Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
1D CNN°ú ±â°è ÇнÀÀ» »ç¿ëÇÑ ³«»ó °ËÃâ |
¿µ¹®Á¦¸ñ(English Title) |
1D CNN and Machine Learning Methods for Fall Detection |
ÀúÀÚ(Author) |
±èÀΰæ
±è´ëÈñ
³ë¼Û
ÀÌÀ籸
Inkyung Kim
Daehee Kim
Song Noh
Jaekoo Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 10 NO. 03 PP. 0085 ~ 0090 (2021. 03) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â °í·ÉÀÚ¸¦ À§ÇÑ °³º° ¿þ¾î·¯ºí(Wearable) ±â±â¸¦ ÀÌ¿ëÇÑ ³«»ó °¨Áö¿¡ ´ëÇØ ³íÇÑ´Ù. ½Å·ÚÇÒ ¼ö ÀÖ´Â ³«»ó °¨Áö¸¦ À§ÇÑ Àúºñ¿ë ¿þ¾î·¯ºí ±â±â¸¦ ¼³°èÇϱâ À§Çؼ ´ëÇ¥ÀûÀÎ µÎ °¡Áö ¸ðµ¨À» Á¾ÇÕÀûÀ¸·Î ºÐ¼®ÇÏ¿© Á¦½ÃÇÑ´Ù. ±â°è ÇнÀ ¸ðµ¨ÀÎ ÀÇ»ç°áÁ¤ ³ª¹«(Decision Tree), ·£´ý Æ÷·¡½ºÆ®(Random Forest), SVM(Support Vector Machine)°ú ½ÉÃþ ÇнÀ ¸ðµ¨ÀÎ ÀÏÂ÷¿ø(One-Dimensional) ÇÕ¼º°ö ½Å°æ¸Á(Convolutional Neural Network)À» »ç¿ëÇÏ¿© ³«»ó °¨Áö ÇнÀ ´É·ÂÀ» Á¤·®ÈÇÏ¿´´Ù. ¶ÇÇÑ ÀÔ·Â µ¥ÀÌÅÍ¿¡ Àû¿ëÇϱâ À§ÇÑ µ¥ÀÌÅÍ ºÐÇÒ, Àüó¸®, Ư¡ ÃßÃâ ¹æ¹ý µîÀ» °í·ÁÇÏ¿© °ËÅäµÈ ¸ðµ¨ÀÇ À¯È¿¼ºÀ» Æò°¡ÇÑ´Ù. ½ÇÇè °á°ú´Â Àü¹ÝÀûÀÎ ¼º´É Çâ»óÀ» º¸¿©ÁÖ¸ç ½ÉÃþÇнÀ ¸ðµ¨ÀÇ À¯È¿¼ºÀ» °ËÁõÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models¡¯ validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.
|
Å°¿öµå(Keyword) |
±â°è ÇнÀ
½ÉÃþ ÇнÀ
³«»ó °ËÃâ
1Â÷¿ø ÇÕ¼º°ö ½Å°æ¸Á
Machine Learning
Deep Learning
Fall Detection
1D Convolutional Neural Network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|