• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.141-148
• /
• 2009

Recently there have been many research efforts focused on imbalanced data classification problems, since they are pervasive but hard to be solved. Approaches to the imbalanced data problems can be categorized into data level approach using re-sampling, algorithmic level one using cost functions, and ensembles of basic classifiers for performance improvement. As an algorithmic level approach, this paper proposes to use multilayer perceptrons with higher-order error functions. The error functions intensify the training of minority class patterns and weaken the training of majority class patterns. Mammography and thyroid data-sets are used to verify the superiority of the proposed method over the other methods such as mean-squared error, two-phase, and threshold moving methods.

• Journal of KIISE:Information Networking
• /
• v.30 no.6
• /
• pp.755-763
• /
• 2003

To improve performance over noisy wireless channels, mobile wireless networks employ forward error correction(FEC) techniques. The performance of static FEC algorithms, however, degrades by poorly matching the overhead of their correction code to the degree of the fluctuating underlying channel error. This paper proposes an adaptive FEC technique called FECA(FEC-level Adaptation), which dynamically tunes FEC strength to the currently estimated channel error rate at the data link layer. FECA is suitable for wireless networks whose error rate is high and slowly changing compared to the round-trip time between two communicating nodes. One such example network would be a sensor network in which the average bit error rate is higher than $10^{-6}$ and the detected error rate at one time lasts a few hundred milliseconds on average. Our experiments show that FECA performs 15% in simulations with theoretically modeled wireless channels and in trace-driven simulations based on the data collected from real sensor networks better than any other static FEC algorithms.

• Journal of The Korean Association For Science Education
• /
• v.29 no.2
• /
• pp.168-178
• /
• 2009

In this study, we investigated the errors that students committed in the processes of constructing graphs on experimental results by the students' science achievement level. A test of constructing a graph about 'the relationship between the pressure and volume of a gas' was administered to 7th graders (N=145). Results revealed that most students committed errors in the processes of constructing the graph, showing 12 error types in the categories of 'Misinterpreting the variables', 'Mismarking the graphical elements', and 'Misusing the data'. The students in the lower achievement level had more errors than those in the higher achievement level in the two error types, that is 'representing the bar graph' and 'marking the scale in the presented data order', but the results were reversed in the three error types, that is 'marking the independent variable and dependent variable reversely', 'adding the data', and 'neglecting the data'. In the other error types, there were little differences in the frequencies of the errors by students' science achievement level.

• Journal of Korea Water Resources Association
• /
• v.54 no.7
• /
• pp.485-493
• /
• 2021

Groundwater is an important water resource that can be used along with surface water. In particular, in the case of island regions, research on groundwater level variability is essential for stable groundwater use because the ratio of groundwater use is relatively high. Researches using artificial intelligence models (AIs) for the prediction and analysis of groundwater level variability are continuously increasing. However, there are insufficient studies presenting evaluation criteria to judge the appropriateness of groundwater level prediction. This study comprehensively analyzed the research results that predicted the groundwater level using AIs for various regions around the world over the past 20 years to present the range of allowable groundwater level prediction errors. As a result, the groundwater level prediction error increased as the observed groundwater level variability increased. Therefore, the criteria for evaluating the adequacy of the groundwater level prediction by an AI is presented as follows: less than or equal to the root mean square error or maximum error calculated using the linear regression equations presented in this study, or NSE ≥ 0.849 or R² ≥ 0.880. This allowable prediction error range can be used as a reference for determining the appropriateness of the groundwater level prediction using an AI.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.967-977
• /
• 2022

The occurrence and intensity of wildfires are increasing with climate change. Emissions from forest fire smoke are recognized as one of the major causes affecting air quality and the greenhouse effect. The use of satellite product and machine learning is essential for detection of forest fire smoke. Until now, research on forest fire smoke detection has had difficulties due to difficulties in cloud identification and vague standards of boundaries. The purpose of this study is to detect forest fire smoke using Level 1 and Level 2 data of Geostationary Environment Monitoring Spectrometer (GEMS), a Korean environmental satellite sensor, and machine learning. In March 2022, the forest fire in Gangwon-do was selected as a case. Smoke pixel classification modeling was performed by producing wildfire smoke label images and inputting GEMS Level 1 and Level 2 data to the random forest model. In the trained model, the importance of input variables is Aerosol Optical Depth (AOD), 380 nm and 340 nm radiance difference, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), formaldehyde (HCHO), nitrogen dioxide (NO₂), 380 nm radiance, and 340 nm radiance were shown in that order. In addition, in the estimation of the forest fire smoke probability (0 ≤ p ≤ 1) for 2,704 pixels, Mean Bias Error (MBE) is -0.002, Mean Absolute Error (MAE) is 0.026, Root Mean Square Error (RMSE) is 0.087, and Correlation Coefficient (CC) showed an accuracy of 0.981.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.528-536
• /
• 2011

