• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.512-520
• /
• 2019

It is quite useful to represent speeches visually for learners who study foreign languages as well as the hearing impaired who cannot directly hear speeches, and a number of researches have been presented in the literature. They remain, however, at the level of representing the characteristics of speeches using colors or showing the changing shape of lips and mouth using the animation-based representation. As a result of such approaches, those methods cannot tell the users how far their pronunciations are away from the standard ones, and moreover they make it technically difficult to develop such a system in which users can correct their pronunciation in an interactive manner. In order to address these kind of drawbacks, this paper proposes a speech visualization model based on the relative distance between the user's speech and the standard one, furthermore suggests actual implementation directions by applying the proposed model to the visualization of Korean vowels. The method extract three formants F1, F2, and F3 from speech signals and feed them into the Kohonen's SOM to map the results into 2-D screen and represent each speech as a pint on the screen. We have presented a real system implemented using the open source formant analysis software on the speech of a Korean instructor and several foreign students studying Korean language, in which the user interface was built using the Javascript for the screen display.

• Database Research
• /
• v.34 no.3
• /
• pp.137-147
• /
• 2018

A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.

• Journal of Convergence for Information Technology
• /
• v.11 no.2
• /
• pp.31-40
• /
• 2021

Blockchain technology is also actively studied in the real estate transaction field, and real estate transactions have various ways. In this paper, we propose a model that simplifies the authentication procedure of auction systems using Ethereum's Ether to solve the problem of offline court auctions. The proposed model is written in Ethereum's Solidity language, the court registers the sale date and the sale date with the DApp browser, and the bidder accesses the address of the individual's wallet created through Metamask's private key. The bidder then selects the desired sale and enters the bid price amount to participate in the auction. The bidder's record of the highest bid price for the sale he wants is written on the Ethereum test network as a smart contract. and creates a block. Finally, smart contracts written on the network are distributed by the court auction manager to all nodes in the blockchain network, and each node in the blockchain network can be viewed and contract verified. As a result of analyzing the smart contracts of the proposed model and the performance of the system, there are fees incurred due to the creation and use of Ether on platforms using Ethereum, and participation. Ether's changes in value affect the price of the sale, resulting in inconsistent fees in smart contracts each time. However, in future work, we issue our own tokens to solve the market volatility problem and commission problem with the value change of Ether, and refine complex court auction systems.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.817-839
• /
• 2021

To manage software safely, the military acquires and manages products in accordance with the RMF A&A. RMF A&A is standard for acquiring IT products used in the military. And it covers the requirements, acquisition through evaluation and maintenance of products. According to the RMF A&A, product development activities should reflect the risks of the military. In other words, developers have mitigated the risks through security by design and supply chain security. And they submit evidence proving that they have properly comply with RMF A&A's security requirements, and the military will evaluate the evidence to determine whether to acquire IT product. Previously, case study of RMF A&A have been already conducted. But it is difficult to apply in real-world, because it only address part of RMF A&A and detailed information is confidential. In this paper, we propose the evidence fulfilling method that can satisfy the requirements of the RMF A&A. Furthermore, we apply the proposed method to real-world drone system for verifying our method meets the RMF A&A.

• Journal of Korea Trade
• /
• v.23 no.8
• /
• pp.110-131
• /
• 2019

Purpose - This paper investigates the implications for facilitating trade in the products of Industry 4.0. To identify the issues caused by the conflicts of policy objectives such as applying the tariff concession under the ITA and imposing the export control, by exploring the case of classification of drones. Design/methodology - We adopted a single case study method to gain a deeper understanding of the complex and multifaceted issues of Customs classification in the context of facilitating trade in the products of Industry 4.0. This study employs the case of drones to explore how these issues of Customs classification affect trade facilitation. We ensured the internal validity of the study by confirming the pattern of the results with the existing theories. Findings - Our main findings can be summarised as follows: the intrinsic nature of the products that converge several technologies causes issues in the classification. The inconsistency in product classification delays customs clearance by hindering the Customs risk-management system that pinpoints products subject to controls. To address the issues, therefore, we proposed fundamental reforms of Customs to empower themselves with management roles. Facilitating trade in the products of Industry 4.0 requires more enhanced Customs capability. Therefore, the reforms should include comprehensive capacity-building activities, such as changes in staff-trainings, promotion system, organisation and culture. Customs also need roles in robust designing of cooperative systems to compensate for the lacks of controls and to ensure concrete risk management for expedited Customs procedures. As well, by equipping the Single Window of Customs with crucial control functions of other ministries, Customs need to support the cooperation. The role of harmonising various preaudits of other ministries with its own is another essential role that ensures predictability of clearance procedure. Originality/value - There are scanty studies in the field of knowledge about what obstacles exist and what solution is available in the course of transforming to 'Industry 4.0'. In filling out the gap of knowledge, this paper is of academic significance in that it applies the research theory on trade facilitation for the specific cases of classification of the product of Industry 4.0 to verify its effectiveness and to extend the subject of the studies to the scope of Industry 4.0. It also has practical significance in that the results have provided implications for reforms of Customs procedures to facilitate trade in the products of Industry 4.0.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.338-343
• /
• 2022

