• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.117-135
• /
• 2003

This study is to propose a procedure solving scale problem of traditional collaborative filtering (CF) approach. The CF approach generally uses some similarity measures like correlation coefficient. So, as the user of the Website increases, the complexity of computation increases exponentially. To solve the scale problem, this study suggests a clustering model-based approach using Self-Organizing Map (SOM) and RFM (Recency, Frequency, Momentary) method. SOM clusters users into some user groups. The preference score of each item in a group is computed using RFM method. The items are sorted and stored in their preference score order. If an active user logins in the system, SOM determines a user group according to the user's characteristics. And the system recommends items to the user using the stored information for the group. If the user evaluates the recommended items, the system determines whether it will be updated or not. Experimental results applied to MovieLens dataset show that the proposed method outperforms than the traditional CF method comparatively in the recommendation performance and the computation complexity.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.174-180
• /
• 2007

In the tone reservation (TR) scheme, it is known that the set of randomly selected peak reduction tones (PRT's) performs better than the contiguous PRT set and the interleaved PRT set in the PAPR reduction of orthogonal frequency division multiplexing (OFDM). It is also known that finding the optimal PRT set corresponds to the secondary peak minimization problem in the TR scheme. However, the problem cannot be solved for the practical number of tones since it is NP-hard. In this paper, a new search algorithm for the near optimal PRT set is proposed based on the fact that the secondary peak value of the PRT set statistically tends to decrease asthe variance of the PRT set decreases.

• Journal of the Korean Society of School Health
• /
• v.20 no.1
• /
• pp.103-111
• /
• 2007

Purpose : The purpose of this study was to investigate the effects of stresses to female university students and their habits of dealing with stresses through drinking alcohol and smoking. Methods : Subjects, 313 students, were selected through convenience sampling method from the 2 four-year universities in Chonbuk and Chonnam province from May to June, 2005. Data were collected through the structured questionnaires that include general characteristics, Quantity Frequency methods, the number of cigarette per day, campus stress scale, and stress coping style scale, and they were analyzed by Cronbach' alpha, descriptive statistics, ANOVA and t-test by using SPSS/PC⁺ program. Results: In this study, 80% of subjects have drunk alcohol. The mean frequency of drinking alcohol per month was 4.68 times and the mean number of alcohol consumption amount per drinking 6.16 glasses. The rate of smoking was 13.7%, and the mean number smoking cigarette per day in the previous month was 12.4. The mean score of stress was 2.20. Among 8 sub-factors of stress, study related stress scored highest among the sub-factors. The mean score of coping styles was 2.50. Among 4 coping styles, hopeful thought was mostly used. Among stresses, the concern of one's future affected her drinking habits. Faculty relationship, academic problem, and value affected smoking habits. Hopeful thought comes out to affect smoking, while drinking, perceived health status, and practice time showed no relationship with coping style. Conclusion: Based on the results, developing a life stress counseling program and effective coping program for women's university students is imperative, especially for those of who show passive attitude toward stress and solve it emotionally instead of using problem-oriented methods. Also, it will be necessary to study further nursing intervention to curb university females' drinking alcohol and smoking.

• Composites Research
• /
• v.34 no.5
• /
• pp.330-336
• /
• 2021

Alumina powder is one of the widely used materials for industry, but there is a problem that the strength of the product changes depending on the powder packing state. To solve the above problem, previous studies have been conducted to increase the particle packing efficiency, but most of the existing studies analyzed the packing characteristics of millimeter-scale particles, so the physical properties are different from those of the micrometer scale. It is difficult to apply to the micrometer scale. In this paper, a three-step experiment was performed using a statistical method to increase packing using micrometer-scale alumina powder. First, a size combination with high packing and a mixing ratio were selected using the mixture test design method, and an appropriate excitation frequency was selected by analyzing the height change according to the frequency change in the vibration test apparatus. Finally, an alumina powder packing experiment was performed based on the experimental results mentioned above. As a result, it was confirmed that the maximum height variation was 42% higher than the maximum value of the 155 measurements performed when selecting the packing size combination. It is thought that this study will serve as basic data for processing and packing research using fine powder.

