• Smart Structures and Systems
• /
• 제33권4호
• /
• pp.253-262
• /
• 2024

Current-based mechanical fault diagnosis is more convenient and low cost since additional sensors are not required. However, it is still challenging to achieve this goal due to the weak fault information in current signals. In this paper, a dual-loss convolutional neural network (DLCNN) is proposed to implement the intelligent bearing fault diagnosis via current signals. First, a novel similarity loss (SimL) function is developed, which is expected to maximize the intra-class similarity and minimize the inter-class similarity in the model optimization operation. In the loss function, a weight parameter is further introduced to achieve a balance and leverage the performance of SimL function. Second, the DLCNN model is constructed using the presented SimL and the cross-entropy loss. Finally, the two-phase current signals are fused and then fed into the DLCNN to provide more fault information. The proposed DLCNN is tested by experiment data, and the results confirm that the DLCNN achieves higher accuracy compared to the conventional CNN. Meanwhile, the feature visualization presents that the samples of different classes are separated well.

• 한국산학기술학회논문지
• /
• 제21권3호
• /
• pp.96-107
• /
• 2020

본 연구는 방사선사를 대상으로 건강신념모델을 적용하여 방사선사 방사선 방어행위 수행도와의 관련 요인을 규명하고자 하였다. 연구대상은 호남지역 내에 근무하는 방사선사 541명을 대상으로 시행되었다. 자료 분석은 SPSS version 18.0 프로그램을 이용하여 t-test, ANOVA, Pearson's correlation, 위계적 다중회귀분석을 하였다. 자료 분석을 실시한 결과는 수정변수에서 교육수준이 높을수록, 일반촬영실 보다는 핵의학검사실 업무 담당자, 신체활동이 많은 경우, 스트레스는 나쁜 경우 보다는 보통인 경우, 방어시설이 좋을수록 방사선 방어행위 수행도가 높았다. 개인의 인지에서 행동계기(β=.292, p<.001), 인지된 심각성(β=.075, p=.010)이 방사선 방어행위 수행도에 영향을 미치는 요인이었다. 행위가능성은 유익성(β=.168, p<.001), 자기효능감(β=.148, p=.007)이 높을수록 방사선 방어행위 수행도가 높았다. 결론적으로 적절한 행동계기가 방어행위에 수행하도록 자극을 줄 수 있는 방어교육을 제공하고, 방사선 방어행위에 있어서 이익을 부각시키는 한편, 높은 수준의 자기효능감을 강화시켜 방어행위 수행도를 높일 필요가 있다. 또한, 방사선에 대한 심각성을 제대로 인지할 수 있도록 관련 정보를 제공하면, 궁극적으로 방사선사의 방사선 방어행위 수행도가 증가할 것이다.

• 여성건강간호학회지
• /
• 제26권1호
• /
• pp.10-18
• /
• 2020

Purpose: The purpose of this study was to investigate work performance and calling as determinants of job satisfaction among nurse midwives. Methods: The participants of this study were registered nurse midwives who had worked in the delivery room for more than 6 months. Data were collected by face-to-face interviews, postal mail, and mobile devices. Subjects completed self-report questionnaires from July to August 2017. The dataset was analyzed using descriptive statistics, the independent t-test, analysis of variance, the Pearson correlation coefficient, and multiple regression. Results: The mean score for job satisfaction was 3.42±0.45. Among the sub-factors, income had the lowest score (2.67±0.72) and management of delivery had the highest score (3.81±0.66). Job satisfaction was significantly different according to marital status (t=2.25, p=.028), residential area (t=2.43, p=.016), and cause of job satisfaction (F=4.54, p=.012). Job satisfaction showed a significant positive correlation with work performance (r=.29, p<.001) and calling (r=.57, p<.001). The correlation between work performance and calling was also positive and statistically significant (r=.32, p<.001). Purpose and meaning (β=.48, p<.001) and marital status (β=-.15, p=.025) significantly influenced job satisfaction. The model developed in this study explained 45% of variation in job satisfaction. Conclusion: Nurse midwives' job satisfaction may be enhanced by entrusting them with professional roles and tasks. Above all, it is necessary to develop and provide programs that help nurse midwives connect their jobs with the meaning and purpose of their lives.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1481-1500
• /
• 2016

