• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.68-84
• /
• 2024

This paper describes the development of a system and algorithms for high-quality welfare services by recognizing behavior development indicators (activity, sociability, danger) in children aged 0 to 2 years old using action recognition technology. Action recognition targeted 11 behaviors from lying down in 0-year-olds to jumping in 2-year-olds, using data directly obtained from actual videos provided for research purposes by three nurseries in the Gwangju and Jeonnam regions. A dataset of 1,867 actions from 425 clip videos was built for these 11 behaviors, achieving an average recognition accuracy of 97.4%. Additionally, for real-world application, the Edge Video Analyzer (EVA), a behavior analysis device, was developed and implemented with a region-specific random frame selection-based PoseC3D algorithm, capable of recognizing actions in real-time for up to 30 people in four-channel videos. The developed system was installed in three nurseries, tested by ten childcare teachers over a month, and evaluated through surveys, resulting in a perceived accuracy of 91 points and a service satisfaction score of 94 points.

• Korean Journal of Radiology
• /
• v.25 no.6
• /
• pp.565-574
• /
• 2024

Objective: To evaluate the safety and clinical outcomes of the Passeo-18 Lux drug-coated balloon (DCB) in endovascular revascularization procedures under real-world conditions in a Korean population with atherosclerotic disease of the infrainguinal arteries, including below-the-knee (BTK) arteries. Materials and Methods: Eight institutions in the Republic of Korea participated in this prospective, multicenter, single-arm, post-market surveillance study. Two hundred patients with Rutherford class 2-5 peripheral arterial disease and infrainguinal lesions suitable for endovascular treatment were competitively enrolled. Data were collected at baseline, the time of intervention, discharge, and 1-, 6-, 12-, and 24-month follow-up visits. The primary safety endpoint was freedom from major adverse events (MAE) within 6 months (except when limiting the time frame for procedure- or device-related mortality to within 30 days), and the primary effectiveness endpoint was freedom from clinically driven target lesion revascularization (CD-TLR) within 12 months after the procedure. Results: A total of 197 patients with 332 target lesions were analyzed. Two-thirds of the patients had diabetes mellitus, and 41.6% had chronic limb-threatening ischemia. The median target lesion length was 100 mm (interquartile range: 56-133 mm). Of the target lesions, 35.2% were occlusions, and 14.8% were located in the BTK arteries. Rate of freedom from MAE was 97.9% at 6 months, and the rate of freedom from CD-TLR was 95.0% and 92.2% at 12 and 24 months, respectively. Subgroup analysis of 43 patients and 49 target lesions involving the BTK arteries showed rate of freedom from MAE of 92.8% at 6 months and rates of freedom from CD-TLR of 88.8% and 84.4% at 12 and 24 months, respectively. Conclusion: The results of the present study, including the BTK subgroup analysis, showed outcomes comparable to those of other DCB studies, confirming the safety and effectiveness of Passeo-18 Lux DCB in the Korean population.

• Korean Journal of Radiology
• /
• v.23 no.2
• /
• pp.256-263
• /
• 2022

Objective: This study aimed to evaluate the image quality and dose reduction of low-dose three-dimensional (3D) rotational angiography (RA) for evaluating intracranial aneurysms. Materials and Methods: We retrospectively evaluated the clinical data and 3D RA datasets obtained from 146 prospectively registered patients (male:female, 46:100; median age, 58 years; range, 19-81 years). The subjective image quality of 79 examinations obtained from a conventional method and 67 examinations obtained from a low-dose (5-seconds and 0.10-μGy/frame) method was assessed by two neurointerventionists using a 3-point scale for four evaluation criteria. The total image quality score was then obtained as the average of the four scores. The image quality scores were compared between the two methods using a noninferiority statistical testing, with a margin of -0.2 (i.e., score of low-dose group - score of conventional group). For the evaluation of dose reduction, dose-area product (DAP) and air kerma (AK) were analyzed and compared between the two groups. Results: The mean total image quality score ± standard deviation of the 3D RA was 2.97 ± 0.17 by reader 1 and 2.95 ± 0.20 by reader 2 for conventional group and 2.92 ± 0.30 and 2.95 ± 0.22, respectively, for low-dose group. The image quality of the 3D RA in the low-dose group was not inferior to that of the conventional group according to the total image quality score as well as individual scores for the four criteria in both readers. The mean DAP and AK per rotation were 5.87 Gy-cm² and 0.56 Gy, respectively, in the conventional group, and 1.32 Gy-cm² (p < 0.001) and 0.17 Gy (p < 0.001), respectively, in the low-dose group. Conclusion: Low-dose 3D RA was not inferior in image quality and reduced the radiation dose by 70%-77% compared to the conventional 3D RA in evaluating intracranial aneurysms.

