• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.247-251
• /
• 1997

FCM(Fuzzy Cognitive Map) is a fuzzy signed directed graph for representing causal reasoning which has fuzziness between causal concepts. Authors have already proposed FCM-based fault diagnostic scheme and verified its usefulness. However, the previously proposed scheme has the problem of lower diagnostic resolution as in the case of other qualitative approaches. In order to improve the diagnostic resolution, a concept of fuzzy number is introduced into the basic FCM-based fault diagnostic algorithm. By incorporation the fuzzy number into fault FCM models, quantitative information such as the transfer gain between the state variables can be effectively utilized for better diagnostic resolution. Furthermore, an enhanced TAM(Temporal Associative Memory) recall procedure and modified and modified pattern matching scheme are also proposed.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2010.05a
• /
• pp.66-71
• /
• 2010

본 논문에서는 멀티 모달리티가 인간의 기억 현상 중에서 특히 회상 현상에 도움이 될 것이 라는 아이디어를 인간 실험과 컴퓨터 시뮬레이션을 통해서 비교 확인한다. 우리는 순차적 멀티모달리티 정보가 기억회상 현상에 미치는 영향을 알아보기 위해서 확률 하이퍼그래프 메모리모델을 사용하여 컴퓨터 시뮬레이션을 수행하였으며, 시뮬레이션 결과를 동일한 데이터를 사용한 인간 실험 결과와 비교하였다. 본 실험에서는 TV 드라마의 비디오 데이터를 이용하여 이전시점의 사진과 문장 정보가 다음 시점의 문장 생성에 미치는 영향을 확인하였다. 본 실험의 목적은 이전 시점의 문장 정보와 문장/사진 정보를 활용하여 멀티 모달리티의 영향을 확인하는 것이며 다양한 시점의 정보를 활용하여 순차성이 회상에 갖는 영향을 확인하는 것이다. 이를 통해서 기억 회상 현상에 있어서 멀티 모달리티가 미치는 영향과 순차적 데이터가 미치는 영향을 보일 수 있었으며, 기계를 통해서 인간의 기억 회상 현상을 재현할 수 있는 시뮬레이션 모델을 구현 하는데 실마리를 제공하였다.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.578-584
• /
• 2004

The CSVM(Current Support Vector Machine) that is a digital architecture performing all phases of recognition process including kernel computing, learning, and recall of SVM(Support Vector Machine) on a chip is proposed. Concurrent operation by parallel architecture of elements generates high speed and throughput. The classification problems of bio data having high dimension are solved fast and easily using the CSVM. Quadratic programming in original SVM learning algorithm is not suitable for hardware implementation, due to its complexity and large memory consumption. Hardware-friendly SVM learning algorithms, kernel adatron and kernel perceptron, are embedded on a chip. Experiments on fixed-point algorithm having quantization error are performed and their results are compared with floating-point algorithm. CSVM implemented on FPGA chip generates fast and accurate results on high dimensional cancer data.

• Journal of Korea Foundry Society
• /
• v.41 no.6
• /
• pp.521-527
• /
• 2021

This study presents a process management method for the detection of casting defects during in high-pressure die casting based on machine learning. The model predicts the defects of the next cycle by extracting the features appearing over the previous cycles. For design of the gearbox, the proposed model detects shrinkage defects with data from three cycles in advance with 98.9% accuracy and 96.8% recall rates.

• Asia Marketing Journal
• /
• v.16 no.4
• /
• pp.59-73
• /
• 2015

Previous research has revealed that people feel past target events are more distant when they recall more intervening events, event markers, that are both accessible in memory and perceived to be related to that target event (Zauberman, Levav, Diehl, and Bhargave 2010). This phenomenon was called the systematic effect of event markers (SEEM). In this research, we explore the moderating effect of the valence of the target event on SEEM and suggest the difficulty of recalling event markers as the possible mechanism. Study 1 shows that SEEM mainly occur when the valence of the target event is negative rather than positive. Study 2 showed that even though people have more difficulty recalling four event markers than one regardless of event valence, the difficulty of recalling event markers only mediates SEEM when the target event valence is negative. Furthermore, when the target event is positive, SEEM does not exist, confirming that the mediating role of the difficulty of recalling event markers on SEEM is moderated by the valence of the target event.

