• Journal of Biomedical Engineering Research
• /
• v.30 no.3
• /
• pp.191-198
• /
• 2009

Phlegm smear testing for acid-fast bacilli (AFB) requires careful examination of tubercle bacilli under a microscope to distinguish between positive and negative findings. The biggest weakness of this method is the visual limitations of the examiners. It is also time-consuming, and mistakes may easily occur. This paper proposes a method of identifying tubercle bacilli that uses a computer instead of a human. To address the challenges of AFB testing, this study designs and investigates image systems that can be used to identify tubercle bacilli. The proposed system uses an electronic microscope to capture digital images that are then processed through feature extraction, image segmentation, image recognition, and neural networks to analyze tubercle bacilli. The proposed system can detect the amount of tubercle bacilli and find their locations. This paper analyzes 184 tubercle bacilli images. Fifty images are used to train the artificial neural network, and the rest are used for testing. The proposed system has a 95.6% successful identification rate, and only takes 0.8 seconds to identify an image.

• Korean Journal of Social Welfare
• /
• v.44
• /
• pp.209-231
• /
• 2001

Recently, child abuse is mentioned in revised Child Welfare Law, on the other hand, elder abuse is not yet recognized as a social problem and little addressed in the field of social service. Like this, elder abuse has gotten less public and professional attention than other areas within the family abuse field. Despite the lack of attention to elder abuse, the number of elder abuse reports and incidents is likely to increase in the future. Based on the recognition that current effort and approach to elder abuse is not appropriate, this study attemped to briefly review laws and programs addressing elder abuse in the United States which have shaped in other contries. In the United States where various laws and programs that address elder abuse exit, there are incresing arguments that addressing elder abuse in the area of social service rather than in the criminal justice systems is more desirable. Because the most common form of elder abuse is not physical abuse but neglect including self-neglect. Self-neglect and neglect caused by caregivers' burden can not be addressed through criminal justice systems appropriately. From these experiences of the United States, the implications for policy, programs, and practice aimed at intervening elder abuse were discussed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.31-34
• /
• 2015

The U.S. music market is a lucrative market for many foreign musicians due to its sheer size and it continues to play a leading role in the world music industry. However, it is a challenge to gain entry into that market and an even greater challenge to achieve success and fame within it. In fact, changes in the media paradigm have allowed for musicians to be able to independently produce their own songs and promote them globally. Some scholars address that the media paradigm shifting from traditional outlets to new outlets gives a chance to bypass traditional gatekeepers when entering the U.S. music market. Based on this scenario, this article examined two songs from Korean singer, Psy: Gangnam Style and Gentleman as a single case study. Utilizing Google Trends as a source of information, this study examined how each song's recognition among American music fans was different based on radio spins on Top 40 commercial radio stations. This article sheds new light on radio, which has been neglected due to the media paradigm shift, and presents how radio programmers are part of a complicated gatekeeping process which ultimately decides which songs are to gain popularity.

• The KIPS Transactions:PartD
• /
• v.17D no.1
• /
• pp.59-66
• /
• 2010

Traditional OCR engines are designed to the scanned documents in calibrated environment. Three dimensional perspective distortion and smooth distortion in images are critical problems caused by un-calibrated devices, e.g. image from smart phones. To meet the growing demand of character recognition of texts embedded in the photos acquired from the non-calibrated hand-held devices, we address the problem in three categorical aspects: rotational invariant method of text region extraction, scale invariant method of text line segmentation, and three dimensional perspective mapping. With the integration of the methods, we developed an OCR for camera-captured images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.589-592
• /
• 2001

본 논문에서는 고속 필기 한글 주소 인식을 위한 낱자 인식기를 제안한다. 인식 대상은 우편번호 여섯 자리에 할당된 주소에 출현 빈도가 높은 필기 한글 469 자이다. 제안된 방법은 낱자 인식 기법을 채택하고 있으며, 인식률과 처리속도를 향상시키기 위하여 2 단계 인식 전략을 채택하였다. 인식기로는 다층퍼셉트론, 최소거리분류기, Subspace 방법을 고려한다. 다층퍼셉트론은 비교적 높은 인식률과 처리속도를 보유하지만 출력값이 확률이 아님으로써 후처리를 필요로 하는 시스템에서 사용하기 어렵다. 최소거리분류기는 간단한 알고리즘으로 처리속도가 높고 확률을 출력하는 장점을 갖지만 인식률이 낮아 활용되기 어렵다. 또한 Subspace 방법은 인식률이 높고 확률을 출력하지만 처리속도가 매우 느리다는 단점이 있다. 따라서 제안방법에서는 처리속도가 높은 인식기 - 다층퍼셉트론, 최소거리분류기 - 를 사용하여 선인식을 수행한 후, 이 결과를 활용하여 인식 대상을 제한한 후 Subspace 방법을 사용하여 정확하게 인식하는 전략을 도입함으로써, 높은 인식결과를 유지하면서 처리속도를 높이고 후처리에 적합하도록 하였다. PE92 데이터베이스를 사용하여 실험한 결과 제안방법이 한글 469 자에 대하여 비교적 높은 인식률과 처리속도를 갖음을 알 수 있었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.2
• /
• pp.77-82
• /
• 2012

