• MALSORI
• /
• no.60
• /
• pp.29-45
• /
• 2006

We investigated whether the first syllable plays an important role in lexical access in Korean visual word recognition. To do so, one lexical decision task (LDT) and two form primed LDT experiments examined the nature of the syllabic neighborhood effect. In Experiment 1, the syllabic neighborhood density and the syllabic neighborhood frequency was manipulated. The results showed that lexical decision latencies were only influenced by the syllabic neighborhood frequency. The purpose of experiment 2 was to confirm the results of experiment 1 with form-primed LDT task. The lexical decision latency was slower in form-related condition compared to form-unrelated condition. The effect of syllabic neighborhood density was significant only in form-related condition. This means that the first syllable plays an important role in the sub-lexical process. In Experiment 3, we conducted another form-primed LDT task manipulating the number of syllabic neighbors in words with higher frequency neighborhood. The interaction of syllabic neighborhood density and form relation was significant. This result confirmed that the words with higher frequency neighborhood are more inhibited by neighbors sharing the first syllable than words with no higher frequency neighborhood in the lexical level. These findings suggest that the first syllable is the unit of neighborhood and the unit of representation in sub-lexical representation is syllable in Korea.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.24-35
• /
• 2018

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2020

This paper proposes acoustic model training using self-attention for low-resource speech recognition. In low-resource speech recognition, it is difficult for acoustic model to distinguish certain phones. For example, plosive /d/ and /t/, plosive /g/ and /k/ and affricate /z/ and /ch/. In acoustic model training, the self-attention generates attention weights from the deep neural network model. In this study, these weights handle the similar pronunciation error for low-resource speech recognition. When the proposed method was applied to Time Delay Neural Network-Output gate Projected Gated Recurrent Unit (TNDD-OPGRU)-based acoustic model, the proposed model showed a 5.98 % word error rate. It shows absolute improvement of 0.74 % compared with TDNN-OPGRU model.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.11-18
• /
• 2023

Recently, in the field of Speech Emotion Recognition (SER), many studies have been conducted to improve accuracy using voice features and modeling. In addition to modeling studies to improve the accuracy of existing voice emotion recognition, various studies using voice features are being conducted. This paper, voice files are separated by time interval in a time series method, focusing on the fact that voice emotions are related to time flow. After voice file separation, we propose a model for classifying emotions of speech data by extracting speech features Mel, Chroma, zero-crossing rate (ZCR), root mean square (RMS), and mel-frequency cepstrum coefficients (MFCC) and applying them to a recurrent neural network model used for sequential data processing. As proposed method, voice features were extracted from all files using 'librosa' library and applied to neural network models. The experimental method compared and analyzed the performance of models of recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) using the Interactive emotional dyadic motion capture Interactive Emotional Dyadic Motion Capture (IEMOCAP) english dataset.

• East Asian mathematical journal
• /
• v.31 no.2
• /
• pp.211-244
• /
• 2015

The arithmetic operation have double-sided character. One is calculation as a process, the other is understanding in results as an outcome of the operation. We harbored suspicion on students' misunderstanding in an outcome of the operation, because the curriculum has focused on the calculation, as a process of arithmetic operation. This study starts with the presentation of this problem, we tried to find the recognition ability and character in the arithmetic operation. We researched the recognition ability for 7th grade 27 students who have enough experience in arithmetic operation when studying in elementary school. And we had an interview with 3students individually, that has an error in understanding in results of arithmetic operation but has no error in calculation. We focused on 3students' detailed appearance of the ability to understand in results of arithmetic operation and analysed the changing appearance after recommending unit record using operation expression. As a result, we could find the abily to underatanding in results of arithmetic operation and applicability to recommend unit record using operation expression. Through these results, we suggested educational implications in understanding in results of arithmetic operation.

