Dataset Information

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis.

ABSTRACT: Soil types have traditionally been determined by soil physical and chemical properties, diagnostic horizons and pedogenic processes based on a given classification system. This is a laborious and time consuming process. Near infrared (NIR) spectroscopy can comprehensively characterize soil properties, and may provide a viable alternative method for soil type recognition. Here, we presented a partial least squares discriminant analysis (PLSDA) method based on the NIR spectra for the accurate recognition of the types of 230 soil samples collected from farmland topsoils (0-10 cm), representing 5 different soil classes (Albic Luvisols, Haplic Luvisols, Chernozems, Eutric Cambisols and Phaeozems) in northeast China. We found that the PLSDA had an internal validation accuracy of 89% and external validation accuracy of 83% on average, while variable selection with the genetic algorithm (GA and GA-PLSDA) improved this to 92% and 93%. Our results indicate that the GA variable selection technique can significantly improve the accuracy rate of soil type recognition using NIR spectroscopy, suggesting that the proposed methodology is a promising alternative for recognizing soil types using NIR spectroscopy.

SUBMITTER: Xie H

PROVIDER: S-EPMC4650675 | biostudies-literature | 2015 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis.

Xie Hongtu H Zhao Jinsong J Wang Qiubing Q Sui Yueyu Y Wang Jingkuan J Yang Xueming X Zhang Xudong X Liang Chao C

Scientific reports 20150618

Soil types have traditionally been determined by soil physical and chemical properties, diagnostic horizons and pedogenic processes based on a given classification system. This is a laborious and time consuming process. Near infrared (NIR) spectroscopy can comprehensively characterize soil properties, and may provide a viable alternative method for soil type recognition. Here, we presented a partial least squares discriminant analysis (PLSDA) method based on the NIR spectra for the accurate reco ...[more]

PMID: 26086823

Similar Datasets

Project description:Background and Objectives: Postoperative cognitive disturbances (POCD) can significantly alter postoperative recovery. Inadequate intraoperative cerebral oxygen supply is one of the inciting causes of POCD. Near-infrared spectroscopy (NIRS) devices monitor cerebral oxygen saturation continuously and can help to guide intraoperative patient management. The aim of the study was to evaluate the applicability of the NIRS-based clinical algorithm during spinal neurosurgery and to find out whether it can influence postoperative cognitive performance. Materials and Methods: Thirty four patients scheduled for spinal neurosurgery were randomized into a study group (n = 23) and a control group (n = 11). We monitored regional cerebral oxygen saturation (rScO2) throughout surgery, using a NIRS device (INVOS 4100). If rScO2 dropped bilaterally or unilaterally by more than 20% from baseline values, or under an absolute value of 50%, the NIRS-based algorithm was initiated in the study group. In the control group, rScO2 was monitored blindly. To evaluate cognitive function, Montreal-Cognitive Assessment (MoCA) scale was used in both groups before and after the surgery. Results: In the study group, rScO2 dropped below the threshold in three patients and the NIRS-based algorithm was activated. Firstly, we verified correct positioning of the head; secondly, we increased mean systemic arterial pressure in the three patients by injecting repeated intravenous bolus doses of Ephedrine, ultimately resulting in an rScO2 increase above the approved threshold level. None of the three patients showed POCD. In the control group, one patient showed a drop in rScO2 of 34% from baseline and presented with a POCD. RScO2 drop occurred with other stable intraoperative measurements. Conclusions: A significant rScO2 drop may occur during spinal surgery in prone position despite other intraoperative measurements remaining stable, allowing it to stay otherwise unrecognized. Use of the NIRS-based clinical algorithm can help to avoid POCD in patients after spinal surgery.

Dataset Information

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis.

Publications

Soil type recognition as improved by genetic algorithm-based variable selection using near infrared spectroscopy and partial least squares discriminant analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure