• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.145-152
• /
• 2024

Closed quotient (CQ) represents the time ratio for which the vocal folds remain in contact during voice production. Because analyzing CQ values serves as an important reference point in vocal training for professional singers, these values have been measured mechanically or electrically by either inverse filtering of airflows captured by a circumferentially vented mask or post-processing of electroglottography waveforms. In this study, we introduced a novel algorithm to predict the CQ values only from audio signals. This has eliminated the need for mechanical or electrical measurement techniques. Our algorithm is based on a gated recurrent unit (GRU)-type neural network. To enhance the efficiency, we pre-processed an audio signal using the pitch feature extraction algorithm. Then, GRU-type neural networks were employed to extract the features. This was followed by a dense layer for the final prediction. The Results section reports the mean square error between the predicted and real CQ. It shows the capability of the proposed algorithm to predict CQ values.

• Tribology and Lubricants
• /
• v.40 no.1
• /
• pp.1-7
• /
• 2024

Ball bearings are a major component of mechanical parts for transmitting rotation. Compared to tapered roller bearings, ball bearings offer less rolling resistance, which leads to reduced heat generation during operation. Because of these characteristics, ball bearings are widely used in electric vehicles and machine tools. The design of ball bearing cages has recently emerged as a major issue in ball bearing design. Cage design requires pre-verification of performance using theoretical or experimental formula or computational fluid dynamics (CFD). However, CFD analysis is time-consuming, making it difficult to apply in case studies for design decisions and is mainly used in performance prediction following design confirmation. To use CFD in the early stages of design, main-taining analytical accuracy while reducing the time required for analysis are necessary. Accordingly, this study proposes a laminar steady-state segment CFD technique to solve the problem of long CFD analytical times and to enable the use of CFD analysis in the early stages of design. To verify the reliability of the CFD analysis, a bearing drag torque test is performed, and the results are compared with the analytical results. The proposed laminar steady-state segment CFD technique is expected to be useful for case studies in bearing design, including cage design.

• Explosives and Blasting
• /
• v.38 no.4
• /
• pp.16-25
• /
• 2020

Multi-setting smart-investigation of the ground and large uncharged hole boring (MSP) method to reduce the blast-induced vibration in a tunnel excavation is carried out over 50m of long-distance boring in a horizontal direction and thus has been accompanied by deviations in boring alignment because of the heavy and one-directional rotation of the rod. Therefore, the deviation has been adjusted through the boring machine's variable setting rely on the previous construction records and expert's experience. However, the geological characteristics, machine conditions, and inexperienced workers have caused significant deviation from the target alignment. The excessive deviation from the boring target may cause a delay in the construction schedule and economic losses. A deep learning-based prediction model has been developed to discover an ideal initial setting of the MSP machine. Dropout, early stopping, pre-training techniques have been employed to prevent overfitting in the training phase and, significantly improved the prediction results. These results showed the high possibility of developing the model to suggest the boring machine's optimum initial setting. We expect that optimized setting guidelines can be further developed through the continuous addition of the data and the additional consideration of the other factors.

• Tunnel and Underground Space
• /
• v.33 no.3
• /
• pp.141-149
• /
• 2023

Recently, as the demand for urban underground space increases, urban tunnel planning is actively progressing. In particular, the application of the roadheader excavation method, which has favorable applicability to urban tunnel, is increasing. However, it is known that the roadheader excavation method has a limitation in that excavation efficiency for high strength rock with a Uniaxial Compressive Strength (UCS) of 100 MPa or more is lowered. In this study, The pre-cracked method was presented as a method to improve the excavation efficiency of roadheader for high strength rock and its applicability was evaluated. The net cutting rate was evaluated using the Bilgin prediction formula, which can calculate the net cutting rate by considering the UCS and RQD (Rock Quality Designation). It was found that the net cutting rate increased as the RQD decreased under the rock condition with the same UCS. This is judged to increase the excavation efficiency of the roadheader in the jointed high strength rock. Additionally, the field applicability of the pre-cracked method for high strength rock was verified through field tests. It was confirmed that the crack zone was formed around the charging hole, and it is considered that the pre-cracked method can be applied to the high strength rock.

• Journal of radiological science and technology
• /
• v.40 no.1
• /
• pp.35-40
• /
• 2017

The purpose of this study was to investigate the relationship between abdominal subcutaneous fat thickness(ASFT) and maternal gestational diabetes mellitus(GDM) measured by ultrasound at period of pregnancy. We compared maternal age, pre-pregnancy body mass index, and weight gain during pregnancy in 286 pregnant women who were diagnosed with early pregnancy ASFT and high GDM screening test(50 g OGTT) of more than 140 mg/dL. ROC curve analysis was used to determine the cut-off value of ASFT for GDM prediction. Maternal age and weight gain during pregnancy were not related to GDM in the mid-trimester and pre-pregnancy body mass index and earely pregnancy ASFT were significantly different between normal and GDM high risk groups. The cut-off value of ASFT for GDM prediction was 2.23 cm(AUC 0.913. Sensitivity 76.19%, Specificity 93.72%). ASFT measured by ultrasound in early pregnancy was useful as an important index for predicting mid-trimester GDM prediction. Therefore, ASFT can be used as an auxiliary diagnostic index for early recognition of GDM.

