• International Journal of Advanced Culture Technology
• /
• 제8권4호
• /
• pp.294-298
• /
• 2020

We was constructed of the spread movement with tremor layer point by the tractile-dot structure that was analyzed the squirm quake forms of the perception movement on the atom liquid. Algorithm of squirm quake forms was used to move the spread tremor on the atom state. To detect the tiny signal, we compared the association average value of the squirm quake form on the atom state. Their subject were issued the valuation standard and perception movement for basic atom condition by the spread tremor. We take to detect the tiny scores of average during perception movement side from the spread tremor that magnetic condition get to a variation of the Ma-αAVG and Ma-αMAX-MIN with 6.25±0.35 units, that electric condition get to a variation for the El-αAVG and El-αMAX-MIN with 5.68±0.42 units. The spread tremor was to investigate the capacity of the tremor form, to uptake a spread data of spread tremor level on the CCPL that was denoted the calm-classification form by the spread perception level system. As the squirm quake forms was demanded by the spread tremor signal, max-average values of perception movement were checked the spread position for association average data. We make mention of squirm quake forms for a signal association and a quake data signal of relation system.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.28-32
• /
• 2021

The article discusses the theoretical and methodological part that characterizes and assessment of the current state of the theory of GR-activity, disclosed the essence and content of the concept of GR-technologies, as well as their classification. The analysis of the system of additional education for children in the social structure, as well as the analysis of the current state of the education system is carried out. The formulation of tasks for the construction of an effective model for the use of GR-technologies in the process of developing the education system using GR-technologies

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• 한국정밀공학회지
• /
• 제13권7호
• /
• pp.45-58
• /
• 1996

We provide a set of information on technologies in the area of mechanical engineering to draw meaningful action plans for the internationalization of National R&D activities. In this study, we employed a modified Delphi method to evaluate levels of our technoligical capabilities and developed countries' as well. We investigate technology acquistion methodologies, technology charcteristics and various aspects of interna- tional cooperation in terms of technology. Then, we analyzed final responses of participants(i.e., the third round results of Delphi method) to see the correlation among various factors in developing mechanical engineeing technologies through international cooperation. The technology classification used in this research was devel- oped by STEPI(Science and Technology Policy Institute). In conclusion, our mechanical engineering technology is investigated to be below the middle level stage of technology(i.e., the stage of digesting acquired technologies) except the shipbuilding equipments technology which is evaluated to be on the top level stage of technology.

• 한국정밀공학회지
• /
• 제12권5호
• /
• pp.98-107
• /
• 1995

The in-process detection of drill wear and breakage is one of the most importnat technical problems in unmaned machining system. In this paper, the monitoring system is developed to monitor abnormal drilling states such as drill breakage, drill wear and unstable cutting using motor current. Drill breakage is detected by level monitoring. Tool wear is classified by fuzzy pattern recognition. The key feature for classification of tool wear is the estimated flank wear which is calculated by the proposed flank wear model. The characteristic of the model is not sensitive to the variation of cutting conditions but is sensitive to drill wear state. Unstable cutting states due to the unsmooth chip disposal and the overload are monitored by the variance/mean ratio of spindle motor current. Variance/mean ratio also includes the information about the prediction of drill wear and drill breakage. The evaluation experiments have shown that the developed system works very well.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권1호
• /
• pp.51-73
• /
• 2023

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNetB0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

• 감성과학
• /
• 제25권4호
• /
• pp.63-76
• /
• 2022

Emotional labor, characterized by a dysfunctional type of emotional regulation called surface acting, has detrimental psychological consequences on employees, including depression and social anxiety. Because such disorders exhibit psychological characteristics manifested through brain activation, previous studies have succeeded in distinguishing individuals with depression and social anxiety from healthy controls using their functional connectivity characteristics. However, it has not been established whether the functional connectivity characteristics associated with emotional labor are distinguishable. Thus, we obtained resting-state fMRI data from participants in the emotion labor (EL) group and control (CTRL) group, and we subjected their whole-brain functional connectivity matrices to a linear support vector machine classifier. Our analysis revealed that the EL and CTRL groups could be successfully distinguished on the basis of individuals' connectivity patterns, and confidence in the classification was correlated with the scores on the depression and social anxiety scales. These results are expected to provide insight on the neurobiological characteristics of emotional labor and enable the sorting of employees undergoing adverse emotional labor utilizing neurobiological observations.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제9권3호
• /
• pp.322-331
• /
• 2003

