• Journal of The Korean Society of Integrative Medicine
• /
• v.12 no.2
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.535-542
• /
• 2013

Since case-based reasoning(CBR) has many advantages, it has been used for supporting decision making in various areas including medical checkup, production planning, customer classification, and so on. However, there are several factors to be set by heuristics when designing effective CBR systems. Among these factors, this study addresses the issue of selecting appropriate neighbors in case retrieval step. As the criterion for selecting appropriate neighbors, conventional studies have used the preset number of neighbors to combine(i.e. k of k-nearest neighbor), or the relative portion of the maximum similarity. However, this study proposes to use the absolute similarity threshold varying from 0 to 1, as the criterion for selecting appropriate neighbors to combine. In this case, too small similarity threshold value may make the model rarely produce the solution. To avoid this, we propose to adopt the coverage, which implies the ratio of the cases in which solutions are produced over the total number of the training cases, and to set it as the constraint when optimizing the similarity threshold. To validate the usefulness of the proposed model, we applied it to a real-world target marketing case of an online shopping mall in Korea. As a result, we found that the proposed model might significantly improve the performance of CBR.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.83-97
• /
• 2021

Wireless sensors that make up the Wireless Sensor Network generally have extremely limited power and resources. The wireless sensor enters the sleep state at a certain interval to conserve power. The Sleep deflation attack is a deadly attack that consumes power by preventing wireless sensors from entering the sleep state, but there is no clear countermeasure. Thus, in this paper, using clustering-based binary search tree structure, the Sleep deprivation attack detection model is proposed. The model proposed in this paper utilizes one of the characteristics of both attack sensor nodes and normal sensor nodes which were classified using machine learning. The characteristics used for detection were determined using Long Short-Term Memory, Decision Tree, Support Vector Machine, and K-Nearest Neighbor. Thresholds for judging attack sensor nodes were then learned by applying the SVM. The determined features were used in the proposed algorithm to calculate the values for attack detection, and the threshold for determining the calculated values was derived by applying SVM.Through experiments, the detection model proposed showed a detection rate of 94% when 35% of the total sensor nodes were attack sensor nodes and improvement of up to 26% in power retention.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Korean Journal of Psychosomatic Medicine
• /
• v.31 no.2
• /
• pp.108-117
• /
• 2023

Objectives : Somatic symptom disorder (SSD) is characterized by the manifestation of a variety of physical symptoms, but little is known about differences in autonomic nervous system activity according to symptom severity, especially within patient groups. In this study, we examined differences in heart rate variability (HRV) across symptom severity in a group of SSD patients to analyze a representative marker of autonomic nervous system changes by symptoms severity. Methods : Medical records were retrospectively reviewed for patients who were diagnosed with SSD based on DSM-5 from September 18, 2020 to October 29, 2021. We applied inverse probability of treatment weighting (IPTW) methods to generate more homogeneous comparisons in HRV parameters by correcting for selection biases due to sociodemographic and clinical characteristic differences between groups. Results : There were statistically significant correlations between the somatic symptom severity and LF (nu), HF (nu), LF/HF, as well as SD1/SD2 and Alpha1/Alpha2. After IPTW estimation, the mild to moderate group was corrected to 27 (53.0%) and the severe group to 24 (47.0%), and homogeneity was achieved as the differences in demographic and clinical characteristics were not significant. The analysis of inverse probability weighted regression adjustment model showed that the severe group was associated with significantly lower RMSSD (β=-0.70, p=0.003) and pNN20 (β=-1.04, p=0.019) in the time domain and higher LF (nu) (β=0.29, p<0.001), lower HF (nu) (β=-0.29, p<0.001), higher LF/HF (β=1.41, p=0.001), and in the nonlinear domain, significant differences were tested for SampEn15 (β=-0.35, p=0.014), SD1/SD2 (β=-0.68, p<0.001), and Alpha1/Alpha2 (ß=0.43, p=0.001). Conclusions : These results suggest that differences in HRV parameters by SSD severity were showed in the time, frequency and nonlinear domains, specific parameters demonstrating significantly higher sympathetic nerve activity and reduced ability of the parasympathetic nervous system in SSD patients with severe symptoms.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.8 no.1
• /
• pp.14-22
• /
• 1972

For the development of acoustic fishing method, the noises of fishes have been recorded and analy/'ed by many scientists. Some specimens of fishes were selected as such Cyprinus carpio, Ctenopharyngodon idellus Carassius carassius, and pagrosol1ms major in this experiment. The noises such as feeding noise, driving away noise, jumping noise and fi llip noise were recorded by the tape recorder, Sony Model 262, through the underwa te r microph I one, Oki ST 6582, and analyzed in frequencies bv octave band analyzer, Rion SA-55, and sound pressure level of source by sound level meter, Rion NA-opNN The supplied feed was placed within 5em apart from the hydrophone. The result of analyzed noises were as follow. Cyprinus carjJio; Feeding noise 250- 500 cps, 92- 99 dB Driving away noise 125-2, 000 eps, 101-112 dB Jumping noise 125-2, 000 eps, 99-116.5 dB Ctenopharyngodon idcllus; Driving away noise 125-1, 000 cps, 96-109 dB Carassius carassius; Feeding noise 250- 500 cps, 91. 5- 99.5 dB Driving away noise 125-1, 000 eps, 99-108 dB Carassius auratus Feeding noise 250 eps, 94-101 dB Driving away noise 125-1, 000 cps, 98-110 dB Pagrosomus major Feeding noise 230-500 cps, 90-101 dB Fillip noise 500 cps, 98-108 dB (1) Feeding noise was produced as like as snap noise of twig and gulping down saliva noise in human and dominant frequency range of the noise is 250-500 cps and noise level 90-101 dB. (2) It was found that feeding noise were not a monotonic but a complex tones though fish took the same food. (3) Driving away noise was produced not so keen and the wave form of the noise is rising very sharp and big amplitude in the oscillograph. Dominant frequency range of this noise was about 150-1, 000 cps and noise level 96-112 dB except thut of carp. (4) The frequency of snapper's fillip noise, when it produced by caudal fin in swimming at the surface of water, was 500 cps and noise level 93-108 dB snd that of jumping noise of carp about 150-2, 000 cps and noise level 99-116.5 dB.

