• Investigative Magnetic Resonance Imaging
• /
• v.10 no.2
• /
• pp.108-116
• /
• 2006

Purpose : High-resolution spiral-scan imaging is performed at 3 Tesla MRI system. Since the gradient waveforms for the spiral-scan imaging have lower slopes than those for the Echo Planar Imaging (EPI), they can be implemented with the gradient systems having lower slew rates. The spiral-scan imaging also involves less eddy currents due to the smooth gradient waveforms. The spiral-scan imaging method does not suffer from high specific absorption rate (SAR), which is one of the main obstacles in high field imaging for rf echo-based fast imaging methods such as fast spin echo techniques. Thus, the spiral-scan imaging has a great potential for the high-speed imaging in high magnetic fields. In this paper, we presented various high-resolution images obtained by the spiral-scan methods at 3T MRI system for various applications. Materials and Methods : High-resolution spiral-scan imaging technique is implemented at 3T whole body MRI system. An efficient and fast higher-order shimming technique is developed to reduce the inhomogeneity, and the single-shot and interleaved spiral-scan imaging methods are developed. Spin-echo and gradient-echo based spiral-scan imaging methods are implemented, and image contrast and signal-tonoise ratio are controlled by the echo time, repetition time, and the rf flip angles. Results : Spiral-scan images having various resolutions are obtained at 3T MRI system. Since the absolute magnitude of the inhomogeneity is increasing in higher magnetic fields, higher order shimming to reduce the inhomogeneity becomes more important. A fast shimming technique in which axial, sagittal, and coronal sectional inhomogeneity maps are obtained in one scan is developed, and the shimming method based on the analysis of spherical harmonics of the inhomogeneity map is applied. For phantom and invivo head imaging, image matrix size of about $100{\times}100$ is obtained by a single-shot spiral-scan imaging, and a matrix size of $256{\times}256$ is obtained by the interleaved spiral-scan imaging with the number of interleaves of from 6 to 12. Conclusion : High field imaging becomes increasingly important due to the improved signal-to-noise ratio, larger spectral separation, and the higher BOLD-based contrast. The increasing SAR is, however, a limiting factor in high field imaging. Since the spiral-scan imaging has a very low SAR, and lower hardware requirements for the implementation of the technique compared to EPI, it is suitable for a rapid imaging in high fields. In this paper, the spiral-scan imaging with various resolutions from $100{\times}100$ to $256{\times}256$ by controlling the number of interleaves are developed for the high-speed imaging in high magnetic fields.

• Investigative Magnetic Resonance Imaging
• /
• v.18 no.2
• /
• pp.87-106
• /
• 2014

Purpose : To describe how a robust implementation of a radial 3D gradient-echo sequence with stack-of-stars sampling can be achieved, to review the imaging properties of radial acquisitions, and to share the experience from more than 5000 clinical patient scans. Materials and Methods: A radial stack-of-stars sequence was implemented and installed on 9 clinical MR systems operating at 1.5 and 3 Tesla. Protocols were designed for various applications in which motion artifacts frequently pose a problem with conventional Cartesian techniques. Radial scans were added to routine examinations without selection of specific patient cohorts. Results: Radial acquisitions show significantly lower sensitivity to motion and allow examinations during free breathing. Elimination of breath-holding reduces failure rates for non-compliant patients and enables imaging at higher resolution. Residual artifacts appear as streaks, which are easy to identify and rarely obscure diagnostic information. The improved robustness comes at the expense of longer scan durations, the requirement for fat suppression, and the nonexistence of a time-to-center value. Care needs to be taken during the configuration of receive coils. Conclusion: Routine clinical use of radial stack-of-stars sequences is feasible with current MR systems and may serve as substitute for conventional fat-suppressed T1-weighted protocols in applications where motion is likely to degrade the image quality.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.717-724
• /
• 2017

