• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.67-73
• /
• 2012

In this paper, Artificial Neural Network(ANN) based motion classification algorithm is proposed to classify wrist motions using surface electromyograms(sEMG). surface EMGs are obtained from two electrodes placed on the flexor carpi ulnaris muscle and extensor carpi ulnaris muscle of 26 subjects under no strain condition during wrist motions and used to recognize wrist motions such as up, down, left, right, and rest. Feature is extracted from obtained EMG signals in time domain for fast processing and used to classify wrist motions using ANN. DAMV, DASDV, MAV, and RMS were used as features and accuracies of motion classification based on ANN were 98.03% for DAMV, 97.97% for DASDV, 96.95% for MAV, 96.82% for RMS.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• Tunnel and Underground Space
• /
• v.17 no.2 s.67
• /
• pp.102-108
• /
• 2007

Generally, the method used most widely for rock mass classification is considering the rock strength and development of joint frequency. However, if rock bed has micro-crack and long joint, this method is not rational. Therefore, the difficulties of excavation in the rock bed with complicated geological condition are decided by combining joint frequency. indoor tests (uniaxiall compressive strength, point load test, indoor elastic wave velocity, etc.) and field seismic refraction survey, and the rock mass classification should be implemented by considering their interrelationship.

• Journal of the Korean Wood Science and Technology
• /
• v.49 no.5
• /
• pp.491-503
• /
• 2021

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.

• Geomechanics and Engineering
• /
• v.30 no.5
• /
• pp.449-460
• /
• 2022

Safe underground construction in a rock mass requires adequate ground investigation and effective determination of rock conditions. The estimation of rock mass behavior is difficult, because rock masses are innately anisotropic and heterogeneous at different scales and are affected by various environmental factors. Quantitative rock mass classification systems, such as the Q-system and rock mass rating, are widely used for characterization and engineering design. The measurement of rock classification parameters is subjective and can vary among observers, resulting in questionable accuracy. Geophysical investigation methods, such as seismic surveys, have also been used for ground characterization. Torsional shear wave propagation characteristics in cylindrical rods are equal to that in an infinite media. A probabilistic quantitative relationship between the Q-value and shear wave velocity is thus investigated considering long-wavelength wave propagation in equivalent continuum jointed rock masses. Individual Q-system parameters are correlated with stress-dependent shear wave velocities in jointed rocks using experimental and numerical methods. The relationship between the Q-value and the shear wave velocity is normalized using a defined reference condition. This relationship is further improved using probabilistic analysis to remove unrealistic data and to suggest a range of Q-values for a given wave velocity. The proposed probabilistic Q-value estimation is then compared with field measurements and cross-hole seismic test data to verify its applicability.

• Journal of the Korean Society of Radiology
• /
• v.85 no.3
• /
• pp.549-565
• /
• 2024

MRI is a crucial tool for diagnosing adenomyosis and identifying its related pathologies. To accurately diagnose adenomyosis, it is necessary to recognize both the typical MRI findings and atypical features of the condition. Recently, a standardized classification system has been developed to facilitate precise presurgical diagnosis of adenomyosis and to determine the appropriate treatment method. Differentiating between various subtypes based on MRI-based classification and identifying different MRI phenotypes can aid in categorizing patients with adenomyosis into specific treatment groups and monitoring their response to therapy.

• Journal of the Korean Institute of Educational Facilities
• /
• v.10 no.4
• /
• pp.31-41
• /
• 2003

The purpose of this study is to analyze the Characteristic of Block Plans related to site types of Elementary Schools in Kangju city. With analysis of 17 elementary school plans, we reached same conclusions. First, there is a possibility of seeing 4 examples that contiguity road condition and proportion of site, neighborhood park location, district units planning, which as classification the condition to feature of location. But the condition which is considered actually from Block Plan appeared with only contiguity road condition and district units planning two onlines. Second, despite there are elements having the possibility effecting to Block Plan, some arrangement forms are repeatedly used. There is a possibility of searching for that cause that it falls in mannerism of space form, type and place when it follows the arrangement form of existing defined as school.

• Journal of Sasang Constitutional Medicine
• /
• v.14 no.3
• /
• pp.17-32
• /
• 2002

Objectives ; A Supplementary Study for Sasangin Identifing is based on Chapter Pathophysiology Part V of [Donggyi Soose Bowon Chobonguan]. And I try to explain that with Sasang Constitutional Theory. After all I want this study given the basis of 'The Guideline of Sasangin's Diagnosis & Treatment(GSDT)'. Methods ; First, I divid ${\ulcorner}$part V${\lrcorner}$ into 4 cartegories (Normal Condition, Abnormal Condition, good or bad Condition, Better or Worse Condition). And then each symtom is analyzed by Sasang Constitutional Medicine(SCM). Conclusions; I am sure that it gives the first step toward Indentifying Sasangin of [Donggyi Soose Bowon]. All of Sasangin Identifing Supplementary are analyzed by SCM. They are divided the identifing for Sasangin classification and Sasangin diagnosis of the disease. And this study will give the basis of ‘GSDT’.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11b
• /
• pp.1323-1328
• /
• 2001

The theory of NAH is based on the assumption of reflection free. However, it is not always possible to meet this condition in many practical cases. Thus, a decomposition of direct and reflected fields is needed to apply NAH to reflective condition for noise problems. In addition, the decomposition of direct and reflected field can give acoustic characteristics of reflecting surfaces. This paper presents that in this condition the decomposition can also be successfully done by MUSIC(Multiple Signal Classification) power method and beamforming method, and that numerical simulation and real experiments verify its performance.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.617-620
• /
• 2017

The periodic monitoring of crop conditions and timely estimation of crop yield are of great importance for supporting agricultural decision-makings, as well as for effectively coping with food security issues. Remote sensing has been regarded as one of effective tools for crop condition monitoring and crop type classification. Since 2010, RDA (Rural Development Administration) has been developing technology for monitoring on crop condition using remote sensing and model. These special papers address recent state-of-the-art of remote sensing and geospatial technologies for providing operational agricultural information, such as, crop yield estimation methods using remote sensing data and process-oriented model, crop classification algorithm, monitoring and prediction of weather and climate based on remote sensing data,system design and architecture of crop monitoring system, history on rice yield forecasting method.