Device-to-Device (D2D) communication underlaying macro-small cell networks, as one of the promising technologies in the era of 5G, is able to improve spectral efficiency and increase system capacity. In this paper, we model the cross- and co-tier D2D communications in two-tier macro-small cell networks. To avoid the complicated interference for cross-tier D2D, we propose a mode selection scheme with a dedicated resource sharing strategy. For co-tier D2D, we formulate a joint optimization problem of power control and resource reuse with the aim of maximizing the overall outage capacity. To solve this non-convex optimization problem, we devise a heuristic algorithm to obtain a suboptimal solution and reduce the computational complexity. System-level simulations demonstrate the effectiveness of the proposed method, which can provide enhanced system performance and guarantee the quality-of-service (QoS) of all devices in two-tier macro-small cell networks. In addition, our study reveals the high potential of introducing cross- and co-tier D2D in small cell networks: i) cross-tier D2D obtains better performance at low and medium small cell densities than co-tier D2D, and ii) co-tier D2D achieves a steady performance improvement with the increase of small cell density.

• Journal of Korea Trade
• /
• 제25권3호
• /
• pp.65-86
• /
• 2021

Purpose - This paper empirically investigates the relationship between the corporate value chain and performance of non- financial businesses of South Korean stock market companies. It aims to explore the evidence that can be used to infer the relationship between value chains and corporate performance in the case of firms forming a value chain with other companies with the means of an equity investment or a special business relationship. Design/methodology - Non-financial corporations listed from 2011 to 2017 on the securities market of South Korea are analyzed. The data used for analysis are found for transactions with the related party by year for all the corporations of non-financial industries in the securities market. Multiple analysis attempts are conducted including the relationship between the value chain and productivity, corporate value, risk-adjusted corporate value, and mediation effects of productivity. The empirical model employs sixteen variables including the value chain index which identifies its impact on various aspects of business performances. Findings - The results of this study clearly supports the phenomenon that corporate productivity and value are enhanced when the corporation expands its value chain established with domestic related firms and overseas companies. Such a positive effect is statistically significant even after the possible risk factors that accompany the expansion of value chain were considered, and productivity plays the role as a medicating variable in the effect of the value chain on the corporation values. Originality/value - The findings of this study confirms that domestic companies' expansion of their value chain centered on the related firms overseas that helped them in terms of the maximization of their productivity and corporate values. This study shows that Korean government's policy on expanding the corporate GVC can enhance the productivity and value of firms. The expansion of value chain and its impact on business performance has not been explored thoroughly, although it is getting more and more important in the global trade operation.

• 정보처리학회논문지C
• /
• 제9C권4호
• /
• pp.513-522
• /
• 2002

기존의 end-to-end 방식에서는 네트워크 내부에서 혼잡(congestion)이 발생했을 경우 각 전송자가 즉시 알아 낼 수 없기 때문에 일정시간 동안 수신된 패킷(packet)의 순서에 대한 정보로 흔잡이 발생했는지에 대해 추론하는 것이다. 이와 같은 방법은 RTT(Round Trip Time)가 커지면 혼잡이 발생할 경우 전송자가 전송 양을 줄인다 해도 이미 전송된 패킷들로 인하여 흔잡이 가중되며 전체적인 TCP 동기화 (TCP Global synchronization) 현상을 피할 수 없게 된다. 반면 네트워크 내부에서 직접적으로 정보를 얻거나 처리를 해 줄 수 있다면 혼잡 발생과 동시에 처리가 가능함으로 기존 방식보다 처리율이 향상될 것이다. 본 논문에서는 액티브 라우터의(Active Network) 피드백 메커니즘을 이용하여 네트워크 내부 정보를 각 전송자가 이용할 수 있도록 하기 위해 라우터와의 통신을 이용하였으며, 코어 라우터의 큐 모듈은 RED(Random Early Detection)를 응용하여 ACC의 누락 메커니즘을 개선하였다. ACC를 확장한 메커니즘인 EACC(Enhanced Active Congestion Control)를 제시하고 모의실험을 통해 기존의 혼잡제어나 ACC(Active Congestion Control)보다 성능이 향상됨을 보여준다.