• Journal of Construction Engineering and Project Management
• /
• v.5 no.1
• /
• pp.11-19
• /
• 2015

This paper presents optimized artificial neural networks (ANNs) claims prediction and decision awareness framework that guides owner organizations in their pre-bid construction project decisions to minimize claims. The framework is composed of two genetic optimization ANNs models: a Claims Impact Prediction Model (CIPM), and a Decision Awareness Model (DAM). The CIPM is composed of three separate ANNs that predict the cost and time impacts of the possible claims that may arise in a project. The models also predict the expected types of relationship between the owner and the contractor based on their behavioral and technical decisions during the bidding phase of the project. The framework is implemented using actual data from international projects in the Middle East and Egypt (projects owned by either public or private local organizations who hired international prime contractors to deliver the projects). Literature review, interviews with pertinent experts in the Middle East, and lessons learned from several international construction projects in Egypt determined the input decision variables of the CIPM. The ANNs training, which has been implemented in a spreadsheet environment, was optimized using genetic algorithm (GA). Different weights were assigned as variables to the different layers of each ANN and the total square error was used as the objective function to be minimized. Data was collected from thirty-two international construction projects in order to train and test the ANNs of the CIPM, which predicted cost overruns, schedule delays, and relationships between contracting parties. A genetic optimization backward analysis technique was then applied to develop the Decision Awareness Model (DAM). The DAM combined the three artificial neural networks of the CIPM to assist project owners in setting optimum values for their behavioral and technical decision variables. It implements an intelligent user-friendly input interface which helps project owners in visualizing the impact of their decisions on the project's total cost, original duration, and expected owner-contractor relationship. The framework presents a unique and transparent hybrid genetic algorithm-ANNs training and testing method. It has been implemented in a spreadsheet environment using MS Excel$^{(R)}$ and EVOLVERTM V.5.5. It provides projects' owners of a decision-support tool that raises their awareness regarding their pre-bid decisions for a construction project.

• Information Systems Review
• /
• v.7 no.2
• /
• pp.23-40
• /
• 2005

Discovering customers' behavioral patterns from large data set and providing them with corresponding services or products are critical components in managing a current business. However, the diversity of customer needs coupled with the limited resources suggests that companies should make more efforts on understanding and managing specific groups of customers, not the whole customers. The key issue of this paper is based on the fact that the behavioral patterns extracted from the specific groups of customers shall be different from those from the whole customers. This paper proposes the idea of pre-segmentation before developing customer classification models. We collected three customers' demographic and transactional data sets from a credit card, a tele-communication, and an insurance company in Korea, and then segmented customers by major variables. Different churn prediction models were developed from each segments and the whole data set, respectively, using the decision tree induction approach, and compared in terms of the hit ratio and the simplicity of generated rules.

• Journal of Korean Elementary Science Education
• /
• v.36 no.1
• /
• pp.31-42
• /
• 2017

This study aimed to investigate the effect of science class using multiple intelligence on science learning motivation, academic achievement and science process skill of elementary student. The number of participants were 98, 4 classes of $3^{rd}$ graders in G elementary school in B city. The experimental group, 2 classes including 49 participants, had science classes using multiple intelligence while the comparative group, 2 classes including 49 participants, took ordinary teacher-driven lessons using teacher's guidebook. Pre and post tests were done before and after executing lessons to assess the changing in each group's science learning motivation, academic achievement and science process skill. The results of this study can be summarized as follows: First, the pre and post test results of science learning motivation revealed that the experimental group had higher improvement compared to the comparative group and the difference was meaningful. Second, the post test results of the science academic achievement showed that the experimental group had higher average value compared to the comparative group and the difference was meaningful. Third, the pre and post test results of basic science process skill showed that the experimental group had higher average value compared to the comparative group and the difference was meaningful, especially in inference and prediction elements.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.497-501
• /
• 2016

Aim: To evaluate the relationship between pre-operative CA-125 levels and myometrial invasion in patients with early-stage endometrioid-type endometrial cancer. Materials and Methods: Two-hundred and sixty patients were diagnosed with endometrial cancer between January 2007 and December 2012. Of these, 136 patients with stage 1 endometrioid histologic-type and documented pre-operative serum CA-125 levels were included in the study. Age, preoperative CA-125 level, histologic grade, surgical grade, and presence of deep myometrial invasion were recorded. Additionally, 16, 20, and 35 IU/ml cutoff values were used and compared to evaluate the relationship between pre-operative CA-125 levels and myometrial invasion. Results: The average serum CA-125 level was $35.4{\pm}36.7$ in patients with deep myometrial invasion, and $21.5{\pm}35.8$ in cases without deep myometrial invasion. The relationship between the presence of deep myometrial invasion and CA-125 cut-off values (16, 20, 35 IU/ml) was statistically significant, although the correlation was weak (p<0.05). When the relationship between 16, 20 and 35 IU/ml CA-125 cut-off values and the presence of deep myometrial invasion was studied, specifity and sensitivity values were identified as: 0.60-0.68 for 16 IU/ml; 0.73-0.48 for 20 IU/ml; and 0.89-0.33 for 35 IU/ml. The sensitivity of 16 IU/ml cut-off value was higher when compared to other values. Conclusions: This study demonstrates that preoperative serum CA-125 values maybe used as a predictive test in patients with early stage endometrioid-type endometrium cancer, and as a prognostic factor alone. Further studies should be conducted to identify different CA-125 cut-off values in patients with low risk endometrial cancer.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.1034-1045
• /
• 2003

In this paper, we study a multicast transport technique for multimedia services of mobile hosts in wireless network environments. To reduce packet loss during hand-off, we propose a Pre-join scheme in overlapped area and a Buffering scheme in crossover routers. To support seamless service in real time multimedia application, these scheme use an optimal path routing which was provided in remote subscription scheme and a prediction scheme of host movements which was considered overlapped area. To evaluate the peformance of our scheme, we compare Bi-direction tunneling of mobile If, Remote subscription, and MoM by using NS-2. As a result, our scheme shows better performance in network overhead, packet loss and bandwidth's use than other schemes.