• The Journal of Society for e-Business Studies
• /
• v.15 no.4
• /
• pp.33-47
• /
• 2010

Web records is valuable information to preserve, because it can be used as a legal evidence about business or e-commerce of a public institution, but it is easily disappeared because of its volatile characteristic. Therefore, archival information package should be defined for long-term preservation. Web records can be stored in the archival information package for electronic records, because web records is a kind of electronic records. However, the NEO(NARS Encapsulation Object), the archival information package for electronic records in Korea, can't able to store web records, because it was developed without consideration of the characteristic of web records. In this paper, we define extended NEO based on the analysis of KoSurWeb and KoDeWeb, that archival information package for document of surface and deep web as well as the NEO. Web records can be preserved and utilized along with electronic records by using the extended NEO. Also it can be used for record and legal evudence by archiving web records of public institution about e-commerce.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.197-200
• /
• 2010

웹 기술이 발달함에 따라 공공기관 웹사이트는 단순한 행정기관의 홍보에서 벗어나 국민과 정부 간의 의사소통의 증거인 동시에 업무의 기록으로서 역할을 담당하고 있다. 따라서 공공기관의 웹사이트들은 공공기록물로 인식하고 보호해야 한다. 하지만 공공기관의 웹기록물 중 하나인 심층 웹기록물은 실시간으로 상이한 페이지를 동적으로 구성하기 때문에 기존의 보존방법과는 다른 수집 보존 활용 기술이 요구된다. 국가기록원은 이러한 특징을 가지고 있는 심층 웹기록물을 장기보존하기 위해서 심층 웹기록물 장기보존 포맷인 KoDeWeb을 연구하고 개발하였다. KoDeWeb은 전자기록물이기 때문에 전자기록물로서 진본성 및 무결성을 보장해야 한다. 본 연구에서는 KoDeWeb의 전자기록물로서의 진본성 및 무결성을 증명하기 위해 국제 전자기록물 표준인 OAIS 참조모델에 KoDeWeb을 맵핑시켰다. 나아가 OAIS표준을 따르고 있는 전자기록물 장기보존 시스템에 KoDeWeb을 사용함으로써, 정부 및 공공기관의 심층 웹기록물 생성 및 수집을 체계화하고, 또한 민간이 운영하는 웹의 심층 웹기록물 장기보존에 활용할 수 있다.

• Journal of Korean Society of Steel Construction
• /
• v.19 no.5
• /
• pp.493-501
• /
• 2007

Recently, in the domestic amount of materials,curtailment and economic efficiency security by purpose, tapered beam application is achieved, but the architectural design technology of today based on the material non-linear method does not consider solutions to problems such as brittle fracture. So, geometric non-linear evaluation thatincludes initial deformation, width-thickness ratio, web stiffener and unbraced length is required. Therefore, in this study, we used ANSYS, a proven finite elementanalysis program,and material and geometric non-linear analysis to study existing and completed tapered H-section as deep beam's analysis model. Main parameters include the width-thickness ratio of web, stiffener, and flange brace, with the experimental result obtained by main variable buckling and limit strength evaluation. We made certain that a large width-thickness ratio of the web decreases the buckling strength and short unbraced web significantly improves ductility.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.159-173
• /
• 2022

This paper proposes a hybrid machine-learning model, which is called DANN-IP, that combines a deep artificial neural network (DANN) and an interior-point (IP) algorithm in order to improve the prediction capacity on the patch loading resistance of steel plate girders. For this purpose, 394 steel plate girders that were subjected to patch loading were tested in order to construct the DANN-IP model. Firstly, several DANN models were developed in order to establish the relationship between the patch loading resistance and the web panel length, the web height, the web thickness, the flange width, the flange thickness, the applied load length, the web yield strength, and the flange yield strength of steel plate girders. Accordingly, the best DANN model was chosen based on three performance indices, which included the R^2, RMSE, and a20-index. The IP algorithm was then adopted to optimize the weights and biases of the DANN model in order to establish the hybrid DANN-IP model. The results obtained from the proposed DANN-IP model were compared with of the results from the DANN model and the existing empirical formulas. The comparison showed that the proposed DANN-IP model achieved the best accuracy with an R^2 of 0.996, an RMSE of 23.260 kN, and an a20-index of 0.891. Finally, a Graphical User Interface (GUI) tool was developed in order to effectively use the proposed DANN-IP model for practical applications.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.37-44
• /
• 2023

