• Smart Structures and Systems
• /
• 제18권6호
• /
• pp.1233-1250
• /
• 2016

Cracks in plate-like structures are some of the main reasons for destruction of the entire structure. In this study, a novel two-stage methodology is proposed for damage detection of flexural plates using an optimized artificial neural network. In the first stage, location of damages in plates is investigated using curvature-moment and curvature-moment derivative concepts. After detecting the damaged areas, the equations for damage severity detection are solved via Bat Algorithm (BA). In the second stage, in order to efficiently reduce the computational cost of model updating during the optimization process of damage severity detection, multiple damage location assurance criterion index based on the frequency change vector of structures are evaluated using properly trained cascade feed-forward neural network (CFNN) as a surrogate model. In order to achieve the most generalized neural network as a surrogate model, its structure is optimized using binary version of BA. To validate this proposed solution method, two examples are presented. The results indicate that after determining the damage location based on curvature-moment derivative concept, the proposed solution method for damage severity detection leads to significant reduction of computational time compared with direct finite element method. Furthermore, integrating BA with the efficient approximation mechanism of finite element model, maintains the acceptable accuracy of damage severity detection.

• 인터넷정보학회논문지
• /
• 제20권5호
• /
• pp.95-104
• /
• 2019

사물인터넷 서비스를 위해 다양한 종류의 디바이스가 사용되고 있으며, 사물인터넷 디바이스들은 주로 비면허 대역의 주파수를 사용하는 통신기술을 활용하고 있다. 비면허 대역의 통신기술에는 몇 가지가 있지만, 현재 WiFi가 가장 대표적으로 사용된다. 사물인터넷 서비스를 위해 사용되는 디바이스는 제한된 기능을 가진 디바이스부터 스마트폰까지 컴퓨팅 리소스가 다양하고, WiFi 와 같은 무선 네트워크를 통해 서비스를 제공한다. 대부분의 사물인터넷 장치는 네트워크 제어를 위한 복잡한 연산을 할 수 없기 때문에 신호세기에 의존하여 WiFi 액세스 포인트를 선정하고 있다. 이는 사물인터넷 서비스 효율을 떨어뜨리는 원인으로 작용한다. 따라서, 본 논문에서는 액세스 포인트를 통해 사물이터넷 디바이스의 WiFi 연결을 제어할 수 있는 지능형 액세스 포인트 시스템을 구현한다. 사물인터넷 디바이스에서 측정된 네트워크 정보를 통해 액세스 포인트에서 피드 포워드 신경망 (feed forward neural network) 알고리즘을 사용하여 학습을 하고, 네트워크 연결 상태를 예측하여 디바이스의 WiFi연결을 제어한다. 이렇게 함으로써 사물인터넷 디바이스의 서비스 효율을 높일 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.46-63
• /
• 2024

One of the biggest dangers in the globe is water contamination. Water is a necessity for human survival. In most cities, the digging of borewells is restricted. In some cities, the borewell is allowed for only drinking water. Hence, the scarcity of drinking water is a vital issue for industries and villas. Most of the water sources in and around the cities are also polluted, and it will cause significant health issues. Real-time quality observation is necessary to guarantee a secure supply of drinking water. We offer a model of a low-cost system of monitoring real-time water quality using IoT to address this issue. The potential for supporting the real world has expanded with the introduction of IoT and other sensors. Multiple sensors make up the suggested system, which is utilized to identify the physical and chemical features of the water. Various sensors can measure the parameters such as temperature, pH, and turbidity. The core controller can process the values measured by sensors. An Arduino model is implemented in the core controller. The sensor data is forwarded to the cloud database using a WI-FI setup. The observed data will be transferred and stored in a cloud-based database for further processing. It wasn't easy to analyze the water quality every time. Hence, an Optimized Neural Network-based automation system identifies water quality from remote locations. The performance of the feed-forward neural network classifier is further enhanced with a hybrid GA- PSO algorithm. The optimized neural network outperforms water quality prediction applications and yields 91% accuracy. The accuracy of the developed model is increased by 20% because of optimizing network parameters compared to the traditional feed-forward neural network. Significant improvement in precision and recall is also evidenced in the proposed work.

• 한국환경과학회지
• /
• 제15권2호
• /
• pp.141-155
• /
• 2006

This study is aimed at the development of a runoff forecasting model to solve the uncertainties occurring in the process of rainfall-runoff modeling and improve the modeling accuracy of the stream runoff forecasting, The study area is the downstream of Naeseung-chun. Therefore, time-dependent data was obtained from the Wolpo water level gauging station. 11 and 2 out of total 13 flood events were selected for the training and testing set of model. The model performance was improved as the measuring time interval$(T_m)$ was smaller than the sampling time interval$(T_s)$. The Neuro-Fuzzy(NF) and TANK models can give more accurate runoff forecasts up to 4 hours ahead than the Feed Forward Multilayer Neural Network(FFNN) model in standard above the Determination coefficient$(R^2)$ 0.7.