• IMMUNE NETWORK
• /
• v.20 no.5
• /
• pp.41.1-41.11
• /
• 2020

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) is a positive-sense single-stranded RNA (+ssRNA) that causes coronavirus disease 2019 (COVID-19). The viral genome encodes twelve genes for viral replication and infection. The third open reading frame is the spike (S) gene that encodes for the spike glycoprotein interacting with specific cell surface receptor - angiotensin converting enzyme 2 (ACE2) - on the host cell membrane. Most recent studies identified a single point mutation in S gene. A single point mutation in S gene leading to an amino acid substitution at codon 614 from an aspartic acid 614 into glycine (D614G) resulted in greater infectivity compared to the wild type SARS-CoV2. We were interested in investigating the mutation region of S gene of SARS-CoV2 from Korean COVID-19 patients. New mutation sites were found in the critical receptor binding domain (RBD) of S gene, which is adjacent to the aforementioned D614G mutation residue. This specific sequence data demonstrated the active progression of SARS-CoV2 by mutations in the RBD of S gene. The sequence information of new mutations is critical to the development of recombinant SARS-CoV2 spike antigens, which may be required to improve and advance the strategy against a wide range of possible SARS-CoV2 mutations.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.71-90
• /
• 2020

Recently, the global insurance industry is rapidly developing digital transformation through the use of artificial intelligence technologies such as machine learning, natural language processing, and deep learning. As a result, more and more foreign insurers have achieved the success of artificial intelligence technology-based InsurTech and platform business, and Ping An Insurance Group Ltd., China's largest private company, is leading China's global fourth industrial revolution with remarkable achievements in InsurTech and Digital Platform as a result of its constant innovation, using 'finance and technology' and 'finance and ecosystem' as keywords for companies. In response, this study analyzed the InsurTech and platform business activities of Ping An Insurance Group Ltd. through the ser-M analysis model to provide strategic implications for revitalizing AI technology-based businesses of domestic insurers. The ser-M analysis model has been studied so that the vision and leadership of the CEO, the historical environment of the enterprise, the utilization of various resources, and the unique mechanism relationships can be interpreted in an integrated manner as a frame that can be interpreted in terms of the subject, environment, resource and mechanism. As a result of the case analysis, Ping An Insurance Group Ltd. has achieved cost reduction and customer service development by digitally innovating its entire business area such as sales, underwriting, claims, and loan service by utilizing core artificial intelligence technologies such as facial, voice, and facial expression recognition. In addition, "online data in China" and "the vast offline data and insights accumulated by the company" were combined with new technologies such as artificial intelligence and big data analysis to build a digital platform that integrates financial services and digital service businesses. Ping An Insurance Group Ltd. challenged constant innovation, and as of 2019, sales reached $155 billion, ranking seventh among all companies in the Global 2000 rankings selected by Forbes Magazine. Analyzing the background of the success of Ping An Insurance Group Ltd. from the perspective of ser-M, founder Mammingz quickly captured the development of digital technology, market competition and changes in population structure in the era of the fourth industrial revolution, and established a new vision and displayed an agile leadership of digital technology-focused. Based on the strong leadership led by the founder in response to environmental changes, the company has successfully led InsurTech and Platform Business through innovation of internal resources such as investment in artificial intelligence technology, securing excellent professionals, and strengthening big data capabilities, combining external absorption capabilities, and strategic alliances among various industries. Through this success story analysis of Ping An Insurance Group Ltd., the following implications can be given to domestic insurance companies that are preparing for digital transformation. First, CEOs of domestic companies also need to recognize the paradigm shift in industry due to the change in digital technology and quickly arm themselves with digital technology-oriented leadership to spearhead the digital transformation of enterprises. Second, the Korean government should urgently overhaul related laws and systems to further promote the use of data between different industries and provide drastic support such as deregulation, tax benefits and platform provision to help the domestic insurance industry secure global competitiveness. Third, Korean companies also need to make bolder investments in the development of artificial intelligence technology so that systematic securing of internal and external data, training of technical personnel, and patent applications can be expanded, and digital platforms should be quickly established so that diverse customer experiences can be integrated through learned artificial intelligence technology. Finally, since there may be limitations to generalization through a single case of an overseas insurance company, I hope that in the future, more extensive research will be conducted on various management strategies related to artificial intelligence technology by analyzing cases of multiple industries or multiple companies or conducting empirical research.

