首页|Findings in the Area of Machine Learning Reported from National Institute of Tec hnology Delhi (Enhancing the Performance of Photonic Sensor Using Machine-learni ng Approach)
Findings in the Area of Machine Learning Reported from National Institute of Tec hnology Delhi (Enhancing the Performance of Photonic Sensor Using Machine-learni ng Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news reporting from Delhi, India, by NewsRx journal ists, research stated, "This article reports on the implementation of adequate m achine-learning (ML) models on different datasets vis-a-vis fiber-optic plasmoni c sensor devices. The variation of the sensor & rsquo;s figure of merit (FOM) with light wavelength (1) and metal layer thickness (d(m)) is consid ered as a starting point and accordingly, the appropriate ML model is chosen." Financial support for this research came from Science Engineering Research Board (SERB), India. The news correspondents obtained a quote from the research from the National Ins titute of Technology Delhi, "The FOM datasets were found to be consistent with t he Gaussian process regressor (GPR) model. The application of GPR with finer res olution (0.001 nm) of 1 on the datasets led to enhanced magnitudes of the sensor & rsquo;s FOM. The dataset (459 points) having nine different val ues of d(m) led to a predicted FOM of 6526.23 at lambda = 1099.343 nm. Furthermo re, the dataset (714 points) having 13 different values of d(m) led to a predict ed FOM value of 6356.98 at lambda =1099.345 nm. These are promising results as f ar as the application of the sensor in biosensing is concerned. Furthermore, the chosen model is found to be highly consistent with the data in terms of trend m atching, and the values of other evaluation parameters [e.g., R-2 and mean absolute error (MAE)] are found to be in consid erably desirable ranges. This study clearly reveals that the selection of an app ropriate ML model and its implementation on various datasets can lead to more ef ficient finalization of the sensor design with enhanced sensing performance."
DelhiIndiaAsiaCyborgsEmerging Te chnologiesMachine LearningNational Institute of Technology Delhi
NETL
NSTL
