• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1076-1084
• /
• 2019

In this paper, we introduced a system that extracts metadata by recognizing characters and objects in media using deep learning technology. In the field of broadcasting, multimedia contents such as video, audio, image, and text have been converted to digital contents for a long time, but the unconverted resources still remain vast. Building media archives requires a lot of manual work, which is time consuming and costly. Therefore, by implementing a deep learning-based metadata generation system, it is possible to save time and cost in constructing media archives. The whole system consists of four elements: training data generation module, object recognition module, character recognition module, and API server. The deep learning network module and the face recognition module are implemented to recognize characters and objects from the media and describe them as metadata. The training data generation module was designed separately to facilitate the construction of data for training neural network, and the functions of face recognition and object recognition were configured as an API server. We trained the two neural-networks using 1500 persons and 80 kinds of object data and confirmed that the accuracy is 98% in the character test data and 42% in the object data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.1-9
• /
• 2016

Railroad bridges account for 25% of the entire high-speed rail network. Railway bridges are subject to gradual structural degradation or fatigue accumulation due to consistent and repeating excitation by fast moving trains. Wireless sensing technology has opened up a new avenue for bridge health monitoring owing to its low-cost, high fidelity, and multiple sensing capability. On the other hand, measuring the transient response during train passage is quite challenging that the current wireless sensor system cannot be applied due to the intrinsic time delay of the sensor network. Therefore, this paper presents a framework for monitoring such transient responses with wireless sensing systems using 1) real-time excessive vibration monitoring through ultra-low-power MEMS accelerometers, and 2) post-event time synchronization scheme. The ultra-low power accelerometer continuously monitors the vibration and trigger network when excessive vibrations are detected. The entire network of wireless smart sensors starts sensing through triggering and the post-event time synchronization is conducted to compensate for the time error on the measured responses. The results of this study highlight the potential of detecting the impact load and triggering the entire network, as well as the effectiveness of the post-event time synchronized scheme for compensating for the time error. A numerical and experimental study was carried out to validate the proposed sensing hardware and time synchronization method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.942-945
• /
• 2010

The development of decentralized power has appeared as part of an effort to decrease the energy loss and the cost for electric power facilities through installing small renewable energy generation systems including solar and wind power generation. Recently a new era for decentralized power environment in building is coming in order to handle the climatic and environmental change occurred all over the world. Especially solar and wind power generation systems can be easily set up and are also economically feasible, and thus many industrial companies enter into this business. This paper suggests the overall architecture for the decentralized renewable power system and the prediction method of power on climatic change. The ultimate goal is to help manage the overall power efficiently and thus provide the technological basis for achieving zero-energy house.

• Journal of KIISE:Databases
• /
• v.33 no.2
• /
• pp.201-213
• /
• 2006

A time-series database is a set of time-series data sequences, each of which is a list of changing values of the object in a given period of time. Subsequence matching is an operation that searches for such data subsequences whose changing patterns are similar to a query sequence from a time-series database. This paper addresses a performance issue of time-series subsequence matching. First, we quantitatively examine the performance degradation caused by the window size effect, and then show that the performance of subsequence matching with a single index is not satisfactory in real applications. We argue that index interpolation is fairly useful to resolve this problem. The index interpolation performs subsequence matching by selecting the most appropriate one from multiple indexes built on windows of their inherent sizes. For index interpolation, we first decide the sites of windows for multiple indexes to be built. In this paper, we solve the problem of selecting optimal window sizes in the perspective of physical database design. For this, given a set of query sequences to be peformed in a target time-series database and a set of window sizes for building multiple indexes, we devise a formula that estimates the cost of all the subsequence matchings. Based on this formula, we propose an algorithm that determines the optimal window sizes for maximizing the performance of entire subsequence matchings. We formally Prove the optimality as well as the effectiveness of the algorithm. Finally, we perform a series of extensive experiments with a real-life stock data set and a large volume of a synthetic data set. The results reveal that the proposed approach improves the previous one by 1.5 to 7.8 times.

• Land and Housing Review
• /
• v.4 no.3
• /
• pp.279-286
• /
• 2013

Driving a prefabricated pile is the efficient construction method with low cost and excellent bearing capacity charateristics. But pile drinving method has often been changed to bored pile method with mechanical boring due to the unexpected problems occurred in the various domestic ground condition with landfill. So, pile driving method has more uncertainty than the Bored Pile method. This paper proposed LRFD design value which is one of limit states design method for the PHC driven pile used as building foundation to guarantee the reliable design with reduced uncertainty. This paper analysed 221 dynamic load test results(E.O.I.D : 93, Resrike : 128) and the different methods of estimating bearing design(Meyerhof method & SPT-CPT conversion method), and proposed LRFD value for each design reliability Index 2.33 and 3.0 for PHC driven pile. LRFD value of PHC driven pile represents 0.43~0.55 for Meyerhof method and 0.40~0.49 for SPT-CPT conversion method according to the deign reliability index.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.3
• /
• pp.55-65
• /
• 2008

For obtaining telematics traffic information(travel time or speed in an individual link), there are many kinds of devices to collect traffic data. Since the GPS satellite signals have been released to civil society, thank to the development of GPS technology, the GPS has become a very useful instrument for collecting traffic data. GPS can reduce the cost of installation and maintenance in contrast with existing traffic detectors which must be stationed on the ground. But. there are Problems when GPS data is applied to the existing filtering techniques used for analyzing the data collected by other detectors. This paper proposes a method to provide users with correct traffic information through filtering abnormal data caused by the unusual driving in collected data based on GPS. We have developed an algorithm that can be applied to real-time GPS data and create more reliable traffic information, by building patterns of past data and filtering abnormal data through selection of filtering areas using Quartile values. in order to verify the proposed algorithm, we experimented with actual traffic data that include probe cars equipped with a built-in GPS receiver which ran through Gangnam Street in Seoul. As a result of these experiments, it is shown that link travel speed data obtained from this algorithm is more accurate than those obtained by existing systems.

