• The Journal of the Acoustical Society of Korea
• /
• v.42 no.2
• /
• pp.102-111
• /
• 2023

Automatic Music Transcription (AMT) is a task that detects and recognizes musical note events from a given audio recording. In this paper, we focus on reducing the latency of real-time AMT systems on piano music. Although neural AMT models have been adapted for real-time piano transcription, they suffer from high latency, which hinders their usefulness in interactive scenarios. To tackle this issue, we explore several techniques for reducing the intrinsic latency of a neural network for piano transcription, including reducing window and hop sizes of Fast Fourier Transformation (FFT), modifying convolutional layer's kernel size, and shifting the label in the time-axis to train the model to predict onset earlier. Our experiments demonstrate that combining these approaches can lower latency while maintaining high transcription accuracy. Specifically, our modified model achieved note F1 scores of 92.67 % and 90.51 % with latencies of 96 ms and 64 ms, respectively, compared to the baseline model's note F1 score of 93.43 % with a latency of 160 ms. This methodology has potential for training AMT models for various interactive scenarios, including providing real-time feedback for piano education.

• Korean journal of applied entomology
• /
• v.62 no.2
• /
• pp.69-78
• /
• 2023

The currently implemented Positive List System, sales manager training, and pesticide sales record systems focus on the safety of determined pesticide use, but the proposed agrochemical pharmacist (AP) system aims accurate diagnosis and reasonable prescription. In this study, 81% of famers claimed expert assistance for purchasing and applying pesticides, and 42~86% of sales managers insisted on the strengthening expertise in diagnosis and prescription. In the institutionalization of AP, a special implementation guideline is essential to embrace the present sales managers with long experience. Sales managers of commercial and agricultural cooperatives recognize the qualifications of agrochemical pharmacists as a strategy to differentiate themselves from competitors, and increase sales through market positioning of "pesticides prescribed by trustworthy agrochemical pharmacists", not sales managers anymore.

• Conservation Science in Museum
• /
• v.29
• /
• pp.99-110
• /
• 2023

The stone fragments that are missing from the stone cultural heritage have limited use beyond being directly fitted to identify their original position, as they are relatively heavy and bulky, and there is the further risk of secondary physical damage during manual work. Therefore, in this study, morphological relationships between the missing parts and the stone fragments were identified through digital restoration, and a three-dimensional (3D) printed replica was created for use at the exhibition for Stone Buddhas in Four Directions in Hwajeon-ri, Yesan, where 72 stone fragments had been excavated together. First, for the digital restoration, stone fragments of similar shapes were selected after the coordinates of the 3D scanning model were aligned in virtual space. In addition, the stone fragments were printed using a 3D printer to check whether they were physically related to the missing parts. Thus, the original positions of a total of nine stone fragments were identified. To utilize these research results in the exhibition, a 1:1 replica of the Stone Buddhas in Four Directions was produced using 3D printing technology, and the nine stone fragments were also restored to their original positions. The digital technology used in this study is of great importance in that it not only made up for the limitations of the direct manual method but also suggested the possibility of expanding its application to the fields of documentation, restoration, and replication of similar cultural heritage.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.5
• /
• pp.83-92
• /
• 2017

Because the exhibition space in the virtual reality is another kind of reality, which exits in another level, it enables us free from time and physical space, so using the virtual reality will be an effective practice for overcoming cultural divide and managing museums. Especially, virtual reality could transform a fixed physical space into portable contents, so this characteristic would be useful and meaningful when applying the outreach program, which claimed to stand for 'museum out of museum' as following. First, it will give more opportunities of experiencing museums to many people because of freedom of physical space, one of the advantages virtual reality has. Second, people will experience and understand the contents under the context, rather than simply exposing information of artifacts one by one. Third, even people who are far from a museum can experience identical contents at the same time, so this synchronicity will enhance communications among people and the society. Fourth, it will provide rich contents to people by putting a variety of exhibitions into one VR device. Fifth, it will be useful for archiving the exhibition with minimizing the loss of contents. Sixth, VR will convert museum visitors from observers to operators. Finally, VR can expand the target audience of the outreach program and develop a variety of education programs. Because museums is a public organization for overcoming cultural divide and enhancing communication, they should adopt virtual reality, which enables to extend the exhibition space and provide more opportunities of experiencing museums.