• The Korean Journal of Physiology and Pharmacology
• /
• v.12 no.3
• /
• pp.101-109
• /
• 2008

The aim of the present study was to examine the effects of ketamine, a dissociative anesthetics, on secretion of catecholamines (CA) secretion evoked by cholinergic stimulation from the perfused model of the isolated rat adrenal gland, and to establish its mechanism of action, and to compare ketamine effect with that of thiopental sodium, which is one of intravenous barbiturate anesthetics. Ketamine ($30{\sim}300{\mu}M$), perfused into an adrenal vein for 60 min, dose- and time-dependently inhibited the CA secretory responses evoked by ACh (5.32 mM), high $K^+$ (a direct membrane-depolarizer, 56 mM), DMPP (a selective neuronal nicotinic NN receptor agonist, $100{\mu}M$) and McN-A-343 (a selective muscarinic M1 receptor agonist, $100{\mu}M$). Also, in the presence of ketamine ($100{\mu}M$), the CA secretory responses evoked by veratridine (a voltage-dependent $Na^+$ channel activator, $100{\mu}M$), Bay-K-8644 (an L-type dihydropyridine $Ca^{2+}$ channel activator, $10{\mu}M$), and cyclopiazonic acid (a cytoplasmic $Ca^{2+}$-ATPase inhibitor, $10{\mu}M$) were significantly reduced, respectively. Interestingly, thiopental sodium ($100{\mu}M$) also caused the inhibitory effects on the CA secretory responses evoked by ACh, high $K^+$, DMPP, McN-A-343, veratridine, Bay-K-8644, and cyclopiazonic acid. Collectively, these experimental results demonstrate that ketamine inhibits the CA secretion evoked by stimulation of cholinergic (both nicotinic and muscarinic) receptors and the membrane depolarization from the isolated perfused rat adrenal gland. It seems likely that the inhibitory effect of ketamine is mediated by blocking the influx of both $Ca^{2+}$ and $Na^+$ through voltage-dependent $Ca^{2+}$ and $Na^+$ channels into the rat adrenal medullary chromaffin cells as well as by inhibiting $Ca^{2+}$ release from the cytoplasmic calcium store, which are relevant to the blockade of cholinergic receptors. It is also thought that, on the basis of concentrations, ketamine causes similar inhibitory effect with thiopental in the CA secretion from the perfused rat adrenal medulla.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of Korea Water Resources Association
• /
• v.52 no.2
• /
• pp.141-148
• /
• 2019

When simulating the daily rainfall amount by existing Markov Chain model, it is general to simulate the rainfall occurrence and to estimate the rainfall amount randomly from the distribution which is similar to the daily rainfall distribution characteristic using Monte Carlo simulation. At this time, there is a limitation that the characteristics of rainfall intensity and distribution by time according to the rainfall duration are not reflected in the results. In this study, 1-day, 2-day, 3-day, 4-day rainfall event are classified, and the rainfall amount is estimated by rainfall duration. In other words, the distributions of the total amount of rainfall event by the duration are set using the Kernel Density Estimation (KDE), the daily rainfall in each day are estimated from the distribution of each duration. Total rainfall amount determined for each event are divided into each daily rainfall considering the type of daily distribution of the rainfall event which has most similar rainfall amount of the observed rainfall using the k-Nearest Neighbor algorithm (KNN). This study is to develop the limitation of the existing rainfall estimation method, and it is expected that this results can use for the future rainfall estimation and as the primary data in water resource design.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.163-170
• /
• 2019

Over the past decade, the development of the Web explosively increased the data. Feature selection step is an important step in extracting valuable data from a large amount of data. This study proposes a novel opinion mining model based on combining feature selection (FS) methods with Word embedding to vector (Word2vec) and BOW (Bag-of-words). FS methods adopted for this study are CFS (Correlation based FS) and IG (Information Gain). To select an optimal FS method, a number of classifiers ranging from LR (logistic regression), NN (neural network), NBN (naive Bayesian network) to RF (random forest), RS (random subspace), ST (stacking). Empirical results with electronics and kitchen datasets showed that LR and ST classifiers combined with IG applied to BOW features yield best performance in opinion mining. Results with laptop and restaurant datasets revealed that the RF classifier using IG applied to Word2vec features represents best performance in opinion mining.