• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.363-363
• /
• 2023

Artificial Neural Networks (ANN) is a powerful tool for addressing various practical problems and it has been extensively applied in areas of water resources. In this study, Artificial Neural Networks (ANNs) were developed for flood forecasting at specific locations on the Han River. The Partial Mutual Information (PMI) technique was used to select input variables for ANNs that are neither over-specified nor under-specified while adequately describing the underlying input-output relationships. Historical observations including discharges at the Paldang Dam, flows from tributaries, water levels at the Paldang Bridge, Banpo Bridge, Hangang Bridge, and Junryu gauge station, and time derivatives of the observed water levels were considered as input candidates. Lagged variables from current time t to the previous five hours were assumed to be sufficient in this study. A three-layer neural network with one hidden layer was used and the neural network was optimized by selecting the optimal number of hidden neurons given the selected inputs. Given an ANN architecture, the weights and biases of the network were determined in the model training. The use of PMI-based input variable selection and optimized ANNs for different sites were proven to successfully predict water levels during flood periods.

• 한국항공우주학회지
• /
• 제37권4호
• /
• pp.350-358
• /
• 2009

본 논문은 재진입 비행체의 TAEM 구간 유도와 제어에 관하여 기술 하였다. TAEM 구간은 공기의 밀도와 비행체의 속도의 범위가 큰 특징을 가지고 있으며, 이들 조건하에 TAEM 구간의 유도를 위한 궤적과 비행체의 상태값을 최적화하였다. 최적화된 상태값은 7가지의 상태이며, 상태값은 Down-range, Cross-range, 비행체의 고도, 속도, 경로각, 방위각, 그리고 비행 거리이다. 최적화 연산을 수행하기 위하여 DIDO 프로그램을 사용하였다. 재진입 비행체의 제어를 위하여 인공 신경망을 이용한 되먹임 선형화 제어법을 사용하였다. 비행체의 동역학 모델은 역전파 모델을 통하여 근사화 되고, 근사화된 동역학 모델과 지연된 제어 입력, 플랜트 출력으로부터 새로운 제어 입력을 생성하게 된다. 이를 이용하여 본 논문에서는 앞서 최적화된 7가지의 상태값을 추종하는 결과를 보였다.

• 한국도로학회논문집
• /
• 제17권3호
• /
• pp.97-105
• /
• 2015

PURPOSES : The Toll Collection System (TCS) operated by the Korea Expressway Corporation provides accurate traffic counts between tollgates within the expressway network under the closed-type toll collection system. However, although origin-destination (OD) matrices for a travel demand model can be constructed using these traffic counts, these matrices cannot be directly applied because it is technically difficult to determine appropriate passenger car equivalent (PCE) values for the vehicle types used in TCS. Therefore, this study was initiated to systematically determine the appropriate PCE values of TCS vehicle types for the travel demand model. METHODS : To search for the appropriate PCE values of TCS vehicle types, a traffic demand model based on TCS-based OD matrices and the expressway network was developed. Using the traffic demand model and a genetic algorithm, the appropriate PCE values were optimized through an approach that minimizes errors between actual link counts and estimated link volumes. RESULTS : As a result of the optimization, the optimal PCE values of TCS vehicle types 1 and 5 were determined to be 1 and 3.7, respectively. Those of TCS vehicle types 2 through 4 are found in the manual for the preliminary feasibility study. CONCLUSIONS : Based on the given vehicle delay functions and network properties (i.e., speeds and capacities), the travel demand model with the optimized PCE values produced a MAPE value of 37.7%, RMSE value of 17124.14, and correlation coefficient of 0.9506. Conclusively, the optimized PCE values were revealed to produce estimates of expressway link volumes sufficiently close to actual link counts.

• 대한전자공학회논문지TC
• /
• 제42권5호
• /
• pp.29-38
• /
• 2005

본 논문은 생태계 군집 시스템을 네트워크 기술에 응용한 적응형 라우팅 알고리즘인 AntNet을 기존의 상용 네트워크 프로세서 기반에서 최적화할 수 있도록 개선된 알고리즘을 제안하는 연구이다. 현재 사용되고 있는 네트워크 프로세서는 단순한 패킷 프로세싱만을 위해 설계되어 AntNet과 같은 복잡한 연산이 필요한 적응형 라우팅 알고리즘을 구현하는데 많은 문제점을 가지고 있다. 이를 분석하고 해결하기 위해 AntNet의 강화인자를 연산하는 부분을 중심으로 적응 성능은 유지하면서도 효율적으로 연산실행시간을 줄일 수 있는 개선된 AntNet알고리즘을 제안하였다. 이를 시뮬레이션을 통해 비교분석함으로서 제안한 개선된 AntNet알고리즘의 효용성을 검증한다.