• 한국통신학회논문지
• /
• 제26권11C호
• /
• pp.75-84
• /
• 2001

본 논문에서는 신경망을 이용한 실시간 고장 검출 및 진단(FDD : Fault Detection and Diagnosis) 시스템을 제안한다. 제안된 시스템은 공조 시스템(FDD : Air Handling Unit)에서 발생 가능한 여러 고장들을 검출하고 진단할 수 있다. 고장 검출 및 진단 기법으로 3층 구조의 전방향(feed-forward) 신경망을 사용하였고, 여기에 사용된 학습 방법은 역전파(back-propagation) 학습 알고리즘이다. 공조 시스템에 적용된 실시간 고장 검출 및 진단 시스템은 비주얼 C++와 비주얼 베이직을 사용하여 구현하였다. 제안된 고장 검출 및 진단 시스템을 실제 운전 중인 공조 시스템에 적용하여 실험하였고, 정확한 고장 검출 및 진단이 수행됨을 실험 결과로서 입증하였다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2015년도 제27회 한글 및 한국어 정보처리 학술대회
• /
• pp.124-128
• /
• 2015

문맥의존 철자오류는 해당 단어만 봤을 때에는 오류가 아니지만 문맥상으로는 오류인 문제를 말한다. 이러한 문제를 해결하기 위해서는 문맥정보를 보아야 하지만, 형태소 분석 단계에서는 자세한 문맥 정보를 보기 어렵다. 본 논문에서는 형태소 분석 정보만을 이용한 철자오류 수정을 위한 문맥으로 사전훈련(pre-training)된 단어 표현(Word Embedding)를 사용하고, 기존의 기계학습 알고리즘보다 좋다고 알려진 딥 러닝(Deep Learning) 기술을 적용한 시스템을 제안한다. 실험결과, 기존의 기계학습 알고리즘인 Structural SVM보다 높은 F1-measure 91.61 ~ 98.05%의 성능을 보였다.

• Advances in Computational Design
• /
• 제5권3호
• /
• pp.291-304
• /
• 2020

In this paper, we develop models to design the airfoil using Multilayer Feed-forward Artificial Neural Network (MFANN) and Support Vector Regression model (SVR). The aerodynamic coefficients corresponding to series of airfoil are stored in a database along with the airfoil coordinates. A neural network is created with aerodynamic coefficient as input to produce the airfoil coordinates as output. The performance of the models have been evaluated. The results show that the SVR model yields the lowest prediction error.

• Structural Engineering and Mechanics
• /
• 제46권5호
• /
• pp.673-693
• /
• 2013

This paper presents a systematic design and training procedure for the feed-forward back-propagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output, an optimization procedure demonstrates accurate training of the NN architecture with only current and velocity as input states. For the inverse damper model, with current as output, the absolute value of velocity and force are used as input states to avoid negative current spikes when tracking a desired damper force. The forward and inverse damper models are trained and validated experimentally, combining a limited number of harmonic displacement records, and constant and half-sinusoidal current records. In general the validation shows accurate results for both forward and inverse damper models, where the observed modeling errors for the inverse model can be related to knocking effects in the measured force due to the bearing plays between hydraulic piston and MR damper rod. Finally, the validated models are used to emulate pure viscous damping. Comparison of numerical and experimental results demonstrates good agreement in the post-yield region of the MR damper, while the main error of the inverse NN occurs in the pre-yield region where the inverse NN overestimates the current to track the desired viscous force.

• Structural Engineering and Mechanics
• /
• 제26권4호
• /
• pp.377-392
• /
• 2007

A discrete sliding mode control (SMC) method based on hybrid model of neural network and nominal model is proposed to reduce the vibration of flexible structures, which is a robust active controller developed by using a sliding manifold approach. Since the thick boundary layer will reduce the virtue of SMC, the multilayer feed-forward neural network is adopted to model the uncertainty part. The neural network is trained by Levenberg-Marquardt backpropagation. The design objective of the sliding mode surface is based on the quadratic optimal cost function. In course of running, the input signal of SMC come from the hybrid model of the nominal model and the neural network. The simulation shows that the proposed control scheme is very effective for large uncertainty systems.

• 대한전기학회논문지
• /
• 제45권2호
• /
• pp.325-328
• /
• 1996

In this paper, we proposed an estimation method of a posterior probability and PDF(Probability density function) using a feed forward neural network and code books of VQ(vector quantization). In this study, We estimates a posterior probability and probability density function, which compose a new parameter with well-known Mel cepstrum and verificate the performance for the five vowels taking from syllables by NN(neural network) and PNN(probabilistic neural network). In case of new parameter, showed the best result by probabilistic neural network and recognition rates are average 83.02%.