As a primary technology of Industry 4.0, human-robot collaboration (HRC) requires additional measures to ensure worker safety. Previous studies on avoiding collisions between collaborative robots and workers mainly detect collisions based on sensors and cameras attached to the robot. This method requires complex algorithms to continuously track robots, people, and objects and has the disadvantage of not being able to respond quickly to changes in the work environment. The present study was conducted to implement a web-based platform that manages collaborative robots by recognizing the emotions of workers - specifically their perception of danger - in the collaborative process. To this end, we developed a web-based application that collects and stores emotion-related brain waves via a wearable device; a deep-learning model that extracts and classifies the characteristics of neutral, positive, and negative emotions; and an Internet-of-things (IoT) interface program that controls motor operation according to classified emotions. We conducted a comparative analysis of our system's performance using a public open dataset and a dataset collected through actual measurement, achieving validation accuracies of 96.8% and 70.7%, respectively.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.45-55
• /
• 2023

With the widespread use of digital devices, anonymous communication technologies such as the dark web and deep web are becoming increasingly popular for criminal activity. Because these technologies leave little local data on the device, they are difficult to track using conventional crime investigation techniques. The United States and the United Kingdom have enacted laws and developed systems to address this issue, but South Korea has not yet taken any significant steps. This paper proposes a new blockchain-based crime investigation method that uses physical memory data analysis to track the behavior of anonymous network users. The proposed method minimizes infringement of basic rights by only collecting physical memory data from the device of the suspected user and storing the tracking information on a blockchain, which is tamper-proof and transparent. The paper evaluates the effectiveness of the proposed method using a simulation environment and finds that it can track the behavior of dark website users with a residual rate of 77.2%.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.247-253
• /
• 2008

Web 2.0 and Semantic Web technology will be merged to be a next generation Web that leads presentation-oriented Web to data-centric Web. In the next generation Web. semantic processing. Web Platform, and data fusion are most important technology factors. Resolving the Link Rot is the one of the essential technologies to enable these features. The Link Rot causes not only simple annoyances to users but also more serious problems including data integrity. loss of knowledge. breach of service. and so forth. We have suggested a new XRI-based persistent Web link architecture to cure the Link Rot that has been considered as a deep-seated Problem of the Web. The Proposed architecture is based on the XRI suggested by OASIS and it is designed to support a persistent link by using URL rewriting. Since the architecture is designed as a server-side technology, it is superior to existing research especially in Interoperability. Transparency and Adoptability. In addition to this, the architecture provides a metadata identification to be used fer context-aware link resolution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.320-330
• /
• 2020

Fire is difficult to achieve good performance in image detection using deep learning because of its high irregularity. In particular, there is little data on fire detection in underground utility facilities, which have poor light conditions and many objects similar to fire. These make fire detection challenging and cause low performance of deep learning models. Therefore, this study proposed a fire detection model using deep learning and estimated the performance of the model. The proposed model was designed using a combination of a basic convolutional neural network, Inception block of GoogleNet, and Skip connection of ResNet to optimize the deep learning model for fire detection under underground utility facilities. In addition, a training technique for the model was proposed. To examine the effectiveness of the method, the trained model was applied to fire images, which included fire and non-fire (which can be misunderstood as a fire) objects under the underground facilities or similar conditions, and results were analyzed. Metrics, such as precision and recall from deep learning models of other studies, were compared with those of the proposed model to estimate the model performance qualitatively. The results showed that the proposed model has high precision and recall for fire detection under low light intensity and both low erroneous and missing detection capabilities for things similar to fire.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.87-93
• /
• 2019

In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.