• The Journal of Korean Academy of Prosthodontics
• /
• v.61 no.3
• /
• pp.227-233
• /
• 2023

Tardive dyskinesia is an involuntary neurological movement disorder caused by long-term use of dopamine receptor-blocking drugs leading to dental implications like uncontrolled gnashing and grinding of teeth which in turn imperil the oral rehabilitation procedures as the excessive load increases the risk of prosthesis fracture. A 40-year male with a medical history of tardive dyskinesia visited the hospital to receive oral rehabilitation for missing maxillary anterior teeth. After the oral examination, tooth preparation was done on teeth 13, 15, and 23. After that silicon impression was made and the gypsum cast was digitalized using a desktop scanner and an interim prosthesis was fabricated by milling a resin block. During the try-in, the occlusal one-third of the interim prosthesis was trimmed, and an auto-polymerizing acrylic resin was applied on the occlusal surfaces and inserted in the patient's mouth. Then, the functionally generated path (FGP) of occluding surfaces of opposing arches was traced on the resin surface. When the resin was hardened, the modified interim prosthesis was removed and digitized using an intraoral scanner. The scan image was used in designing the occlusal morphology of definitive prosthesis by modifying the design of the interim prosthesis using the dual scan method. Lastly, a monolithic zirconia prosthesis was fabricated by milling a zirconia block. The definitive prosthesis was delivered reflecting the patient's occlusal scheme. This case report shows that the FGP technique with the dual scan method can help in fabricating fixed prosthesis with harmonious occlusion in a tardive dyskinesia patient.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.10
• /
• pp.309-318
• /
• 2023

Recently, each country has been moving to introduce an LCA (Life Cycle Assessment) to regulate greenhouse gas emissions. The LCA is a mean of measuring and evaluating greenhouse gas emissions generated over the entire life cycle of a vehicle. Reliable data for each electric vehicle component is needed to increase the reliability of the LCA results. To this end, studies on life cycle evaluation models using blockchain technology have been conducted. However, in the existing model, key product information is exposed to other participants. And each time parts data information is updated, it must be recorded in the blockchain ledger in the form of a transaction, which is inefficient. In this paper, we proposed a DID(Decentralized Identity)-based data collection model for LCA to collect vehicle component data and verify its validity effectively. The proposed model increases the reliability of the LCA by ensuring the validity and integrity of the collected data and verifying the source of the data. The proposed model guarantees the validity and integrity of collected data. As only user authentication information is shared on the blockchain ledger, the model prevents indiscriminate exposure of data and efficiently verifies and updates the source of data.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.3
• /
• pp.74-82
• /
• 2024

In this study, feature point detection and displacement measurement performance depending on feature extraction algorithms were compared and analyzed according to environmental changes and target types in the feature point-based displacement measurement algorithm. A three-story frame structure was designed for performance evaluation, and the displacement response of the structure was digitized into FHD (1920×1080) resolution. For performance analysis, the initial measurement distance was set to 10m, and increased up to 40m with an increment of 10m. During the experiments, illuminance was fixed to 450lux or 120lux. The artificial and natural targets mounted on the structure were set as regions of interest and used for feature point detection. Various feature detection algorithms were implemented for performance comparisons. As a result of the feature point detection performance analysis, the Shi-Tomasi corner and KAZE algorithm were found that they were robust to the target type, illuminance change, and increase in measurement distance. The displacement measurement accuracy using those two algorithms was also the highest. However, when using natural targets, the displacement measurement accuracy is lower than that of artificial targets. This indicated the limitation in extracting feature points as the resolution of the natural target decreased as the measurement distance increased.

• Industry Promotion Research
• /
• v.9 no.2
• /
• pp.69-75
• /
• 2024

Korea has entered the ranks of advanced countries in terms of economic size and technological competitiveness. However, its industrial accident fatality rate remains among the lowest in OECD countries, and recent incidents such as various building collapses have resulted in numerous deaths of workers or citizens, reminiscent of accidents in developing countries. According to the 2022 Industrial Accident Status Analysis by the Ministry of Employment and Labor, out of the 874 fatalities in work-related accidents in 2022 across all industries, 402 were in the construction industry, accounting for approximately 46% of all fatalities. In particular, the construction industry's fatality rate stands at 1.61, significantly higher than the overall industry fatality rate of 0.43, indicating its severity. Construction ranks highest in terms of fatality rates, with mining at 12.18 and fishing at 1.80. When categorizing construction projects into private and public, private projects show significantly higher figures in terms of contracts, contract amounts, accident numbers, and fatalities compared to public projects. However, unlike public agencies, many private clients lack adequate safety and health activities and lack established safety and health systems. This study aims to raise awareness among private clients about the need to establish safety and health systems and enhance safety and health activities, and to discuss the direction of future development of advanced safety and health practices among private clients.