• Geomechanics and Engineering
• /
• v.39 no.1
• /
• pp.27-41
• /
• 2024

Accurately estimating the performance of tunnel boring machines (TBMs) is crucial for mitigating the substantial financial risks and complexities associated with tunnel construction. Machine learning (ML) techniques have emerged as powerful tools for predicting non-linear time series data. In this research, six advanced meta-heuristic optimization algorithms based on long short-term memory (LSTM) networks were developed to predict TBM penetration rate (TBM-PR). The study utilized 1125 datasets, partitioned into 20% for testing, 70% for training, and 10% for validation, incorporating six key input parameters influencing TBM-PR. The performances of these LSTM-based models were rigorously compared using a suite of statistical evaluation metrics. The results underscored the profound impact of optimization algorithms on prediction accuracy. Among the models tested, the LSTM optimized by the particle swarm optimization (PSO) algorithm emerged as the most robust predictor of TBM-PR. Sensitivity analysis further revealed that the orientation of discontinuities, specifically the alpha angle (α), exerted the greatest influence on the model's predictions. This research is significant in that it addresses critical concerns of TBM manufacturers and operators, offering a reliable predictive tool adaptable to varying geological conditions.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.265-272
• /
• 2020

In the research of brain computer interface (BCI) technology, one of the big problems encountered is how to deal with some people as called the BCI-illiteracy group who could not control the BCI system. To approach this problem efficiently, we investigated a kind of spectral EEG characteristics in the prior resting state in association with BCI performance in the following BCI tasks. First, spectral powers of EEG signals in the resting state with both eyes-open and eyes-closed conditions were respectively extracted. Second, a convolution neural network (CNN) based binary classifier discriminated the binary motor imagery intention in the BCI task. Both the linear correlation and binary prediction methods confirmed that the spectral EEG characteristics in the prior resting state were highly related to the BCI performance in the following BCI task. Linear regression analysis demonstrated that the relative ratio of the 13 Hz below and above the spectral power in the resting state with only eyes-open, not eyes-closed condition, were significantly correlated with the quantified metrics of the BCI performance (r=0.544). A binary classifier based on the linear regression with L1 regularization method was able to discriminate the high-performance group and low-performance group in the following BCI task by using the spectral-based EEG features in the precedent resting state (AUC=0.817). These results strongly support that the spectral EEG characteristics in the frontal regions during the resting state with eyes-open condition should be used as a good predictor of the following BCI task performance.

• Journal of Venture Innovation
• /
• v.3 no.2
• /
• pp.77-93
• /
• 2020

The purpose of this study is to investigate the effect of person-job fit on job performance. In the process, the moderating effect of the meaning of work and the mediating effect of work engagement was investigated. For this purpose, survey data were collected from 304 employees working at the company organization and analyzed using correlation and regression analysis. The summary of the study is as follows. First, there is a significant correlation between realistic person-job fit and perceived person-job fit. Second, perceived person-job fit is a significant predictor of job performance. Third, there is a mediating effect of work engagement in the relationship between person-job fit and job performance. Fourth, there is a moderating effect of the meaning of work in the relationship between person-job fit and work engagement. This study demonstrates the correlation of realistic and perceived person-job fit, which has not been studied in Korea before. It was found that person-job fit influences job performance through mediating emotional variables such as work engagement. From the point of view of organization managers, there is a need to provide a work environment that is appropriate for the characteristics of the employees and to manage how employees perceive person-job fit. In particular, it is necessary to support employees to recognize that their work promotes their growth and contributes to the public good. Finally, the limitations of the study and future research tasks were proposed.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.9-26
• /
• 2005

In the pursuit of ever higher levels of performance, recent computer systems have made use of deep pipeline, dynamic scheduling and multi-issue superscalar processor technologies. In this situations, branch prediction schemes are an essential part of modem microarchitectures because the penalty for a branch misprediction increases as pipelines deepen and the number of instructions issued per cycle increases. In this paper, we propose a novel branch prediction scheme, direction-gshare(d-gshare), to improve the prediction accuracy. At first, we model a neural network with the components that possibly affect the branch prediction accuracy, and analyze the variation of their weights based on the neural network information. Then, we newly add the component that has a high weight value to an original gshare scheme. We simulate our branch prediction scheme using Simple Scalar, a powerful event-driven simulator, and analyze the simulation results. Our results show that, compared to bimodal, two-level adaptive and gshare predictor, direction-gshare predictor(d-gshare. 3) outperforms, without additional hardware costs, by up to 4.1% and 1.5% in average for the default mont of embedded direction, and 11.8% in maximum and 3.7% in average for the optimal one.

