• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.827-833
• /
• 2022

This study aims to prevent secondary traffic accidents with high severity by overcoming the limitations of existing traffic information collection systems through analysis of traffic information collection detectors and various algorithms used to detect unexpected situations. In other words, this study is meaningful present that analyzing the 'unexpected situation that causes secondary traffic accidents' and 'Existing traffic information collection system' accordingly presenting a solution that can preemptively prevent secondary traffic accidents, intelligent traffic information collection system that enables accurate information collection on all sections of the road. As a result of the experiment, the reliability of data transmission reached 97% based on 95%, the data transmission speed averaged 209ms based on 1000ms, and the network failover time achieved targets of 50sec based on 120sec.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.29-43
• /
• 2023

It is necessary to grasp the characteristics of traffic flow passing through a specific road section and the topological structure of the road in advance in order to quickly prepare a movement management strategy in the event of a disaster or disaster. It is because it can be an essential basis for road managers to assess vulnerabilities by microscopic road units and then establish appropriate monitoring and management measures for disasters or disaster situations. Therefore, this study presented spatial density, time occupancy, and betweenness centrality index to evaluate vulnerabilities by road link in the city department and defined spatial-temporal and topological vulnerabilities by clustering analysis based on distance and density. From the results of this study, road administrators can manage vulnerabilities by characterizing each road link group. It is expected to be used as primary data for selecting priority control points and presenting optimal routes in the event of a disaster or disaster.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.395-401
• /
• 2023

Sound Event Detection (SED) aims to identify not only sound category but also time interval for target sounds in an audio waveform. It is a critical technique in field of acoustic surveillance system and monitoring system. Recently, various models have introduced through Detection and Classification of Acoustic Scenes and Events (DCASE) Task 4. This paper explored how to design optimal parameters of DenseNet based model, which has led to outstanding performance in other recognition system. In experiment, DenseRNN as an SED model consists of DensNet-BC and bi-directional Gated Recurrent Units (GRU). This model is trained with Mean teacher model. With an event-based f-score, evaluation is performed depending on parameters, related to model architecture as well as model training, under the assessment protocol of DCASE task4. Experimental result shows that the performance goes up and has been saturated to near the best. Also, DenseRNN would be trained more effectively without dropout technique.

• Journal of the Korea Society for Simulation
• /
• v.18 no.1
• /
• pp.41-51
• /
• 2009

A discrete event simulation model is developed to evaluate the performances of three different revenue management methods for an air cargo network from Northeast China to North America and Europe. In the first method, a bid price model is applied only to the routes that pass through Incheon. In the second method, the bid price model is applied to all the routes. In third method, bid price and virtual nesting models are applied to the routes that pass through Incheon. The results show that the total revenue significantly increases with the employment of pricing and capacity control. The developed simulation model is a useful research tool to study marketing strategies for air cargo operations.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.49-56
• /
• 2023

With the development of technology worldwide, bridges are becoming larger, and the number of old bridges is also rapidly increasing. Monitoring the structural health of large, aging bridges is essential to preventing large-scale accidents. In this study, the application of a LoRa low-power wide-area network (LPWAN)-based wireless measurement system was investigated, and a LoRa wireless measurement system was established in the cable-stayed bridge section of Cheonsa Bridge, located in Shinan-gun, Jeollanam-do, Korea. The applicability of the LoRa LPWAN-based wireless monitoring system to large marine bridges was reviewed by comparing the performance and economic feasibility with wire-based monitoring systems that were built and operated by establishing a measurement system for the pylons, cables, and reinforcing girders of the bridge.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.394-394
• /
• 2020

최근 빈번히 발생하고 있는 슈퍼 태풍과 집중호우로 인해 크고 작은 침수피해가 발생하고 있다. 우리나라는 4대강 사업을 통해 주요 국가하천에 대한 정비를 마친 바 있으나 이후 지속적으로 변화하는 하천 환경에 대한 홍수예측 모형의 반영은 미비한 실정이었다. 따라서 본 연구에서는 낙동강 본류 및 지류의 최신 단면자료를 수집하여 수리학적 홍수예측모형에 반영하고자 하였다. 또한, 기존의 모형에 비해 정확도를 개선할 수 있는 방안을 모색하여 적용성을 검증하고 이를 반영한 수리학적 홍수예측 모형을 제시하고자 한다. 본 연구에서는 낙동강 본류 및 주요 지류에 대한 최신 횡단면 측량자료를 활용하여 1차원 수리학적 홍수예측 모형을 구축하고 2012년 태풍 산바 사상에 대한 검보정을 실시하였다. 대상구간은 안동조정지댐으로부터 낙동강 하구둑 하류 8km지점이며, 상류단 경계조건은 안동조정지댐 방류량을 입력하고 하류단 경계조건은 가덕도 조위관측소의 조위를 활용하였다. 또한, 반변천, 내성천, 위천, 감천, 금호강, 황강, 남강 등 7개 지류에 대한 하도를 하도추적이 가능한 네트워크 모형으로 구축함으로써 지류에 대한 홍수예보에 활용할 수 있도록 하였다. 낙동강 본류의 하도 길이는 340km, 824개의 단면으로 구성하였으며, 지류를 포함한 전체 하도 길이는 572km, 1,570개의 단면으로 구성하였다. 또한, 낙동강 본류에 위치한 8개의 다기능보와 지류에 위치한 횡단구조물의 반영을 위해 다기능보의 제원 및 하천기본계획을 참고하여 내부경계조건으로 활용하였다. 본 연구에서 구축된 낙동강 본류 및 지류의 수리학적 홍수예측 모형을 낙동강 유역에 대한 홍수주의보 및 홍수경보 등 홍수특보 발령 업무에 활용함으로써 정확한 홍수예보가 가능하도록 하였다.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.103-112
• /
• 2023