• Journal of KIISE:Databases
• /
• v.28 no.4
• /
• pp.732-741
• /
• 2001

In the relational database systems the join operation is one of the most time-consuming query operations. Many parallel join algorithms have been developed 개 reduce the execution time Multiple hash join algorithm using allocation tree is one of the most efficient ones. However, it may have some delay on the processing each node of allocation tree, which is occurred in tuple-probing phase by the difference between one page reading time of outer relation and the processing time of already read one. This delay problem was solved by using the concept of synchronization of page execution time with we had proposed In this paper the effects of the performance improvements in each node of the allocation tree are extended to the whole allocation tree and the performance evaluation about that is processed. In addition we propose an efficient algorithm for multiple hash joins in limited number of processor environments according to the relationship between the number of input relations in the allocation tree and the number of processors allocated to the tree. Finally. we analyze the performance by building the analytical cost model and verify the validity of it by various performance comparison with previous method.

• Korean Journal of Construction Engineering and Management
• /
• v.9 no.3
• /
• pp.206-213
• /
• 2008

Due to the following reasons, the management of curtain wall parts and material is very Important. Firstly, curtain wall work is one of the main works in High-rise building construction for it takes about $10{\sim}15%$ of the total construction cost. Secondly, the whole process of curtain wall work including manu acture, delivery, storage, installation and maintenance is very complicated and sometimes more than 30 companies involve in the process. Thus there are many control points for curtain wall units. Thirdly, there are not enough space on site for material storage and this situation is more serious for sites in urban area. The purpose of this research is to validate an information systems using RFID technology that is developed to manage the curtain wall units following the process of curtain wall work. For the validation, the cycle times of curtain wall work before and a ter the system was used. The results show that using the systems shorten the cycle time of the curtain wall work. Thus it is concluded that the system can increase the efficiency of managing curtain wall work.

• Journal of Science and Technology Studies
• /
• v.3 no.2 s.6
• /
• pp.29-60
• /
• 2003

Inter-Korean Cooperation in Science and Technology will contribute to building the trust between S.K and N.K as a leading factor and cut down the cost of unification by diminishing the technology lag and the gap of economic level. This study has shown that we can increase the productivity of unified Korea Innovation system if we systematically analyse the present condition of the Inter-Korean Cooperation and promote Inter-Korean Cooperation. In this study, the author analyses the present condition of the Inter-Korean Cooperation with integrated framework of three aspects to clear up the policy of Inter-Korean Cooperation. First, in the national aspect, we make use of the notion of international cooperation and multilateral mechanism of an international organization. Thereafter, we make out the alternatives in the aspects of international relationship and legal and institutional view Second, in the unification aspect, we consider the Inter-Korean Cooperation by the notion of national innovation system. Thereafter, we make out the alternative in the aspect of a phase-dependent approach. Finally, in technology aspect, we consider the Inter-Korean Cooperation by the notion of technology gap, the framework of technology transfer, and technology dependency theory. As a conclusion, through this study, the author have tried to integrate the various theoretical backgrounds. As a result, the author could analyse the present condition of ter-Korean Cooperation in Science and Technology and team a good lesson from it; Therefore, we can use it as a means of evaluation on a cooperation program and prediction for the future status of cooperation.

• Journal of Korea Water Resources Association
• /
• v.52 no.10
• /
• pp.729-742
• /
• 2019

Natural disasters such as floods has been increased in many parts of the world, also Korea is no exception. The biggest part of natural damage in South Korea was caused by the flooding during the rainy season in every summer. The existing flood vulnerability analysis cannot explain the reality because of the repeated changes in topography. Therefore, it is necessary to calculate a new flood vulnerability index in accordance with the changed terrain and socio-economic environment. The priority of the investment for the flood prevention and mitigation has to be determined using the new flood vulnerability index. Total 25 urban districts in Seoul were selected as the study area. Flood vulnerability factors were developed using Pressure-State-Response (PSR) structures. The Pressure Index (PI) includes nine factors such as population density and number of vehicles, and so on. Four factors such as damage of public facilities, etc. for the Status Index (SI) were selected. Finally, seven factors for Response Index (RI) were selected such as the number of evacuation facilities and financial independence, etc. The weights of factors were calculated using AHP method and Fuzzy AHP to implement the uncertainties in the decision making process. As a result, PI and RI were changed, but the ranks in PI and RI were not be changed significantly. However, SI were changed significanlty in terms of the weight method. Flood vulnerability index using Fuzzy AHP shows less vulnerability index in Southern part of Han river. This would be the reason that cost of flood mitigation, number of government workers and Financial self-reliance are high.