• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.233-242
• /
• 2018

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting feature point based on only R peak through optimal R wave. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30. The achieved scores indicate the average of 99.02% in R wave detection and the rate of 94.85% in PVC classification.

• Journal of Environmental Health Sciences
• /
• v.41 no.2
• /
• pp.90-101
• /
• 2015

Objective: This study was conducted to develop a chemical oxygen demand (COD) regression model using water quality monitoring data (January, 2014) obtained from the Han River auto-monitoring stations. Methods: Surface water quality data at 198 sampling stations along the six major areas were assembled and analyzed to determine the spatial distribution and clustering of monitoring stations based on 18 WQPs and regression modeling using selected parameters. Statistical techniques, including combined genetic algorithm-multiple linear regression (GA-MLR), cluster analysis (CA) and principal component analysis (PCA) were used to build a COD model using water quality data. Results: A best GA-MLR model facilitated computing the WQPs for a 5-descriptor COD model with satisfactory statistical results ($r^2=92.64$,$Q{^2}_{LOO}=91.45$,$Q{^2}_{Ext}=88.17$). This approach includes variable selection of the WQPs in order to find the most important factors affecting water quality. Additionally, ordination techniques like PCA and CA were used to classify monitoring stations. The biplot based on the first two principal components (PCs) of the PCA model identified three distinct groups of stations, but also differs with respect to the correlation with WQPs, which enables better interpretation of the water quality characteristics at particular stations as of January 2014. Conclusion: This data analysis procedure appears to provide an efficient means of modelling water quality by interpreting and defining its most essential variables, such as TOC and BOD. The water parameters selected in a COD model as most important in contributing to environmental health and water pollution can be utilized for the application of water quality management strategies. At present, the river is under threat of anthropogenic disturbances during festival periods, especially at upstream areas.

• Journal of Power Electronics
• /
• v.16 no.2
• /
• pp.717-730
• /
• 2016

The harmonic components of grid voltage result in oscillations of the calculated phase obtained via phase synchronization. This affects the security and stability of grid-connected converters. Moving average filter, delayed signal cancellation and their related harmonic elimination algorithms are major methods for such issues. However, all of the existing methods have their limitations in dealing with multiple harmonics issues. Furthermore, few studies have focused on a comparison and evaluation of these algorithms to achieve optimal algorithm selections in specific applications. In this paper, these algorithms are quantitatively analyzed based on the derived mathematical models. Moreover, an enhanced moving average filter and enhanced delayed signal cancellation algorithms, which are applicable for eliminating a group of selective harmonics with only one calculation block, are proposed. On this basis, both a comprehensive comparison and a quantitative evaluation of all of the aforementioned algorithms are made from several aspects, including response speed, required data storage size, sensitivity to sampling frequency, and elimination of random noise and harmonics. With the conclusions derived in this paper, better overall performance in terms of harmonic elimination can be achieved. In addition, experimental results under different conditions demonstrate the validity of this study.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.253-260
• /
• 2012

Target detection is very difficult with complex clutters in IRST(Infrared Search and Track) system for a long distance target. Especially sea-clutter and ocean-surface with non-uniform temperature distribution make it difficult to detect incoming targets in images obtained in sea environment. In this paper, we propose a novel method based on morphological method for estimation of ocean surface with non-uniform temperature flow. In order to estimate the exact ocean surface temperature flow, we divided it into upper and lower bound flow. And after estimating it, the final ocean surface temperature flow is derived by a mean value of the estimated results. Also, we apply the multi-weighted technique with a variety of sizes of structure elements to overcome sub-sampling effect by using morphology method. Experimental results for ocean surface images acquired from many different environments are compared with results of existing method to verify the performance of the proposed methods.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.859-868
• /
• 2004

We propose a method of selecting initial training examples for active learning so that it can reach high accuracy faster with fewer further queries. Our method is based on the assumption that an active learner can reach higher performance when given an initial training set consisting of diverse and typical examples rather than similar and special ones. To obtain a good initial training set, we first cluster examples by using k-means clustering algorithm to find groups of similar examples. Then, a representative example, which is the closest example to the cluster's centroid, is selected from each cluster. After these representative examples are labeled by querying to the user for their categories, they can be used as initial training examples. We also suggest a method of using the centroids as initial training examples by labeling them with categories of corresponding representative examples. Experiments with various text data sets have shown that the active learner starting from the initial training set selected by our method reaches higher accuracy faster than that starting from randomly generated initial training set.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.328-338
• /
• 2017

