| Item type |
SIG Technical Reports(1) |
| 公開日 |
2019-02-25 |
| タイトル |
|
|
タイトル |
Towards a Semantic-based Mobile Health Monitoring Mechanism |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Towards a Semantic-based Mobile Health Monitoring Mechanism |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
自律化・最適化 |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Graduate School of Information Science Kyushu Sangyo University |
| 著者所属 |
|
|
|
Graduate School of Information Science Kyushu Sangyo University |
| 著者所属(英) |
|
|
|
en |
|
|
Graduate School of Information Science Kyushu Sangyo University |
| 著者所属(英) |
|
|
|
en |
|
|
Graduate School of Information Science Kyushu Sangyo University |
| 著者名 |
Sigdel, Shree Ram
Bernady, Apduhan
|
| 著者名(英) |
Sigdel, Shree Ram
Bernady, Apduhan
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
The increasing population of aging people and the lack of human resources have created great challenges in society. Here, we consider machine learning in edge computing and semantic technologies to detect and improve the predictability in mobile health monitoring of human activity. With multi-modal sensor data, we conducted pre-processing to sanitize the data and extracted the ECG data. We used and compare the performance of random forests and SVM machine learning algorithms to identify the patterns of body activity. We achieved approximately 95% accuracy with random forest which was better than SVM, at 93%. While observing the confusion matrix we were able to identify the majority of mismatched data belonging to initial value of sensors while recording a particular activity. The preliminary experiments provided promising results and insights on the data semantization process to improve the prediction accuracy of human activity. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
The increasing population of aging people and the lack of human resources have created great challenges in society. Here, we consider machine learning in edge computing and semantic technologies to detect and improve the predictability in mobile health monitoring of human activity. With multi-modal sensor data, we conducted pre-processing to sanitize the data and extracted the ECG data. We used and compare the performance of random forests and SVM machine learning algorithms to identify the patterns of body activity. We achieved approximately 95% accuracy with random forest which was better than SVM, at 93%. While observing the confusion matrix we were able to identify the majority of mismatched data belonging to initial value of sensors while recording a particular activity. The preliminary experiments provided promising results and insights on the data semantization process to improve the prediction accuracy of human activity. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11235941 |
| 書誌情報 |
研究報告コンピュータセキュリティ（CSEC）
巻 2019-CSEC-84,
号 20,
p. 1-6,
発行日 2019-02-25
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8655 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-CSEC19084020.pdf (1.6 MB)