This paper presents a hardware-implemented face regions stabilization algorithm that stabilizes facial regions using the locations and sizes of human faces found by a face detection system. Face detection algorithms extract facial features or patterns determining the presence of a face from a video source and detect faces via a classifier trained on example faces. But face detection results has big variations in the detected locations and sizes of faces by slight shaking. To address this problem, the high frequency reduce filter that reduces variations in the detected face regions by taking into account the face range information between the current and previous video frames are implemented in addition to center distance comparison and zooming operations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2764-2782
• /
• 2021

Existing city-level boundary nodes identification methods need to locate all IP addresses on the path to differentiate which IP is the boundary node. However, these methods are susceptible to time-delay, the accuracy of location information and other factors, and the resource consumption of locating all IPes is tremendous. To improve the recognition rate and reduce the locating cost, this paper proposes an algorithm for city-level boundary node identification based on bidirectional approaching. Different from the existing methods based on time-delay information and location results, the proposed algorithm uses topological analysis to construct a set of candidate boundary nodes and then identifies the boundary nodes. The proposed algorithm can identify the boundary of the target city network without high-precision location information and dramatically reduces resource consumption compared with the traditional algorithm. Meanwhile, it can label some errors in the existing IP address database. Based on 45,182,326 measurement results from Zhengzhou, Chengdu and Hangzhou in China and New York, Los Angeles and Dallas in the United States, the experimental results show that: The algorithm can accurately identify the city boundary nodes using only 20.33% location resources, and more than 80.29% of the boundary nodes can be mined with a precision of more than 70.73%.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• Knowledge Management Research
• /
• v.20 no.1
• /
• pp.133-153
• /
• 2019

Due to the uncertainty of dynamic business environment, modern organizations have been giving attention to dynamic capabilities beyond traditional notion of core competence. Among them, absorptive capacity and boundary-spanning activity are considered the most important. The former refers to activities regarding acquisition, assimilation, transformation and exploitation of internal and external knowledge. The latter is composed of boundary-loosening and boundary-tightening activities to detect internal or external information and then to preserve, protect, or acquire resources. Thus, both have achieved wide recognition as a potential source of change and innovation. This study investigated the cross-level relation between boundary-spanning leadership at team level and absorptive capacity at individual level. We also explored self-efficacy and extra-role behavior that can affect employees' absorptive capacity. To test multi-level analysis, the survey data were collected from 862 members in 137 teams of different firms. Results revealed that boundary-spanning leadership had the positive cross-level impact on absorptive capacity in the team context. Moreover, absorptive capacity was positively associated with self-efficacy and extra-role behavior at individual level. Based on these findings, we provided theoretical and practical implications to address rapidly changing environments and discussed limitations of this paper for further research.

• Tuberculosis and Respiratory Diseases
• /
• v.82 no.1
• /
• pp.6-14
• /
• 2019

Sepsis is a life-threatening condition caused by infection and represents a substantial global health burden. Recent epidemiological studies showed that sepsis mortality rates have decreased, but that the incidence has continued to increase. Although a mortality benefit from early-goal directed therapy (EGDT) in patients with severe sepsis or septic shock was reported in 2001, three subsequent multicenter randomized studies showed no benefits of EGDT versus usual care. Nonetheless, the early administration of antibiotics and intravenous fluids is considered crucial for the treatment of sepsis. In 2016, new sepsis definitions (Sepsis-3) were issued, in which organ failure was emphasized and use of the terms "systemic inflammatory response syndrome" and "severe sepsis" was discouraged. However, early detection of sepsis with timely, appropriate interventions increases the likelihood of survival for patients with sepsis. Also, performance improvement programs have been associated with a significant increase in compliance with the sepsis bundles and a reduction in mortality. To improve sepsis management and reduce its burden, in 2017, the World Health Assembly and World Health Organization adopted a resolution that urged governments and healthcare workers to implement appropriate measures to address sepsis. Sepsis should be considered a medical emergency, and increasing the level of awareness of sepsis is essential.