRecognitionAcceleration2009,\n title = {Activity Recognition from Acceleration Data Based on Discrete Consine Transform and {{SVM}}},\n issn = {1062922X},\n doi = {10.1109/ICSMC.2009.5346042},\n abstract = {This paper developed a high-accuracy human activity recognition system based on single tri-axis accelerometer for use in a naturalistic environment. This system exploits the discrete cosine transform (DCT), the Principal Component Analysis (PCA) and Support Vector Machine (SVM) for classification human different activity. First, the effective features are extracted from accelerometer data using DCT. Next, feature dimension is reduced by PCA in DCT domain. After implementing the PCA, the most invariant and discriminating information for recognition is maintained. As a consequence, Multi-class Support Vector Machines is adopted to distinguish different human activities. Experiment results show that the proposed system achieves the best accuracy is 97.51\\%, which is better than other approaches.},\n issue = {October},\n journaltitle = {Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics},\n date = {2009},\n pages = {5041--5044},\n keywords = {SVM,Activity recognition,Discrete cosine transform,Principal component analysis,Tri-axial accelerometer},\n author = {He, Zhenyu and Jin, Lianwen},\n file = {/home/dimitri/Nextcloud/Zotero/storage/IIUPVJQK/He, Jin - 2009 - Activity recognition from acceleration data based on discrete consine transform and SVM.pdf}\n}\n\n","author_short":["He, Z.","Jin, L."],"key":"heActivityRecognitionAcceleration2009","id":"heActivityRecognitionAcceleration2009","bibbaseid":"he-jin-activityrecognitionfromaccelerationdatabasedondiscreteconsinetransformandsvm","role":"author","urls":{},"keyword":["SVM","Activity recognition","Discrete cosine transform","Principal component analysis","Tri-axial accelerometer"],"downloads":0},"bibtype":"article","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.031Z","downloads":0,"keywords":["svm","activity recognition","discrete cosine transform","principal component analysis","tri-axial accelerometer"],"search_terms":["activity","recognition","acceleration","data","based","discrete","consine","transform","svm","he","jin"],"title":"Activity Recognition from Acceleration Data Based on Discrete Consine Transform and SVM","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}