• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.3
• /
• pp.289-299
• /
• 2019

Various sizes of ROVs are being utilized in offshore industrial, scientific, and military applications all around the world. Because of innovative developments in science and technology, image acquisition devices such as sonar devices and cameras have been reduced in size and their performance has been improved. Thus, we can expect better accuracy and higher resolution even in the case of exploration using a small ROV. The purpose of this paper is to prepare a standard procedure for the identification of unidentified hazardous materials found during the National Oceanographic Survey. In this paper, we propose an IDEF (Integrated DEFinition) method modeling technique to identify unidentified targets using a small ROV. In accordance with the proposed procedure, an ROV survey was carried out on target No.16 with a four-ton-class fishing boat as a support vessel on September 18th of 2018 in the sea near Daebu Island. Unidentified targets, which were not known by the multi-beam data obtained from the ship, could be identified as concrete pipes by analyzing the HD camera and high-resolution sonar images acquired by the ROV. The whole proposed procedure could be verified, and the survey with the small ROV required about 10 days to identify the target in one place.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.457-467
• /
• 2019

In recent years, various methods have been attempted to visually manage the construction site efficiently, and in particular, there has been a tendency to use a UAV or a drone in the air rather than a land on a construction site, Can be visually photographed and recorded or analyzed. In this study, the unmanned aerial photographs were taken at least three times and the USN sensors were simultaneously operated on the main structure at the time of shooting, The goal of this research was to make the image information and environmental information of the construction site available for efficient construction management by matching. As a result, not only professional engineers at construction sites but also administrative managers can visually confirm the detailed situation of the site at the time of the construction site and the completion status, and can help decision making in appropriate budget input and appropriate resource support The experts in each field discussed the safety management of the construction site, the prevention of disaster and various factors of change which can be changed by natural environment factors.

• Journal of Information Technology Applications and Management
• /
• v.25 no.3
• /
• pp.43-54
• /
• 2018

In recent years, international cooperation has become important not only at the humanitarian level but also at the socio-economic level. As a result, major foreign countries are increasing capital-intensive international cooperation. In this environment, Korea needs to look for differentiated international cooperation plans centered on sustainable talent cultivation and move away from capital-based international cooperation. In this study, we analyzed the case of HRD (Human Resource Development) center in Cambodia as an international cooperation model between industry-academia-college for training software (SW) workforce. The HRD Center in Cambodia is an educational institution that fosters SW talent and can be viewed as an international cooperation model that can influence the ICT industry in Cambodia as an educational platform. In fact, 190 people who have been hired so far have entered various fields. 97% of graduates have been satisfied with HRD center and 90% of them are willing to recommend the center. In particular, as highlighted in the case study, the HRD Center has had a positive effect on not only cultivating self-initiated learning-based SW talent, but also formulating positive image of Korea and Korean companies thereby facilitating entry into the global market. The HRD Center in Cambodia has developed a virtuous cycle of fostering human resources, providing education, advancing industry and building a cooperative network. Korea has transformed into a platform for international cooperation and human resource development and education by providing active support and aid. This case study will be utilized as a new model of international cooperation with SW expert training platform for Korea.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.55-62
• /
• 2019

We examined the Audit Quality on the Socially Responsible Investment(SRI) Corporate. We used 1,497 sample data from 2014 to 2016. In short, the result of this paper's is as followed. Socially Responsible Investment(SRI) has a positive relevance with Audit Quality. Socially Responsible Investment(SRI) has a positive relevance with Audit Fee, Audit Time and Audit Size specifically. Therefore we can support that a firm has a high level of Socially Responsible Investment(SRI) will have the better the Audit Quality according to this study. This study contributes as follow. We can verify that the more Socially Responsible Investment(SRI) the better Quality of Accounting Information. We expect that this study can be helped positive image enhancement of Socially Responsible Investment(SRI) Corporate. So we hope that our paper can contribute sound capital market's development.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.15-21
• /
• 2021

The type of crimes is diverse and the number of crimes is increasing as society changes. This phenomenon is showing a higher trend in places with higher population density. Accordingly, many organizations install CCTV to reduce crime and provide key evidence of crime. Nevertheless, it is still weak to deal with crimes such as video manipulation targeting CCTV. Although blockchain-based CCTV image integrity techniques are applied to prevent manipulation, they only guarantee the manipulation integrity of the entire video and can't explain how certain sections of the video has been manipulated. Therefore, in this research, we propose a system for supporting explainable CCTV video integrity based on a block chain.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.19 no.6
• /
• pp.105-112
• /
• 2009

Nowadays, completely automated public turing tests to tell computers and humans apart(CAPTCHAs) are widely used to prevent various attacks by automated software agents such as creating accounts, advertising, sending spam mails, and so on. In early CAPTCHAs, the characters were simply distorted, so that users could easily recognize the characters. From that reason, using various techniques such as image processing, artificial intelligence, etc., one could easily break many CAPTCHAs, either. As an alternative, By adding noise to CAPTCHAs and distorting the characters in CAPTCHAs, it made the attacks to CAPTCHA more difficult. Naturally, it also made users more difficult to read the characters in CAPTCHAs. To improve the readability of CAPTCHAs, some CAPTCHAs used different colors for the characters. However, the usage of the different colors gives advantages to the adversary who wants to break CAPTCHAs. In this paper, we suggest a method of increasing the recognition ratio of CAPTCHAs based on colors.

• Journal of Platform Technology
• /
• v.8 no.4
• /
• pp.20-28
• /
• 2020

In this paper, a voice, object, and optical character recognition platform including voice recognition-based smart wearable devices, smart devices, and web AI servers was proposed as an appropriate technology to help the visually impaired to live independently by learning the life cycle of the visually impaired in advance. The wearable device for the visually impaired was designed and manufactured with a reverse neckband structure to increase the convenience of wearing and the efficiency of object recognition. And the high-sensitivity small microphone and speaker attached to the wearable device was configured to support the voice recognition interface function consisting of the app of the smart device linked to the wearable device. From experimental results, the voice, object, and optical character recognition service used open source and Google APIs in the web AI server, and it was confirmed that the accuracy of voice, object and optical character recognition of the service platform achieved an average of 90% or more.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.313-318
• /
• 2021

In order to treat a disease, it is necessary to take the medication on time, but many people often violate or forget the time they take the medicine. Applications are emerging to solve these problems using information technology. However, for existing applications, it is difficult to use because it provides only a notification functions, user interface is inconvenient, and photo registration of the medication is impossible. To solve these problems, the study developed a smart medicine management application that allows users to set up their taking routines, check if they are taking them, search hospitals and pharmacies, and attach images of medicines they are taking. Through this appliaction, it is possible to reduce the frequency of forgetting the time taken and to take accurate medication by checking the actual image. It also supports the setting of a taking routine to support multiple medications with different taking cycles. It can also provide information about hospital and pharmacies close to their current location to increase access to hospital and pharmacies.