• 한국통신학회논문지
• /
• 제31권11A호
• /
• pp.1059-1067
• /
• 2006

AODV(Ad-hoc On-Demand Distance Vector) 라우팅 프로토콜은 Ad-hoc 네트워크에서 이동 노드를 사용할 수 있도록 제안된 라우팅 프로토콜이다. AODV 라우팅 프로토콜을 사용하는 Ad-hoc 네트워크에서 고속으로 이동하는 노드가 포함되어 있는 경우 항상 최적 경로를 확보할 수 없는 문제로 인하여 경로 단절과 전송 지연이 발생한다 따라서 본 논문에서는 고속으로 변화하는 네트워크의 토폴로지에서 항상 최적의 경로를 확보 할 수 있는 메커니즘을 통하여 경로의 단절과 전송 지연을 최소화할 수 있는 AODV를 기반으로 하는 라우팅 프로토콜을 제안하였으며 ns2 시뮬레이터를 이용하여 제안 프로토콜을 평가하였다. Ad-hoc 네트워크를 위한 여러 가지 기반 기술의 검증을 위하여 실제의 Ad-hoc 네트워크 테스트 베드를 구현하였다. 본 논문에서는 AODV 라우팅 프로토콜, NAT, Netfilter등의 Ad-hoc을 위한 소프트웨어 검증을 위한 많은 이벤트 메시지를 성능 저하 없이 동작시킬 수 있는 고성능의 임베디드 시스템을 설계 개발하였다. 개발된 하드웨어를 이용한 Ad-hoc 네트워크 테스트 베드에서 AODV 라우팅 프로토콜의 정상 동작과 기존 인터넷 망과의 연동을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.903-907
• /
• 2004

This paper introduces LnCP(Living Network Control Protocol)-based home network system and proposes high level message which is utilized between LnCP Home network Server and User Control Point. LnCP is very optimized protocol for digital home appliances. Then proposed system and implementation of these ideas are presented.

• 한국자동차공학회논문집
• /
• 제10권2호
• /
• pp.132-140
• /
• 2002

A momentum backpropagation neural network is prepared to carry out real-time dynamics simulations of a passenger car. A full-car model of fifteen degrees of freedom was constructed for vehicle dynamics analysis. Human body dynamics analysis was performed for a male driver(50 percentile Korean adult) restrained by a three point seatbelt system. The trained data using the neural network were obtained using a dynamic solver, ADAMS . The neural network were formed based on the dynamics of the simulator. The optimized hidden layer was obtained by selecting the optimal number of hidden layers. The driving scenario including bump passing and lane changing has been used for the estimation of the proposed neural network. A comparison between the trained data and neural network outputs is found to be satisfactory to show the applicability of the suggested approach.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권1호
• /
• pp.62-65
• /
• 2015

Wireless Sensor Network consists of several sensor nodes, these nodes loss some of their energy after the process of communication. So an energy efficient approach is required to improve the life of the network. In case of broadcast network, LEACH protocol uses an aggregative approach by creating cluster of nodes. Now the major concern is to built such clusters over WSN in an optimized way. This work presents the improvement over LEACH protocol. Hence we have different work environments where the network is having different capacities. The proposed work shows how the life time of the network will improve when the number of nodes varies within the network.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.72-75
• /
• 2004

In this paper, the task assignment strategy considering communication delay and the priority of distributed tasks is proposed for the real-time network system in order to maximize the utilization of the system. For the task assignment strategy, the relationship among priority of tasks in network nodes, the calculation time of each task, and the end-to-end response time including the network delay is formulated firstly. Then, the task assignment strategy using the genetic algorithm is proposed to optimize the utilization of the system considering the LCM(Least Common Multiple) period. The effectiveness of proposed strategy is proven by the simulation for estimating the performance such as the utilization and the response time of the system in case of changing the number of tasks and the number of network nodes.

• 한국생산제조학회지
• /
• 제8권5호
• /
• pp.70-75
• /
• 1999

Adaptive control in the robotic GMA(Gas Metal Arc) welding is employed to monitor the information about weld characteristics and process paramters as well as modification of those parameters to hold weld quality within the acceptable limits. Typical characteristics are the bead geometry composition micrrostructure appearance and process parameters which govern the quality of the final weld. The main objectives of this paper are to realize the mapping characteristicso f penetration through the learning. After learning the neural network can predict the pene-traition desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) were chosen from an error analysis. partial-penetration single-pass bead-on-plate welds were fabricated in 12mm mild steel plates in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the penetration with reasonable accuracy and gurarantee the uniform weld quality.