• Journal of The Korean Society For Urban Railway
• /
• v.6 no.4
• /
• pp.223-231
• /
• 2018

Since the introduction of PSD in 2005, the number of accidents involving passengers falling onto the tracks accidentally or intentionally have drastically decreased, but the number of PSD related passenger accidents is increasing. While existing papers on PSD have been devoted to systemic introduction and system improvement, papers on passenger casuality accidents due to deteriorated PSD have been limited. This paper proposes revising of the scenario model for passenger accidents using classified hazard sources of PSD.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.929-944
• /
• 2019

Many critical applications require accurate real-time human action recognition. However, there are many hurdles associated with capturing and pre-processing image data, calculating features, and classification because they consume significant resources for both storage and computation. To circumvent these hurdles, this paper presents a recognition machine learning (ML) based system model which uses reduced data structure features by projecting real 3D skeleton modality on virtual 2D space. The MMU VAAC dataset is used to test the proposed ML model. The results show a high accuracy rate of 97.88% which is only slightly lower than the accuracy when using the original 3D modality-based features but with a 75% reduction ratio from using RGB modality. These results motivate implementing the proposed recognition model on an embedded system platform in the future.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.543-545
• /
• 2019

Recently, the demand for smart farms is increasing due to the increase in the cultivation area such as horticulture, fruit trees and special crops. However, due to the irregular weather changes and the cultivation method of the crops due to the different cultivation environment, there are frequent occurrence of diseases and insect pests and infectious diseases due to system error or carelessness, and the cycle is also very short. In addition, the Smart Farm business has been built by combining various sensors (temperature, humidity, CO2, illumination) and LED lighting, but it is costly in terms of frequent errors, lack of power supply, And thus the management can not be efficiently managed. Therefore, this paper combines real time sensing technology based on IoT Platform and high performance control technology to control pests and equipment errors and monitor the growth status of crops in real time based on big data analysis and Artificial Intelligence System.

• Journal of KIBIM
• /
• v.8 no.4
• /
• pp.13-22
• /
• 2018

Future performance prediction of bridges is challenging task for structural engineers. Well-organized information from design, construction and operation stages is essential for the assessment of structures. Digital twin model is a new concept to realize more reliable data platform for management of infrastructures. Damage history including degradation of material, cracking, corrosion, etc. needs to be accumulated in the digital model. The digital model is linked to the analysis model for the assessment of structural performance considering changed mechanical properties of structural components. In this paper, initial definition digital twin model of a PSC-I girder bridge is proposed.

• Computers and Concrete
• /
• v.23 no.6
• /
• pp.399-408
• /
• 2019

Structural health monitoring is important for the safety of lives and asset management. In this study, numerical models were developed for the piezoresistive behavior of smart concrete based on finite element (FE) method. Finite element models were calibrated with experimental data collected from compression test. The compression test was performed on smart concrete cube specimens with 75 mm dimensions. Smart concrete was made of cement CEM II 42.5 R, silica fume, fine and coarse crushed limestone aggregates, brass fibers and plasticizer. During the compression test, electrical resistance change and compressive strain measurements were conducted simultaneously. Smart concrete had a strong linear relationship between strain and electrical resistance change due to its piezoresistive function. The piezoresistivity of the smart concrete was modeled by FE method. Twenty-noded solid brick elements were used to model the smart concrete specimens in the finite element platform of Ansys. The numerical results were determined for strain induced resistivity change. The electrical resistivity of simulated smart concrete decreased with applied strain, as found in experimental investigation. The numerical findings are in good agreement with the experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.129-135
• /
• 2019

This paper is part of research and development for stand-alone solar system without commercial power supply. It implements firmware of controller for operation of stand-alone solar system by applying IoT technology and also develops communication modules that allow multiple solar lamps to send and receive data through wireless network. The controller of the developed stand-alone solar system can effectively charge the power generated by the solar module, taking into account the battery's charge and discharge characteristics. It also has the advantage of attaching wireless communication modules to solar lamp posts to establish wireless communication networks without incurring communication costs. In addition, by establishing IoT gateway middleware platform for each installation site, it forms a foundation to operate multiple solar lamp posts into multiple clusters. And, it is expected that the data collected in each cluster will be used to enable configuration and control of operational information, thereby inducing convenience and efficiency of remote operation and management.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.376-380
• /
• 2018

Objectives: This research presents the design and development of a software architecture using natural language processing tools and the use of an ontology of knowledge as a knowledge base. Methods: The software extracts, manages and represents the knowledge of a text in natural language. A corpus of more than 200 medical domain documents from the general medicine and palliative care areas was validated, demonstrating relevant knowledge elements for physicians. Results: Indicators for precision, recall and F-measure were applied. An ontology was created called the knowledge elements of the medical domain to manipulate patient information, which can be read or accessed from any other software platform. Conclusions: The developed software architecture extracts the medical knowledge of the clinical histories of patients from two different corpora. The architecture was validated using the metrics of information extraction systems.

• International journal of advanced smart convergence
• /
• v.10 no.2
• /
• pp.10-14
• /
• 2021

Today people adopt various contents from their mobile devices which lead to numerous platforms. As technology of 5G, IOT, and smart phone develops, the number of people who create, edit, collect, and share their own videos, photos, and articles continues to increase. As more contents are shared online, the numbers of data being stolen continue to increase too. To prevent these cases, an authentication method is needed to encrypt the content and prove it as its own content. In the report, we propose a few methods to secure various misused content with secondary security. A unique private key is designed when people create new contents through sending photos or videos to platforms. The primary security is to encrypt the "Private Key" with a public key algorithm, making its data-specific "Timeset" that doesn't allow third-party users to enter. For the secondary security, we propose to use Message Authentication Codes(MACs) to certify that we have produced the content.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.871-874
• /
• 2013

기존 PC에서 발생되는 악성코드가 안드로이드 모바일 플랫폼에서 스미싱 어플리케이션으로 급증하고 있다. 스마트 폰 사용자는 SMS에 의해 악성코드를 설치하게 되며, 악성코드가 소액결제 서비스 인증번호를 가로채어 C&C 서버 등으로 송신함으로써 30 만원 이내의 금전적 손해를 일으키게 된다. 본 논문에서는 GCM(Google Cloud Messaging)과 MDM(Mobile Device Management)을 이용하여 사용자의 스마트 폰에서 동작하고 있는 악성 어플리케이션을 탐지하고, 악성 행위를 통제시키며 사용자로부터 직접 어플리케이션을 삭제하길 권하는 시스템을 설계하여 제안하고자 한다.

• Journal of TMJ Balancing Medicine
• /
• v.11 no.1
• /
• pp.1-11
• /
• 2021

Dystonia is a neurological disorder characterized by involuntary and uncontrollable muscle tonus abnormalities. It is a huge burden not only to the patients and their families, but also to the field of medicine, in that there has hardly been any substantial change in the concept of and approach to this intractable disorder and therefore no breakthrough to its diagnosis, evaluation and treatment. As an effort to solve the current impasse, this review briefly summarizes the current concept, etiology, diagnosis, treatment and management, and then suggests a rather new therapeutic approach to this disorder, based on the concept of neurological balance and TMJ integrative approach. These new approaches will provide a platform for the clinicians and researchers to have a leap in the concept, diagnosis and therapeutics.