• Journal of the Korean Society of Radiology
• /
• v.85 no.4
• /
• pp.714-726
• /
• 2024

Researchers have developed various algorithms utilizing artificial intelligence (AI) to automatically and objectively diagnose patterns and extent of pulmonary emphysema or interstitial lung diseases on chest CT scans. Studies show that AI-based quantification of emphysema on chest CT scans reveals a connection between an increase in the relative percentage of emphysema and a decline in lung function. Notably, quantifying centrilobular emphysema has proven helpful in predicting clinical symptoms or mortality rates of chronic obstructive pulmonary disease. In the context of interstitial lung diseases, AI can classify the usual interstitial pneumonia pattern on CT scans into categories like normal, ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation. This classification accuracy is comparable to chest radiologists (70%-80%). However, the results generated by AI are influenced by factors such as scan parameters, reconstruction algorithms, radiation doses, and the training data used to develop the AI. These limitations currently restrict the widespread adoption of AI for quantifying pulmonary emphysema and interstitial lung diseases in daily clinical practice. This paper will showcase the authors' experience using AI for diagnosing and quantifying emphysema and interstitial lung diseases through case studies. We will primarily focus on the advantages and limitations of AI for these two diseases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.5
• /
• pp.842-856
• /
• 1994

The various services that a broadband integrated services digital network (B-ISDN) carries, have a wide range of delay, delay jitter and cell loss probability requirements. Design of appropriate control schemes for B-ISDN is an extremely important and challenging problem. In this paper, we proposed multiplexing algorithm with both delay and loss priorities in order to satisfy the diverse requirements. For the implementation of cell lose priority, we assumed that voice cells are generated as non-discardable(i.e., high priority) and discardable (i.e., low priotity)cells. The low priority voice cell may be discarded inside the network if congestion occurs. The cell dropping scheme is shown to reduce cell losses as well as delays for both voice and data. Such a load shedding scheme is expected to improve significantly utilization of B-ISDN.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.9
• /
• pp.2326-2333
• /
• 2009

In the adaptable bandwidth allocation technique, a transmission plan for variable rate video data is made by smoothing algorithms such as CBA algorithm and the data is sent by the transmission plan considering network traffic. But the CBA algorithm, the MCBA algorithm, MVBA algorithm and the other smoothing algorithms produce a transmission plan where the size of the increasing interval of transmission rate is generally larger than the size of the decreasing interval. And the transmission rate in CBA algorithm, the MCBA algorithm, the MVBA algorithm is changed in overflow curve during the increasing interval of transmission rate. This may cause many frames to be discarded when available transmission rate is larger than transmission rate by the transmission plan. In this paper, the smoothing algorithm, where transmission rate is changed in the middle of underflow curve and overflow curve to decrease the number of discarded frames, but the transmission rate increases at the minimum, and the CBA algorithm, the MCBA algorithm, the MVBA algorithm are applied to a transmission plan in the adaptable bandwidth allocation technique, and the minimum frame rates, the average frame rates, the variation of frame rates, and the numbers of discarded frames are compared in among algorithms.

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.5
• /
• pp.494-500
• /
• 2006

Life Cycle Assessment(LCA) is an environmental assessment tool for evaluating environmental burdens associated with products, processes and activities from the raw material acquisition stage to the end-of-life stage. End-of-life stage as well as other processes requires a reliant database in order to increase the confidence in the LCA results. In this study, the flow of Personal Computer(as PC) in the end-of-life stage was examined and the database of two scenarios has been established, i.e. one is part reuse and the other is no part reuse, in the end-of-life phase of PC. Also, key environmental issues were identified by carrying out LCA on a PC in the end-of-life phase for eight environmental impact categories. The 'ozone layer depletion' contributes the highest environmental impact due to generation of $Cl_2$ gas during the incineration of waste plastics. In addition, the scenario 1(part reuse) is more environmentally sound than the scenario 2(no part reuse) when comparing two scenarios.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.1025-1027
• /
• 2022

도시화가 급속도로 진행됨에 따라서 일상생활에서 생활폐기물의 관리와 처리에 대한 문제가 심각해지고 있다. 이 문제를 해결하고자 어플리케이션을 통해 생활폐기물 처리를 쉽게 할 수 있는 시스템을 제안한다. '싹처리'는 편리성, 정확성, 확장성, 수익성을 가지고 (중)대형 생활 폐기물 처리하는 딥러닝 어플리케이션이다. 어플리케이션 내의 저장된 딥러닝 과정으로 학습되어진 생활폐기물 분류 모델을 통해 폐기물 사진을 자동 인식하는 과정으로 누구나 쉽게 폐기물 배출을 신청할 수 있다. 정확한 딥러닝 알고리즘과 전이학습, 데이터 검수 등을 통해 높은 성능의 사물 자동 인식을 할 수 있다. 이 시스템을 통해 임산부, 장애인, 독거노인 등의 사회적 약자는 불필요한 과정 없이 손쉽게 폐기물을 처리할 수 있고, 더 나아가 중고시장의 활성화에 기여할 수 있는 가치가 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.531-536
• /
• 2006

