• Bulletin of the Korean Mathematical Society
• /
• v.48 no.3
• /
• pp.523-537
• /
• 2011

A receiver operating characteristic (ROC) curve plots the true positive rate of a classier against its false positive rate, both of which are accuracy measures of the classier. The ROC curve has several interesting geometrical properties, including concavity which is a necessary condition for a classier to be optimal. In this paper, we study the nonparametric maximum likelihood estimator (NPMLE) of a concave ROC curve and its modification to reduce bias. We characterize the NPMLE as a solution to a geometric programming, a special type of a mathematical optimization problem. We find that the NPMLE is close to the convex hull of the empirical ROC curve and, thus, has smaller variance but positive bias at a given false positive rate. To reduce the bias, we propose a modification of the NPMLE which minimizes the $L_1$ distance from the empirical ROC curve. We numerically compare the finite sample performance of three estimators, the empirical ROC curve, the NMPLE, and the modified NPMLE. Finally, we apply the estimators to estimating the optimal ROC curve of the variance-threshold classier to segment a low depth of field image and to finding a diagnostic tool with multiple tests for detection of hemophilia A carrier.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.7
• /
• pp.81-90
• /
• 2018

In this paper, reducing lense Vignetting effect and adaptive learning rate method are proposed to complement Scribner's neural network for nuc algorithm which is the effective algorithm in statistic SBNUC algorithm. Proposed reducing vignetting effect method is updated weight and bias each differently using different cost function. Proposed adaptive learning rate for updating weight and bias is using sobel edge detection method, which has good result for boundary condition of image. The ordinary statistic SBNUC algorithm has problem to compensate lense vignetting effect, because statistic algorithm is updated weight and bias by using gradient descent method, so it should not be effective for global weight problem same like, lense vignetting effect. We employ the proposed methods to Scribner's neural network method(NNM) and Torres's reducing ghosting correction for neural network nuc algorithm(improved NNM), and apply it to real-infrared detector image stream. The result of proposed algorithm shows that it has 10dB higher PSNR and 1.5 times faster convergence speed then the improved NNM Algorithm.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2014.02a
• /
• pp.128.2-128.2
• /
• 2014

Long-wave infrared detectors using the type-II InAs/GaSb strained superlattice (T2SL) material system with the nBn structure were designed and fabricated. The band gap energy of the T2SL material was calculated as a function of the thickness of the InAs and GaSb layers by the Kronig-Penney model. Growth of the barrier material (Al0.2Ga0.8Sb) incorporated Te doping to reduce the dark current. The full width at half maximum (FWHM) of the 1st satellite superlattice peak from the X-ray diffraction was around 45 arc sec. The cutoff wavelength of the fabricated device was ${\sim}10.2{\mu}m$ (0.12eV) at 80 K while under an applied bias of -1.4V. The measured activation energy of the device was ~0.128 eV. The dark current density was shown to be $1.2{\times}10^{-5}A/cm^2$ at 80 K and with a bias -1.4 V. The responsivity was 1.9 A/W at $7.5{\mu}m$ at 80K and with a bias of -1.9V.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.2
• /
• pp.55-62
• /
• 2019

The stereo geometry establishment based on the precise sensor modeling is prerequisite for accurate stereo data processing. Ground control points are generally required for the accurate sensor modeling though it is not possible over the area where the accessibility is limited or reference data is not available. For the areas, the relative orientation should be carried out to improve the geometric consistency between the stereo data though it does not improve the absolute positional accuracy. The relative orientation requires conjugate points that are well distributed over the entire image region. Therefore the automatic conjugate point extraction is required because the manual operation is labor-intensive. In this study, we applied the method consisting of the key point extraction, the search space minimization based on the epipolar line, and the rigorous outlier detection based on the RPCs (Rational Polynomial Coefficients) bias compensation modeling. We tested different parameters of window sizes for Kompsat-2 across track stereo data and analyzed the RPCs precision after the bias compensation for the cases whether the epipolar line information is used or not. The experimental results showed that matching outliers were inevitable for the different matching parameterization but they were successfully detected and removed with the rigorous method for sub-pixel level of stereo RPCs precision.

• Physical Therapy Rehabilitation Science
• /
• v.10 no.2
• /
• pp.185-196
• /
• 2021

Objective: Falling is one of main accident to facilitate the physical injuries in order adults. The purpose of the systematic review was to determine the effects of postural balance training whether the recovery of falls in elderly with normal physical function or not throughout summing the selected studies quantitatively. Design: A systematic review Methods: MEDLINE and other four databases were searched up to April 20, 2021 and randomized controlled trials (RCTs) evaluating postural balance approaches on fall risks in elderly. The researched studies excluded the double studies, titles and abstract, and finally full-reported study. The selected RCTs studies were extracted characteristics of the studies and summary of results based on PICOS-SD (population, intervention, comparison, outcomes, and setting- study design) model to synthesize the papers qualitatively. Results: The review involved 22 RCT reports with 4,847 community older adults aged 65 years or over. Nineteen of the selected RCT studies reported dual or multimodal exercises show the beneficial effect for older adults compared to one-type treatment or no intervention. All of selected showed low risk in the selection, attrition, and reporting bias. However, detection bias showed low risk at 75% records of the involved RCTs and performance bias was low risk at only three records. Conclusions: The results of the systematic review propose that a standardized therapeutic approach and the intensity are needed for improving risk of falls in older adults.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.7
• /
• pp.1386-1392
• /
• 2009

