• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.251-260
• /
• 2020

In , music becomes a passage of spaces in dreams and at the same time causes a problem of temporality between spaces with different time speeds. This paper aims to examine the temporality of the music through Bergson's concept of time. The music used in the film, 《Non, je ne regrette rien》, is divided into the original version, the slowed-down version, and the rearranged version with the slowed-down, and this study visually confirmed the characteristics and similarities through practical analysis. From the perspective of Bergson's perception and memory diagram, non-diegetic music of the actual(the rearranged version) in which diegetic music of the virtual(the slowed-down version) inherent, plays the role of film music and music signal simultaneously. Also, the original version and the slowed-down version are the relationship of durational identity with qualitative changes. We looked at the position in the inverted cone diagram and applied their relationship to the diagram. It is a great achievement of this study that we explored the temporality of music in the multi-layered structure of , based on Bergson's philosophy of coexisting with the present and the past.

• TTA Journal
• /
• s.131
• /
• pp.28-29
• /
• 2010

올해 극장가를 가장 뜨겁게 달궜던 영화는 크리스토퍼 놀란 감독의 <인셉션(Inception, 2010)>일 것이다. 이 영화는 꿈을 스크린에서 환상적으로 그려냈다는 점에서도 놀라움을 줬지만 그보다 더 충격적인 것은 꿈을 훔치고, 꿈을 통해 다른 사람의 기억을 조작한다는 발상이었다. 이렇게 인간의 꿈마저 스크린을 옮겨낼 수 있기에 할리우드를 '꿈의 공장'이라고 부르는 것이다. 그렇다면 꿈이란 무엇이기에 꿈속에서는 현실에서 불가능한 많은 것들이 벌어지는 것일까?

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.407-412
• /
• 2017

In the film Inception, we can see that the human dream world is depicted using Freud's psychoanalytical subconscious theory. Through the expression of the subconscious, And the ability to think and think deeply of human nature, such as presenting a new perspective to insight and expression. Based on Freud 's subconscious theory, this paper explores the expression of the dream world and the subconscious in the film and examines the meaning expression of the film through it. The main character is well described as living a chaotic life in obsession with obsessions and obsessions due to his subconscious uncontrollable through his dreams and dreams of being satisfied by the way the oppressed thoughts and desires are disguised I feel that I feel my foolishness and mood as a masturbation by dreaming and dreaming to turn back the moments of regret. In addition, conflicts and confrontations between consciousness and subconscious are expressed well in the form of confusion in reality and dreams. This application and application of humanities studies is a good example of the production of in-depth popular arts content, as we can see that it can add to the weight of depth setting, plot development, and above all creative time and space creation.

• Journal of Digital Convergence
• /
• v.15 no.10
• /
• pp.437-444
• /
• 2017

Christopher Nolan's film "Inception (2012)", which depicts the world of dreams as a unique space-time and opens a new chapter in the expression of dreams, portrays the dreamy world of unconsciousness. However, I can find limitations and contradictions in the expression of the actual dreams and essence of unrealistic structures and forms. I can find David Lynch's movies "Mulholland drive (2001)", which are closer to Freud's psychoanalysis in expressing the actual presentation process of dreams Through comparative analysis, I try to analyze the interpretation and context of the dream mentioned by Freud. The film "Inception" can be appreciated in terms of space time and rich imagination created from the point of view of science fiction movies, but it shows that logical reasonability is weak in view of applying the essence of dream. On the other hand, the film "Mulholland Drive" describes the illogical, confusing and unhappy feeling of unconsciousness by giving logic and order based on the interpretation of Freud's psychoanalytic dreams, is. In this way, it is possible to portray more realistic scenes of dreams only through the portrayal of dreams and unconsciousness based on Freud's psychoanalytic viewpoint.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.257-258
• /
• 2017

머신러닝 기법을 다양한 분야에 사용되는 연구가 한창이다. 본 논문에서는 악성 코드의 분류 시스템에 머신러닝 기법을 적용하였다. 악성 코드 파일을 적당한 크기로 이미지화하여 텐서 플로우의 인셉션 V3에 적용하였다. 실험 결과, 이미지의 사이즈 조정과 파라미터 조정을 통해 매우 만족할 만한 수준으로 악성 코드를 잘 분류함을 확인할 수 있었다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.9-18
• /
• 2021

Although Generative Adversarial Networks (GANs) have gained great popularity in computer vision and related fields, generating audio signals independently has yet to be presented. Unlike images, an audio signal is a sampled signal consisting of discrete samples, so it is not easy to learn the signals using CNN architectures, which is widely used in image generation tasks. In order to overcome this difficulty, GAN researchers proposed a strategy of applying time-frequency representations of audio to existing image-generating GANs. Following this strategy, we propose an improved method for increasing the fidelity of synthesized audio signals generated by using GANs. Our method is demonstrated on a public speech dataset, and evaluated by Fréchet Inception Distance (FID). When employing our method, the FID showed 10.504, but 11.973 as for the existing state of the art method (lower FID indicates better fidelity).

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1166-1174
• /
• 2019

This paper propose and experiment advanced PersonNet, a human identification model, with advanced performance. We apply the inception layer to extract feature points, and increase the existing 32 feature points to 154. Also, we modify the CND method used by PersonNet to mitigate asymmetry, and apply weights to the feature map of pedestrian images in three parts, thereby making the features more distinct. Three databases were used for performance evaluation : CUHK01, CUHK03 and Market-1501. The experiment results showed 27-31% improvement in performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.132-137
• /
• 2019

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.