• 전자통신동향분석
• /
• 제37권5호
• /
• pp.22-32
• /
• 2022

Optical character recognition is a primary technology required in different fields, including digitizing archival documents, industrial automation, automatic driving, video analytics, medicine, and financial institution, among others. It was created in 1928 using pattern matching, but with the advent of artificial intelligence, it has since evolved into a high-performance character recognition technology. Recently, methods for detecting curved text and characters existing in a complicated background are being studied. Additionally, deep learning models are being developed in a way to recognize texts in various orientations and resolutions, perspective distortion, illumination reflection and partially occluded text, complex font characters, and special characters and artistic text among others. This report reviews the recent deep learning-based text detection and recognition methods and their various applications.

• Geomechanics and Engineering
• /
• 제29권3호
• /
• pp.219-228
• /
• 2022

The most widely used parameter to represent rock abrasiveness is the Cerchar abrasivity index (CAI). The CAI value can be applied to predict wear in TBM cutters. It has been extensively demonstrated that the CAI is affected significantly by cementation degree, strength, and amount of abrasive minerals, i.e., the quartz content or equivalent quartz content in rocks. The relationship between the properties of rocks and the CAI is investigated in this study. A database comprising 223 observations that includes rock types, uniaxial compressive strengths, Brazilian tensile strengths, equivalent quartz contents, quartz contents, brittleness indices, and CAIs is constructed. A linear model is developed by selecting independent variables while considering multicollinearity after performing multiple regression analyses. Machine learning-based regression methods including support vector regression, regression tree regression, k-nearest neighbors regression, random forest regression, and artificial neural network regression are used in addition to multiple linear regression. The results of the random forest regression model show that it yields the best prediction performance.

• 한국멀티미디어학회논문지
• /
• 제21권10호
• /
• pp.1182-1194
• /
• 2018

The Dynamic Adaptive Streaming over HTTP(DASH) is envisioned to evolve to meet an increasing demand on providing seamless video streaming services in the near future. The DASH performance heavily depends on the client's adaptive quality selection algorithm that is not included in the standard. The existing conventional algorithms are basically based on a procedural algorithm that is not easy to capture and reflect all variations of dynamic network and traffic conditions in a variety of network environments. To solve this problem, this paper proposes a novel quality selection mechanism based on the Deep Q-Network(DQN) model, the DQN-based DASH Adaptive Bitrate(ABR) mechanism. The proposed mechanism adopts a new reward calculation method based on five major performance metrics to reflect the current conditions of networks and devices in real time. In addition, the size of the consecutive video segment to be downloaded is also considered as a major learning metric to reflect a variety of video encodings. Experimental results show that the proposed mechanism quickly selects a suitable video quality even in high error rate environments, significantly reducing frequency of quality changes compared to the existing algorithm and simultaneously improving average video quality during video playback.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4385-4399
• /
• 2021

The Internet of Things (IoT) eHealth systems composed by Wireless Body Area Network (WBAN) has emerged recently. Sensor nodes are placed around or in the human body to collect physiological data. WBAN has many different applications, for instance health monitoring. Since the limitation of the size of the battery, besides speed, reliability, and accuracy; design of WBAN protocols should consider the energy efficiency and time delay. To solve these problems, this paper adopt the end-edge-cloud orchestrated network architecture and propose a transmission based on reinforcement algorithm. The priority of sensing data is classified according to certain application. System utility function is modeled according to the channel factors, the energy utility, and successful transmission conditions. The optimization problem is mapped to Q-learning model. Following this online power control protocol, the energy level of both the senor to coordinator, and coordinator to edge server can be modified according to the current channel condition. The network performance is evaluated by simulation. The results show that the proposed power control protocol has higher system energy efficiency, delivery ratio, and throughput.

