• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.8
• /
• pp.628-635
• /
• 2017

It is important to prescribe and take medicines that are appropriate for symptoms, since medicines are closely related to human health and life. Moreover, it becomes more important to accurately classify genuine medicines with counterfeit, since the number of counterfeit increases worldwide. However, the number of high-quality experts who have enough experience to properly classify them is limited and there exists a need for the automatic technique to classify medicine tablets. In this paper, we propose a method to classify the tablets by using a handheld spectrometer which provides both Near Infra-Red (NIR) and visible light spectrums. We adopted Support Vector Machine(SVM) as a machine learning algorithm for tablet classification. As a result of the simulation, we could obtain the classification accuracy of 99.9 % on average by using both NIR and visible light spectrums. Also, we proposed a two-step SVM approach to discriminate the counterfeit tablets from the genuine ones. This method could improve both the accuracy and the processing time.

• Korean Journal of Environmental Biology
• /
• v.39 no.4
• /
• pp.581-589
• /
• 2021

Using visible-near infrared(Vis-NIR) spectra combined with machine learning methods, the feasibility of quick and non-destructive classification of Convolvulaceae species was studied. The main aim of this study is to classify six Convolvulaceae species in the field in different geographical regions of South Korea using a handheld spectrometer. Spectra were taken at 1.5 nm intervals from the adaxial side of the leaves in the Vis-NIR spectral region between 400 and 1,075 nm. The obtained spectra were preprocessed with three different preprocessing methods to find the best preprocessing approach with the highest classification accuracy. Preprocessed spectra of the six Convolvulaceae sp. were provided as input for the machine learning analysis. After cross-validation, the classification accuracy of various combinations of preprocessing and modeling ranged between 43.4% and 98.6%. The combination of Savitzky-Golay and Support vector machine methods showed the highest classification accuracy of 98.6% for the discrimination of Convolvulaceae sp. The growth stage of the plants, different measuring locations, and the scanning position of leaves on the plant were some of the crucial factors that affected the outcomes in this investigation. We conclude that Vis-NIR spectroscopy, coupled with suitable preprocessing and machine learning approaches, can be used in the field to effectively discriminate Convolvulaceae sp. for effective weed monitoring and management.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.1
• /
• pp.31-37
• /
• 2014

The aim of this study was the non-destructive evaluation of bloody eggs using VIS/NIR spectroscopy. The bloody egg samples used to develop the sorting mode were produced by injecting chicken blood into the edges of egg yolks. Blood amounts of 0.1, 0.7, 0.04, and 0.01 mL were used for the bloody egg samples. The wavelength range for the VIS/NIR spectroscopy was 471 to 1154 nm, and the spectral resolution was 1.5nm. For the measurement system, the position of the light source was set to $30^{\circ}$, and the distance between the light source and samples was set to 100 mm. The minimum exposure time of the light source was set to 30 ms to ensure the fast sorting of bloody eggs and prevent heating damage of the egg samples. Partial least squares-discriminant analysis (PLS-DA) was used for the spectral data obtained from VIS/NIR spectroscopy. The classification accuracies of the sorting models developed with blood samples of 0.1, 0.07, 0.04, and 0.01 mL were 97.9%, 98.9%, 94.8%, and 86.45%, respectively. In this study, a novel nondestructive sorting technique was developed to detect bloody brown eggs using spectral data obtained from VIS/NIR spectroscopy.

• Journal of agriculture & life science
• /
• v.46 no.2
• /
• pp.49-61
• /
• 2012

This study was carried out to investigate the chemical composition and the inorganic constituents of the green tea at the 3 picking periods (Ujeon, Sejag, Jungjag) in Hadong. The results as follows ; The contents of chlorophyll, tannin, vitamin-c and total catechin were increased as picking periods increased but the contents of total nitrogen, total free amino acids, theanine and caffeine were decreased on the reverse. The inorganic constituents Mg, Ca and Mn were increased as picking periods getting late but the Na, K, B contents were decreased on the reverse. The contents of the total nitrogen, chlorophyll, total free amino acid, theanine, caffeine and total catechin and Na, Mg, Ca, B and Se were insignificant differences between Ujeon and Sejag.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.146-146
• /
• 2017

현대의 스마트폰 및 태블릿pc등을 가능하게 만든 집적 기술 중의 하나는 3차원 집적 회로(3D-IC)와 같은 패키징 기술이다. 이러한 첨단 3차원 집적 기술은 메모리집적을 통한 대용량 메모리 모듈 개발뿐만 아니라, 메모리와 프로세서의 집적, high-end FPGA, Back side imaging (BSI) 센서 모듈, MEMS 센서와 ASIC 집적, High Bright (HB) LED 모듈 등에 적용되고 있다. 3D-IC의 3차원 모듈 제작 시에는 기존에 발생하지 않았던 여러 가지 파괴 모드들이 발생하고 있는데 Thermal/Photonic Emission 장비 등 기존의 2차원 결함분리 (Fault Isolation) 기술로는 첨단의 3차원 적층 제품들에서 발생하는 불량을 비파괴적으로 혹은 3차원적으로 분리하는 것이 불가능하므로, 비파괴 3차원 결함 분리 기술은 향후 선행 제품 적기 개발에 매우 필수적인 기술이다. 본 연구는 3D-IC 반도체의 비파괴적 내부결함 검사를 위하여 가시광선-근적외선 대역(351nm~1770nm)의 InGaAs (Indium Galium Arsenide) 계열 영상검출기 (imaging detector)를 사용하여 분광 시스템 광학 설계를 통한 초분광 영상 기반 검출 모듈을 제작하였다. 제작된 초분광 영상 기반 검출 모듈을 이용하여 구리 회로 위에 실리콘 웨이퍼가 3단 적층 된 반도체 더미 샘플의 초분광 영상을 촬영하였으며, 촬영된 초분광 영상에 대하여 Chemometrics model 기반의 분석기술을 적용하여 실리콘 웨이퍼 내부의 집적 구조에 대한 검사가 가능함을 확인하였다.