• Asia pacific journal of information systems
• /
• v.18 no.4
• /
• pp.57-81
• /
• 2008

Knowledge is an essential strategic weapon for sustaining competitive advantage and is the key determinant for organizational growth. When knowledge is shared and disseminated throughout the organization, it increases an organization's value by providing the ability to respond to new and unusual situations. The growing importance of knowledge as a critical resource has forced executives to pay attention to their organizational knowledge. Organizations are increasingly undertaking knowledge management initiatives and making significant investments. Knowledge sourcing is considered as the first important step in effective knowledge management. Most firms continue to make an effort to realize the benefits of knowledge management by using various knowledge sources effectively. Appropriate knowledge sourcing strategies enable organizations to create, acquire, and access knowledge in a timely manner by reducing search and transfer costs, which result in better firm performance. In response, the knowledge management literature has devoted substantial attention to the analysis of knowledge sourcing strategies. Many studies have categorized knowledge sourcing strategies into intemal- and external-oriented. Internal-oriented sourcing strategy attempts to increase firm performance by integrating knowledge within the boundary of the firm. On the contrary, external-oriented strategy attempts to bring knowledge in from outside sources via either acquisition or imitation, and then to transfer that knowledge across to the organization. However, the extant literature on knowledge sourcing strategies focuses primarily on large organizations. Although many studies have clearly highlighted major differences between large and small firms and the need to adopt different strategies for different firm sizes, scant attention has been given to analyzing how knowledge sourcing strategies affect firm performance in small firms and what are the differences between small and large firms in the patterns of knowledge sourcing strategies adoption. This study attempts to advance the current literature by examining the impact of knowledge sourcing strategies on small firm performance from a holistic perspective. By drawing on knowledge based theory from organization science and complementarity theory from the economics literature, this paper is motivated by the following questions: (1) what are the adoption patterns of different knowledge sourcing strategies in small firms (i,e., what sourcing strategies should be adopted and which sourcing strategies work well together in small firms)?; and (2) what are the performance implications of these adoption patterns? In order to answer the questions, this study developed three hypotheses. First hypothesis based on knowledge based theory is that internal-oriented knowledge sourcing is positively associated with small firm performance. Second hypothesis developed on the basis of knowledge based theory is that external-oriented knowledge sourcing is positively associated with small firm performance. The third one based on complementarity theory is that pursuing both internal- and external-oriented knowledge sourcing simultaneously is negatively or less positively associated with small firm performance. As a sampling frame, 700 firms were identified from the Annual Corporation Report in Korea. Survey questionnaires were mailed to owners or executives who were most erudite about the firm s knowledge sourcing strategies and performance. A total of 188 companies replied, yielding a response rate of 26.8%. Due to incomplete data, 12 responses were eliminated, leaving 176 responses for the final analysis. Since all independent variables were measured using continuous variables, supermodularity function was used to test the hypotheses based on the cross partial derivative of payoff function. The results indicated no significant impact of internal-oriented sourcing strategies while positive impact of external-oriented sourcing strategy on small firm performance. This intriguing result could be explained on the basis of various resource and capital constraints of small firms. Small firms typically have restricted financial and human resources. They do not have enough assets to always develop knowledge internally. Another possible explanation is competency traps or core rigidities. Building up a knowledge base based on internal knowledge creates core competences, but at the same time, excessive internal focused knowledge exploration leads to behaviors blind to other knowledge. Interestingly, this study found that Internal- and external-oriented knowledge sourcing strategies had a substitutive relationship, which was inconsistent with previous studies that suggested complementary relationship between them. This result might be explained using organizational identification theory. Internal organizational members may perceive external knowledge as a threat, and tend to ignore knowledge from external sources because they prefer to maintain their own knowledge, legitimacy, and homogeneous attitudes. Therefore, integrating knowledge from internal and external sources might not be effective, resulting in failure of improvements of firm performance. Another possible explanation is small firms resource and capital constraints and lack of management expertise and absorptive capacity. Although the integration of different knowledge sources is critical, high levels of knowledge sourcing in many areas are quite expensive and so are often unrealistic for small enterprises. This study provides several implications for research as well as practice. First this study extends the existing knowledge by examining the substitutability (and complementarity) of knowledge sourcing strategies. Most prior studies have tended to investigate the independent effects of these strategies on performance without considering their combined impacts. Furthermore, this study tests complementarity based on the productivity approach that has been considered as a definitive test method for complementarity. Second, this study sheds new light on knowledge management research by identifying the relationship between knowledge sourcing strategies and small firm performance. Most current literature has insisted complementary relationship between knowledge sourcing strategies on the basis of data from large firms. Contrary to the conventional wisdom, this study identifies substitutive relationship between knowledge sourcing strategies using data from small firms. Third, implications for practice highlight that managers of small firms should focus on knowledge sourcing from external-oriented strategies. Moreover, adoption of both sourcing strategies simultaneousiy impedes small firm performance.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.21 no.1
• /
• pp.15-22
• /
• 2017

