• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.179-186
• /
• 2009

This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.

• Asia pacific journal of information systems
• /
• v.19 no.3
• /
• pp.151-179
• /
• 2009

The purpose of this study is to make an empirical analysis on the factors affecting the intention for the continuous use of the BSC system, which has been recently spread in the public sector. Because the object of acceptance is the performance management system based on BSC (Balanced Scorecard) implemented in the form of information systems, this study proposes a research model by applying TAM (Technology Acceptance Model). Independent variables are factors affecting the acceptance of BSC system such as training, communication, IS support, CEO support and personal innovativeness, and we examine their effects on the dependent variable, namely, intention on continuous use via mediating variables: perceived usefulness and perceived ease of use. A questionnaire survey was conducted with public institutions(firms) that had introduced and were operating the BSC system; 264 valid questionnaires are adopted. Collected data are analyzed using SPSS 16.0 and AMOS 7.0. Results of reliability test show that all analyzed data are reliable. In validity test, one item regarding communication was excluded; 9 latent variables and 34 observed variables are used in the final analysis. Based on the results of the hypothesis test through path analysis using a structural equation model, 10 out of 16 hypotheses are accepted. Factors affecting perceived usefulness are training and IS(Information System) support. The analysis results indicate that perceived ease of use is mainly affected by IS support, CEO support, and personal innovativeness among the factors related to the acceptance of the BSC system. This suggests that, contrary to the expectation that the BSC system may be used without difficulty, the management's active support is required in order to attain expected improvement in productivity and work efficiency. This was also pointed out in case studies on the construction of the BSC system in public sectors. On the other hand, perceived ease of use is found to affect perceived usefulness. This supports the results of previous researches on TAM. Perceived ease of use and perceived usefulness are found to affect the attitude towards the use of the system. The intention on continuous use is affected more by perceived usefulness than by the attitude towards the use of system. This result supports the results of previous researches on TAM, showing that the BSC system is utilized substantially in worksites. This study is considered meaningful in that it was actually performed on users at public institutions(firms) that had introduced the BSC system and that it empirically tested hypotheses on the acceptance of the BSC system by applying TAM to the research model.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.7 no.1
• /
• pp.60-68
• /
• 2012

In this study, the manufacturing process of micro capsulized PCM (phase changing material) for thermal storage performance of latent heat was investigated to save energy during the use of buildings: i.e. use of melamine-type resin as the micro-capsule material and paraffin wax as the inner material that are together used in concrete walls. For the manufacturing process of the micro-capsulized PCM, the amount of SDS addition as surfactant was the key variable and the resulting thermal storage performance depended on the SDS amount. With increasing amount of SDS, the micro capsulation became much easier while the capsule surface became harder. The micro capsules became uniform at an optimum SDS addition. The addition of SDS also affected the thermal capacity: with increasing SDS amount, the heat storage and release tendency at melting point was more clearly manifested. The current investigation is part of a study under progress to explore the use of PCM in concrete walls to save building maintenance cost and energy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.448-456
• /
• 2020

This study found that it is critical to consider farmers' intention to adopt new technology in order to facilitate the spread of new technology. Based on this assumption, the research team analyzed the following: factors that influence intention of adoption and marginal effects on those factors. The data were collected from 99 farmers who did not participate in the pilot projects on dissemination of new technologies developed by the Rural Development Administration (RDA). A total of 19 observed variables were set to measure seven latent variables: educational support; technical support; funding support; compatibility; trialability; observability; and antipathy. The intention to adopt new technology was established as the dependent variable. According to the ordered logit analysis, educational support, observability, and antipathy were found to have significantly affected the intention to adopt new technology; their odds ratio were 6.938, 2.716, and 0.501, respectively. According to the marginal analysis, educational support, observability, and antipathy were found to have significantly affected the intention to adopt new technology; their marginal effects were 20.2 %, 10.4 %, and -7.2 %, respectively. Therefore, this study suggests the following to facilitate the spread of new technology: first, provide quality support services through effective deduction; second, increase the visibility of new technology; and third, enhance the credibility of agricultural institutions by developing continuous relations with farmers to reduce their antipathy.

• Korean Security Journal
• /
• no.61
• /
• pp.235-254
• /
• 2019

This study identifies a factor structure regarding the criterion of terror awareness by using confirmatory factor analysis. The study provides information whether the criterion fits in the analysis of terror awareness in Korea or not. Data of 176 public officials working at the National Assembly collected in 「Study on the Improvement of Security in the National Assembly Building」(Choi O-Ho and others, 2016) was used in the analysis. Study results showed the fit statistics of 3 questions regarding concern in terror, 5 questions regarding cognition of terror occurrence, 3 questions regarding countermeasure of terror, and 3 questions regarding equipments against terror satisfied the standard. Also, standard regression coefficient exceeded the standard and was shown to be fit. Concern in terror, as a latent variable, was below the standard value of average variance extracted. However, focused validity was secured by obtaining other values fit. This study proceeded distinct validation test to supplement data. The test results showed that the criterion level was fit. Thus, further survey should include questions that are appropriate to measure the awareness of terror based not only on theories and previous studies but also on questions of terror awareness tested in this study. Such development in surveys will support the means of data measurement.

