• The Korean Journal of Applied Statistics
• /
• v.28 no.3
• /
• pp.495-509
• /
• 2015

We study a classification problem of significant differences in the proportion of two groups known as the unbalanced classification problem. It is usually more difficult to classify classes accurately in unbalanced data than balanced data. Most observations are likely to be classified to the bigger group if we apply classification methods to the unbalanced data because it can minimize the misclassification loss. However, this smaller group is misclassified as the larger group problem that can cause a bigger loss in most real applications. We compare several classification methods for the unbalanced data using sampling techniques (up and down sampling). We also check the total loss of different classification methods when the asymmetric loss is applied to simulated and real data. We use the misclassification rate, G-mean, ROC and AUC (area under the curve) for the performance comparison.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.11 no.3
• /
• pp.241-248
• /
• 2001

The main factors of breakthrough are known to sampling time, flow rate, concentration of the sample, temperature, humidity, and the physical characteristics of the solid sorbent tube. However, no study has been reported the effect of temperature and sampling volume on the breakthrough of acharcoal tube during vinyl chloride monomer (VCM) sampling. The objective of this study is to suggest the optimal sampling condition during VCM sampling based on National Institute for Occupational Safety and Health (NIOSH) method. To evaluate adequate sampling volume for VCM without breakthrough, volume of 1, 2, 3, 4, and 5 L each from VCM of 1, 5, 10, 15, and 20ppm at flow rate of 0.05 L/min were sampled in $22^{\circ}C$ and $40^{\circ}C$. At $22^{\circ}C$, in the case of 1, 5, 10, and 15ppm, VCM was adsorbed completely in first section of charcoal tube regardless of sampling volume. But in 20ppm, detection rates are 99.56% in first section and 0.44% in second section. At $40^{\circ}C$ of 1ppm, VCM was adsorbed completely in first section. In 10, 15, and 20ppm, detection rates of second, third, and forth sections were decreased significantly by reduction of sampling volume. In determination of breakthrough based on NIOSH method, no breakthrough was occurred in 20ppm at $22^{\circ}C$. At $40^{\circ}C$, breakthrough was occurred in 10, 15, and 20ppm when sampling volume was 5L. Although no breakthrough was occurred when sampling volume was 3L. Finally, in environment of temperature around $22^{\circ}C$, breakthrough may not occurred up to 20ppm during sampling for VCM. During sampling for VCM in environment of temperature around $40^{\circ}C$, no breakthrough occurred in 1-5ppm and 10-20ppm when sampling volume is 5L and 3L respectively. This result suggests that the sampling volume should be considered when VCM sampling under hot conditions (> $22^{\circ}C$) by the NIOSH method No. 1007.

• Spatial Information Research
• /
• v.8 no.1
• /
• pp.171-182
• /
• 2000

Random sampling or systematic sampling method is commonly used to assess the accuracy of classification results. In remote sensing, with these sampling method, much time and tedious works are required to acquire sufficient ground truth data. So , a more effective sampling method that can retain the characteristics of the population is required. In this study, fractal analysis is adopted as an index for reference sampling . The fractal dimensions of the whole study area and the sub-regions are calculated to choose sub-regions that have the most similar dimensionality to that of whole-area. Then the whole -area s classification accuracy is compared to those of sub-regions, respectively, and it is verified that the accuracies of selected sub regions are similar to that of full-area . Using the above procedure, a new kind of reference sampling method is proposed. The result shows that it is possible to reduced sampling area and sample size keeping up the same results as existing methods in accuracy tests. Thus, the proposed method is proved cost-effective for reference data sampling.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.169-176
• /
• 2008

This study was intended to analyze difference of vocal folds movements between upon wakeup and in several hours later in the morning. The difference of vocal fold movements was compared with fundamental frequency and a range of fundamental frequencies from maximum to minimum. The participants were 30 female adults between 20 and 29 years old. Voice samples were collected from their reading sentence (Jeong, 1993). The first sampling was conducted within 5 minutes after wakeup, while the second on 1 hour after the first sampling. Finally, the third voice sample was collected on 6 hours after the second sampling. The results of this study were as follows: First, fundamental frequency of the participants were by hour significantly time-dependent(F=7.843). Post-hoc multiple comparison (LSD) was conducted to determine when the difference could be observed. The result showed significant differences between upon wakeup and 6 hours later (p< .001) and between 1 hour later and 6 hours later (p< .05). Second, there were a significantly time-dependent ranges of fundamental frequencies of participants by hour (F=3.130). According to the results of the LSD analysis the significant differences in range of fundamental frequencies were found between upon wakeup and 1 hour later and also between wakeup and 6 hours later (p< .05). The results above indicate that vocal fold movements upon wakeup is different from those of several hours later.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.6 no.4
• /
• pp.286-292
• /
• 2006

This paper presents the design of a low-voltage wide-band switched-capacitor (SC) filter for wireless communication receiver applications. The filter is the 5th-order Elliptic lowpass filter. With the clock frequency of 50MHz implying that an effective sampling frequency is 100MHz with double sampling scheme, the cut-off frequency of the filter is programmable to be 1.25MHz, 2.5MHz, 5MHz and 10MHz. For low-power systems powered by a single-cell battery, the SC filter was elaborately designed to operate at 1.2V power supply. Simulation result shows that the 3rd-order input intercept point (IIP3) can be up to 27dBm. The filter was fabricated in a $0.25-{\mu}m$ 1P5M standard CMOS technology and measured frequency responses show good agreement with the simulation ones. The current consumption is 34mA at a 1.2V power supply.