• 가정∙방문간호학회지
• /
• 제29권3호
• /
• pp.329-338
• /
• 2022

Purpose: This study aimed to develop an infection control e-learning training program for long-term care facility care workers to prevent emerging infectious diseases and evaluate its effectiveness. Method: The program was developed using the analysis design development implementation evaluation (ADDIE) model. The effectiveness of the program was evaluated for 30 care workers. The knowledge and performance of the care workers before and after the program were analyzed by a t-test. Results: In the analysis stages, a literature review on infection control, knowledge and performance of infection control, and education needs was performed, and focus group interviews with ten care workers were conducted. In the design stage, education topics, educational content, and educational methods were selected for the program. A video was produced centered on eight themes. In the development stage, a system for education was developed, and each topic was uploaded. In the implementation stage, the program was applied to 30 care workers, and a questionnaire was administered. In the program's final evaluation, there was a significant difference in infection control knowledge (t=3.06, p=.005), and there was no significant difference in infection control performance. Conclusion: In this study, the necessary topics were finally selected by quantitatively and qualitatively analyzing the educational needs of care workers taking care of the elderly in long-term care facilities. It is necessary to understand the long-term effect and the degree of performance of the observation method in the future.

• 한국전자거래학회지
• /
• 제25권2호
• /
• pp.15-27
• /
• 2020

본 연구는 일정계획을 위한 간트 차트(Gantt Chart) 생성과정을 세로로 세우면 일자형만 존재하는 테트리스(Tetris) 게임과 유사하다는 아이디어에서 출발하였다. 테트리스 게임에서 X축은 M개의 설비(Machine)들이 되고 Y축은 시간이 된다. 모든 설비에서 모든 종류(Type)의 주문은 분리 없이 작업 가능하나 작업물 종류가 다를 경우에는 시간지체 없이 작업 준비비용(SetupCost)이 발생한다는 가정이다. 본 연구에서는 앞에서 설명한 게임을 간트리스(Gantris)라 명명하고 게임환경을 구현 하였으며, 심층 강화학습을 통해서 학습한 인공지능이 실시간 스케줄링한 일정계획과 인간이 실시간으로 게임을 통해 수립한 일정계획을 비교하였다. 비교연구에서 학습환경은 단일 주문목록 학습환경과 임의 주문목록 학습환경에서 학습하였다. 본 연구에서 수행한 비교대상 시스템은 두 가지로 4개의 머신(Machine)-2개의 주문 종류(Type)가 있는 시스템(4M2T)과 10개의 머신-6개의 주문종류가 있는 시스템(10M6T)이다. 생성된 일정계획의 성능지표로는 100개의 주문을 처리하는데 발생하는 Setup Cost, 총 소요 생산시간(makespan)과 유휴가공시간(idle time)의 가중합이 활용되었다. 비교연구 결과 4M2T 시스템에서는 학습환경에 관계없이 학습된 시스템이 실험자보다 성능지표가 우수한 일정계획을 생성하였다. 10M6T 시스템의 경우 제안한 시스템이 단일 학습환경에서는 실험자보다 우수한 성능 지표의 일정계획을 생성하였으나 임의 학습환경에서는 실험자보다 부진한 성능지표를 보였다. 그러나 job Change 횟수 비교에서는 학습시스템이 4M2T, 10M6T 모두 사람보다 적은 결과를 나타내어 우수한 스케줄링 성능을 보였다.