As the revitalization of the global maritime industry continues, the number of foreign ships navigating the maritime territories of maritime neighboring countries has rapidly increased. However, large-scale marine accidents have occurred, caused by the insufficient establishment of a system for management and operation relative to vessels' safety-condition. To address that, the IMO has granted the right to exercise port state control, especially for foreign vessels, to countries with jurisdiction over maritime territories with strengthening regulations and guidelines. In particular, the Republic of Korea, as a member of the TOKYO MOU, is conducting PSC, but as of 2020, the proportion of foreign ships was three times higher than that of national ships that called in domestic ports. However, the inspection rate was low at 9% which has not met the recommended level by the TOKYO MOU. Thus, this study conducted an IPA analysis as well as content analysis, by collecting the practical opinions and views of PSCO through objective questionnaires and written expert interviews, for improving the efficiency and effectiveness of domestic PSC. As a result, it was derived that the importance and performance related to human factors such as life on board, working environment, and response to safety accidents should be improved in to raise the quality of PSC inspection. Additionally, the work environment and performance of PSC in domestic ports for foreign vessels could be improved, if multifaceted support bases are established, for administrative unification of related tests for PSC, recruitment of PSCO, activation of the defection-reporting system, reorganization of the PSC execution group, etc.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.562-565
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. However, this irregular weight distribution is not possible to be recognized with the current weight measurement system for vehicles on roads. To address this limitation, we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles from the CCTV, black box, and hand-held camera point of view. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data. From the result, we believe that public big data can be utilized more efficiently and applied to the development of an object detection-based overloaded vehicle detection model.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.53-60
• /
• 2002

Motion of lung tumors from respiration has been reported in the literature to be as large as of 1-2 cm. This motion requires an additional margin between the Clinical Target Volume (CTV) and the Planning Target Volume (PTV). While such a margin is necessary, it may not be sufficient to ensure proper delivery of Intensity Modulated Radiotherapy (IMRT) to the CTV during the simultaneous movement of the DMLC. Gated treatment has been proposed to improve normal tissues sparing as well as to ensure accurate dose coverage of the tumor volume. The following questions have not been addressed in the literature: a) what is the dose error to a target volume without gated IMRT treatment\ulcorner b) what is an acceptable gating window for such treatment. In this study, we address these questions by proposing a novel technique for calculating the 3D dose error that would result if a lung IMRT plan were delivered without gating. The method is also generalized for gated treatment with an arbitrary triggering window. IMRT plans for three patients with lung tumor were studied. The treatment plans were generated with HELIOS for delivery with 6 MV on a CL2100 Varian linear accelerator with a 26 pair MLC. A CTV to PTV margin of 1 cm was used. An IMRT planning system searches for an optimized fluence map ${\Phi}$ (x,y) for each port, which is then converted into a dynamic MLC file (DMLC). The DMLC file contains information about MLC subfield shapes and the fractional Monitor Units (MUs) to be delivered for each subfield. With a lung tumor, a CTV that executes a quasi periodic motion z(t) does not receive ${\Phi}$ (x,y), but rather an Effective Incident Fluence EIF(x,y). We numerically evaluate the EIF(x,y) from a given DMLC file by a coordinate transformation to the Target's Eye View (TEV). In the TEV coordinate system, the CTV itself is stationary, and the MLC is seen to execute a motion -z(t) that is superimposed on the DMLC motion. The resulting EIF(x,y)is inputted back into the dose calculation engine to estimate the 3D dose to a moving CTV. In this study, we model respiratory motion as a sinusoidal function with an amplitude of 10 mm in the superior-inferior direction, a period of 5 seconds, and an initial phase of zero.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.1
• /
• pp.60-66
• /
• 2023

Currently, the maritime industry is focusing on developing technologies that promote autonomy and intelligence, such as smart ships, autonomous ships, and eco-friendly technologies, to enhance ship operational efficiency. Many countries are conducting research on different methods to ensure ship safety while increasing operational efficiency. This study aims to develop a real-time ship operational efficiency analysis model using data analysis methods to address the current limitations of the present technologies in the real-time evaluation of operational efficiency. The model selected ship operational efficiency factors and ship operational condition factors to compare the operational efficiency of the ship with present and classified factors to determine whether the present ship operational efficiency is appropriate. The study involved selecting a target ship, collecting data, preprocessing data, and developing classification models. The results of the research were obtained by determining the improved ship operational efficiency based on the ship operational condition factors to support ship operators.