• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1729-1738
• /
• 2021

Machine learning has a close relationship with cognitive psychology and brain science and is developing together. This paper analyzes the OASIS-3 dataset using machine learning techniques and proposes a model for predicting dementia. Dimensional reduction through PCA (Principal Component Analysis) is performed on the data quantifying the volume of each area among OASIS-3 data, and only important elements (features) are extracted and then various machine learning including gradient boosting and stacking Apply the models and compare the performance of each. Unlike previous studies, the proposed technique has a great differentiation because it uses not only the brain biometric data, but also basic information data such as the participant's gender and medical information data of the participant. In addition, it was shown that the proposed technique through various performance evaluations is a model that can better predict dementia by finding features that are more related to dementia among various numerical data.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.114-125
• /
• 2023

The physics-informed neural network (PINN) has been proposed to overcome the limitations of various numerical methods used to solve partial differential equations (PDEs) and the drawbacks of purely data-driven machine learning. The PINN directly applies PDEs to the construction of the loss function, introducing physical constraints to machine learning training. This technique can also be applied to wave equation modeling. However, to solve the wave equation using the PINN, second-order differentiations with respect to input data must be performed during neural network training, and the resulting wavefields contain complex dynamical phenomena, requiring careful strategies. This tutorial elucidates the fundamental concepts of the PINN and discusses considerations for wave equation modeling using the PINN approach. These considerations include spatial coordinate normalization, the selection of activation functions, and strategies for incorporating physics loss. Our experimental results demonstrated that normalizing the spatial coordinates of the training data leads to a more accurate reflection of initial conditions in neural network training for wave equation modeling. Furthermore, the characteristics of various functions were compared to select an appropriate activation function for wavefield prediction using neural networks. These comparisons focused on their differentiation with respect to input data and their convergence properties. Finally, the results of two scenarios for incorporating physics loss into the loss function during neural network training were compared. Through numerical experiments, a curriculum-based learning strategy, applying physics loss after the initial training steps, was more effective than utilizing physics loss from the early training steps. In addition, the effectiveness of the PINN technique was confirmed by comparing these results with those of training without any use of physics loss.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.47
• /
• pp.63-94
• /
• 2002

On the purpose to suggest an advanced scheme in assessing the domestic wheat quality, this paper reviewed the inspection systems of wheat in major wheat producing countries as well as the quality criteria which are being used in wheat grading and classification. Most wheat producing countries are adopting both classifications of class and grade to provide an objective evaluation and an official certification to their wheat. There are two main purposes in the wheat classification. The first objectives of classification is to match the wheat with market requirements to maximize market opportunities and returns to growers. The second is to ensure that payments to glowers aye made on the basis of the quality and condition of the grain delivered. Wheat classes has been assigned based on the combination of cultivation area, seed-coat color, kernel and varietal characteristics that are distinctive. Most reputable wheat marketers also employ a similar approach, whereby varieties of a particular type are grouped together, designed by seed coat colour, grain hardness, physical dough properties, and sometimes more precise specification such as starch quality, all of which are genetically inherited characteristics. This classification in simplistic terms is the categorization of a wheat variety into a commercial type or style of wheat that is recognizable for its end use capabilities. All varieties registered in a class are required to have a similar end-use performance that the shipment be consistent in processing quality, cargo to cargo and year to year, Grain inspectors have historically determined wheat classes according to visual kernel characteristics associated with traditional wheat varieties. As well, any new wheat variety must not conflict with the visual distinguishability rule that is used to separate wheats of different classes. Some varieties may possess characteristics of two or more classes. Therefore, knowledge of distinct varietal characteristics is necessary in making class determinations. The grading system sets maximum tolerance levels for a range of characteristics that ensure functionality and freedom from deleterious factors. Tests for the grading of wheat include such factors as plumpness, soundness, cleanliness, purity of type and general condition. Plumpness is measured by test weight. Soundness is indicated by the absence or presence of musty, sour or commercially objectionable foreign odors and by the percentage of damaged kernels that ave present in the wheat. Cleanliness is measured by determining the presence of foreign material after dockage has been removed. Purity of class is measured by classification of wheats in the test sample and by limitation for admixtures of different classes of wheat. Moisture does not influence the numerical grade. However, it is determined on all shipments and reported on the official certificate. U.S. wheat is divided into eight classes based on color, kernel Hardness and varietal characteristics. The classes are Durum, Hard Red Spring, Hard Red Winter, Soft Red Winter, Hard White, soft White, Unclassed and Mixed. Among them, Hard Red Spring wheat, Durum wheat, and Soft White wheat are further divided into three subclasses, respectively. Each class or subclass is divided into five U.S. numerical grades and U.S. Sample grade. Special grades are provided to emphasize special qualities or conditions affecting the value of wheat and are added to and made a part of the grade designation. Canadian wheat is also divided into fourteen classes based on cultivation area, color, kernel hardness and varietal characteristics. The classes have 2-5 numerical grades, a feed grade and sample grades depending on class and grading tolerance. The Canadian grading system is based mainly on visual evaluation, and it works based on the kernel visual distinguishability concept. The Australian wheat is classified based on geographical and quality differentiation. The wheat grown in Australia is predominantly white grained. There are commonly up to 20 different segregations of wheat in a given season. Each variety grown is assigned a category and a growing areas. The state governments in Australia, in cooperation with the Australian Wheat Board(AWB), issue receival standards and dockage schedules annually that list grade specifications and tolerances for Australian wheat. AWB is managing "Golden Rewards" which is designed to provide pricing accuracy and market signals for Australia's grain growers. Continuous payment scales for protein content from 6 to 16% and screenings levels from 0 to 10% based on varietal classification are presented by the Golden Rewards, and the active payment scales and prices can change with market movements.movements.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.5
• /
• pp.337-343
• /
• 2014