3차원 게임은 게임 시나리오의 다양한 요소에 의한 복잡도가 증가함에 따라 게임 객체들의 상호 관계를 제어하기 위한 문제점을 가진다. 그러므로, 게임 시스템은 각 게임 객체들의 응답을 조정하는 방법의 필요성을 가진다. 또한, 게임 시나리오의 결과에 따라 게임 객체들의 행동 애니메이션을 제어하기 위한 개념들도 필요하다. 사실적 게임 시뮬레이션을 생성하기 위해 시스템은 게임 객체들의 상호작용을 디자인 할 수 있는 구조를 포함해야 한다. 본 논문에서 게임 시나리오상에 게임 객체들의 상호작용 설계를 위해 동적 제어를 디자인하는 기법을 소개한다. 이 방법을 위해 특정 규칙을 이용한 의사결정이 가능한 지능적 에이전트 기반 구조로써 게임 에이전트 시스템을 제안한다. 게임 에이전트 시스템은 환경 데이터 처리, 게임 객체 시뮬레이션, 게임 객체들간의 상호작용 제어, 게임 객체들의 다양한 상호 관계를 정의할수 있는 시각 저작 인터페이스를 제공하기 위해 이용되어진다. 이들 기술들은 게임 객체의 자율성과 연관된 충돌 회피 기법 등을 처리한다. 또한, 장면의 변경으로부터 게임 객체들의 일관된 의사 결정력을 가능하게 한다. 본 논문에서는 규칙기반 행동 제어가 게임 객체의 시뮬레이션을 안내하기 위해 디자인되어졌다. 시각적 요소들로 구성된 에이전트 상태 결정 네트워크는 정보전달과 게임 객체들 사이의 현상태를 추론할 수 있다. 이들 기법들은 실시간으로 게임 객체들간의 동작 상태 변이를 체크하고 모니터링 할 수 있다. 마지막으로 간단한 사례 연구 예와 함께 제어 기법의 타당성을 제시한다.