• Journal of East-West Nursing Research
• /
• v.16 no.2
• /
• pp.131-137
• /
• 2010

Purpose: The purpose of this study was to investigate the relationship between depression status and cognitive function in the community female aged. Methods: This was a descriptive study. Data were collected using individual-based interviews from 120 senior female residents in the Hall for the aged in the city of S. The length of time for data collection was from June 18 to 29, 2007. The tool of data collection was Korean Version of Mini-Mental State Examination (Kwon & Park, 1989), Short-form Geriatric Depression Scale (Bae, 1996). Results: Depression & cognition showed significant differences according to age, regular exercise. The depression group scored significantly lower than the normal group in total score of cognition, orientation, memory recall. Conclusion: It is necessary to prepare the composite programs, which can improve not only cognition but depression in the community female aged.\

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.230-231
• /
• 2023

악성코드를 탐지하는 기법 중 동적 분석데이터와 같은 시계열 데이터는 프로그램마다 호출되는 API의 수가 모두 다르다. 하지만 딥러닝 모델을 통해 분석할 때는 모델의 입력이 되는 데이터의 크기가 모두 같아야 한다. 이에 본 논문은 TF-IDF(Term Frequency-Inverse Document Frequency)와 슬라이딩 윈도우 기법을 이용해 프로그램의 동적 특성을 유지하면서 데이터의 길이를 일정하게 만들 수 있는 전처리 기법과 LSTM(Long Short-Term Memory) 모델을 통해 정확도(Accuracy) 95.89%, 재현율(Recall) 97.08%, 정밀도(Precision) 95.9%, F1-score 96.48%를 달성했다.

• The Journal of the Korea Contents Association
• /
• v.18 no.1
• /
• pp.185-195
• /
• 2018

We try to explore the effect of the emotions of viewers caused by the insertion of the in-program adversiging on the advertising effect. To test our hypotheses, we collected the data through two lab experiments and analyze the data with t-test. The results are as follows. First, high engagement to the media contents impacts positively on the feeling of viewer's irritation when the movie clip is interrupted and an in-program advertising is inserted. Second, the negative emotions of the irration are congruented, which affect the attitude of the advertised product negatively. On the other hand, the irritation caused by the in-program advertising had a positive effect on the brand awareness and memory(recall) of the advertised product because of high state of arousal. These results enrich the understanding about the role of in-program advertising which affect viewer's feeling and behvior. Moreover, these findings provides managerial implications to help advertising managers manage their in-program advertising more effectively.

• Journal of Digital Convergence
• /
• v.18 no.1
• /
• pp.53-58
• /
• 2020

Various imperative statements that can be represented in the way in which the product or service is used describe how or how to achieve the goals, or induce or prohibit a specific action. This study focuses on The Effects of age and type of imperative sentence (directive vs. declarative) on behavioral intention and recall. As a result of the experiment, older people who have shorter lives remaining access information in a more emotional way, so they have been rejected by directive (vs. declarative) statements that felt more negative feelings, resulting in lowered behavioral intention. Conversely, the negative feeling caused by directive statements increased salience of directive (vs. declarative) sentence for older people more, which in turn increased memory for older people. Process analysis showed that emotions when exposed to statements mediated these results. The results of this study show that in order to improve consumers' behavioral response and/or the performance of information processing, it is necessary to deeply consider their age and how to construct the statement.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.2
• /
• pp.236-240
• /
• 2008

People use diary or photograph for recall-ing their memory in order to satisfy their desires for recording their lives. If the experienced events are organized to a story, S/he can share her/his experience with others, and recall her/his significant events easily. In this paper, we propose a method that generates a story with Petri net and user contexts collected from mobile device. Here, we use Petri-net as a representation method that links human activities or experience causally. It is appropriate solution for modeling parallel events in real world, and for representing non-linear story line. In order to show the usefulness of the proposed method, we show an example of generating a story of user's experience with user contexts from mobile device and evaluate them.