• 전자공학회논문지S
• /
• 제34S권11호
• /
• pp.148-155
• /
• 1997

Ths signal processing technqiue of FET type electrolyte sensors using the back propagation neural network was studied to reduce the interference effects of the different electrolytes. The FET-type electrolyte sensors, pH-ISFET, K-ISFET, and Ca-ISFET, were prepared to measure the pH, K, and Ca electrolytes. Neural network consisted of three layers was learned with 8 patterns and 9 patterns. The sensor output obtained with arbitrary concentrations was processed by the learned neural network. The errors obtained from calibration curve for pH, K, and Ca were .+-.0.039 pH, .+-.2.508 mmol/l, and .+-.1.807 mmol/l, respectively, without considering the interference effects. The errors of the network output for pH, K, and Ca were reduced to .+-.0.005 pH, .+-.0.436 mmol/l, and .+-.0.381 mmol/l in case of 9 patterns, respectively. the signal processing using the neural network can reduce the errors ofthe electrolyte sensor outputs caused by the interference effect, thereby providing effectiveness in the improvement of the sensor selectivity.

• 융합신호처리학회논문지
• /
• 제2권1호
• /
• pp.88-94
• /
• 2001

In the position control system, the output of a controller is generally used as the input of a plant but the undesired noise is included in the output of a controller. Therefore, there is a need to use a precompensator for rejecting the undesired noise. In this paper, the expanded PID controller with a precompensator is constructed. The precompensator and PID controller are designed by a neural network with two-hidden layer and these coefficients are changed automatically to be a desired response of system when the response characteristic is changed under a condition.

• Structural Monitoring and Maintenance
• /
• 제5권4호
• /
• pp.507-519
• /
• 2018

In this paper, damage assessment in wind-turbine towers using vibration-based artificial neural networks (ANNs) is numerically investigated. At first, a vibration-based ANNs algorithm is designed for damage detection in a wind turbine tower. The ANNs architecture consists of an input, an output, and hidden layers. Modal parameters of the wind turbine tower such as mode shapes and frequencies are utilized as the input and the output layer composes of element stiffness indices. Next, the finite element model of a real wind-turbine tower is established as the test structure. The natural frequencies and mode shapes of the test structure are computed under various damage cases of single and multiple damages to generate training patterns. Finally, the ANNs are trained using the generated training patterns and employed to detect damaged elements and severities in the test structure.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권3호
• /
• pp.143-148
• /
• 2022

In this paper, we employ deep neural network (DNN) to discern Android user interaction data distribution from artificial data distribution. We utilize real Android user interaction trace dataset collected from [1] to evaluate our DNN design. In particular, we use sequential model with 4 dense hidden layers and 1 dense output layer in TensorFlow and Keras. We also deploy sigmoid activation function for a dense output layer with 1 neuron and ReLU activation function for each dense hidden layer with 32 neurons. Our evaluation shows that our DNN design fulfills high test accuracy of at least 0.9955 and low test loss of at most 0.0116 in all cases of artificial data distributions.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2006년도 6th International Meeting on Information Display
• /
• pp.966-969
• /
• 2006

An optical model based on the optical thin-film theory is derived to calculate the output radiance of small molecules organic light-emitting diodes (OLEDs). We have designed the high efficiency OLEDs using the reflectance phase control of dielectric layers. It is found that OLED with a single $TiO_2$ dielectric layer is a good candidate to enhance the outcoupling efficiency and increase the color purity.

• 대한전자공학회논문지
• /
• 제27권8호
• /
• pp.1239-1249
• /
• 1990

In this paper, using the neural network design techniques, an adaptive Mahalanobis distance classifier(AMDC) is designed. This classifier has three layers: input layer, internal layer and output layer. The connection from input layer to internal layer is fully connected, and that from internal to output layer has partial connection that might be thought as an Oring. If two ormore clusters of patterns of one class are laid apart in the feature space, the network adaptively generate the internal nodes, whhch are corresponding to the subclusters of that class. The number of the output nodes in just same as the number of the classes to classify, on the other hand, the number of the internal nodes is defined by the number of the subclusters, and can be optimized by itself. Using the method of making the subclasses, the different patterns that are of the same class can easily be distinguished from other classes. If additional training is needed after the completion of the traning, the AMDC does not have to repeat the trainging that has already done. To test the performance of the AMDC, the experiments of classifying 500 Hangeuls were done. In experiment, 20 print font sets of Hangeul characters(10,000 cahracters) were used for training, and with 3 sets(1,500 characters), the AMDC was tested for various initial variance \ulcornerand threshold \ulcorner and compared with other statistical or neural classifiers.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.

• 전기전자학회논문지
• /
• 제25권1호
• /
• pp.133-138
• /
• 2021

본 논문에서는 높은 출력 전력을 확보함과 동시에 효율을 개선시킬 수 있는 전력 증폭기 구조를 제안하였다. 전력 소모를 최소화하기 위하여 구동 증폭단은 공통-소스 구조를 적용하였으며, 높은 출력 전력 확보를 위하여 전력 증폭단은 스택 구조를 적용하였다. 제안하는 구조의 검증을 위하여 아홉 개의 금속층을 제공하는 65-nm RFCMOS 공정을 이용하여 Ku 대역 전력 증폭기를 설계하였다. 동작 주파수 14 GHz에서 16 GHz 일 때, P1dB, power-added efficiency 및 전력 이득은 각각 20 dBm 이상, 23 dB 이상 및 25% 이상으로 확인 되었다.

• 한국전자통신학회논문지
• /
• 제17권3호
• /
• pp.473-482
• /
• 2022

코로나 시대에서 감염의 위험을 줄이기 위하여 반드시 마스크를 착용하여야 하며, 건축 공사장과 같은 위험한 작업 환경에서 일하는 직원의 안전을 위하여 헬맷을 쓰는 것은 필수불가결하다. 본 논문에서는 헬멧과 마스크의 착용 여부를 분류하는 효과적인 딥러닝 모델 HelmetMask-Net를 제안한다. HelmetMask-Net은 CNN 기반으로 설계되며, 전처리, 컨벌류션 계층, 맥스풀링 계층과 4 가지 출력이 있는 완전결합 계층으로 구성되며, 헬멧, 마스크, 헬멧과 마스크, 헬멧과 마스크을 착용하지 않은 4 가지 경우를 구분한다. 정확도, 최적화, 초월 변수의 수를 고려한 실험으로 2 컨볼루션 계층과 AdaGrad 최적화를 가진 구조가 선정되었다. 모의 실험 결과 99%의 정확도를 보여 주었고, 기존의 모델에 비하여 성능이 우수함을 확인하였다. 제안된 분류기는 코비드 19 시대에 직원의 안전을 향상시킬 수 있을 것이다.