• Clean Technology
• /
• v.17 no.3
• /
• pp.215-224
• /
• 2011

It is an important issue to develop quality assessing system for biofuel for the purpose of accelerating the mass production of biofuel. It is particularly challenging to conduct testing method in the mass production of bioethanol while meeting quality specifications such as ASTM (American Society for Testing & Materials) D4806-10. In order to address this challenge, this paper proposes on-line spectroscopic quality assesment system based on Near Infrared spectrum and Partial Least Squares method in Chemometrics. As a result of testing a number of preprocessing methods and Partial Least Squares, it was found out that Savitzky-Golay method showed the best performance in terms of spectrum correction, noise reduction, and model maintenance. The proposed system allows us to assess multiple quality components continuously using spectroscopic facilities with the cheap cost. Since the value of R2 is more than 0.99, it is possible to replace the laboratory analysis.

• The Science & Technology
• /
• no.5 s.468
• /
• pp.6-9
• /
• 2008

외부 행성에서 생명체 전구물질인 유기물 성분이 처음으로 발견됐다. 미항공우주국 연구진은 '네이처'에서 지난해 5월 허블우주망원경의 근적외선 카메라 및 다중목표물 분광계(NICMOS)를 이용해 지구에서 63광년 떨어진 여우자리에 있는 목성 크기 행성 HD 189733b 대기권에서 메탄 화합물을 발견했다고 밝혔다. 탄소와 수소로 이루어진 메탄은 태양계 행성 대부분에서 발견되지만 외부 행성에서 발견되기는 이번이 처음이다. 연구진은 이 행성에서 물도 발견됐지만 중심별과 가까워 온도가 $900^{\circ}C$로 생명체가 살기에는 너무 뜨겁다며 조건이 이보다 좋은 행성이라면 생명물질을 추적해 볼 만하다고 밝혔다. 지구 대기권에서 메탄은 화학반응을 통해 빠른 속도로 분해되지만 작은 행성에서라면 지구에서처럼 분해된 메탄에서 나온 수소가 빠른 속도로 우주로 빠져 나올 것으로 예상된다. 과학자들은 지구 크기의 행성에서 많은 양의 메탄이 발견된다는 것은 생물학적 과정의 결과일 가능성이 있는 것으로 보고 있다. 메탄은 비생물학적 과정에서도 형성될 수 있지만 이런 경우 다량의 입자를 만들지는 않는다. 과학자들은 2013년 발사될 제임스 웹 망원경을통해다른외부행성에서물과메탄을찾아나설계획이다.

• Journal of the Korean Applied Science and Technology
• /
• v.16 no.1
• /
• pp.21-24
• /
• 1999

Sesame seed (Sesamum indicum L.) is an important seasoning in Korea and most korean consumer tend to eat the korean sesame seed as the best than other ones produced in oriental countries such as China and Japan. Near infrared reflectance spectroscopy (NIRS) was applied for discrimination according to geographical origin (Korea, China and so on) of sesame seeds. Near-infrared spectroscopy among the many kinds of techniques could provide a rapid screening, low cost solution to discriminate geographical origin of sesame seed. The objective of this study is to determine if NIR technique could be used to discriminate between the korean sesame seed and non-korean sesame seed by using the new method. Rapid, precise and nondestructive analysis method for determination of the geographic origin of sesame seeds were discriminated relative accurately according to geographical origin using PLS regression method.

• Journal of the Korean Chemical Society
• /
• v.47 no.5
• /
• pp.447-459
• /
• 2003

Generalized 2D correlation spectroscopy has been applied extensively to the analysis of spectral data sets obtained during the observation of a system under some external perturbation. It is used in various fields of spectroscopy including IR, Raman, UV, fluorescence, X-ray diffraction, and X-ray absorption spectroscopy (XAS) as well as chromatography. 2D hetero-spectral correlation analysis compares two completely different types of spectra obtained for a system under the same perturbation. Because of the wide range of applications of this technique, it has become one of the standard analytical techniques for the analytical chemistry, physical chemistry, biochemistry, and so on, and for studies of polymers, biomolecules, nanomaterials, etc. In this paper, we will introduce the principle of generalized 2D correlation spectroscopy and its applications that we have studied.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.1-6
• /
• 2006

The purpose of this study is to develop to portable near infrared analyzer measuring the sugar content of the fruits on a tree before harvesting ones. The portable near infrared system consists of a tungsten lamp, a coaxial optical fiber bundle and a multi-channel detector, which has 256 pixels and a concave transmission grating. Reflectance NIR spectra of orange were recorded by using a coaxial optical fiber bundle. The spectra were collected over the spectral range $400{\sim}1100nm$. Partial least squares regression(PLSR) was applied for a calibration and validation for determination of sugar contents. The multiple correlation coefficient was 0.99 and standard errors of calibration(SEC) was 0.069 brix. The calibration model predicted the sugar content for validation set with standard errors of prediction(SEP) of 0.092 brix. The sugar content in fruits was successfully quantified using the portable near infrared analyzer.