• Journal of Korean Society of Transportation
• /
• v.21 no.4
• /
• pp.29-44
• /
• 2003

A balanced evaluation system for a bus route network was proposed for a mid-sized suburban city. The evaluation system consists of 7 criteria-accessibility, riding comfort. transfer rate, directness of route, productivity of operation, regional equity, and minimum requirement of bus fleet - and quantitative indicators representing each of the criteria. The proposed system was applied in Siheung, a suburban city in Seoul Metropolitan Area. Four alternative scenarios of bus route network including the existing one were evaluated. The results showed that the suggested criteria and indicators are acceptable for the evaluation of a bus route network. In order to enhance the proposed evaluation procedure, further studies on the normalization of produced values and weights for each of the indicators are needed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.126-126
• /
• 2018

최근 우리나라는 기후변화로 인한 이상기후 현상 중 가뭄에 대한 발생빈도가 증가하고 있다. 가뭄은 다른 자연재해에 비해 지속기간이 길고 규모가 광범위하여, 사회 경제적인 피해가 크게 발생한다. 이러한 가뭄에 대비하기 위해서는 지역적으로 적합한 가뭄 대책을 수립해야 하며, 이를 위해서는 가뭄 위험도 평가가 선행되어야 한다. 지역적 가뭄 위험도를 평가하기 위해서는 기상학적 요인뿐만 아니라 사회 경제적인 요인에 의한 영향을 고려하는 가뭄 취약성 평가가 수반되어야 한다. 본 연구에서는 지역별 가뭄 취약성 평가를 수행하기 위해, 지역별 용수 수요 및 공급관련 인자와 선행연구에서 정의된 가뭄 위험인자들 중 8개(생활 농업 공업 용수공급량, 인구밀도, 1인당 가용수자원량, 물 자급률, 취수율, 물 이용 공평성)를 선택하였다. 베이지안 네트워크(Bayesian Network) 기법을 통해 선정된 사회 경제적 요인들과 가뭄과의 상관관계를 분석하여 각 지역의 특성을 고려한 가뭄 위험요인별 확률을 산정하였다. 최종적으로 산정된 주요 가뭄 위험요인별 확률을 우선순위에 따른 가중치를 적용하여 지역별 가뭄 취약성지수(Drought Vulnerability Index, DVI)를 산정하였고, 이를 이용하여 우리나라의 행정구역별로 취약성 평가를 수행하고 지도로 표시하였다. 지역별 가뭄 취약성 평가를 수행한 결과 익산, 상주, 완주 순으로 높게 나타났으며, 계룡, 과천, 종로순으로 가장 낮게 산정되었다. 또한 광역자치단체의 평균 가뭄 취약성지수를 산정한 결과 전라북도 지역이 가장 높게 나타났으며, 대구 및 대전광역시가 가장 낮게 나타났다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.9-17
• /
• 2021

Humans are social animals that have gained information or social interaction through dialogue. In conversation, the mood of the word can change depending on the sensibility of one person to another. Relationships between characters in films are essential for understanding stories and lines between characters, but methods to extract this information from films have not been investigated. Therefore, we need a model that automatically analyzes the relationship aspects in the movie. In this paper, we propose a method to analyze the relationship between characters in the movie by utilizing deep learning techniques to measure the emotion of each character pair. The proposed method first extracts main characters from the movie script and finds the dialogue between the main characters. Then, to analyze the relationship between the main characters, it performs a sentiment analysis, weights them according to the positions of the metabolites in the entire time intervals and gathers their scores. Experimental results with real data sets demonstrate that the proposed scheme is able to effectively measure the emotional relationship between the main characters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.4
• /
• pp.147-152
• /
• 2018

Underwater transient signals are complex, variable and nonlinear, resulting in a difficulty in accurate modeling with reference patterns. We analyze one type of underwater transient signals, in the form of whale sounds, using the MFCC(Mel-Frequency Cepstral Constant) and synthesize them from the MFCC and the weighted $L_2$-norm minimization techniques. The whales in this experiments are Humpback whales, Right whales, Blue whales, Gray whales, Minke whales. The 20th MFCC coefficients are extracted from the original signals using the MATLAB programming and reconstructed using the weighted $L_2$-norm minimization with the inverse MFCC. Finally, we could find the optimum weighted factor, 3~4 for reconstruction of whale sounds.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.1-9
• /
• 2019

The image obtained from systems such as autonomous driving cars or fire-fighting robots often suffer from several degradation such as noise, motion blur, and compression artifact due to multiple factor. It is difficult to apply image recognition to these degraded images, then the image restoration is essential. However, these systems cannot recognize what kind of degradation and thus there are difficulty restoring the images. In this paper, we propose the deep neural network, which restore natural images from images degraded in several ways such as noise, blur and JPEG compression in situations where the distortion applied to images is not recognized. We adopt the channel attention modules and skip connections in the proposed method, which makes the network focus on valuable information to image restoration. The proposed method is simpler to train than other methods, and experimental results show that the proposed method outperforms existing state-of-the-art methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1341-1347
• /
• 2020

Legacy studies for classifying arrhythmia have been studied in order to improve the accuracy of classification, Neural Network, Fuzzy, Machine Learning, etc. In particular, deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose parameter extraction based on AR and arrhythmia classification through a deep learning. For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The classification rate of PVC is evaluated through MIT-BIH arrhythmia database. The achieved scores indicate arrhythmia classification rate of over 97%.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.389-399
• /
• 2021

In recent years, word embedding has been a popular field of natural language processing research and a skip-gram has become one successful word embedding method. It assigns a word embedding vector to each word using contexts, which provides an effective way to analyze text data. However, due to the limitation of vector space model, primary word embedding methods assume that every word only have a single meaning. As one faces multi-sense words, that is, words with more than one meaning, in reality, Neelakantan (2014) proposed a multi-sense skip-gram (MSSG) to find embedding vectors corresponding to the each senses of a multi-sense word using a clustering method. In this paper, we propose a modified method of the MSSG to improve statistical accuracy. Moreover, we propose a data-adaptive choice of the number of clusters, that is, the number of meanings for a multi-sense word. Some numerical evidence is given by conducting real data-based simulations.

• Knowledge Management Research
• /
• v.22 no.2
• /
• pp.289-300
• /
• 2021

Proptech, which has applied information technology to the real estate market, is leading real estate transaction innovation by presenting various value creation models. This study categorizes and understands values that are created and shared in proptech-based businesses, and develops evaluation data that reflects the relative importance of individual value areas. To this end, the dimension of value creation of proptech was hierarchically constructed, and the degree of relative value creation of the sub-industries of the proptech industry was evaluated. In order to grasp the relative importance of the proposed indicators, AHP analysis was conducted for industry and academic experts. In the first stage, intangible values, relational values, and advanced values were presented. It was derived as weights between indicators through two-way comparison. This study aims to improve and develop the value-creation capability of the entire Korean proptech ecosystem in the future by evaluating the value-created competence of each sector of the proptech industry.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.