• 한국전자거래학회지
• /
• 제24권1호
• /
• pp.1-16
• /
• 2019

최근 온실가스의 증가로 인한 기후변화 대응의 필요성과 전력수요의 증가로 인해 태양광발전량(PV) 예측의 중요성은 급격히 증가하고 있다. 특히, 태양광 발전량을 예측하는 것은 합리적인 전력 가격결정과 시스템 안정성 및 전력 생산 균형과 같은 문제를 효과적으로 해결하기 위해 전력생산 계획을 합리적으로 계획하는데 도움이 될 수 있다. 그러나 일사량, 운량, 온도 등과 같은 기후정보 및 계절 변화로 인한 태양광 발전량이 무작위적으로 변화하기 때문에 정확한 태양광 발전량을 예측하는 것은 도전적인 일이다. 따라서 본 논문에서는 딥러닝 모델을 통해 기후 및 계절정보를 이용하여 학습함으로써 장기간 태양광 발전량 예측 성능을 향상시킬 수 있는 기법을 제안한다. 본 연구에서는 대표적인 시계열 방법 중 하나인 계절형 ARIMA 모델과 하나의 은닉층으로 구성되어 있는 ANN 기반의 모델, 하나 이상의 은닉층으로 구성되어 있는 DNN 기반의 모델과의 비교를 통해 본 연구에서 제시한 모델의 성능을 평가한다. 실데이터를 통한 실험 결과, 딥러닝 기반의 태양광 발전량 예측 기법이 가장 우수한 성능을 보였으며, 이는 본 연구에서 목표로 한 태양광 발전량 예측 성능 향상에 긍정적인 영향을 나타내었음을 보여준다.

• 디지털콘텐츠학회 논문지
• /
• 제11권3호
• /
• pp.307-314
• /
• 2010

국내에서의 사이버교육에 대한 수요는 점차적으로 늘어나고 있으며 이와 같은 상황에서 학습효과를 높일 수 있는 온라인 강의 콘텐츠 디자인에 관한 연구의 필요성이 제기되고 있다. 본 연구에서는 한국사이버대학교에서 제공되고 있는 기술적 정보 유형에 따른 온라인 강의 콘텐츠의 유형을 파악하고 한국사이버대학교 재학생 1,173명을 대상으로 온라인 설문을 실시하여 가장 선호하는 강의 유형과 가장 교육효과가 높은 강의유형을 조사하였다. 그리고 학생들의 강의 유형에 대한 수강경험이 강의 유형의 선호도에 영향을 주는가를 조사하였으며 강의 콘텐츠의 인터페이스 디자인에 관한 요구사항도 알아보았다. 학생들이 가장 선호하는 강의 유형은 e-Stream+flash의 유형이었으며 멀티미디어형 강의가 학습에 효과적이라고 응답하였다. 대부분의 학생들이 경험해 본 유형의 강의 콘텐츠를 선호하였으며 인터페이스 디자인 측면에서는 왼쪽의 고정메뉴를 선호하였다. 온라인 강의에서 강의 콘텐츠의 충실성 뿐 아니라 학습효과를 높일 수 있는 강의 콘텐츠 디자인도 매우 중요한 요소이다. 국내에서 사이버 교육에 관한 수요가 증가하고 있으므로 학습효과를 높일 수 있는 콘텐츠 디자인에 관한 연구는 앞으로 계속 이루어져야 한다고 생각한다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권3호
• /
• pp.65-91
• /
• 2021

Purpose In this study, we investigated the impact of perceived risk and switching costs on switching intention to cloud service based on PPM (Pull-Push-Mooring) model. Design/methodology/approach We focused on revealing the switching factors of the switching intention to the cloud services. The switching factors to the cloud services were defined as perceived risk consisting of performance risk, economic risk, and security risk, and switching costs consisting of financial and learning costs. On the PPM model, we defined the pull factors consisting of perceived usefulness and perceived ease of use, and the push factor as satisfaction of the legacy system, and the mooring factor as policy supports. Findings The results of this study as follows; (1) Among the perceived risk factors, performance risk has a negative effect on the ease of use of pull factors, and finally it was found to affect the switching intention to the cloud services. Therefore, cloud service providers need to improve trust in cloud services, service timeliness, and linkage to the legacy systems. And it was found that economic risk and security risk among the perceived risk factors did not affect the switching intention to the cloud services. (2) Of the perceived risk factors, financial cost and learning cost did not affect the satisfaction of the legacy system, which is a push factor. It indicates that the respondents are positively considering switching to cloud service in the future, despite the fact that the respondents are satisfied with the use of the legacy system and are aware of the switching cost to cloud service. (3) Policy support was found to improve the switching intention to cloud services by alleviating the financial and learning costs required for cloud service switching.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.