An analysis is presented for super-high-speed optical demodulation by an avalanche photodiode(APD) with electric mixing. A normalized gain is defined to evaluate the performance of the optical mixing detection. Unlike previous work, we include the effect of the nonlinear variation of the APD capacitance with bias voltage as well as the effect of parasitic and amplifier input capacitance. As a results, the normalized gain is dependent on the signal frequency and the frequency difference between the signal and the local oscillator frequency. However, the current through the equivalent resistance of the APD is almost independent of signal frequency. The mixing output is mainly attributed to the nonlinearity of the multiplication factor. We show also that there is an optimal local oscillator voltage at which the normalized gain is maximized for a given avalanche photodiode.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.1089-1092
• /
• 1995

A planar vibratory gyroscope using electrostatic actuation and electromagnetic detection is proposed. The gyroscope has large sensitivity and can be fabricated by using surface micrimachining, bulk micromachining and conventional machining technology. In this paper, the gyroscope and the electromagnetic detecting system equations are derived to determine the output characteristics for the planar vibratory gyroscope using electrostatic acturation and electromagnetic detection. The maximum output is obtained when the driving frequencyequals to the detecting frequency. The resonant frequencies of the resonator are determined by the beam stiffness, i.e. the material constants and spring dimensions. The dimensions of the beams are determined using the analytic vibration modelling. The expected resonant frequencies are 200Hz both and the sensitivity is 62mV/deg/sec with 4000 electronic circuit amplifying coefficient for an AC drive voltage of 3V bias voltage of 15V and DC field current of 50 mA.

• Journal of the Korean Vacuum Society
• /
• v.9 no.1
• /
• pp.76-80
• /
• 2000

CF & $CF_2$ radicals in a $C_4F_8$ inductively coupled plasma were observed with laser induced fluorescence. 251.9nm UV laser was used for the $CF_2$ excitation and 265.3nm UV emitted light for the detection which has the maximum intensity among many induced fluorescence lights. In the case of CF radical detection, 232.9nm UV laser was used for the excitation and 247.6nm for the detection. $CF_2$ radical density increased toward substrate, while CF radical had its maximum at about 10nm away from the substrate. The atomic fluorine density which was studied by the actinometry increased as the position moves away from the substrate. This phenomena was thought to have a close relation with the polymer growth on the wafer. When the bias voltage increased, $CF_2$ , CF radicals decreased while the atomic fluorine increased tio some extent and then decreased, which was thought to be due to the change in the ionization and dissociation.

• Journal of Korea Water Resources Association
• /
• v.34 no.4
• /
• pp.357-364
• /
• 2001

Sometimes the observed data is too small to discriminate it from noise of the instrument. Say, the data can be recorded as below DL(Detection Level) value. Even though the data below Detection Level(BDL) is small vague, it can be resulted in wrong estimates for mean and variance. However, in practice, the BDL data is generally eliminated as N.D. (Not Detected) and do not record it in Korea. This study investigates the distributions according to the data values of ammonia concentration (NH$_3$-N) in Puyeo intake. Also we try to find out DL value and an appropriate method for the estimations of mean and variance of BDL values that can be discriminate the distributions. The DL is estimated by trial and error method. The appropriate method for the estimations of mean and variance of above the detection level(ADL)and BDL dada sets is selected, and the mean and variance are estimated. As a result, it is found that the Bias Corrected Maximum Likelihood Estimator is the most accurate method for NH$_3$-N in Puyeo intake.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.1-9
• /
• 2023

Stress is a significant issue in modern society, often triggered by external or internal factors that are difficult to manage. When high stress persists over a long term, it can develop into a chronic condition, negatively impacting health and overall well-being. However, it is challenging for individuals experiencing chronic stress to recognize their condition, making early detection and management crucial. Using biosignals measured from wearable devices to detect stress could lead to more effective management. However, there are two main problems with using biosignals: first, manually extracting features from these signals can introduce bias, and second, the performance of classification models can vary greatly depending on the subject of the experiment. This paper proposes a model that reduces bias using convo utional autoencoders, which can represent the key features of data, and enhances generalizability by employing soft voting, a method of ensemble learning, to minimize performance variability. To verify the generalization performance of the model, we evaluate it using LOSO cross-validation method. The model proposed in this paper has demonstrated superior accuracy compared to previous studies using the WESAD dataset.