• Horticultural Science & Technology
• /
• v.30 no.3
• /
• pp.270-277
• /
• 2012

Greenhouse industry has been growing in many countries due to both the advantage of stable year-round crop production and increased demand for fresh vegetables. In greenhouse cultivation, $CO_2$ concentration plays an essential role in the photosynthesis process of crops. Continuous and accurate monitoring of $CO_2$ level in the greenhouse would improve profitability and reduce environmental impact, through optimum control of greenhouse $CO_2$ enrichment and efficient crop production, as compared with the conventional management practices without monitoring and control of $CO_2$ level. In this study, a mathematical model was developed to estimate the $CO_2$ emission from soil as affected by environmental factors in greenhouses. Among various model types evaluated, a linear regression model provided the best coefficient of determination. Selected predictor variables were solar radiation and relative humidity and exponential transformation of both. As a response variable in the model, the difference between $CO_2$ concentrations at the soil surface and 5-cm depth showed are latively strong relationship with the predictor variables. Segmented regression analysis showed that better models were obtained when the entire daily dataset was divided into segments of shorter time ranges, and best models were obtained for segmented data where more variability in solar radiation and humidity were present (i.e., after sun-rise, before sun-set) than other segments. To consider time delay in the response of $CO_2$ concentration, concept of time lag was implemented in the regression analysis. As a result, there was an improvement in the performance of the models as the coefficients of determination were 0.93 and 0.87 with segmented time frames for sun-rise and sun-set periods, respectively. Validation tests of the models to predict $CO_2$ emission from soil showed that the developed empirical model would be applicable to real-time monitoring and diagnosis of significant factors for $CO_2$ enrichment in a soil-based greenhouse.

• Korean Journal of Culture and Social Issue
• /
• v.26 no.3
• /
• pp.303-327
• /
• 2020

Previous studies have examined the relationship between domain satisfaction and life satisfaction. However, a comprehensive investigation of satisfaction with multiple domains and their relative contributions to life satisfaction and hedonic balance are missing in the literature. And most studies were conducted in English speaking countries and only a few cross-cultural studies have been conducted. In the current research, we compared Korean and European Canadian university students to examine how domain satisfactions (satisfaction with healthy lifestyles, family relationships, appearance, financial situation, academic performance) are associated with life satisfaction and hedonic balance. We then examined the relative contributions of people's satisfaction ratings on the life domains to their life satisfaction and hedonic balance. Positive correlations were observed between satisfaction with each of the five life domains, and life satisfaction and hedonic balance across the two cultural groups. Interestingly, satisfactions with healthy lifestyles was the dominant predictor of Koreans' life satisfaction and hedonic balance. Satisfaction with appearance was the dominant predictor of European Canadians' life satisfaction and hedonic balance followed by satisfaction with healthy lifestyles. Overall, these results suggest that there are common life domains that contribute to subjective well-being and that there are specific life domains that may contribute more to subjective well-being depending on the culture.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.3
• /
• pp.303-334
• /
• 2014

This study aims to develop standard indicators and methodology for college & university libraries' evaluation based on the agreement among various stake-holders, then suggests a new evaluation system. For the goal, we identify purposes and required conditions, then develop indicators for the evaluation through open-ended interviews, a questionnaire survey, and focus group for reaching an agreement on the included indicators among the stake-holders, finally we construct the overall evaluation structure and weighting system. The overall structure is developed based on process-centered approach, then both the internal and functional viewpoint and external and service-oriented viewpoint are considered. The weighting system is based on the balance among the process categories, such as resources, process, and output elements. Additionally, we suggest methodology for the evaluation and annual improvement process for ongoing improvement of the evaluation system. We expect that the results from this study will contribute not only to the evaluation activities but also to active discussions on library performance and its predictor factors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.45-57
• /
• 2005

