• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.755-761
• /
• 2023

As digital transformation accelerates, the proportion of non-face-to-face services in financial services is also increasing. Recently, user experience has emerged to secure competitiveness in mobile services, and analysis techniques to improve user experience have emerged. User review data, one of the data used for quantitative evaluation, contains a lot of unnecessary information, which is time-consuming to derive improvement directions. Therefore, this study aims to develop a UX analysis system based on the hierarchy of UX needs by using a cosine similarity algorithm and analyze user review data of Kookmin Bank, Woori Bank, Kakao Bank, and Toss for verification. This study proved that the developed UX analysis system is a system that can effectively analyze UX through the analysis of user review data. The system of this study is expected to be easily used to identify improvement plans for the hierarchy of UX needs in an agile organization that needs to quickly reflect customer feedback.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.137-142
• /
• 2010

Although multi-model speech recognizer has been shown to be quite successful in noisy speech recognition, the results were based on general speech front-ends which do not take into account noise adaptation techniques. In this paper, for the accurate evaluation of the multi-model based speech recognizer, we adopted a quite noise-robust speech front-end, AFE, which was proposed by the ETSI for the noisy DSR environment. For the performance comparison, the MTR which is known to give good results in the DSR environment has been used. Also, we modified the structure of the multi-model based speech recognizer to improve the recognition performance. N reference HMMs which are most similar to the input noisy speech are used as the acoustic models for recognition to cope with the errors in the selection of the reference HMMs and the noise signal variability. In addition, multiple SNR levels are used to train each of the reference HMMs to improve the robustness of the acoustic models. From the experimental results on the Aurora 2 databases, we could see better recognition rates using the modified multi-model based speech recognizer compared with the previous method.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.238-252
• /
• 2009

Due to the rapid increase of available contents via the convergence of broadcasting and internet, the efficient access to personally preferred contents has become an important issue. In this paper, for recommendation scheme for TV programs using a collaborative filtering technique is studied. For recommendation of user preferred TV programs, our proposed recommendation scheme consists of offline and online computation. About offline computation, we propose reasoning implicitly each user's preference in TV programs in terms of program contents, genres and channels, and propose clustering users based on each user's preferences in terms of genres and channels by dynamic fuzzy clustering method. After an active user logs in, to recommend TV programs to the user with high accuracy, the online computation includes pulling similar users to an active user by similarity measure based on the standard preference list of active user and filtering-out of the watched TV programs of the similar users, which do not exist in EPG and ranking of the remaining TV programs by proposed rank model. Especially, in this paper, the BM (Best Match) algorithm is extended to make the recommended TV programs be ranked by taking into account user's preferences. The experimental results show that the proposed scheme with the extended BM model yields 62.1% of prediction accuracy in top five recommendations for the TV watching history of 2,441 people.

• Mood & Emotion
• /
• v.16 no.3
• /
• pp.109-122
• /
• 2018

Objectives : The objective of this study was to revise the Korean Medication Algorithm Project for Bipolar Disorder (KMAP-BP) 2014: Children and Adolescents. Methods : We performed the survey, using a questionnaire comprising 22 questions according to each situation, in children and adolescents with bipolar disorder. Results : First-line pharmacotherapeutic strategies for manic episode in children with bipolar disorder were a combination of mood stabilizer (MS) and an atypical antipsychotics (AAP), monotherapy with an AAP, risperidone, and aripiprazole. Aripiprazole was selected as first-line medication for depressive episode in children with bipolar disorder, and aripiprazole, and risperidone were selected as first-line at high-risk children. First-line pharmacotherapeutic strategies for manic episode in adolescents were a combination of MS and an AAP, monotherapy with an AAP valproate, lithium, risperidone (Treatment of Choice, TOC), aripiprazole, and quetiapine. First-line pharmacotherapeutic strategies for depressive episode in adolescents, were a combination of an atypical antipsychotics and lamotrigine, valproate, aripiprazole (TOC), risperidone, and quetiapine. For depressive episodes in adolescents at high risk for bipolar disorder, valproate, aripiprazole (TOC), and risperidone were selected as first-line medication. Conclusion : We expect that the present KMAP-BP 2018-children and adolescents, is useful for clinicians to treat children and adolescents with bipolar disorder.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.167-176
• /
• 2022

We designed a borehole deviation survey tool applicable for steel-cased holes, K-DEV, and developed a prototype for a depth of 500 m aiming to development of own equipment required to secure deep subsurface characterization technologies. K-DEV is equipped with sensors that provide digital output with verified high performance; moreover, it is also compatible with logging winch systems used in Korea. The K-DEV prototype has a nonmagnetic stainless steel housing with an outer diameter of 48.3 mm, which has been tested in the laboratory for water resistance up to 20 MPa and for durability by running into a 1-km deep borehole. We confirmed the operational stability and data repeatability of the prototype by constantly logging up and down to the depth of 600 m. A high-precision micro-electro-mechanical system (MEMS) gyroscope was used for the K-DEV prototype as the gyro sensor, which is crucial for azimuth determination in cased holes. Additionally, we devised an accurate trajectory survey algorithm by employing Unscented Kalman filtering and data fusion for optimization. The borehole test with K-DEV and a commercial logging tool produced sufficiently similar results. Furthermore, the issue of error accumulation due to drift over time of the MEMS gyro was successfully overcome by compensating with stationary measurements for the same attitude at the wellhead before and after logging, as demonstrated by the nearly identical result to the open hole. We believe that the methodology of K-DEV development and operational stability, as well as the data reliability of the prototype, were confirmed through these test applications.