• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.9A
• /
• pp.1332-1339
• /
• 2000

This paper presents the architecture and design of a high speed asymmetric data transmission baseband MODEM ASIC chip for CATV networks. The implemented MODEM chip supports the physical layer of the DOCSIS(Data Over Cable Service Interface Specification) standard in MCNS(Multimedia Cable Network System) The chip consists of a QPSK/16-QAM transmitter and a 64/256-QAM receiver which contain a symbol timing recovery circuit, a carrier recovery circuit, a blind equalizer using MMA and LMS algorithms. The chip can support data rates of 64Mbps at 256 QAM and 48Mbps at 64-QAM and can provide symbol rates up to 8MBaud. This symbol rate is faster than existing QAM receivers. We have performed logic synthesis using the $0.35\mu\textrm{m}$ standard cell library. The total number of gates is about 290,000 and the implemented chip is being fabricated and will be delivered soon.

• Journal of Sensor Science and Technology
• /
• v.21 no.2
• /
• pp.144-150
• /
• 2012

A microphone for fully implantable hearing device was generally implanted under the skin of the temporal bone. So, the implanted microphone's characteristics can be affected by the accompanying noise due to masticatory movement. In this paper, the implantable microphone with 2-channels structure was designed for reduction of the generated noise signal by masticatory movement. And an experimental model for generation of the noise by masticatory movement was developed with considering the characteristics of human temporal bone and skin. Using the model, the speech signal by a speaker and the artificial noise by a vibrator were supplied simultaneously into the experimental model, the electrical signals were measured at the proposed microphone. The collected signals were processed using a general adaptive filter with least mean square(LMS) algorithm. To confirm performance of the proposed methods, the correlation coefficient and the signal to noise ratio(SNR) before and after the signal processing were calculated. Finally, the results were compared each other.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.12
• /
• pp.1772-1781
• /
• 2017

In this study, the design methodology for alleviating the overfitting problem of Polynomial Neural Networks(PNN) is realized with the aid of two kinds techniques such as L2 regularization and Sum of Squared Coefficients (SSC). The PNN is widely used as a kind of mathematical modeling methods such as the identification of linear system by input/output data and the regression analysis modeling method for prediction problem. PNN is an algorithm that obtains preferred network structure by generating consecutive layers as well as nodes by using a multivariate polynomial subexpression. It has much fewer nodes and more flexible adaptability than existing neural network algorithms. However, such algorithms lead to overfitting problems due to noise sensitivity as well as excessive trainning while generation of successive network layers. To alleviate such overfitting problem and also effectively design its ensuing deep network structure, two techniques are introduced. That is we use the two techniques of both SSC(Sum of Squared Coefficients) and $L_2$ regularization for consecutive generation of each layer's nodes as well as each layer in order to construct the deep PNN structure. The technique of $L_2$ regularization is used for the minimum coefficient estimation by adding penalty term to cost function. $L_2$ regularization is a kind of representative methods of reducing the influence of noise by flattening the solution space and also lessening coefficient size. The technique for the SSC is implemented for the minimization of Sum of Squared Coefficients of polynomial instead of using the square of errors. In the sequel, the overfitting problem of the deep PNN structure is stabilized by the proposed method. This study leads to the possibility of deep network structure design as well as big data processing and also the superiority of the network performance through experiments is shown.

• Food Science of Animal Resources
• /
• v.41 no.2
• /
• pp.312-323
• /
• 2021

The purpose of this study was to use 1H nuclear magnetic resonance (1H NMR) to quantify taste-active and bioactive compounds in chicken breasts and thighs from Korean native chicken (KNC) [newly developed KNCs (KNC-A, -C, and -D) and commercial KNC-H] and white-semi broiler (WSB) used in Samgye. Further, each breed was differentiated using multivariate analyses, including a machine learning algorithm designed to use metabolic information from each type of chicken obtained using 1H-13C heteronuclear single quantum coherence (2D NMR). Breast meat from KNC-D chickens were superior to those of conventional KNC-H and WSB chickens in terms of both taste-active and bioactive compounds. In the multivariate analysis, meat portions (breast and thigh) and chicken breeds (KNCs and WSB) could be clearly distinguished based on the outcomes of the principal component analysis and partial least square-discriminant analysis (R2=0.945; Q2=0.901). Based on this, we determined the receiver operating characteristic (ROC) curve for each of these components. AUC analysis identified 10 features which could be consistently applied to distinguish between all KNCs and WSB chickens in both breast (0.988) and thigh (1.000) meat without error. Here, both 1H NMR and 2D NMR could successfully quantify various target metabolites which could be used to distinguish between different chicken breeds based on their metabolic profile.

• Journal of ILASS-Korea
• /
• v.27 no.2
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• Smart Structures and Systems
• /
• v.31 no.1
• /
• pp.57-68
• /
• 2023

Bridge hangers, such as those in suspension and cable-stayed bridges, suffer from cumulative fatigue damage caused by dynamic loads (e.g., cyclic traffic and wind loads) in their service condition. Thus, the identification of damage to hangers is important in preserving the service life of the bridge structure. This study develops a new method for condition assessment of bridge hangers. The tension force of the bridge and the damages in the element level can be identified using the Bayesian optimization method. To improve the number of observed data, the additional mass method is combined the Bayesian optimization method. Numerical studies are presented to verify the accuracy and efficiency of the proposed method. The influence of different acquisition functions, which include expected improvement (EI), probability-of-improvement (PI), lower confidence bound (LCB), and expected improvement per second (EIPC), on the identification of damage to the bridge hanger is studied. Results show that the errors identified by the EI acquisition function are smaller than those identified by the other acquisition functions. The identification of the damage to the bridge hanger with various types of boundary conditions and different levels of measurement noise are also studied. Results show that both the severity of the damage and the tension force can be identified via the proposed method, thereby verifying the robustness of the proposed method. Compared to the genetic algorithm (GA), particle swarm optimization (PSO), and nonlinear least-square method (NLS), the Bayesian optimization (BO) performs best in identifying the structural damage and tension force.