• Fire Science and Engineering
• /
• v.33 no.2
• /
• pp.132-138
• /
• 2019

This study examined the drinking status to determine the relationship between the AUDIT-K (Alcohol Use Disorders Identification Test-Korean) and job stress of firefighters. The study subject was 267 firefighters in areas C, K, and P, who were surveyed to investigate their drinking status and job stress. According to the study, the AUDIT-K was 152 people (56.9%) in the normal drinking group and 115 people (43.1%) in the problem drinking group. The most frequent answer of the frequency of drinking was 83 people (31.1%) in the 2-4 times of a month; the amount of drinking was 10 cups or more by 101 people (37.8%) in one sitting; the frequency of heavy drinking was every day in 77 people (28.8%). High group of job stress showed a significantly higher odds ratio with the problem drinking group (OR = 5.458, 95% CI = 1.108-26.886). Among them, the interpersonal relation conflict was found to be a major factor affecting AUDIT-K (OR = .332, 95% CI = .134 - .820). Therefore, their AUDIT-K scores can be lowered by reducing the job stress and interpersonal relation conflicts.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.139-142
• /
• 2009

RFID(Radio Frequency IDentification) technology is an automatic identification method using radio frequencies between RFID reader which collects the information and tag which transmits the information. RFID technology develops passive RFID which transmit the only ID to active RFID which transmit the additional information such as sensing information. However, ISO/IEC 18000-7 as active RFID standard has a problem which cannot use multiple channel. To solve this problem, we use the 2.4GHz bandwidth technology and we propose the dynamic channel allocation method which can efficiently allot a channel. we show the operation of the dynamic channel allocation method through design and implement with CC2500DK of Taxas Instrument.

• Smart Structures and Systems
• /
• v.30 no.1
• /
• pp.75-88
• /
• 2022

Engineering structures in operation essentially belong to time-varying or nonlinear structures and the resultant response signals are usually non-stationary. For such time-varying structures, it is of great importance to extract time-dependent dynamic parameters from non-stationary response signals, which benefits structural health monitoring, safety assessment and vibration control. However, various traditional signal processing methods are unable to extract the embedded meaningful information. As a newly developed technique, variational mode decomposition (VMD) shows its superiority on signal decomposition, however, it still suffers two main problems. The foremost problem is that the number of modal components is required to be defined in advance. Another problem needs to be addressed is that VMD cannot effectively separate non-stationary signals composed of closely spaced or overlapped modes. As such, a new method named generalized adaptive variational modal decomposition (GAVMD) is proposed. In this new method, the number of component signals is adaptively estimated by an index of mean frequency, while the generalized demodulation algorithm is introduced to yield a generalized VMD that can decompose mode overlapped signals successfully. After that, synchrosqueezing wavelet transform (SWT) is applied to extract instantaneous frequencies (IFs) of the decomposed mono-component signals. To verify the validity and accuracy of the proposed method, three numerical examples and a steel cable with time-varying tension force are investigated. The results demonstrate that the proposed GAVMD method can decompose the multi-component signal with overlapped modes well and its combination with SWT enables a successful IF extraction of each individual component.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.9-17
• /
• 2023

In this paper, we propose a one-class vibration anomaly detection system for bearing defect diagnosis. In order to reduce the economic and time loss caused by bearing failure, an accurate defect diagnosis system is essential, and deep learning-based defect diagnosis systems are widely studied to solve the problem. However, it is difficult to obtain abnormal data in the actual data collection environment for deep learning learning, which causes data bias. Therefore, a one-class classification method using only normal data is used. As a general method, the characteristics of vibration data are extracted by learning the compression and restoration process through AutoEncoder. Anomaly detection is performed by learning a one-class classifier with the extracted features. However, this method cannot efficiently extract the characteristics of the vibration data because it does not consider the frequency characteristics of the vibration data. To solve this problem, we propose an AutoEncoder model that considers the frequency characteristics of vibration data. As for classification performance, accuracy 0.910, precision 1.0, recall 0.820, and f1-score 0.901 were obtained. The network design considering the vibration characteristics confirmed better performance than existing methods.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.34 no.3
• /
• pp.175-180
• /
• 2023

Objectives: The coronavirus disease 2019 (COVID-19) pandemic has led to a decrease in face-to-face classes worldwide, affecting the mental health of children and their parents. The global pandemic has increased children's overall use of electronic media. This study analyzed the effect of children's screen time on problematic behaviors during the COVID-19 pandemic. Methods: A total of 186 parents from Suwon, South Korea, were recruited to participate in an online survey. The mean age of the children was 10.14 years old, and 44.1% were females. The questionnaire included questions on children's screen time, problematic behaviors, and parental stress. Children's behavioral problems were evaluated using the Behavior Problem Index, whereas the Parental Stress Scale was used to estimate parental stress. Results: The mean smartphone usage frequency of the children was 5.35 days per week, and the mean smartphone screen time was 3.52 hours per day. Smartphone screen time (Z=4.49, p<0.001) and usage frequency (Z=2.75, p=0.006) were significantly correlated with children's behavioral problem scores. The indirect effect of parental stress on this relationship was also statistically significant (p=0.049, p=0.045, respectively). Conclusion: This study suggests that children's smartphone screen time has affected problematic behaviors during the COVID-19 pandemic. Furthermore, parental stress is related to the relationship between children's screen time and problematic behaviors.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.