• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.592-599
• /
• 2020

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

• Culinary science and hospitality research
• /
• v.17 no.3
• /
• pp.65-75
• /
• 2011

The purpose of the study was to explore the relationship between satisfaction and future behavior intention of cafeteria users. Respondents of the research were cafeteria users in major colleges in Kyunggi province. A total of 300 questionnaires were distributed between October 1, 2010 and October 20, 2010 but only281 questionnaires were used for the analysis. Based on 14 selection attributes, factor analysis showed that the KMO value of 0.634, which was extracted by Verimax vertical rotation, and=610.084(p<0.001). In addition, the distributional explanation showed a total of 61.685%. Five factors were obtained as ingredients, food, menu, maintenance, and internal environment factors according to the feature of each variable. The Cronbach value according to confidence and validity tests was 0.703. The explanation was 16.3% and the influence on satisfaction included ingredients, maintenance, and internal environment. The effect on future behavior intention was significant at the level of p<0.001. This study has limitations in that it has generalized the findingson consumers of university cafeterias; therefore, follow-up studies must be conducted.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.2
• /
• pp.189-194
• /
• 2020

This paper analyzes the gradient descent method, which is the one most used for learning neural networks. Learning means updating a parameter so the loss function is at its minimum. The loss function quantifies the difference between actual and predicted values. The gradient descent method uses the slope of the loss function to update the parameter to minimize error, and is currently used in libraries that provide the best deep learning algorithms. However, these algorithms are provided in the form of a black box, making it difficult to identify the advantages and disadvantages of various gradient descent methods. This paper analyzes the characteristics of the stochastic gradient descent method, the momentum method, the AdaGrad method, and the Adadelta method, which are currently used gradient descent methods. The experimental data used a modified National Institute of Standards and Technology (MNIST) data set that is widely used to verify neural networks. The hidden layer consists of two layers: the first with 500 neurons, and the second with 300. The activation function of the output layer is the softmax function, and the rectified linear unit function is used for the remaining input and hidden layers. The loss function uses cross-entropy error.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.284-293
• /
• 2010

For the successful deployment of Mobile Internet, fast handover technologies are essential. For the past few years several handover mechanisms are suggested, and Fast Handover for Proxy Mobile IPv6 (PFMIPv6) is one of the promising schemes for this purpose. In this paper, we propose a novel L2/L3 cross layer handover scheme based on ARIMA prediction model to apply PFMIPv6 to Mobile Internet environment effectively. Performance gains are evaluated in terms of probabilities of predictive-mode operation, handover latencies, packet loss probabilities, and signaling costs. Three mobilities models are used for our simulation: Manhattan Model, Open Area Model, and Freeway Model. Simulation results show that the proposed scheme can increase probabilities of predictive-mode operation and reduce handover latency, packet loss probabilities, and signaling cost.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.2
• /
• pp.91-99
• /
• 2009

Mobile WiMAX is an emerging technology that can provide ubiquitous Internet access. To provide seamless service in mobile WiMAX environment, delay or disruption in dealing with mobility must be minimized. However offering seamless services on IEEE 802.16e networks is very hard due to long handover latency both in layer 2 and 3. In this paper, we propose a fast cross-layer handover scheme based on prediction algorithm. With the help of the prediction, layer-3 handover activities are able to occur prior to layer-2 handover, and therefore, total handover latency can be reduced. The experiments conducted with system parameters and propagation model defined by WiMAX Forum demonstrate that the proposed method predicts the future signal level accurately and reduces the total handover latency.