Purpose During Brain SPECT study, critical factor for proper study with $^{99m}Tc-ECD$ or $^{99m}Tc-HMPAO$ is one of the important causes to patent's movement. It causes both improper diagnosis and examination failure. In this study, we evaluated the effect of Dynamic Continuous Mode Acquisition compared to Step and Shoot Mode to raise efficacy and reject the data set with movement, as well as, be reconstructed in certain criteria. Materials and Methods Deluxe Jaszczak phantom and Hoffman 3D Brain phantom were used to find proper standard data set and exact time. Step and Shoot Mode and Dynamic Continuous Mode Acquisition were performed with SymbiaT16. Firstly, Deluxe Jaszczak phantom was filled with $Na^{99m}TcO_4$ 370 MBq and obtained in 60 minutes to check spatial resolution compared with Step and Shoot Mode and Dynamic Continuous Mode. The second, the Hoffman 3D Phantom filled with $Na^{99m}TcO_4$ 74 MBq was acquired for 15 Frame/minutes to evaluate visual assessment and quantification. Finally, in the Deluxe Jaszczak phantom, Spheres and Rods were measured by MI Apps program as well as, checking counts with the frontal lobe, temporal lobe, occipital lobe, cerebellum and hypothalamus parts was performed in the Hoffman 3D Brain Phantom. Results In Brain SPECT Study, using Dynamic Continuous Mode rather than current Step and Shoot Mode, we can do the reading using the 20 to 50 % of the acquired image, and during the test if the patient moves, we can remove unneeded image to reduce the rate of restudy and reinjection. Conclusion Dynamic Continuous Mode in Brain study condition enhances effects compared to Step and Shoot Mode. And also is powerful method to reduce reacquisition rate caused by patient movement. The findings further indicate that it suggest rejection limit to maintain clinical value with certain reconstruction factors compared with Tomo data set. Further examination to improve spatial resolution, SPECT/CT should be the answer for that.

