TY - JOUR
T1 - Training a new instrument to measure cotton fiber maturity using transfer learning
AU - Turner, Chris
AU - Sari-Sarraf, Hamed
AU - Hequet, Eric
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7
Y1 - 2017/7
N2 - This paper presents a novel transfer learning regression method that utilizes data from an older instrument to train a new instrument to assess the same measurement. The method assumes that the instruments measure the same property but by different methodologies, and that samples presented to one apparatus are not available to the other. The algorithm makes use of a single feature common to both instruments to create a link with which to transfer information regarding the distribution of the resulting measurements, or labels. The goal is to generate a model in the domain of the new instrument that maps data from analyzed samples to an output measurement. This modeling process is accomplished through an iterative algorithm that supports many types of regression schemes. Results are shown using both synthetic and real world data sets, which demonstrate the effectiveness of the proposed method. Finally, we present how this technique is used to train a new instrument designed to measure cotton fiber maturity.
AB - This paper presents a novel transfer learning regression method that utilizes data from an older instrument to train a new instrument to assess the same measurement. The method assumes that the instruments measure the same property but by different methodologies, and that samples presented to one apparatus are not available to the other. The algorithm makes use of a single feature common to both instruments to create a link with which to transfer information regarding the distribution of the resulting measurements, or labels. The goal is to generate a model in the domain of the new instrument that maps data from analyzed samples to an output measurement. This modeling process is accomplished through an iterative algorithm that supports many types of regression schemes. Results are shown using both synthetic and real world data sets, which demonstrate the effectiveness of the proposed method. Finally, we present how this technique is used to train a new instrument designed to measure cotton fiber maturity.
KW - Cotton fiber maturity
KW - Histogram specification
KW - Machine learning
KW - Regression
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85017476920&partnerID=8YFLogxK
U2 - 10.1109/TIM.2017.2666203
DO - 10.1109/TIM.2017.2666203
M3 - Article
AN - SCOPUS:85017476920
SN - 0018-9456
VL - 66
SP - 1668
EP - 1678
JO - IEEE Transactions on Instrumentation and Measurement
JF - IEEE Transactions on Instrumentation and Measurement
IS - 7
M1 - 7893700
ER -