To improve the running safety of a tram operating on a concrete embedded track, a bogie, the core system of the tram, was developed and fabricated. After it was integrated with the prototype car body, a short distance track with a sharp curve and steep gradient was constructed for the test operation. A formula to check the interference of the wheel flange with the track during running was proposed. Based on the results provided by the formula, the track was designed. Another simple formula was derived to estimate the derailment quotient and the wheel unloading ratio. During running on the track, the acceleration of the car body was measured and the interface status between the wheel and the track was monitored by a video system. According to the results calculated by these simple formulas, the derailment quotient and wheel unloading ratio were estimated to be within the safety criteria. In the actual test, no derailment occurred and the measured acceleration satisfied the criteria. Also, there was no interference between the wheel and track. The video monitoring results showed no signs of derailment, such as the climbing of the wheel. The pinion in the center showed good running safety, contacting smoothly with the rack. The measurements of environmental noise proved that the criteria were satisfied.

• Geophysics and Geophysical Exploration
• /
• v.14 no.3
• /
• pp.220-226
• /
• 2011

In the elastic wave equations, both horizontal and vertical displacements are defined. Since we can measure both the horizontal and vertical displacements in field acquisition, these displacements compose a displacement vector. In this study, we propose a frequency-domain elastic waveform inversion technique taking advantage of the magnitudes of displacement vectors to define objective function. When we apply this displacement-vector objective function to the frequency-domain waveform inversion, the inversion process naturally incorporates the back-propagation algorithm. Through the inversion examples with the Marmousi model and the SEG/EAGE salt model, we could note that the RMS error of the solution obtained by our algorithm decreased more stably than that of the conventional method. Particularly, the density of the Marmousi model and the low-velocity sub-salt zone of the SEG/EAGE salt model were successfully recovered. Since the gradient direction obtained from the proposed objective function is numerically unstable, we need additional study to stabilize the gradient direction. In order to perform the waveform inversion using the displacementvector objective function, it is necessary to acquire multi-component data. Hence, more rigorous study should be continued for the multi-component land acquisition or OBC (Ocean Bottom Cable) multi-component survey.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.471-476
• /
• 2016

In this paper, recognition system for continuous human action is explained by using motion history image and histogram of oriented gradient with spotter model based on depth information, and the spotter model which performs action spotting is proposed to improve recognition performance in the recognition system. The steps of this system are composed of pre-processing, human action and spotter modeling and continuous human action recognition. In pre-processing process, Depth-MHI-HOG is used to extract space-time template-based features after image segmentation, and human action and spotter modeling generates sequence by using the extracted feature. Human action models which are appropriate for each of defined action and a proposed spotter model are created by using these generated sequences and the hidden markov model. Continuous human action recognition performs action spotting to segment meaningful action and meaningless action by the spotter model in continuous action sequence, and continuously recognizes human action comparing probability values of model for meaningful action sequence. Experimental results demonstrate that the proposed model efficiently improves recognition performance in continuous action recognition system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2023

Research using AI and big data is also being actively conducted in the health and medical fields such as disease diagnosis and treatment. Most of the existing research data used cohort data from research institutes or some patient data. In this paper, the difference in the prediction rate of survival and the factors affecting survival between breast cancer patients in their 40~50s and other age groups was revealed using health insurance review claim data held by the HIRA. As a result, the accuracy of predicting patients' survival was 0.93 on average in their 40~50s, higher than 0.86 in their 60~80s. In terms of that factor, the number of treatments was high for those in their 40~50s, and age was high for those in their 60~80s. Performance comparison with previous studies, the average precision was 0.90, which was higher than 0.81 of the existing paper. As a result of performance comparison by applied algorithm, the overall average precision of Decision Tree, Random Forest, and Gradient Boosting was 0.90, and the recall was 1.0, and the precision of multi-layer perceptrons was 0.89, and the recall was 1.0. I hope that more research will be conducted using machine learning automation(Auto ML) tools for non-professionals to enhance the use of the value for health insurance review claim data held by the HIRA.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.39-57
• /
• 2022