• Journal of Korean Critical Care Nursing
• /
• v.11 no.3
• /
• pp.95-107
• /
• 2018

Purpose : This study aimed to investigate the public's perception of reimbursement for the education and counseling services provided to advanced practice nurses in intensive care units. Method : This was a secondary data analysis study. The original data were collected utilizing an online panel. The sample comprised 615 individuals aged between 19 and 49 years nationwide. The study variables included the public's perception of reimbursement for education and counseling services, age, gender, education level, income, and health status. Variables such as past experience of being admitted to an intensive care unit by self, family, or relatives and the recognition of advanced practice nurses were also examined. Results : The mean of the perception score was 3.15 on a 4-point scale ranging from 1 (strongly disagree) to 4 (strongly agree). Among the participants, 89.2% answered "somewhat agreed" or "strongly agreed" to the question about the education and counseling services being covered by the National Health Insurance. Moreover, education level, past experience of being admitted to an intensive care unit by self, family, or relatives, and recognition of advanced practice nurses were significantly associated with the perception score. Conclusion : Efforts should be made to publicize the need for the education and counseling services that are provided to advanced practice nurses in intensive care units.

• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.617-630
• /
• 2019

Currently most of the vision-based structural identification research focus either on structural input (vehicle location) estimation or on structural output (structural displacement and strain responses) estimation. The structural condition assessment at global level just with the vision-based structural output cannot give a normalized response irrespective of the type and/or load configurations of the vehicles. Combining the vision-based structural input and the structural output from non-contact sensors overcomes the disadvantage given above, while reducing cost, time, labor force including cable wiring work. In conventional traffic monitoring, sometimes traffic closure is essential for bridge structures, which may cause other severe problems such as traffic jams and accidents. In this study, a completely non-contact structural identification system is proposed, and the system mainly targets the identification of bridge unit influence line (UIL) under operational traffic. Both the structural input (vehicle location information) and output (displacement responses) are obtained by only using cameras and computer vision techniques. Multiple cameras are synchronized by audio signal pattern recognition. The proposed system is verified with a laboratory experiment on a scaled bridge model under a small moving truck load and a field application on a footbridge on campus under a moving golf cart load. The UILs are successfully identified in both bridge cases. The pedestrian loads are also estimated with the extracted UIL and the predicted weights of pedestrians are observed to be in acceptable ranges.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.617-619
• /
• 2021

Since Manchu characters are written vertically and are connected without spaces within a word, a preprocessing process is required to separate the character area and the units that make up the characters before recognizing the characters. In this paper, we describe a preprocessing method that extracts the character area and cuts off the unit of the character. Unlike existing research that presupposes a method of recognizing each word or character unit, or recognizing the remaining part after removing the stem of a continuous character, this method cuts the character into each recognizable unit. It can be applied to the method of recognizing letters by combining the units. Through an experiment, the effectiveness of this method was verified.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.5
• /
• pp.775-783
• /
• 1990

In this paper we implemented the fast thinning unit by modifying the pipeline architecture which was proposed by Stanley R. Sternberg. The unit is useful in preprocessing such as image representation and pattern recognition etc. This unit is composed of interface part, local memory part, address generation part, thinning processing part and control part. In thinning processing part, we shortened the thinning part which performed by means of look up table using window mapping table. Thus we improved the weakness of SAP, in which the number of delay pipeline and window pipeline are equal to image column size. Two independent memorys using tri-state buffer enable the two direction flow of address generated by address generation part. This unit avoids the complexity of architecture and has flexibility of image size by means of simple modification of logic bits.

• Korean Journal of Occupational Health Nursing
• /
• v.10 no.1
• /
• pp.5-23
• /
• 2001

The purpose of this study was to analyse the level of recognition and performance of clinical nurses about the prevention of nosocomial infection. Subjects of the study were 425 nurses working at two university hospitals. Self report questionnaires were used to measure the level of recognition and performance about the prevention of nosocomial infection. These instruments had five dimensions of the management of nosocomial infection : hand washing, fluid therapy, foley catheterization, respiratory tract, and aseptic articles. Reliability coefficients of these instruments were found Cronbach's ${\alpha}=.94-.95$. Data were collected from August 1 to August 15, 2000. The results of the study were as follows : 1) The mean score of the recognition scores about the management of nosocomial infection was 3.89. 2) The mean score of the performance about the management of nosocomial infection was 3.42. 3) The mean score of the recognition about the management of nosocomial infection was significantly higher than the performance score(t=25.72. p<.001). 4) There was significant difference in the score of the recognition about managment in nosocomial infection according to nurses working unit(p<.001).