• Journal of Climate Change Research
• /
• v.3 no.2
• /
• pp.117-128
• /
• 2012

The Government of South Korea has continued its effort to fixate virtuous circle of economic growth and climate change response to cope with international demands and pressure to commitment for greenhouse gas reduction effectively. Nationally, Korean Government has established "Enforcement of the Framework Act on Low carbon, Green Growth"(2010. 4. 13) to implement national mid-term GHG mitigation goal(30% reduction by 2020 compare to BAU), which established the foundation for phased GHG mitigation by setting up the sectoral and industrial goal, adopting GHG and Energy Target Management System. Also, follow-up measures are taken such as planning and control of mid-term and short-term mitigation target by detailed analysis of potential mitigation of sector and industry, building up the infrastructure for periodic and systematic analysis of target management. Likewise, it is required to establish more accurate, reliable and detailed sectoral GHG inventory for successfully establishment and implement the frame act. In comparison to the $CO_2$ emission, Especially fluorinated greenhouse gases (HFCs, PFCs, $SF_6$) are lacking research to build the greenhouse gas inventories to identify emissions sources and collection of the applicable collection activities data. In this study, with the refrigeration and air conditioning sector being used to fluorine refrigerant(HFCs) as the center, greenhouse gas emission estimation methodology for evaluating the feasibility of using this methodology look over and mobile air conditioning, fixed air conditioning, household refrigeration equipment, commercial refrigeration equipment for the greenhouse gas emissions were calculated. First look at in terms of methodology, refrigeration and air conditioning sector GHG emissions in developing country-specific emission factors and activity data of the industrial sector the construction of the DB is not enough, it's 2006 IPCC Guidelines Tier 2a (emission factor approach) rather than the Tier 2b (mass balance approach) deems appropriate, and each detail by process, sectoral activity data more accurate, if DB is built Tier 2a (emission factor approach) can be applied will also be judged. Refrigeration and air conditioning sector in 2009 due to the use of refrigerant greenhouse gas emissions ($CO_2eq.$) assessment results, portable air conditioner 1,974,646 ton to year, fixed-mount air conditioner 1,011,754 ton to year, household refrigeration unit 4,396 ton to year, commercial refrigeration equipment 1,263 ton to year was estimated to total 2,992,037 tons.

• Progress in Medical Physics
• /
• v.23 no.2
• /
• pp.91-98
• /
• 2012

Verification of internal organ motion during treatment and its feedback is essential to accurate dose delivery to the moving target. We developed an offline based internal organ motion verification system (IMVS) using cine EPID images and evaluated its accuracy and availability through phantom study. For verification of organ motion using live cine EPID images, a pattern matching algorithm using an internal surrogate, which is very distinguishable and represents organ motion in the treatment field, like diaphragm, was employed in the self-developed analysis software. For the system performance test, we developed a linear motion phantom, which consists of a human body shaped phantom with a fake tumor in the lung, linear motion cart, and control software. The phantom was operated with a motion of 2 cm at 4 sec per cycle and cine EPID images were obtained at a rate of 3.3 and 6.6 frames per sec (2 MU/frame) with $1,024{\times}768$ pixel counts in a linear accelerator (10 MVX). Organ motion of the target was tracked using self-developed analysis software. Results were compared with planned data of the motion phantom and data from the video image based tracking system (RPM, Varian, USA) using an external surrogate in order to evaluate its accuracy. For quantitative analysis, we analyzed correlation between two data sets in terms of average cycle (peak to peak), amplitude, and pattern (RMS, root mean square) of motion. Averages for the cycle of motion from IMVS and RPM system were $3.98{\pm}0.11$ (IMVS 3.3 fps), $4.005{\pm}0.001$ (IMVS 6.6 fps), and $3.95{\pm}0.02$ (RPM), respectively, and showed good agreement on real value (4 sec/cycle). Average of the amplitude of motion tracked by our system showed $1.85{\pm}0.02$ cm (3.3 fps) and $1.94{\pm}0.02$ cm (6.6 fps) as showed a slightly different value, 0.15 (7.5% error) and 0.06 (3% error) cm, respectively, compared with the actual value (2 cm), due to time resolution for image acquisition. In analysis of pattern of motion, the value of the RMS from the cine EPID image in 3.3 fps (0.1044) grew slightly compared with data from 6.6 fps (0.0480). The organ motion verification system using sequential cine EPID images with an internal surrogate showed good representation of its motion within 3% error in a preliminary phantom study. The system can be implemented for clinical purposes, which include organ motion verification during treatment, compared with 4D treatment planning data, and its feedback for accurate dose delivery to the moving target.