This paper presents a continuum-based shape design sensitivity analysis(DSA) method for crack propagation problems using a reproducing kernel method(RKM), which facilitates the remeshing problem required for finite element analysis(FEA) and provides the higher order shape functions by increasing the continuity of the kernel functions. A linear elasticity is considered to obtain the required stress field around the crack tip for the evaluation of J-integral. The sensitivity of displacement field and stress intensity factor(SIF) with respect to shape design variables are derived using a material derivative approach. For efficient computation of design sensitivity, an adjoint variable method is employed tather than the direct differentiation method. Through numerical examples, The mesh-free and the DSA methods show excellent agreement with finite difference results. The DSA results are further extended to a shape optimization of crack propagation problems to control the propagation path.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.4
• /
• pp.17-27
• /
• 2007

The enhanced distributed channel access (EDCA) of IEEE 802.11e has been standardized for supporting Quality of Service (QoS) in wireless LANs. In the EDCA, support of QoS can be achieved statistically by reducing the probability of medium access for lower priority traffics. In other words, it provides statistical channel access rather than deterministically prioritized access to high priority traffic. Therefore, lower priority traffics affect the performance of higher priority traffics. Consequently, at the high loads, the EDCA does not guarantee the QoS of multimedia applications such as voice and video even though it provides higher priority. In this paper, we propose a simple and effective scheme, called deterministic priority channel access (DPCA), for improving the QoS performance of the EDCA mechanism. In order to provide guaranteed priority channel access to multimedia applications, the proposed scheme uses a busy tone for limiting the transmissions of lower priority traffics when higher priority traffic has data packets to send. Performance of the proposed scheme is investigated by numerical analysis and simulation. Our results show that the proposed scheme outperforms the EDCA in terms of throughput, delay, jitter, and drop under a wide range of contention levels.

• Journal of Biomedical Engineering Research
• /
• v.36 no.4
• /
• pp.115-122
• /
• 2015

A standard air flow generator system was developed to generate air flows of various levels simultaneously applied to two different air flow transducer modules. Axes of two identical standard syringes for spirometer calibration were connected with each other and driven by a servo-motor. Linear displacement transducer was also connected to the syringe axis to accurately acquire the volume change signal. The user can select either sinusoidal or square waveform of volume change and manually input any volume as well as maximal flow rate levels ranging 0~3 l and 0~15 l/s, respectively. Various volume and flow levels were input to operate the system, then the volume signal was acquired followed by numerical differentiation to obtain the air flow signal. The measured volumes and maximal air flow rates were compared with the user input data. The relative errors between the user-input and the measured stroke volumes were all within 0.5%, demonstrating very accurate driving of the system. In case of the maximal flow rate, relatively large error was observed when the syringe was driven very fast within a very short time duration. However, except for these few data, most measured flow rates revealed relative errors of approximately 2%. When the measure and user-input stroke volume and maximal flow rate data were analyzed by linear regression analysis, respectively, the correlation coefficients were satisfactorily higher than 0.99 (p < 0.0001). These results demonstrate that the servo-motor controls the syringes with enough accuracy to generate standard air flows. Therefore, the present system would be very much practical for calibration process as well as performance evaluation and comparison of two different air flow transducer modules.

• Korean Journal of Head & Neck Oncology
• /
• v.9 no.1
• /
• pp.25-32
• /
• 1993

The nodular hyperplasia of the thyroid is a common thyriod disease. Nodular hyperplasia does rarely progress to thyroid cancer. The differentiation of a nodular hyperplasia from a neoplasm may be simple or difficult, both clinically and anatomically. The papillary carcinoma of the thyroid is the most common type of thyroid malignancies. There were few studies about cytogenetic observation in thyroid cancer. But only one case of banding observation in nodular hyperplasia have been reported. In order to compare the chromosomal changes in the thyroid cancer and the noncancerous thyroid disease, we performed cytogenetic analysis in two papillary carcinoma and two nodular hyperplasia after cell culture. The chromosomal pattern of the nodular hyperplasia found was very heterogenous but no clonal abnormaly in both cases was observed. Case I : A modal chromosomal number was in 42-46 range. Chromosome 8, 19, 21. 22 were commonly lost. 9 structural anomalities among 51 analysed cells were observed but they were not clonal. Case II: A modal chromosomal number was 43. Chromosome 17 and 19 were commonly lossed. Common cytogenetic characters of this two nodular hyperplasia are hypodiploidity and very heterogenous chromosomal pattern. The result about the papillary carcinoma are as follow. In one case some numerical and structural chromosomal changes were observed. But they were not clonal abnormality. In another case the chromosomal pattern found was very heterogenous with a clonal abnormality of del(11)(q23). The modal number was 46. The del(11)(q23) a chromosomal change in papillary carcinoma of the thyroid have previously been reported(Eva Olah et al. 1989). We suggest that 11q deletion may be important role to pathogenesis of papillary carcinoma of the thyroid. According to this results, we could not find out specific differences about chromosomal changes and any relationship between the papillary carcinoma and the nodular hyperplasia.