• Journal of Plant Biotechnology
• /
• v.42 no.1
• /
• pp.60-70
• /
• 2015

The aim of this study was to investigate whether fourier transform infrared (FT-IR) spectroscopy can be applied to simultaneous determination of fatty acids contents in different soybean cultivars. Total 153 lines of soybean (Glycine max Merrill) were examined by FT-IR spectroscopy. Quantification of fatty acids from the soybean lines was confirmed by quantitative gas chromatography (GC) analysis. The quantitative spectral variation among different soybean lines was observed in the amide bond region ($1,700{\sim}1,500cm^{-1}$), phosphodiester groups ($1,500{\sim}1,300cm^{-1}$) and sugar region ($1,200{\sim}1,000cm^{-1}$) of FT-IR spectra. The quantitative prediction modeling of 5 individual fatty acids contents (palmitic acid, stearic acid, oleic acid, linoleic acid, linolenic acid) from soybean lines were established using partial least square regression algorithm from FT-IR spectra. In cross validation, there were high correlations ($R^2{\geq}0.97$) between predicted content of 5 individual fatty acids by PLS regression modeling from FT-IR spectra and measured content by GC. In external validation, palmitic acid ($R^2=0.8002$), oleic acid ($R^2=0.8909$) and linoleic acid ($R^2=0.815$) were predicted with good accuracy, while prediction for stearic acid ($R^2=0.4598$), linolenic acid ($R^2=0.6868$) had relatively lower accuracy. These results clearly show that FT-IR spectra combined with multivariate analysis can be used to accurately predict fatty acids contents in soybean lines. Therefore, we suggest that the PLS prediction system for fatty acid contents using FT-IR analysis could be applied as a rapid and high throughput screening tool for the breeding for modified Fatty acid composition in soybean and contribute to accelerating the conventional breeding.

• Horticultural Science & Technology
• /
• v.32 no.1
• /
• pp.105-114
• /
• 2014

We established a high throughput screening system of African yam tuber lines which contain high contents of total carotenoids, flavonoids, and phenolic compounds using ultraviolet-visible (UV-VIS) spectroscopy and Fourier transform infrared (FT-IR) spectroscopy in combination with multivariate analysis. The total carotenoids contents from 62 African yam tubers varied from 0.01 to $0.91{\mu}g{\cdot}g^{-1}$ dry weight (wt). The total flavonoids and phenolic compounds also varied from 12.9 to $229{\mu}g{\cdot}g^{-1}$ and from 0.29 to $5.2mg{\cdot}g^{-1}$dry wt. FT-IR spectra confirmed typical spectral differences between the frequency regions of 1,700-1,500, 1,500-1,300 and $1,100-950cm^{-1}$, respectively. These spectral regions were reflecting the quantitative and qualitative variations of amide I, II from amino acids and proteins ($1,700-1,500cm^{-1}$), phosphodiester groups from nucleic acid and phospholipid ($1,500-1,300cm^{-1}$) and carbohydrate compounds ($1,100-950cm^{-1}$). Principal component analysis (PCA) and subsequent partial least square-discriminant analysis (PLS-DA) were able to discriminate the 62 African yam tuber lines into three separate clusters corresponding to their taxonomic relationship. The quantitative prediction modeling of total carotenoids, flavonoids, and phenolic compounds from African yam tuber lines were established using partial least square regression algorithm from FT-IR spectra. The regression coefficients ($R^2$) between predicted values and estimated values of total carotenoids, flavonoids and phenolic compounds were 0.83, 0.86, and 0.72, respectively. These results showed that quantitative predictions of total carotenoids, flavonoids, and phenolic compounds were possible from FT-IR spectra of African yam tuber lines with higher accuracy. Therefore we suggested that quantitative prediction system established in this study could be applied as a rapid selection tool for high yielding African yam lines.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.45-54
• /
• 2012

Location-based services with GPS positioning technology as a key technology, but recognizing the current location through satellite communication is not possible in an indoor location-aware technology, low-power short-range communication is primarily made of the study. Especially, as Chirp Spread Spectrum(CSS) based location-aware approach for low-power physical layer IEEE802.15.4a is selected as a standard, Ranging distance estimation techniques and data transfer speed enhancements have been more developed. It is known that the distance measured by CSS ranging has quite a lot of noise as well as its bias. However, the noise problem can be adjusted by modeling the non-zero mean noise value by a scaling factor which corresponds to the change of magnitude of a measured distance vector. In this paper, we propose a localization system using the CSS signal to measure distance for a mobile node taken a measurement of the exact coordinates. By applying the extended kalman filter and least mean squares method, the localization system is faster, more stable. Finally, we evaluate the reliability and accuracy of the proposed algorithm's performance by the experiment for the realization of localization system.