TY - GEN
T1 - Deep learning application trial to lung cancer diagnosis for medical sensor systems
AU - Shimizu, Ryota
AU - Yanagawa, Shusuke
AU - Monde, Yasutaka
AU - Yamagishi, Hiroki
AU - Hamada, Mototsugu
AU - Shimizu, Toru
AU - Kuroda, Tadahiro
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/27
Y1 - 2016/12/27
N2 - Personal and easy-To-use health checking system is an attractive application of sensor systems. Sensing data analysis for diagnosis is important as well as preparing small and mobile sensor nodes because sensing data include variations and noises reflecting individual difference of people and sensing conditions. Deep Neural Network, or Deep Learning, is a well-known method of machine learning and it is effective for feature extraction from pictures. Then, we thought Deep Learning also can extract features from sensing data. In this paper, we tried to build a diagnosis system of lung cancer based on Deep Learning. Input data of the system was generated from human urine by Gas Chromatography Mass Spectrometer (GC-MS) and our system achieved 90% accuracy in judging whether the patient had lung cancer or not. This system will be useful for pre-And personal diagnosis because collecting urine is very easy and not harmful to human body. We are targeting installation of this system not only to gas chromatography systems but also to some combination of multiple sensors for detecting gases of low concentration.
AB - Personal and easy-To-use health checking system is an attractive application of sensor systems. Sensing data analysis for diagnosis is important as well as preparing small and mobile sensor nodes because sensing data include variations and noises reflecting individual difference of people and sensing conditions. Deep Neural Network, or Deep Learning, is a well-known method of machine learning and it is effective for feature extraction from pictures. Then, we thought Deep Learning also can extract features from sensing data. In this paper, we tried to build a diagnosis system of lung cancer based on Deep Learning. Input data of the system was generated from human urine by Gas Chromatography Mass Spectrometer (GC-MS) and our system achieved 90% accuracy in judging whether the patient had lung cancer or not. This system will be useful for pre-And personal diagnosis because collecting urine is very easy and not harmful to human body. We are targeting installation of this system not only to gas chromatography systems but also to some combination of multiple sensors for detecting gases of low concentration.
KW - Deep learning
KW - Deep neural network
KW - Gas chromatography mass spectrometer(GC-MS)
KW - Stacked autoencoder
UR - http://www.scopus.com/inward/record.url?scp=85010280617&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010280617&partnerID=8YFLogxK
U2 - 10.1109/ISOCC.2016.7799852
DO - 10.1109/ISOCC.2016.7799852
M3 - Conference contribution
AN - SCOPUS:85010280617
T3 - ISOCC 2016 - International SoC Design Conference: Smart SoC for Intelligent Things
SP - 191
EP - 192
BT - ISOCC 2016 - International SoC Design Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th International SoC Design Conference, ISOCC 2016
Y2 - 23 October 2016 through 26 October 2016
ER -