This paper proposes the GMOPTBoost algorithm to improve the performance of the AdaBoost algorithm for bankruptcy prediction in which class imbalance problem is inherent. AdaBoost algorithm has the advantage of providing a robust learning opportunity for misclassified samples. However, there is a limitation in addressing class imbalance problem because the concept of arithmetic mean accuracy is embedded in AdaBoost algorithm. GMOPTBoost can optimize the geometric mean accuracy and effectively solve the category imbalance problem by applying Gaussian gradient descent. The samples are constructed according to the following two phases. First, five class imbalance datasets are constructed to verify the effect of the class imbalance problem on the performance of the prediction model and the performance improvement effect of GMOPTBoost. Second, class balanced data are constituted through data sampling techniques to verify the performance improvement effect of GMOPTBoost. The main results of 30 times of cross-validation analyzes are as follows. First, the class imbalance problem degrades the performance of ensembles. Second, GMOPTBoost contributes to performance improvements of AdaBoost ensembles trained on imbalanced datasets. Third, Data sampling techniques have a positive impact on performance improvement. Finally, GMOPTBoost contributes to significant performance improvement of AdaBoost ensembles trained on balanced datasets.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.135-135
• /
• 2017

Greenhouse have been developed to provide the plants with good environmental conditions for cultivation crop, two major factors of which are the inside air temperature and humidity. The inside temperature are influenced by the heating systems, ventilators and for systems among others, which in turn are geverned by some type of controller. Likewise, humidity environment is the result of complex mass exchanges between the inside air and the several elements of the greenhouse and the outside boundaries. Most of the existing models are based on the energy balance method and heat balance equation for modelling the heat and mass fluxes and generating dynamic elements. However, greenhouse are classified as complex system, and need to make a sophisticated modeling. Furthermore, there is a difficulty in using classical control methods for complex process system due to the process are non linear and multi-output(MIMO) systems. In order to predict the time evolution of conditions in certain greenhouse as a function, we present here to use of recurrent neural networks(RNN) which has been used to implement the direct dynamics of the inside temperature and inside humidity of greenhouse. For the training, we used algorithm of a backpropagation Through Time (BPTT). Because the environmental parameters are shared by all time steps in the network, the gradient at each output depends not only on the calculations of the current time step, but also the previous time steps. The training data was emulated to 13 input variables during March 1 to 7, and the model was tested with database file of March 8. The RMSE of results of the temperature modeling was $0.976^{\circ}C$, and the RMSE of humidity simulation was 4.11%, which will be given to prove the performance of RNN in prediction of the greenhouse environment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.161-170
• /
• 2017

The balise is a device for the railroad signal control systems, which is installed between both rail. The balise sends fixed or variable data, named telegram, to the train with wireless method. The telegram includes the position information, the movable distance under the signal status, the gradient, the speed, the temporary speed limit, etc. This research is on a design of the DBPL encoder for the balise. Normally the DBPL encoder for the balise is with the ASIC or FPGA technology. In this research, the DBPL encoder is designed with commercial low power operable micro-controller. The firmware(logic level encode) and the SPI Bus function block(physical level output) of the micro-controller are used for the DBPL encode. Under the european standard, the required working speed of the DBPL encoder is 564.48Kbps. The DBPL encoder of this research is tested under the speed of 564.48Kbps, and it worked properly.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.259-266
• /
• 2016

Recently, CCTV cameras are emplaced actively to reinforce security and intelligent surveillance systems have been under development for detecting and monitoring of the objects in the video. In this study, we propose a method for detection of upper body in intelligent surveillance system using FCM-based RBFNN classifier realized with the aid of HOG features. Firstly, HOG features that have been originally proposed to detect the pedestrian are adopted to train the unique gradient features about upper body. However, HOG features typically exhibit a very high dimension of which is proportional to the size of the input image, it is necessary to reduce the dimension of inputs of the RBFNN classifier. Thus the well-known PCA algorithm is applied prior to the RBFNN classification step. In the computer simulation experiments, the RBFNN classifier was trained using pre-classified upper body images and non-person images and then the performance of the proposed classifier for upper body detection is evaluated by using test images and video sequences.