• 재활복지
• /
• v.21 no.1
• /
• pp.253-277
• /
• 2017

The purpose of this study was to develop the Constraints in Physical Activity Scale for people with physical Disabilities(CPASD) which measures the constraints in physical activity of people with physical disabilities. For this study, the 5 step analytic framework of unified validity developed by Messick (1995), the framework for conducting a strong program of construct validation by Benson (1998) method were applied. Furthermore, the validity of CPASD was systematically presented by applying common factor model and measurement model to 264 persons with physical disabilities. The conclusion based on the results and discussions of this study is as follows. First, CPASD presented evidence of job validity. Four factors (17 items) were developed, consisting of leader constraints, economic constraints, prejudice, and exercise environment constraints through the analysis of the factor structure and the fit of factor coefficients. Second, the factor structure of the developed CPASD (leader constraint, economic constraint, prejudice, exercise environment constraint) was statistically distinguished and stably reflected the existing exercise participation constraints theory. Third, the developed CPASD presented evidence of the validity of the criteria. Leader constraints and prejudice were negatively correlated with positive motor emotions, leader constraints, prejudice, and exercise environment constraints were positively correlated with negative motor emotions. Therefore, in future research, it is necessary to reevaluate the current system and actual condition related to leader constraints, economic constraints, prejudices, and exercise environment constraints derived as factors of CPASD. To do this, it is necessary to judge the degree of reality based on the causal relationship verification and IRT theory using CPASD.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.237-248
• /
• 2021

Based on sports known to reduce adolescents' smartphone addiction, this study aims to identify the structural causal relationship between sport commitment and smartphone addiction. First of all, based on prior studies, it was intended to show that adolescents' sport commitment is effective in reducing smartphone addiction through social support and ego-resilience, and that such causal relationships vary significantly depending on gender. To this end, a survey of 605 middle and high school students was conducted, and the structural relationship between the four established latent variables was analyzed by analyzing the structural equation model using the SPSS 25.0 and AMOS 23.0 programs. According to the analysis, adolescents' sport commitment was found to have an adverse effect on smartphone addiction, and social support and ego-resilience in the relationship between the two variables were found to have a mediated effect. In addition, these results showed significant differences in gender. This study expanded the field of smartphone addiction and sports convergence study by revealing the relationship between sport commitment as psychological recognition variable and addiction Unlike previous studies using a participation time, duration, and intensity, and suggested that structural relationships with personal characteristic variables and gender-specific approaches are important. Through this, it is meaningful that it provided basic data for in-depth convergence study in the smartphone addiction and development of gender-specific programs.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.185-207
• /
• 2022

Recently, with the development of deep learning technology, researches to apply a deep learning algorithm to analyze unstructured data such as text and images are being actively conducted. Text classification has been studied for a long time in academia and industry, and various attempts are being performed to utilize data characteristics to improve classification performance. In particular, a hierarchical relationship of labels has been utilized for hierarchical classification. However, the top-down approach mainly used for hierarchical classification has a limitation that misclassification at a higher level blocks the opportunity for correct classification at a lower level. Therefore, in this study, we propose a methodology for classifying hierarchical data using the autoencoder-based deeply supervised network that high-level classification does not block the low-level classification while considering the hierarchical relationship of labels. The proposed methodology adds a main classifier that predicts a low-level label to the autoencoder's latent variable and an auxiliary classifier that predicts a high-level label to the hidden layer of the autoencoder. As a result of experiments on 22,512 academic papers to evaluate the performance of the proposed methodology, it was confirmed that the proposed model showed superior classification accuracy and F1-score compared to the traditional supervised autoencoder and DNN model.

• Journal of the Korea Safety Management & Science
• /
• v.25 no.4
• /
• pp.45-56
• /
• 2023

This study attempted to provide implications by analyzing the impact of business Owner's safety commitment on industrial accidents and examining the mediating role of management supervisors' safety leadership and worker participation. Analysis was conducted on 2,067 manufacturing sites with 20 to 50 employees in the 10th Occupational Safety and Health Survey data. SPSS waw used to secure the reliability of the measurement variable. Hypothesis vertification was carried out after securing the suitability and validity of the structural model using AMOS. The direct impact of three latent variables on industrial accidents was confirmed: the business owner's safety commitment, the management supervisor's safety leadership, and the worker participation. The employer's safety will and the management supervisor's safety leadership do not directly affect industial accidents, but it has been verified that worker participation has a diret impact on industrial accident reduction. In addition, it has been confirmed that the safety leadership and worker participation of the management. Supervior have a complete mediating effect on the reduction of industrial accidents by mediating with the safety leadership of the management supervior and the participation of the workers. This study analyzed the impact on industrial accidents by dividing the stakeholders constituting the workplace into three classes: business owners, superviors, and workers, but the results suggest that employers and all workers inside the workplace may be organically linked to achieving the goal of reducing industrial accidents. Therefore, in order to establish an autonomous safety management system for safety and health at workerplaces, efforts are needed to reduce industrial accidents in their respective location by forming an organic community among internal stakeholders.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.4
• /
• pp.545-554
• /
• 2024

Sustainable development is recognized as the direction humanity should pursue, and transportation policies also aim to achieve sustainability by efficiently utilizing limited resources. Among them, parking policy is an important task that requires strategic implementation for sustainable transportation development in many cities. Shared parking is actively being considered for the efficient utilization of existing transportation facilities. In this study, we analyzed major influencing factors using a structural equation model to promote shared parking and derived policy implications accordingly. The most influential latent variable on shared parking preference was donation experience, followed by satisfaction with public transportation and satisfaction with existing sharing policies. The preference for shared parking was found to have a virtuous cycle effect on social value as it influenced the spread of shared value. In the end, the implementation of the parking sharing policy will improve the visible traffic environment. However, it is evident that the impact of promoting invisible shared values is more significant. In other words, the main implication of this study is that to implement the parking sharing policy effectively, more emphasis should be placed on recognizing the shared value and promoting the awareness of sustainable development.