• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.234-240
• /
• 2021

In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

• The Journal of Internal Korean Medicine
• /
• v.40 no.3
• /
• pp.409-424
• /
• 2019

Objectives: This research aimed to confirm the efficacy of oriental medicine in sixth cranial nerve palsy and to evaluate the quality of the studies. Methods: Using the medical subject heading (MeSH) keywords "abducens nerve palsy", "abducens nerve paralysis", "sixth nerve palsy", "herbal medicine", "Chinese medicine", "oriental medicine" and "acupuncture", we collected the research papers through an electronic database search in Oriental Medicine Advanced Searching Integrated System (OASIS), National Discovery for Science Leaders (NDSL), PubMed, Cochran Library, and China National Knowledge Infrastructure (CNKI). Results: A total of 136 papers were searched from the databases. Among these, 15 case reports and 8 randomized controlled trials (RCTs) met our criteria. 17 articles were found on the use of acupuncture as the main intervention, 11 on the use of herbal medicine as the main intervention, and 9 on the use of electroacupuncture as the main intervention. The frequently used acupoints were LI4, EX-HN5, GB1, BL2, TE23, LR3, BL1, ST2, GB20, and ST36. All 23 studies confirmed the efficacy of Korean medicine. According to the assessment using the risk of bias, the overall quality of the RCTs was low. Conclusions: Twenty-three papers suggested that Korean medicine treatment for abducens nerve palsy was effective in many cases. Analyzing the potential bias was difficult.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.109-118
• /
• 2019

Road information is one of the most significant geospatial data for applications such as transportation, city planning, map generation, LBS (Location-Based Service), and GIS (Geographic Information System) database updates. Robust technologies to acquire and update accurate road information can contribute significantly to geospatial industries. In this study, we analyze the limitations of ACO (Ant Colony Optimization) road extraction, which is a recently introduced object-based road extraction method using high-resolution satellite images. Object-based ACO road extraction can efficiently extract road areas using both spectral and morphological information. This method, however, is highly dependent on object descriptor information and requires manual designations of descriptors. Moreover, reasonable iteration closing point needs to be specified. In this study, we perform improved ACO road extraction on VHR (Very High Resolution) optical satellite image by proposing an optimization stopping criteria and descriptors that complements the limitations of the existing method. The proposed method revealed 52.51% completeness, 6.12% correctness, and a 51.53% quality improvement over the existing algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.29-34
• /
• 2019

In this study, a gasoline test vehicle was evaluated for drive quality in emissions and fuel economy tests. The measurement results were compared with the manufacturer's suggested values to evaluate whether the tolerance ranges (fuel efficiency -5%, greenhouse gas +5%) were exceeded. We carried out tests with test subjects based on the SAE J2951 evaluation method. The test vehicle was a 2L gasoline vehicle. The drive following performance was found to increase under deliberate driving conditions and decreased in smooth driving conditions. As a result of the analysis of the drive following performance, the closer the value is to 1, the more accurate the driving is. (-) indicates harsh conditions, and (+) indicates gentle conditions. The basic data on the driver following between testers was obtained by analysis of the tests. The fuel efficiency correlation with the drive following performance within the target speed range of the fuel consumption mode. In the future, these measurement results can serve as key data for securing an exhaust gas database and fuel efficiency system for each measurement mode.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.187-194
• /
• 2021

OSINT(Open Source Intelligence), rapidly increasing on the surface web in various forms, can also be used for criminal investigations by using profiling. This technique has become quite common in foreign investigative agencies such as the United States. On the other hand, in Korea, it is not used a lot, and there is a large deviation in the quantity and quality of information acquired according to the experience and knowledge level of investigator. Unlike Bazzell's most well-known model, we designed a Korean-style OSINT-based profiling technique that considers the Korean web environment and provides timeline information, focusing on the improved workflow. The database schema to improve the efficiency of profiling is also presented. Using this, we can obtain search results that guarantee a certain level of quantity and quality. And it can also be used as a standard training course. To increase the effectiveness and efficiency of criminal investigations using this technique, it is necessary to strengthen the legal basis and to introduce automation technologies.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• Economic and Environmental Geology
• /
• v.56 no.6
• /
• pp.887-897
• /
• 2023

Leading waste disposal countries, such as Sweden, Switzerland, and the United Kingdom, conduct safety assessments across all stages of High-Level Radioactive Waste Deep Geological Disposal Facilities-from planning and site selection to construction, operation, closure, and post-closure management. As safety assessments are repeatedly performed at each stage, generating vast amounts of diverse data over extended periods, it is essential to construct a database for safety assessment and establish a data management system. In this study, the safety assessment data management systems of leading countries, were analyzed, categorizing them into 1) input and reference data for safety assessments, 2) guidelines for data management, 3) organizational structures for data management, and 4) computer systems for data management. While each country exhibited differences in specific aspects, commonalities included the classification of safety assessment input data based on disposal system components, the establishment of organizations to supply, use, and manage this data, and the implementation of quality management systems guided by instructions and manuals. These cases highlight the importance of data management systems and document management systems for securing the safety and enhancing the reliability of High-Level Radioactive Waste Disposal Facilities. To achieve this, the classification of input data that can be flexibly and effectively utilized, ensuring the consistency and traceability of input data, and establishing a quality management system for input data and document management are necessary.