• The monthly packaging world
• /
• s.267
• /
• pp.80-92
• /
• 2015

산업통상자원부가 주최하고 한국생산기술연구원이 주관하는 2015년도 "제9회 미래패키징 신기술 정부포상"수상작이 선정됐다. 미래지식산업인 패키징산업 종사자의 긍지와 자부심 함양의 계기를 실천하고, 패키징산업 종사자의 사기진작과 패키징산업 활성화를 도모하기 위해 매년 진행되고 있는 미래패키징신기술 정부포상은 패키징 산업 기술인의 기술개발 의욕을 고취하고 패키징산업 기술성과 및 산업발전 기여도에 대한 정부포상를 실현하며 패키징산업 종사자간 정보교류 극대화 및 공동체 의식 함양으로 일체감을 조성시켜왔다는 평가를 받고 있다. 미래패키징 신기술 정부포상은 기업부문 및 학생부문, 그리고 공로부문으로 나누어 수상자를 선정, 진행되고 있다. 기업부문은 패키징 완제품, 친환경패키징, 패키징관련기계(설비) 및 관련부품, 패키징인쇄(라벨링), 패키징원부자재 생산 및 가공공정, 패키징디자인 등의 분야에서 신기술 개발 또는 개선으로 수출신장, 매출 수익 증대 및 발명특허 획득을 통해 패키징 기술력 발전에 기여한 기업의 패키징제품 또는 패키징디자인을 대상으로 하고 있으며, 학생부문은 패키징 디자인 관련분야 전공자로 패키징과 연관된 컨셉으로 상품성, 창의성, 표현성, 친환경성, 지속가능성 등이 어우러진 독창적인 패키징제품 또는 패키징디자인을 대상으로 진행하고 있다. 또한 공로부문은 패키징 산업 관련 산업계, 학계, 연구계, 유관기관에 종사하는 자로서 패키징 관련 핵심 기술개발, 경영, 마케팅 면에서 패키징 산업 발전에 기여한 공적이 뚜렷한 자, 패키징산업발전 정책연구 및 패키징산업 육성에 기여한 기업 또는 개인을 대상으로 하고 있다. 제9회 미래패키징 신기술 정부포상 심사 결과 삼성전자(주)의 'Curved UHD TV 용(用) Curved 포장 Box'가 국무총리상으로 선정됐으며, (주)대륙제관의 '폭발방지 맥스부탄'을 비롯해 4개사가 산업통상자원부 장관상으로 선정되는 등 총 29개사가 수상 기업으로 선정됐다. 공로부문에서는 (주)남경의 김선창 회장과 (주)화남인더스트리의 석용찬 회장이 산업통상자원부장관 표창자로 선정됐다. 이 외에도 학생부문에 17개 작품이 선정, 수상이 예정되어 있다. 본 고에서는 기업부문 수상작 및 공로부문 수상자들의 활약상을 살펴보도록 한다.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.859-872
• /
• 2016

Land cover classification is an important tool for preventing natural disasters, collecting environmental information, and monitoring natural resources. Hyperspectral imaging is widely used for this task thanks to sufficient spectral information. However, the curse of dimensionality, spatiotemporal variability, and lack of labeled data make it difficult to classify the land cover correctly. We propose a novel classification framework for land cover classification of hyperspectral data based on convolutional neural networks. The proposed framework naturally incorporates full spectral features with the information from neighboring pixels and has advantages over existing methods that require additional feature extraction or pre-processing steps. Empirical evaluation results show that the proposed framework provides good generalization power with classification accuracies better than (or comparable to) the most advanced existing classifiers.

• Journal of Digital Convergence
• /
• v.12 no.11
• /
• pp.531-539
• /
• 2014

Recent studies of multiple participatory interactive media designs hows that the key element to this area is the participation of the audience. Due to this matter, this paper discusses the categories of the phase and looks into the characteristics of participatory matters to clarify the distinction. The categories that has been mentioned in this paper are multiple participatory types and active participatory types. Based on this matter, research practicing the Mira has been conducted in two separate groups - video and sound, and suggests the solution to the problems that has occurred during the process of implementing the final video system called 'The 360 Project'. The fact that the paper suggests a small range of participatory categories and hasn't come up with a certain analysis to the final outcome appears as a limit. The inadequacy will be supplemented throughout the following paper, hoping there will be improved versions of multiple participatory researches.

• Journal of Digital Convergence
• /
• v.14 no.9
• /
• pp.579-588
• /
• 2016

This study is to identify the relationship between cultural physical education class of enjoyment factor, class satisfaction, and exercise continuation behavior. For this purpose, 275 out of 300 copies of survey aimed at students in four universities located in Gyeong-gi province were used. PAWS 18.0 program was used for analysis to present descriptive statistics. Principal component analysis and rotation of Max Berry were used among exploratory factor analysis to check factor extraction and internal consistency. Cronbach's alpha was used for checking reliability. Multiple regression analysis was used to clarify the relationship between enjoyment factor, class satisfaction, and exercise continuation behavior of cultural physical education. These are the following conclusions. First, instructional behavior, grade in physical education, environment, and exercise ability among the enjoyment factors in cultural physical education class have a significant effect on persistence of exercise. Second, instructional behavior and grade in physical education are the factors of class satisfaction and the have a significant effect on persistence of exercise.

• Journal of Digital Convergence
• /
• v.18 no.1
• /
• pp.219-229
• /
• 2020

The purpose of this study was to develop a short biomedical ethics tool for healthcare workers, compare it with pre-existing tool, and increase reliability. Data were collected from 211 healthcare workers working in G-do. Exploratory factor analysis was carried out using Varimax rotation extraction method in IBM SPSS WIN/21.0. Convergent validity of the tool was verified by regression and correlation analysis with original tool score. Reliability was verified by calculating intraclass correlation coefficient and internal consistency coefficient. The short, reduced 21 questions tool reflected 84% of pre-existing tool's biomedical ethics. Its reliability was higher than the 29 question tool for nursing students, but there were differences in the components of subdomains and reliability coefficient. Additional development of questions through qualitative research and interviews are needed to increase reliability of the subdomains. Measurement of biomedical ethics dilemma with the tool that has validity and reliability is needed, followed by replication studies.