In this paper, we analyze the location accuracy of real-time locating systems (RTLSs) in multipath environments in which the RTLSs comply with the ISO/IEC 24730-2 international standard. To analyze the location error of RTLS in multipath environments, we consider a direct path and indirect path, in which time and phase are delayed, and also white Gaussian noise is added. The location error depends strongly on both the noise level and phase difference under a low signal-to-noise ratio (SNR) regime, but only on the noise level under a high SNR regime. The phase difference effect can be minimized by matching it to the time delay difference at a ratio of 180 degrees per 1 chip time delay (Tc). At a relatively high SNR of 10 dB, a location error of less than 3 m is expected at any phase and time delay value of an indirect signal. At a low SNR regime, the location error range increases to 8.1 m at a 0.5 Tc, and to 7.3 m at a 1.5 Tc. However, if the correlation energy is accumulated for an 8-bit period, the location error can be reduced to 3.9 m and 2.5 m, respectively.

• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.563-572
• /
• 2002

Wireless mobile networks tend to drop a large portion of packets due to propagation errors rather than congestion. To Improve reliability over noisy wireless channels, wireless networks can employ forward error correction (FEC) techniques. Static FEC algorithms, however, can degrade the performance by poorly matching their overhead to the degree of the underlying channel error, especially when the channel path loss rate fluctuates widely. This paper investigates the benefits of an adaptable FEC mechanism for wireless networks with severe packet loss by analytical analysis or measurements over a real wireless network called sensor network. We show that our adaptive FEC named FECA (FEC-level Adaptation) technique improves the performance by dynamically tuning FEC strength to the current amount of wireless channel loss. We quantify these benefits through a hybrid simulation integrating packet-level simulation with bit-level details and validate that FECA keeps selecting the appropriate FEC-level for a constantly changing wireless channel.

• Journal of Elementary Mathematics Education in Korea
• /
• v.14 no.3
• /
• pp.885-905
• /
• 2010

This study questions that mathematical evaluations strive to memorize fragmentary knowledge and have an objective test. To solve these problems on mathematical education We did descriptive test. Through the descriptive test, students think and express their ideas freely using mathematical terms. We want to know if that procedure is correct or not, and, if they understand what was being presented. We studied this because We want to analyze where and what kinds of faults they committed, and be able to correct an error so as to establish a correct mathematical concept. The result from this study can be summarized as the following; First, the mistakes students make when solving the descriptive tests can be divided into six things: error of question understanding, error of concept principle, error of data using, error of solving procedure, error of recording procedure, and solving procedure omissions. Second, students had difficulty with the part of the descriptive test that used logical thinking defined by mathematical terms. Third, errors pattern varied as did students' ability level. For high level students, there were a lot of cases of the solving procedure being correct, but simple calculations were not correct. There were also some mistakes due to some students' lack of concept understanding. For middle level students, they couldn't understand questions well, and they analyzed questions arbitrarily. They also have a tendency to solve questions using a wrong strategy with data that only they can understand. Low level students generally had difficulty understanding questions. Even when they understood questions, they couldn't derive the answers because they have a shortage of related knowledge as well as low enthusiasm on the subject.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.176-179
• /
• 2003

This study was conducted to extract the feature set of English writing error for suggesting adequate English writing program and making automated scoring system. The frequent committed error and the error across the level of writing proficiency were reported. Also, It is reported that the correlation between type of error and native speaker's rating score.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.39 no.7
• /
• pp.12-21
• /
• 2002

In this paper, we propose a new hybrid ARQ scheme to consider real-time and non real-time services in a wireless ATM network. Real-time and non-real-time services require different error control schemes according to each service characteristics. Therefore, in the next generation mobile communication environments where these service scenarios should be deployed, hybrid ARQ scheme using RCPC code with variable coding rate becomes one of the most suitable solutions. Because the variable coding rate is applied according to traits of transmitted frame and channel status, hybrid ARQ scheme using RCPC code can expect UEP effect. The UEP scheme does not apply equal error protection level to all information, but does high error protection level to more important information. In Our scheme, UEP of high error protection level is applied to real-time service, and UEP of low error protection and retransmission techniques are applied to non real-time service. We show that the proposed hybrid ARQ scheme improves channel utilization efficiency and yields high error correction behaviors.