• Journal of Chest Surgery
• /
• v.57 no.2
• /
• pp.160-168
• /
• 2024

Background: Data on perioperative outcomes of emergent versus elective resection in esophageal cancer patients requiring esophagectomy are lacking. We investigated whether emergent resection was associated with increased risks of morbidity and mortality. Methods: Data on patients with esophageal malignancy who underwent esophagectomy from 2005 to 2020 were retrospectively analyzed from the American College of Surgeons National Surgical Quality Improvement Program database. Thirty-day complication and mortality rates were compared between emergent esophagectomy (EE) and non-emergent esophagectomy. Logistic regression assessed factors associated with complications and mortality. Results: Of 10,067 patients with malignancy who underwent esophagectomy, 181 (1.8%) had EE, 64% had preoperative systemic inflammatory response syndrome, sepsis, or septic shock, and 44% had bleeding requiring transfusion. The EE group had higher American Society of Anesthesiologists (ASA) class and functional dependency. More transhiatal esophagectomies and diversions were performed in the EE group. After EE, the rates of 30-day mortality (6.1% vs. 2.8%), overall complications (65.2% vs. 44.2%), bleeding, pneumonia, prolonged intubation, and positive margin (17.7% vs. 7.4%) were higher, while that of anastomotic leak was similar. On adjusted logistic regression, older age, lower albumin, higher ASA class, and fragility were associated with increased complications and mortality. McKeown esophagectomy and esophageal diversion were associated with a higher risk of postoperative complications. EE was associated with 30-day postoperative complications (odds ratio, 2.39; 95% confidence interval, 1.66-3.43; p<0.0001). Conclusion: EE was associated with a more than 2-fold increase in complications compared to elective procedures, but no independent increase in short-term mortality. These findings may help guide data-driven critical decision-making for surgery in select cases of complicated esophageal malignancy.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_2
• /
• pp.1565-1576
• /
• 2023

An atmospheric correction algorithm based on the radiative transfer model is required to obtain remote-sensing reflectance (R_rs) from the Geostationary Ocean Color Imager-II (GOCI-II) observed at the top-of-atmosphere. This R_rs derived from the atmospheric correction is utilized to estimate various marine environmental parameters such as chlorophyll-a concentration, total suspended materials concentration, and absorption of dissolved organic matter. Therefore, an atmospheric correction is a fundamental algorithm as it significantly impacts the reliability of all other color products. However, in clear waters, for example, atmospheric path radiance exceeds more than ten times higher than the water-leaving radiance in the blue wavelengths. This implies atmospheric correction is a highly error-sensitive process with a 1% error in estimating atmospheric radiance in the atmospheric correction process can cause more than 10% errors. Therefore, the quality assessment of R_rs after the atmospheric correction is essential for ensuring reliable ocean environment analysis using ocean color satellite data. In this study, a Quality Assurance (QA) algorithm based on in-situ R_rs data, which has been archived into a database using Sea-viewing Wide Field-of-view Sensor (SeaWiFS) Bio-optical Archive and Storage System (SeaBASS), was applied and modified to consider the different spectral characteristics of GOCI-II. This method is officially employed in the National Oceanic and Atmospheric Administration (NOAA)'s ocean color satellite data processing system. It provides quality analysis scores for R_rs ranging from 0 to 1 and classifies the water types into 23 categories. When the QA algorithm is applied to the initial phase of GOCI-II data with less calibration, it shows the highest frequency at a relatively low score of 0.625. However, when the algorithm is applied to the improved GOCI-II atmospheric correction results with updated calibrations, it shows the highest frequency at a higher score of 0.875 compared to the previous results. The water types analysis using the QA algorithm indicated that parts of the East Sea, South Sea, and the Northwest Pacific Ocean are primarily characterized as relatively clear case-I waters, while the coastal areas of the Yellow Sea and the East China Sea are mainly classified as highly turbid case-II waters. We expect that the QA algorithm will support GOCI-II users in terms of not only statistically identifying R_rs resulted with significant errors but also more reliable calibration with quality assured data. The algorithm will be included in the level-2 flag data provided with GOCI-II atmospheric correction.