Recently, the need to prevent battery fires and accidents has emerged, as the use of lithium-ion batteries has increased. In order to prevent accidents, it is necessary to predict the state of health (SOH) and check the replacement timing of the battery with a lot of degradation. This paper proposes a model for predicting the degradation state of a battery by using four battery degradation indicators: maximum voltage arrival time, current change time, maximum temperature arrival time, and incremental capacity (IC) that can be obtained in the battery charging process, and LSTM using an attention mechanism. The performance of the proposed model was measured using the NASA battery data set, and the predictive performance was improved compared to that of the general LSTM model, especially in the SOH 90-70% section, which is close to the battery replacement cycle.

• Journal of Korean Society of Transportation
• /
• v.20 no.5
• /
• pp.113-130
• /
• 2002

In this paper, we developed DNL(Dynamic Network Loading) model based on Moving cell theory to analyze the dynamic characteristics of traffic flow in congested network. In this paper vehicles entered into link at same interval would construct one cell, and the cells moved according to Cell following rule. In the past researches relating to DNL model a continuous single link is separated into two sections such as running section and queuing section to describe physical queue so that various dynamic states generated in real link are only simplified by running and queuing state. However, the approach has some difficulties in simulating various dynamic flow characteristics. To overcome these problems, we present Moving cell theory which is developed by combining Car following theory and Lagrangian method mainly using for the analysis of air pollutants dispersion. In Moving cell theory platoons are represented by cells and each cell is processed by Cell following theory. This type of simulation model is firstly presented by Cremer et al(1999). However they did not develop merging and diverging model because their model was applied to basic freeway section. Moreover they set the number of vehicles which can be included in one cell in one interval so this formulation cant apply to signalized intersection in urban network. To solve these difficulties we develop new approach using Moving cell theory and simulate traffic flow dynamics continuously by movement and state transition of the cells. The developed model are played on simple network including merging and diverging section and it shows improved abilities to describe flow dynamics comparing past DNL models.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.1
• /
• pp.48-59
• /
• 2009

Next generation mobile communication system will have various access networks and provide seamless multimedia data service to mobile nodes. The WiNGS system, one of these access network, has superior RAT(Radio Access Technology) and network connectivity other than previous ones. In this paper, we propose link-layer SR-ARQ between mobile node and WAGW to solve packet re-ordering problem during handover. In the proposed scheme, we apply the adaptive timer at the SR-ARQ sender to reduce unnecessary packet retransmission during handoff and delayed NAK algorithm at the SR-ARQ receiver for delaying NAK response due to temporary out-of-sequenced frames. We evaluate the performance of the proposed scheme by implementing the new SR-ARQ protocol at the link-layer using ns-2 simulator, and show the handover performance is improved greatly by preventing unnecessary retransmission.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.23-31
• /
• 2010

The increasing demands on low-power, and low-complexity video encoder have been motivating extensive research activities on distributed video coding (DVC) in which the encoder compresses frames without utilizing inter-frame statistical correlation. In DVC encoder, contrary to the conventional video encoder, an error control code compresses the video frames by representing the frames in the form of syndrome bits. In the meantime, the DVC decoder generates side information which is modeled as a noisy version of the original video frames, and a decoder of the error-control code corrects the errors in the side information with the syndrome bits. The noisy observation, i.e., the side information can be understood as the output of a virtual channel corresponding to the orignal video frames, and the conditional probability of the virtual channel model is assumed to follow a Laplacian distribution. Thus, performance improvement of DVC systems depends on performances of the error-control code and the optimal reconstruction step in the DVC decoder. In turn, the performances of two constituent blocks are directly related to a better estimation of the parameter of the correlation channel. In this paper, we propose an algorithm to estimate the parameter of the correlation channel and also a low-complexity version of the proposed algorithm. In particular, the proposed algorithm minimizes squared-error of the Laplacian probability distribution and the empirical observations. Finally, we show that the conventional algorithm can be improved by adopting a confidential window. The proposed algorithm results in PSNR gain up to 1.8 dB and 1.1 dB on Mother and Foreman video sequences, respectively.