• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.373-373
• /
• 2000

In this paper, we propose a fuzzy modeling algorithm which divides the input space more efficiently than convention methods by taking into consideration correlations between components of sample data. The proposed fuzzy modeling algorithm consists of two steps: coarse tuning, which determines consequent parameters approximately using FCRM clustering method, and fine tuning, which adjusts the premise and consequent parameters more precisely by gradient descent algorithm. To evaluate the performance of the proposed fuzzy mode, we use the numerical data of nonlinear function.

• Proceedings of the Korean Society for Applied Microbiology Conference
• /
• 2004.06a
• /
• pp.203-208
• /
• 2004

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.182-190
• /
• 2021

Deep learning is an advanced technology for large-scale data analysis, with numerous promising cases like image processing, object detection and significantly more. It becomes customarily to use transfer learning and fine-tune a pre-trained CNN model for most image recognition tasks. Having people taking photos and tag themselves provides a valuable resource of in-data. However, these tags and labels might be noisy as people who annotate these images might not be experts. This paper aims to explore the impact of noisy labels on fine-tuning pre-trained CNN models. Such effect is measured on a food recognition task using Food101 as a benchmark. Four pre-trained CNN models are included in this study: InceptionV3, VGG19, MobileNetV2 and DenseNet121. Symmetric label noise will be added with different ratios. In all cases, models based on DenseNet121 outperformed the other models. When noisy labels were introduced to the data, the performance of all models degraded almost linearly with the amount of added noise.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.4
• /
• pp.15-23
• /
• 2017

The WGS conversion project of cadastral drawing (promoted by the Ministry of Land) is not able to reflect the cadastral registration due to subtle differences such as area and location. When converting the digital cadastral region to the world geodetic system, the boundary point coordinates must be changed to the legal coordinate units. However, there is a phenomenon that occurs in which the minute area changes do not coincide with the area registered in the cadastral registration when the coordinate unit is changed. In this study, we have developed a method to adjust many parcels collectively by applying a passive fine-tuning method used in cadastral resurvey project to solve these problems. Total 1, total 2+1, interval 1, interval 2+1, etc. were classified based on the number of parcels that need to be considered for the range of adjustment and the area condition. The analysis of the experimental area (after developing SW for comparison of each method) showed that the total 2+1 method is suitable for the location accuracy and the interval 2+1 method is suitable for the temporal efficiency.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.76-83
• /
• 2023

This study proposes a method to assist webtoon artists in the process of webtoon creation by utilizing a pretrained Text-to-Image model to generate webtoon images from text. The proposed approach involves fine-tuning a pretrained Stable Diffusion model using a webtoon dataset transformed into the desired webtoon style. The fine-tuning process, using LoRA technique, completes in a quick training time of approximately 4.5 hours with 30,000 steps. The generated images exhibit the representation of shapes and backgrounds based on the input text, resulting in the creation of webtoon-like images. Furthermore, the quantitative evaluation using the Inception score shows that the proposed method outperforms DCGAN-based Text-to-Image models. If webtoon artists adopt the proposed Text-to-Image model for webtoon creation, it is expected to significantly reduce the time required for the creative process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.87-89
• /
• 2022

Recently, as more consumers spend more time at home due to COVID-19, the time spent on digital consumption such as SNS and OTT, which can be easily used non-face-to-face, naturally increased. Since 2019, when COVID-19 occurred, digital consumption has doubled from 44% to 82%, and it is important to quickly and accurately grasp and apply trends by analyzing consumers' emotions due to the rapidly changing digital characteristics. However, there are limitations in actually implementing services using emotional analysis in small systems rather than large-scale systems, and there are not many cases where they are actually serviced. However, if even a small system can easily analyze consumer trends, it will help the rapidly changing modern society. In this paper, we propose a lightweight trend analysis system that builds a learning network through Transfer Learning (Fine Tuning) of the BERT Model and interlocks Crawler for real-time data collection.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.5
• /
• pp.94-99
• /
• 2010

This paper presents a design procedure of digitally controlled oscillator(DCO) for power optimization. By controlling coarse tuning bits and fine tuning bits of DCO, the proposed design procedure can optimize the power dissipation and does not affect the LSB resolution, frequency range, linearity, portability. For optimization, the relationship between control bits and power dissipation of the DCO was analyzed. The DCO circuits using and unusing proposed design technique have been designed, simulated and proved using 0.13um, 1.2V CMOS library. The DCO circuit with proposed design technique has operation range between 283MHz and 1.1GHz and has 1.7ps LSB resolution and consumes 2.789mW at frequency of 1GHz.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.356-359
• /
• 1997

Recently many studies have been conducted of fuzzy modeling since it can describe a nonlinear system better than the conventional methods. A famous researcher, M. Sugeno, suggested a fuzzy model which superbly describes a nonlinear system. In this paper, we suggest a new identification method for Sugeno-typo fuzzy model. The suggested algorithm is much simpler than the original identification strategy adopted in [1]. The algorithm suggested in this paper is somewhat similar to that of [2]. that is, the algorithm suggested in this paper consists of two consists of two steps: coarse tuning and fine tuning. In this paper, double clustering strategy is proposed for coarse tuning. Finally, the results of computer simulation are given to demonstrate the validity of this algorithm.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.17 no.2
• /
• pp.1-9
• /
• 1980

A voltage synthesizing channel selection circuit was designed to improve on the conventional vol tape synthesizer which has been memorized each charnel's tuning vol cage itself. In the course of this study, tuning voltage was calculated by channel number entered from 10 keys. Then this circuit has tie function of direct access channel selection and rear display of channel number for the whole range of UHF and VHF, Attention was also given to realize the fine tuning by searching each commended channel, and the sequential selection by using 2keys, and the flash of channel indicator in case of inactive station.