In this paper, a zero torque control scheme adopting current sharing function (CSF) used in integrated Switched Reluctance Motor (SRM) drive with DC battery charger is proposed. The proposed control scheme is able to achieve the keeping position (KP), zero torque (ZT) and power factor correction (PFC) at the same time with a simple novel current sharing function algorithm. The proposed CSF makes the proper reference for each phase windings of SRM to satisfy the total charging current of the battery with zero torque output to hold still position with power factor correction, and the copper loss minimization during of battery charging is also achieved during this process. Based on these, CSFs can be used without any recalculation of the optimal current at every sampling time. In this proposed integrated battery charger system, the cost effective, volume and weight reduction and power enlargement is realized by function multiplexing of the motor winding and asymmetric SR converter. By using the phase winding as large inductors for charging process, and taking the asymmetric SR converter as an interleaved converter with boost mode operation, the EV can be charged effectively and successfully with minimum integral system. In this integral system, there is a position sliding mode controller used to overcome any uncertainty such as mutual inductance or DC offset current sensor. Power factor correction and voltage adaption are obtained with three-phase buck type converter (or current source rectifier) that is cascaded with conventional SRM, one for wide input and output voltage range. The practicability is validated by the simulation and experimental results by using a laboratory 3-hp SRM setup based on TI TMS320F28335 platform.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.7
• /
• pp.764-770
• /
• 2019

In this research, text mining techniques were used to analyze the papers related to the "4th Industry". In order to analyze the papers, total of 685 papers were collected by searching with the keyword "4th industry" in Korea Journal Index(KCI) from 2016 to 2019. We used Python-based web scraping program to collect papers and use topic modeling techniques based on LDA algorithm implemented in R language for data analysis. As a result of perplexity analysis on the collected papers, nine topics were determined optimally and nine representative topics of the collected papers were extracted using the Gibbs sampling method. As a result, it was confirmed that artificial intelligence, big data, Internet of things(IoT), digital, network and so on have emerged as the major technologies, and it was confirmed that research has been conducted on the changes due to the major technologies in various fields related to the 4th industry such as industry, government, education field, and job.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.455-464
• /
• 2022

There are two unique characteristics of the datasets from a manufacturing process. They are the severe class imbalance and lots of Out-of-Distribution samples. Some good strategies such as the oversampling over the minority class, and the down-sampling over the majority class, are well known to handle the class imbalance. In addition, SMOTE has been chosen to address the issue recently. But, Out-of-Distribution samples have been studied just with neural networks. It seems to be hardly shown that Out-of-Distribution detection is applied to the predictive model using conventional machine learning algorithms such as SVM, Random Forest and KNN. It is known that conventional machine learning algorithms are much better than neural networks in prediction performance, because neural networks are vulnerable to over-fitting and requires much bigger dataset than conventional machine learning algorithms does. So, we suggests a new approach to utilize Out-of-Distribution detection based on SVM algorithm. In addition to that, bagging technique will be adopted to improve the precision of the model.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• The KIPS Transactions:PartC
• /
• v.19C no.4
• /
• pp.239-246
• /
• 2012

The function of location estimation in WPAN has been studied and specified on the ultra wide band optionally. But the devices based on CSS(Chirp Spread Spectrum) specification has been used widely in the market because of its functionality, cheapness and support of development. As the CSS device uses 2.4GHz for a carrier frequency and the sampling frequency is lower than that of the UWB, the resolution of a timestamp is very coarse. Then actually the error of a measured distance is very large about 30cm~1m at 10 m depart. And the location error in ($10m{\times}10m$) environment is known as about 1m~2m. So for some applications which require more accurate location information, it is very natural and important to develop a sophisticated post processing algorithm after distance measurements. In this paper, we have studied extended Kalman filter with the frequency offsets of anchor nodes, and proposed a novel algorithm frequency offset compensated extended Kalman filter. The frequency offsets are composed with a variable as a common frequency offset and constants as individual frequency offsets. The proposed algorithm shows that the accurate location estimation, less than 10cm distance error, with CSS WPAN nodes is possible practically.