• Biomedical Science Letters
• /
• v.25 no.1
• /
• pp.99-106
• /
• 2019

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish ${\beta}$-Amyloid ($A{\beta}$) positive from $A{\beta}$ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). $^{18}F$-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD. An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for $A{\beta}$ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for $A{\beta}$ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify $^{18}F$-Florbetaben amyloid brain PET image for $A{\beta}$ positivity using PCA-SVM model, with no additional effects on GMM.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.31-38
• /
• 2021

In this paper, in order to obtain the optimization of the RNN model used for sentiment analysis, the correlation of each model was studied by observing the trend of loss and accuracy according to hyperparameter tuning. As a research method, after configuring the hidden layer with LSTM and the embedding layer that are most optimized to process sequential data, the loss and accuracy of each model were measured by tuning the unit, batch-size, and embedding size of the LSTM. As a result of the measurement, the loss was 41.9% and the accuracy was 11.4%, and the trend of the optimization model showed a consistently stable graph, confirming that the tuning of the hyperparameter had a profound effect on the model. In addition, it was confirmed that the decision of the embedding size among the three hyperparameters had the greatest influence on the model. In the future, this research will be continued, and research on an algorithm that allows the model to directly find the optimal hyperparameter will continue.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.46.4-47
• /
• 2015

Carnegie Hubble Program II (hereafter CHP II) is a large Hubble Space Telescope (HST) observing campaign in the cycle 22 composed of a total of 184 orbits (132 primes + 52 parallels), which aims to measure H0 directly with an unprecedented accuracy. Unlike our previous efforts in CHP I which used Cepheids as a yardstick, CHP II takes the Population II (Pop II) distance indicators such as RR Lyraes and tip of the red giant branch stars (TRGBs) to set up a new calibration to Type Ia supernovae (SN Ia) distance. The Pop II distance scales have two immediate advantages over the classical Cepheid method: 1) The period-luminosity relation of the RR Lyrae has a scatter that is a factor of 2 smaller; 2) The RR Lyrae/TRGB distance scale can be applied to both elliptical and spiral galaxies. This will provide a great systematic benefit by ultimately allowing us to double the number of SN Ia distances based on geometry. By taking advantage of this Pop II route, we expect to measure H0 value to 3 % of error which will be the highest accuracy H0 measurement to date using the "Distance Ladder" method. In this talk I will present a brief background/overview on the CHP II, observations/data acquisition status, and ongoing research progress/preliminary results.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.49 no.2
• /
• pp.9-14
• /
• 2012

In this study, multi-finger RF MOSFET substrate parameters are accurately extracted by using S-parameters measured from common source-bulk and common source-gate test structures. Using this extraction method, the accuracy of an asymmetrical model with three substrate resistances is verified by observing better agreement with measured Y-parameters than a simple model with a single substrate resistance. The modeled S-parameters of the asymmetrical model also show excellent agreement with measured ones up to 20GHz.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.4
• /
• pp.291-302
• /
• 2017

Radiometric calibration is a prerequisite to quantitative remote sensing, and its accuracy has a direct impact on the reliability and accuracy of the quantitative application of remotely sensed data. This paper presents absolute radiometric calibration of the KOMPSAT-3 (KOrea Multi Purpose SATellite-3) and cross calibration using the Landsat-8 OLI (Operational Land Imager). Absolute radiometric calibration was performed using a reflectance-based method. Correlations between TOA (Top Of Atmosphere) radiances and the spectral band responses of the KOMPSAT-3 sensors in Goheung, South Korea, were significant for multispectral bands. A cross calibration method based on the Landsat-8 OLI was also used to assess the two sensors using near simultaneous image pairs over the Libya-4 PICS (Pseudo Invariant Calibration Sites). The spectral profile of the target was obtained from EO-1 (Earth Observing-1) Hyperion data over the Libya-4 PICS to derive the SBAF (Spectral Band Adjustment Factor). The results revealed that the TOA radiance of the KOMPSAT-3 agree with Landsat-8 within 5.14% for all bands after applying the SBAF. The radiometric coefficient presented here appears to be a good standard for maintaining the optical quality of the KOMPSAT-3.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.11
• /
• pp.17-23
• /
• 2017