Recently, many of researchers have been studied in data processing oriented middleware for wireless sensor networks with the rapid advances on sensor and wireless communication technologies. In a wireless sensor network, a middleware should handle the data loss problem at an intermediate sensor node caused by instantaneous data burstness to support efficient processing and fast delivering of the sensing data. To handle this problem, a simple data discarding or data compressing policy for reducing the total amount of data to be transferred is typically used. But, data discarding policy decreases the correctness of a collected data, in other hand, data compressing policy requires additional processing overhead with the high complexity of the given algorithm. In this paper, it proposes a data-average method for enhancing the efficiency of data aggregation and correctness where the sensed data should be delivered only with the limited computing power and energy resource. With the proposed method, unnecessary data transfer of the overlapped data is eliminated and data correctness is enhanced by using the proposed averaging scheme when an instantaneous data burstness is occurred. Finally, with the TOSSTM simulation results on TinyBB, we show that the correctness of the transferred data is enhanced.

• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.313-325
• /
• 2022

This study aims to identify the conditional direct and indirect effects by Gender in the relationship between Learning Agility, Unlearning and Learning Flow for university students. Based on the data collected from 265 university students the conditional effectiveness of the research model was analyzed using Process v3.4 for SPSS. As a result, first, the Learning Agility of university students had a statistically significant effect Unlearning and Learning Flow. Second, Learning Agility had a statistically significant direct effect on Learning Flow by gender but, the moderated effect of Learning Flow had a significant negative effect. Third, the moderated mediating effect of Unlearning by gender was found to be significant in the relationship between Learning Agility and Learning Flow of university students. Based on these results, implications of education at university were presented.

• Proceedings of the KAIS Fall Conference
• /
• 2008.11a
• /
• pp.301-303
• /
• 2008

CSMA/CA를 기반으로 하는 IEEE 802.11 무선랜의 MAC에서는 데이터 전송을 제어하기 위한 방법으로 DCF와 PCF를 사용한다. IEEE 802.11 무선랜의 기본적인 액세스 방법으로 사용하는 DCF에서는 스테이션간의 충돌을 줄이기 위해서 임의의 백오프 시간을 각 스테이션의 경쟁윈도우(Contention Window) 범위에서 결정한다. 스테이션은 패킷 전송 후 충돌이 발생하면, 윈도우 크기를 두 배로 증가시키며, 패킷을 성공적으로 전송하면 윈도우 크기를 최소 경쟁 윈도우(Minimum Contention Window)로 감소한다. DCF는 경쟁 스테이션이 적은 상황에서는 비교적 우수한 성능을 보이나 경쟁 스테이션의 수가 많은 경우 처리율, 패킷지연 관점에서 성능이 저하되는 문제점이 있다. 본 논문에서는 IEEE 802.11 MAC 계층 DCF 방식에서의 평균폐기시간에 여러 연구결과들을 비교분석한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.177-179
• /
• 2014

컨텐츠 중심 네트워크(CCN)는 데이터 송수신을 위해 IP 주소로 종단 간 1:1 연결을 맺어야 하는 기존 인터넷의 비효율성을 해결하고자 등장한 미래 인터넷 기술 중 하나이다. CCN은 IP 주소 대신 컨텐츠의 이름을 사용하여 라우팅을 수행하며 네트워크상의 노드들이 컨텐츠를 저장하고 컨텐츠를 요청하는 인근의 소비자들에게 배포하는 방식을 사용한다. 하지만 기존의 CCN은 최초 데이터 패킷이 도착한 하나의 경로로만 컨텐츠를 수신하고 이후에 도착한 데이터 패킷은 폐기하기 때문에 전송률과 대역폭 측면에서 비효율적이다. 따라서 본 논문에서는 다수의 노드에 서로 다른 데이터 청크를 요청하여 다중경로를 통해 컨텐츠를 효율적으로 수신하는 기법을 제안한다.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.4
• /
• pp.309-340
• /
• 2019

Although overseas countries have already developed data life cycle for the preservation and curation of data since the 1990s, the research in Korea has been very insufficient. In this study, we analyzed the data life cycles developed in DCC, ICPSR, IWGDD, DataONE, USGS and UKDA to propose data life cycle for efficient management of research data. As a result of the analysis, the common components derived are 'Plan', 'Create & Collect', 'Process', 'Preserve', 'Dispose', 'Access & Use', 'Describe', 'Assure' and 'Backup & Secure'. In addition, the nine components were subdivided into stages to describe the details to be carried out at that stage. It is expected that the content of this study will be applicable in the future development of data life cycle for research data management in Korea.