• Journal of Environmental Science International
• /
• v.18 no.10
• /
• pp.1079-1088
• /
• 2009

The statistics of monitoring on soil quality is a report statistics which is made on the basis of Article 15, Environment Strategy Basic Law and Article 5, Soil Environment Conservation Law. This study was conducted according to quality assessment of Korea National Statistical Office. The assessment of quality infrastructure advised that the authority bring up and increase completely responsible officer and secure the budget. The assessment of user satisfaction and reflection of request propose that the statistics is focused on soil background concentration, decrease soil sampling points and extend survey period. The assessment of error management system per processes of detailed preparation suggest change of the statistics objective, a reduction of sampling points and improvement of survey period and soil measurement properties. Accuracy assessment of data proposed cuts of sampling points, accessibility increment and build up of management system linking subordinates and Ministry of Environment. The substantiality assessment of data service demonstrated information environment improvement for users including reference expression and records of statistics table and figure contents.

• Economic and Environmental Geology
• /
• v.25 no.2
• /
• pp.145-151
• /
• 1992

In order to study the optimum depth for the soil geochemical exploration in the area which is affected by agricultural activities and waste disposal of metal mine, the soil samples were sampled from the B layer of residual soil and vertical 7 layers up to 250 cm in the rice field and 3 layers up to 90 cm in the ordinary field. They were analyzed for Au, As, Cu, Pb and Zn by AAS, AAS-graphite furnace and ICP. To investigate the proper depth for the soil sampling in the contaminated area, the data were treated statistically by applying correlation coefficient, factor analysis and trend analysis. It is conclude that soil geochemical exploration method could be applied in the farm-land and a little contaminated area. The optimum depth of soil sampling is 60 cm in the ordinary field, and 150~200 cm in the rice field. Soil sampling in the area of a huge mine waste disposal is not recommendable. Plotting of geochemical map with factor scores as a input data shows a clear pattern compared with the map of indicater element such as As or Au. The second or third degree trend surface analysis is effective in inferring the continuity of vein in the area where the outcrop is invisible.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.14 no.24
• /
• pp.187-192
• /
• 1991

We consider a filling process problem on a production line. Up to present this problem have examined by 100% inspection. Thus a target value is determined which takes into account the regular selling prices, the reprocess cost, the excess quality cost and the process variability and so on. However, in this paper we propose a solution under specified sampling plan when the inspection is nondestructive.

• Journal of the Korean Society of Systems Engineering
• /
• v.11 no.1
• /
• pp.55-65
• /
• 2015

In steel making plant, sampling system for raw material such as iron ore, limestone is necessary for quality control purpose. For the sake of efficiency and productivity, automation of the sampling system is highly desirable. From technical standpoint, the development of the automated system requires multi-disciplinary domain knowledge such as mechanical engineering, industrial engineering, information technology and computer engineering. Up to present time, the development has been mainly carried out by a single domain expert with project manager. The automated system developed in this way caused problems in the final system. This paper suggests a systems engineering approach to the development of automation for raw material sampling plant via a tailored process called Plant Systems Engineering (PSE) Process based on ISO/IEC 15288. Through the PSE process, we could derive right requirements and architecture of the Systems Of Interest (SOI), and we were convinced that the PSE Process can be applied to many other Plant Systems.

• ETRI Journal
• /
• v.33 no.3
• /
• pp.326-334
• /
• 2011

This paper outlines the time jitter effect of a sampling clock on a software-defined radio technology-based digital intermediate frequency (IF) transceiver for a mobile communication base station. The implemented digital IF transceiver is reconfigurable to high-speed data packet access (HSDPA) and three bandwidth profiles: 1.75 MHz, 3.5 MHz, and 7 MHz, each incorporating the IEEE 802.16d worldwide interoperability for microwave access (WiMAX) standard. This paper examines the relationship between the signal-to-noise ratio (SNR) characteristics of a digital IF transceiver with an under-sampling scheme and the sampling jitter effect on a multichannel orthogonal frequency-division multiplexing (OFDM) signal. The simulation and experimental results show that the SNR of the OFDM system with narrower band profiles is more susceptible to sampling clock jitter than systems with relatively wider band profiles. Further, for systems with a comparable bandwidth, HSDPA outperforms WiMAX, for example, a 5 dB error vector magnitude improvement at 15 picoseconds time jitter for a bandwidth of WiMAX 3.5 MHz profile.