In this paper, we implemented a respiration measurement system consisting of piezoelectric sensor, respiration signal processing device, and a viewer on a notebook. We tried an experiment for measuring respiration and detecting sleep apnea syndrome when a subject lay on a bed. We applied the respiration measurement algorithm to sensor data obtained from four subjects. In order to get a good graph shape, data manipulation methods such as moving averages and maximum values were applied. The window size for moving average was chosen as N=70, and the threshold value for each subject was customized. In this case, the proposed system showed 96.0% accuracy. When the maximum value among 90 data was applied instead of moving average, our system achieved 95.1% accuracy. In an experiment for detecting sleep apnea syndrome, the system showed that sleep apnea occurred correctly and calculated the average interval of sleep apnea. While infants or the elderly as well as patients with sleep apnea syndrome are lying down on a bed, our results are also expected to be able to cope with some accidental emergency situation by observing their respiration and detecting sleep apnea.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.4933-4956
• /
• 2016

Use-After-Free (UAF) is a common lethal form of software vulnerability. By using tools such as Web Browser Fuzzing, a large amount of samples containing UAF vulnerabilities can be generated. To evaluate the threat level of vulnerability or to patch the vulnerabilities, automatic deduplication and exploitability determination should be carried out for these samples. There are some problems existing in current methods, including inadequate pertinence, lack of depth and precision of analysis, high time cost, and low accuracy. In this paper, in terms of key dangling pointer and crash context, we analyze four properties of similar samples of UAF vulnerability, explore the method of extracting and calculate clustering eigenvalues from these samples, perform clustering by fast search and find of density peaks on a large number of vulnerability samples. Samples were divided into different UAF vulnerability categories according to the clustering results, and the exploitability of these UAF vulnerabilities was determined by observing the shape of class cluster. Experimental results showed that the approach was applicable to the deduplication and exploitability determination of a large amount of UAF vulnerability samples, with high accuracy and low performance cost.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.9 no.4
• /
• pp.204-211
• /
• 2004

Autonomous profiling CTD floats are a useful tool for observing the oceans. We, however, cannot perform post-deployment calibration of the CTD's attached to the floats, and the assessment of the accuracy and stability of the profile data from the floats is one of the important issues in the delayed mode quality control of the profiles. Variations in salinity in the intermediate level of East Sea is comparable to the accuracy of salinity data required by the international Argo Program, which is 0.01. Therefore, we can assess the credibility of salinity data from the floats deployed in the East Sea using three independent methods while considering the East Sea as a salinity calibration bath. The methods utilized here are 1) comparison of high quality CTD data and float data obtained at similar locations at similar time, 2) comparison of float data obtained at similar locations at similar time, and 3) investigation of long term stability and accuracy of salinity data from parking depths. All three methods show that without any calibration, the salinity data satisfy the accuracy criterion by the Argo Program. While assuming that the intermediate level temperature in the East Sea is as homogeneous as the salinity, we have applied the three methods to temperature data. We found that the accuracy of temperature reading is 0.01$^{\circ}C$, which is about twice larger than the requirement by the Argo Program, 0.005$^{\circ}C$. This does not mean that the temperature readings are inaccurate, because the intermediate level temperature does vary spacially and temporally more than the accuracy interval required by the Argo Program. If we take into account the variation in the intermediate level temperature, the accuracy of temperature data from the floats is not significantly different from that proposed by the Argo Program. Therefore, one could use both temperature and salinity profiles from the floats assessed in this study without calibration.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.480-483
• /
• 1997

A fossil power plant can be modeled by a lot of algebraic equations and differential equations. When we simulate a large, complicated fossil power plant by a computer such as workstation or PC, it takes much time until overall equations are completely calculated. Therefore, new processing systems which have high computing speed is ultimately needed to develope real-time simulators. Vital points of real-time simulators are accuracy, computing speed, and deadline observing. In this paper, we present a enhanced strategy in which we can provide powerful computing power by parallel processing of DSP processors with communication links. We designed general purpose DSP modules, and a VME interface module. Because the DSP module is designed for general purpose, we can easily expand the parallel system by just connecting new DSP modules to the system. Additionally we propose methods about downloading programs, initial data to each DSP module via VME bus, DPRAM and processing sequences about computing and updating values between DSP modules and CPU30 board when the simulator is working.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.817-820
• /
• 2005

The gate-length dependence of maximun oscillation frequency $f_{MAX}$ is modeled by using scaling equations of equivalent-circuit parameters extracted from measured S-parameters of Nano-scale MOSFETs. The accuracy of the modeled $f_{MAX}$ is verified by observing good agreements with measured ones. It is observed that the $f_{MAX}$ initially increases with decreasing $L_g$ and then $f_{MAX}$ becomes saturated from $L_g$ less than 65nm.