• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.596-599
• /
• 2001

Extracting of car licens plate is important for identifying the car. Since there are some problems such as poor ambient lighting problem, bad weather problem and so on, the car images we distorted and the tar license plate is difficult to be extracted. This paper proposes a method of extracting car license plate using motor vehicle regulation. In this method, some features of car license plate according to motor vehicle regulation such as color information, shape are applied to determine the candidate of car license plates. For the result of recognition by neural network, the candidate which has characters and numbers patterns according to motor vehicle regulation is certified as license-plate region. The results of the experiments with 70 samples of real car images shoe the performance of car license-plate extraction by 84.29%, and the recognition rate is 80.81%.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.225-239
• /
• 2019

Together with the emergence of Information and Communications Technology(ICT) and 4th Industrial Revolution, digital content is arising as a front-runner in the knowledge society. 21 century opened up an era of digital and cultural content, which is the industry to generating added values from future industries. This study aims to empirically examine the casual relation between three factors from Organizational Justice Theory Distributive, Procedural, Interactional Justices, and turnover intention through Organizational Immersion. A sample group for the analysis was employees at small/medium-sized digital content businesses with less than 60 workers. 200 questionnaires were distributed to the group for a week from July 22 to 28, 2019. 154 responses were collected and analyzed in this study, after eliminating 4 poor responses. The result of the study on Organizational Justice at digital content businesses showed that, first, Distributive Justice of the employees showed a positive influence on Organizational Immersion. Second, the employees' Procedural Justice showed a positive influence on Organizational Immersion. Third, the employee' Interactional Justice showed a positive influence on Organizational Immersion. Fourth, the employees' Organizational Immersion showed a positive influence on their turnover intention.

• International Journal of Contents
• /
• v.18 no.2
• /
• pp.32-46
• /
• 2022

In recent years, large-scale and high-density use of LED on facades has exposed some disadvantages, such as light pollution, high energy consumption, unsustainability, and poor interactivity. Because of the development of smartphones and augmented reality (AR), AR has emerged as a new technology available to users to interact with the media façade. As an augmented reality app for public space, the AR map app can superimpose virtual images on the surface of a building to form an AR media façade, which can be applied in the fields of navigation, advertising, interactive public art, smart retail, etc. This study establishes the variables influencing usage intention and the consequent outcomes of Huawei AR map app and uses the technology acceptance model (TAM) to discuss their relationship. Results show that consumer innovativeness, information quality, and design quality have a strong influence on perceived ease of use. Information quality has a positive impact on perceived usefulness, but design quality has a weak influence. Also, the design quality of Huawei AR map app and consumer innovativeness have a higher effect on perceived enjoyment than information quality. Users' usage attitude and perceived usefulness when using Huawei AR map app are key factors determining their usage intention. This study inspires city planners, architects, developers, and designers of AR apps that augmented reality can partly replace media façade, and that investment in augmented reality will achieve significant sustainable economic and social benefits.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• Management & Information Systems Review
• /
• v.13
• /
• pp.27-47
• /
• 2003

The strategic usages of IT(Information Technology) can convey important competitive advantages with an operational productivity. For this reason, many firms have heavily invested in IT and computing power. However, many companies were getting expected results by IT investment, but some companies had to be satisfied with a poor results. The question of whether or not benefit lead to expected performance is not easy to answer. The purpose of this study was to investigate the relationship among IT strategy, IT investment, and IT performance to resolve this problem. The 147 questionnaire responses completed by IS managers in manufacturing sector was conducted for a test of research hypothesis. ANOVA was used to investigate the relationship among three constructs and six factors. An operational performince of fitted group between IT strategy and IT investment was higher than not fitted group(H1). And also an competitive performance of fitted group between IT strategy and IT investment was higher than not fitted group(H2). The study shows a positive relationship between IT strategic orientation, IT investment direction, and performance of IT. The research results provide empirical evidence that supports the research hypothesis that closer fit between IT strategies and IT investment directions does lead to increase operational and competitive performance of IT.

• IE interfaces
• /
• v.22 no.3
• /
• pp.252-262
• /
• 2009

It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used the statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM (SSVM), for detecting high and low yields. SSVM is step-by-step adjustment of parameters to be precisely the classification for actual high and low yield lot. The objective of this paper is to examine the feasibility of SVM and SSVM in the yield classification. The experimental results show that SVM and SSVM provides a promising alternative to yield classification for the field data.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.522-539
• /
• 2021

In order to solve the problems of the existing audio fingerprint method when extracting audio fingerprints from long speech segments, such as too large fingerprint dimension, poor robustness, and low retrieval accuracy and efficiency, a robust audio fingerprint retrieval method based on feature dimension reduction and feature combination is proposed. Firstly, the Mel-frequency cepstral coefficient (MFCC) and linear prediction cepstrum coefficient (LPCC) of the original speech are extracted respectively, and the MFCC feature matrix and LPCC feature matrix are combined. Secondly, the feature dimension reduction method based on information entropy is used for column dimension reduction, and the feature matrix after dimension reduction is used for row dimension reduction based on energy feature dimension reduction method. Finally, the audio fingerprint is constructed by using the feature combination matrix after dimension reduction. When speech's user retrieval, the normalized Hamming distance algorithm is used for matching retrieval. Experiment results show that the proposed method has smaller audio fingerprint dimension and better robustness for long speech segments, and has higher retrieval efficiency while maintaining a higher recall rate and precision rate.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2016.02a
• /
• pp.426.1-426.1
• /
• 2016

We report high work function Aluminum doped zinc oxide (AZO) films as insertion layer as a function of O2 flow rate between transparent conducting oxides (TCO) and hydrogenated amorphous silicon oxide (a-SiOx:H) layer to improve open circuit voltage (Voc) and fill factor (FF) for high efficiency thin film solar cell. However, amorphous silicon (a-Si:H) solar cells exhibit poor fill factors due to a Schottky barrier like impedance at the interface between a-SiOx:H windows and TCO. The impedance is caused by an increasing mismatch between the work function of TCO and that of p-type a-SiOx:H. In this study, we report on the silicon thin film solar cell by using as insertion layer of O2 reactive AZO films between TCO and p-type a-SiOx:H. Significant efficiency enhancement was demonstrated by using high work-function layers (4.95 eV at O2=2 sccm) for engineering the work function at the key interfaces to raise FF as well as Voc. Therefore, we can be obtained the conversion efficiency of 7 % at 13mA/cm2 of the current density (Jsc) and 63.35 % of FF.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.263-267
• /
• 2005

Presentation is the most important factor in the usability of a web site. A poor layout makes a bad influence on the searching ability of the user by reducing search speed and causing mistakes. Recently many web sites visualize 3D information and there is plenty of research on it. Such a layout improves the usability of web pages and information awareness both in quantity and quality. This paper proposes design guides on 3D information browsing and has experiments on searching speed of the users for 2D and 3D displays of the same data and were analyzed.