• 한국해양공학회지
• /
• 제31권6호
• /
• pp.405-412
• /
• 2017

Because of the rapid development of computer technology in recent years, wave models can utilize parallel calculations for the high-resolution prediction of open sea and coastal areas with high accuracy. Parallel calculations also allow national agencies in the relevant sectors to produce marine forecasting data through massive parallel calculations. Meanwhile, the eastern coast of the Korean Peninsula has been increasingly damaged by swell-like high waves, and many researchers and scientists are continuing their efforts to anticipate and reduce the damage. In general, the short-term transformation of swell-like high waves can be reproduced relatively well in the third generation wave models, but the transformation of relatively long period waves needs to be simulated with higher accuracy in terms of the nonlinear wave interactions to gain a better understanding of the low-frequency wave generation and development mechanisms. In this study, we developed a calculation module to improve the calculation of the nonlinear energy transfer in the 3rd generation wave model and integrated it into the wave model to effectively consider the nonlinear wave interaction. First, the nonlinear energy transfer calculation module and third generation model were combined. Then, the combined model was used to reproduce the wave transformation due to the nonlinear interaction, and the performance of the developed operation module was verified.

• 한국자동차공학회논문집
• /
• 제21권6호
• /
• pp.64-71
• /
• 2013

In this study we designed a lean $NO_x$ trap (LNT) model with $GT-POWER^{TM}$ program and then the LNT model was compared to the bench flow reactor test results. This model consists of 9 kinetic reactions to represent the main steps of NO oxidation, $NO_x$ adsorption, $NO_x$ release and then its reduction. The comparison was performed on the operating conditions at the space velocity of 50,000 1/hr and 80,000 1/hr with the temperature range of $200^{\circ}C{\sim}500^{\circ}C$ with the even spaced temperature step of $50^{\circ}C$. The experimental results show that the $NO_x$ conversion efficiency was enhanced by the temperature up to $350^{\circ}C$ and then decayed at higher temperatures. The LNT model predicts the similar trend of the $NO_x$ conversion efficiency to the experimental results below $350^{\circ}C$, but overestimates above $350^{\circ}C$. This overestimation comes from the higher reduction efficiency which was obtained by the different reduction gas composition such as $C_3H_6$ in the model to replace $CH_4$, $C_2H_4$ in the bench test.

• 한국안전학회지
• /
• 제36권1호
• /
• pp.1-8
• /
• 2021

To simulate a process model in the field of chemical engineering, it is very important to identify the physical properties of novel materials as well as existing materials. However, it is difficult to measure the physical properties throughout a set of experiments due to the potential risk and cost. To address this, this study aims to develop a property prediction model based on the group contribution method for aromatic chemical compounds including benzene rings. The benzene rings of aromatic materials have a significant impact on their physical properties. To establish the prediction model, 42 important functional groups that determine the physical properties are considered, and the total numbers of functional groups on 147 aromatic chemical compounds are counted to prepare a dataset. Support vector regression is employed to prepare a prediction model to handle sparse and high-dimensional data. To verify the efficacy of this study, the results of this study are compared with those of previous studies. Despite the different datasets in the previous studies, the comparison indicated the enhanced performance in this study. Moreover, there are few reports on predicting the physical properties of aromatic compounds. This study can provide an effective method to estimate the physical properties of unknown chemical compounds and contribute toward reducing the experimental efforts for measuring physical properties.

• 한국정보전자통신기술학회논문지
• /
• 제17권4호
• /
• pp.190-197
• /
• 2024

O2O 상점 모델은 온/오프라인의 경계를 허물어 고객에게 큰 편의성을 제공하는 플랫폼이다. 이러한 플랫폼을 효과적으로 운영하기 위해서는 소상공인들이 필요한 정보를 디지털 형태로 제공해야 한다. 특히, 한글 메뉴판을 디지털화하는 과정이 수동으로 진행될 경우 여러 문제점을 일으킬 수 있으며, OCR 기술 사용 시 한글의 인식 정확도가 낮아 오류 인식의 가능성이 높다. 이에 본 논문에서는 한글 메뉴판의 자동 인식을 위해 대표적인 OCR 모델인 EasyOCR을 기반으로 하되, 한글 문자 인식의 낮은 정확도를 개선하고자 한다. 제안하는 모델은 VGG와 ResNet의 구조적 장점을 통합하고, 어텐션 메커니즘을 도입하여 한글 문자의 인식 성능을 크게 향상시키도록 설계한다. 실험 결과, 제안하는 모델은 EasyOCR에 비해 Accuracy 기준 약 3.5%, Confidence Score와 Normalized Edit Distance 기준 약 1%의 인식 정확도 향상을 보였다. 따라서, 제안한 방법이 기존 문제를 효과적으로 해결할 수 있음을 입증한다.