• 인지과학
• /
• 제33권1호
• /
• pp.51-75
• /
• 2022

경두개 직류전기자극(transcranial Direct Current Stimulation; tDCS)은 지각, 인지, 운동 등의 뇌기능 향상 및 발달 효과가 입증되며, 다양한 분야에서 활용 및 응용되는 비침습적 뇌자극술이다. tDCS 효과는 뇌의 해부학적 구조, 뇌의 노화 정도 등의 뇌신경활성화 특징에 따라 다르게 나타난다는 연구결과들이 보고되고 있다. 일주기 리듬(circadian rhythm)은 대략 하루 주기의 수면과 각성의 생리적 변화패턴을 의미하며 뇌신경활성화 상태는 일주기 리듬에 따라 다르게 나타난다. 일주기 유형(chronotype)은 하루 중에 발현되는 각성도의 크기에 따라 아침의 각성도가 큰 유형은 아침형으로 저녁의 각성도가 큰 유형은 저녁형으로 나누어진다. 본 연구는 일주기 리듬에 의해 변하는 뇌기능 특징이 tDCS 효과에 미치는 영향을 알아보고자 한다. 총 20명의 건강한 성인 대상으로 실험을 진행하였고, 참가자들은 일주기 유형을 분류하기 위해 아침형-저녁형 설문지에 의해 주간형(아침형, 중간형)과 야간형(저녁형)으로 분류했다. 본 실험은 Zoom 프로그램을 이용하여 참가자와 실험자가 온라인으로 만나서 실험을 진행했다. 실험이 확정된 참가자는 실험자로부터 뇌파 기기, 뇌파 데이터를 획득하는 앱이 있는 핸드폰, 핸드폰 거치대, 뇌자극 기기의 사용방법에 대한 설명을 듣고 기기를 테스트해보고 기기를 전달받았다. 기기사용의 어려움을 가진 2명의 참가자는 대면 실험을 진행하여, 실험자가 기기작동을 하여 실험에 참여했다. 일주기 리듬의 상태에 따른 뇌자극 효과를 알아보기 위해 1주일 간격으로 아침과 저녁에 실험했으며, tDCS 자극 전과 후의 신경활성화 반응의 차이를 뇌파를 이용하여 측정하였다. 뇌자극에 의한 뇌기능 변화를 확인하기 위해 자극 전의 뇌파와 자극 후 뇌파가 다른 패턴을 보이며 분류가 잘되는 지를 예측 정확도로 분석했으며, 뇌기능 특징 변화가 일주기 리듬과 일주기 유형에 따라 다르게 나타나는지 확인하기 위해 각 조건의 분류조건(아침/저녁, 주간형/야간형)에서 추출된 주요 EEG 특성을 비교했다. 54개의 뇌파 특성값을 추출하여 SVM(Support Vector Machine) 기계학습 알고리즘으로 분류 모델을 구축하였고, 구축된 모델을 Leave-One-Out 교차검증(Leave-One-Out Cross-Validation)을 사용하여 자극 전과 후의 뇌파 반응을 예측하는지 평가하였고, 분류예측모델의 주요 예측 인자를 확인하는 주요 특성 분석을 진행하였다. 아침과 저녁의 tDCS에 따른 뇌파 특징을 분류하는 예측 정확도는 모두 98%로 나타났으며, 주간형의 아침 자극 조건과 저녁 자극 조건의 예측 정확도는 92%와 96%이며, 야간형의 아침자극 조건과 저녁 자극 조건의 예측 정확도는 모두 94%로 나타났다. 아침 자극 전과 후의 뇌파를 분류하는 상위 3개의 주요 EEG 특성결과는 주간형과 야간형에 따라 다르게 나타났다. 주간형은 좌측 측두 두정엽과 전전두엽의 뇌파 특성값이 나타났으며, 야간형은 측두 두정엽의 뇌파 특성값들만 나타났다. 저녁 자극전과 후의 뇌파를 분류하는 상위 3개의 주요 EEG 특성 결과 또한 주간형과 야간형에 따라 다르게 나타났다. 주간형은 우측 측두 두정엽과 좌측 전두엽의 뇌파 특성값이 나타났으며, 야간형은 측두 두정엽과 전두엽의 뇌파 특성값이 나타났다. 이와 같은 연구결과는 일주기 리듬과 유형에 따라 아침과 저녁의 뇌기능 특징이 다르게 나타나서 뇌자극 효과가 다르게 나타날 수 있음을 확인한 결과이다. 본 연구의 결과는 효과적인 뇌자극을 위해 개인의 뇌신경 활성화 상태 및 특징에 따라서 뇌자극 프로토콜을 조정할 필요성을 제시한다는 데에 의의를 찾을 수 있다.

• 한국치위생학회지
• /
• 제6권4호
• /
• pp.295-309
• /
• 2006

This study was conducted among 831 industrial workers in Gumi City in Gyung-Sang-Buk Do for the purpose of acquiring knowledge to improve quality of life though industrial workers' oral health promotion. Oral examination and questionnaire surveying were used to evaluate workers' oral health state and subjective health state and analyze their effect on quality of life. 1. The number of workers in the study were 831 in all; there were more males who accounted for 74.6%. 43.7% of the subject were 29 years old, accounting for the largest age group. Their academic backgrounds are 53.6% workers who graduated from high schools or lower educational institutions, and 46.4% workers who graduated from college or higher educational institutions. 80.7% of the subjects replied that their economic state belonged to the middle class. Their job classification indicates that 70.2% were working in production and engineering fields and that the seniority of 55.3% workers was less than 55.3%. 2. The result of evaluating the effects of oral health state on individual well-being and quality of life using OHIP indicates that younger people, singles(p<0.01) than the married, those in worse economic situation and those with shorter seniority(p<0.01) had higher effect of oral health state on quality of life. In addition, those whose health or oral health was not good (p<0.01), those with liked tough texture of food and snacks(p<0.05), those with more frequency of drinking(p<0.01) and those with more smoking tended to have higher effect of oral health state on daily life or quality of life. Besides, OHIP confirmed that oral health state is a measurement tool that can evaluate its effect on individual well-being and quality of life. The suggestion for future studies is to develop Korean style OHIP that can be used conveniently and efficiently by expanding the subject area up to the whole country and validating the samples gained from random sampling.