• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.253-254
• /
• 1999

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1071-1071
• /
• 2001

Near-infrared spectroscopy (NIRS) is potentially a powerful and revolutionary technology for environmental analysis. It is supported by a large body of scientific and experiential knowledge. The instrumentation is well-developed, with easy-to-use, highly dependable instruments, but at the same time it is still developing, particularly with the production of more portable and rapid instruments, and more powerful software. NIRS is used globally in numerous industries for commodity analysis. Yet NIRS is largely unknown in the field of environmental chemistry and monitoring, and is not even routinely used in soil analysis, where the research literature on NIRS extends over four decades. Part of the explanation for the poor visibility of NIRS is the fact that NIRS is not routinely taught in Chemistry programs in universities, where most environmental chemists and environmental technicians are trained. This presentation examines the unique capabilities of NIRS, such as rapid, real-time analysis; analysis of whole samples; simultaneous analysis of multiple constituents; cost-effectiveness, and portability, as they match needs for analysis in several environmental areas. Examples of NIRS usage and published and unpublished results will be described for such areas as soil and sediment analysis; water quality monitoring; and nutrient loading in application of manures and sewage sludge (biosolids) to land. Present barriers to the use of NIRS in environmental analysis will be discussed. It is argued that emerging environmental problems and increasing attention to some traditional problems will enhance the application of NIRS in the future.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.207-209
• /
• 1999

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.9 no.3
• /
• pp.163-167
• /
• 1989

Near infrared reflectance spectroscopy (NIRS) analysis of commercial farm alfalfa hay for crude prowin (CP), neutral detergent fiber(NDF), and acid detergent fiber(ADF) was compared with wet chemistry results. There were no differences between NIRS and wet chemistry results in CP and ADF content, but there were differences (P <.05) between NIRS and wet chemistry results for sample No.2, 4, 5 in NDF content.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.669-670
• /
• 2004

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 1999.11a
• /
• pp.228-229
• /
• 1999

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.46 no.3
• /
• pp.248-252
• /
• 2001

Near infrared spectroscopy (NIRS) is a rapid and accurate analytical method for determining the composition of agricultural products and feeds. An important merit of the NIRS analytical system is consistent predictions across instruments. However, proper calibration is the most important factor for a NIRS analytical system. Forty samples were obtained from Kyonggi-do Agricultural Research and Extension Services, and used to develop calibrations for crude protein content and crude oil content. Calibrations equations were developed using multiple linear regression (MLR). Accuracy and precision of NIRS predictions were adequate for quality measurement for the two constituents in kidney bean seed. In calibration sample sets (N=30), multiple correlation coefficient between NIR and lab measurements is 0.90 for seed, 0.97 for powder in seed protein concentration and 0.40 for seed and 0.92 for powder in seed oil concentration, respectively. It is concluded that NIRS method is suitable for the determination of seed composition in whole kidney bean.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.305-307
• /
• 2021

Alzheimer's Disease (AD) is a cognitive disorder characterized by memory impairment that can be assessed at early stages based on administering clinical tests. However, the AD pathophysiological mechanism is still poorly understood due to the difficulty of distinguishing different levels of AD severity, even using a variety of brain modalities. Therefore, in this study, we present a hybrid EEG-fNIRS modalities to compensate for each other's weaknesses with the help of Machine Learning (ML) techniques for classifying four subject groups, including healthy controls (HC) and three distinguishable groups of AD levels. A concurrent EEF-fNIRS setup was used to record the data from 41 subjects during Oddball and 1-back tasks. We employed both a traditional neural network (NN) and a CNN-LSTM hybrid model for fNIRS and EEG, respectively. The final prediction was then obtained by using majority voting of those models. Classification results indicated that the hybrid EEG-fNIRS feature set achieved a higher accuracy (71.4%) by combining their complementary properties, compared to using EEG (67.9%) or fNIRS alone (68.9%). These findings demonstrate the potential of an EEG-fNIRS hybridization technique coupled with ML-based approaches for further AD studies.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.46 no.2
• /
• pp.106-111
• /
• 2001

The applicability of near infrared reflectance spectroscopy(NIRS) was tested to determine the protein and oil contents in ground soybean [Glycine max (L.) Merr.] seeds. A total of 189 soybean calibration samples and 103 validation samples were used for NIRS equation development and validation, respectively. In the NIRS equation of protein, the most accurate equation was obtained at 2, 8, 6, 1(2nd derivative, 8 nm gap, 6 points smoothing and 1 point second smoothing) math treatment condition with SNV-D (Standard Normal Variate and Detrend) scatter correction method and entire spectrum by using MPLS (Modified Partial Least Squares) regression. In the case of oil, the best equation was obtained at 1, 4, 4, 1 condition with SNV-D scatter correction method and near infrared (1100-2500nm) region by using MPLS regression. Validation of these NIRS equations showed very low bias (protein:-0.016%, oil : -0.011 %) and standard error of prediction (SEP, protein: 0.437%, oil: 0.377%) and very high coefficient of determination ($R^2$, protein: 0.985, oil : 0.965). Therefore, these NIRS equation seems reliable for determining the protein and oil content, and NIRS method could be used as a mass screening method of soybean seed.

• Food Science and Biotechnology
• /
• v.18 no.1
• /
• pp.60-65
• /
• 2009

Near infrared reflectance spectroscopy (NIRS) was used as a rapid and non-destructive method to determine the protein content in intact and ground seeds of pea (Pisum sativum L.) germplasms grown in Korea. A total of 115 samples were scanned in the reflectance mode of a scanning monochromator at intact seed and flour condition, and the reference values for the protein content was measured by auto-Kjeldahl system. In the developed ground and intact NIRS equations for analysis of protein, the most accurate equation were obtained at 2, 8, 6, 1 math treatment conditions with standard normal variate and detrend scatter correction method and entire spectrum (400-2,500 nm) by using modified partial least squares regression (n=78). External validation (n=34) of these NIRS equations showed significant correlation between reference values and NIRS estimated values based on the standard error of prediction (SEP), $R^2$, and the ratio of standard deviation of reference data to SEP. Therefore, these ground and intact NIRS equations can be applicable and reliable for determination of protein content in pea seeds, and non-destructive NIRS method could be used as a mass analysis technique for selection of high protein pea in breeding program and for quality control in food industry.