In this paper, we extend the performance of bidirectional TCP connection over end-to-end network that uses transfer rate-based flow and congestion control. The sharing of a common buffer by TCP packets and acknowledgement has been known to result in an effect called ack compression, where acks of a connection arrive at the source bunched together, resulting in unfairness and degraded throughput. The degradation in throughput due to bidirectional traffic can be significant. Even in the simple case of symmetrical connections with adequate window size, the connection efficiency is improved about 20% for three levels of background traffic 2.5Mbps, 5.0Mbps and 7.5Mbps. Otherwise, the throughput of jitter is reduced about 50% because round trip delay time is smaller between source node and destination node. Also, we show that throughput curve is improved with connection rate algorithm which is proposed for TCP congetion avoidance as a function of aggressiveness threshold for three levels of background traffic 2.5Mbps, 5Mbps and 7.5Mbps. By analyzing the periodic bursty behavior of the source IP queue, we derive estimated for the maximum queue size and arrive at a simple predictor for the degraded throughput, applicable for relatively general situations.

• Atmosphere
• /
• v.21 no.4
• /
• pp.497-506
• /
• 2011

Korean mid- and upper-level aviation turbulence guidance (KTG) system is developed using the unified model (UM)-based regional data assimilation and prediction system (RDAPS) of the Korea Meteorological Administration. The KTG system includes three steps. First, the KTG system calculates a suite of diagnostics in the UM-RDAPS domain. Second, component diagnostics that have different units and numerical magnitudes are normalized into the values between 0 and 1, according to their own thresholds in the KTG system. Finally, normalized diagnostics are combined into one KTG predictor by measuring the weighting scores based on the probability of detection, which is calculated using the observed pilot reports (PIREPs) exclusively of moderate-or-greater (MOG) and null (NIL) intensities. To investigate the optimal performance of the KTG system, two types (RD-KTG and UM-KTG) of the KTG systems are developed and evaluated using the PIREPs over Korea and East Asia. Component diagnostics and their thresholds in the RD-KTG are founded on the 8-yrs (2002.12-2010.11) MM5-based RDAPS (previous version of the RDAPS; ${\Delta}x$ = 30 km) and PIREPs data, while those in the UM-KTG are based on the 6 months (2010.12-2011.5) UM-based RDAPS (${\Delta}x$ = 12 km) and PIREPs data. In comparison between the RD-KTG and UM-KTG, overall performance of the UM-KTG (0.815) is better than that of the RD-KTG (0.79) during the recent 6 months, because forecasting skill for the upper-level wind is higher in the UM-RDAPS than in the MM5-RDAPS. It is also found that the UM-KTG is more efficient than the RD-KTG according to the statistical evaluations and sensitivity tests to the number of component diagnostics.

• Architectural research
• /
• v.17 no.1
• /
• pp.13-20
• /
• 2015

The physical environment can dramatically affect students' feeling and their behavior, educational attainment, and the way in which we do school activities. Unlimited access to campus areas without appropriate securities have reported an increase of crime in school area and safety issues has encouraged school facility planners to install securities devices at every corner of buildings. However, it is still questionable whether this approach is enough to protect students and staffs from the victimization of crime, including thefts, burglaries and sexual offences. There has been continued doubt about the safety of educational facilities where individual college students are studying and enjoying extra-curricular activities. Therefore, the purpose of this study is intended to investigate the effects of perception of safety by students on the level of academic performance at public outdoor environment of university campus. An extensive literature noted that the central element of modern school design principle mainly holds the theory of crime prevention through environmental design (CPTED) and the concept of defensible space. The second generation of CPTED also focused on social soft issues as well as situational factors, which extends beyond mere physical design to include social factors. The correlation analysis found that the effect of sense of safety does appear to be statistically significant on the facilitation of academic achievement. However, the analysis of Chi-square concluded that the perception of safety was not related to demographic and socio-economic profiles of the group except for gender. Further, stepwise multiple regression analysis revealed that the most prime predictor for academic achievement were 'safe public outdoor space/paths' at university campus environment, implying careful design of public open space and sidewalks based on the guideline of CPTED. The study also demonstrated that as the level of positive perception of safety rose, the overall academic achievement also responded to the specified rate (${\beta}=.99$). Finally, the findings reinforce an evidence that high-quality school environments are a positive factor in student academic performance.