• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1624-1627
• /
• 2005

We proposed a design technique for auto-landing guidance and control system. This technique utilizes linear controller and neural network. Main features of this technique is to use conventional linear controller and compensate for the error coming from the model uncertainties and/or reference model mismatch. In this study, the multi-perceptron neural network with single hidden layer is adopted to compensate for the errors. Glide-slope capture logic for auto-landing guidance and control system is designed in this technique. From the simulation results, it is observed that the responses of velocity and pitch angle to commands are fairly good, which are directly related to control inputs of throttle and elevator, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.1
• /
• pp.13-22
• /
• 1991

In this paper we designed 2 bit ECC(Error Checking and Correction) circuit using Single Layer Perceptron type neural networks. We used (11, 6) block codes having 6 data bits and 8 check bits with appling cyclic hamming codes. All of the circuits are layouted by CMOs 2um double metal design rules. In the result of circuit simulation, 2 bit ECC circuit operates at 67MHz of input frequency.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.3
• /
• pp.137-144
• /
• 1990

We describe how single layer perceptrons and new nonsymmetry feedback type neural networks can be implemented by VLSI CMOS technology. The network described provides a flexible tool for evaluation of boolean expressions and arithmetic equations. About 50 CMOS VLSI chips with an architecture based on two neural networks have been designed and me being fabricated by 2-micrometer double metal design rules. These chips have been developed to study the potential of neural network models for the use in character recognition and for a neural compute.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.377-380
• /
• 2002

신경회로망은 문자인식, 자동제어 등의 여러 분야에 널리 쓰이는 방식이다. 그러나 신경회로망을 구현하는데는 연산량이 많아서 실시간으로 구현하기에 어려움이 많이 따른다. 본 논문은 신경회로망을 구현하는데 필요한 연산을 살펴보고 그 연산을 구현하는 방법을 비교 분석하였다. 신경회로망을 구현하기 위해 DSP(Digital Signal Processor), PC의 FPU(Floating Point Unit), Intel사의 Pentium 계열 프로세서에서 지원하는 SIMD(Single Instruction Multiple Data) 기술을 사용하여 결과를 비교 분석 하였다. 신경회로망의 핵심인 MLP(Multi Layer Perceptron) 연산에 대해 실험한 결과 SIMD 기술을 이용하는 방법이 다른 방법에 비해 2배이상 좋은 결과를 나타내었다.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.619-625
• /
• 1995

This paper constructs a feed-forward learning complex algorithm which replaced by the backpropagation learning. This algorithm first attempts to organize the pattern vectors into clusters by Generalized Learning Vector Quantization(GLVQ) clustering algorithm(Nikhil R. Pal et al, 1993), second, regroup the pattern vectors belonging to different clusters, and the last, recognize into regrouping pattern vectors by single layer perceptron. Because this algorithm is feed-forward learning algorithm, time is less than backpropagation algorithm and the recognition rate is increased. We use 250 ASCII code bit patterns that is normalized to 16$\times$8. As experimental results, when 250 patterns devide by 10 clusters, average iteration of each cluster is 94.7, and recognition rate is 100%.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.271-276
• /
• 2002

The test statistic in ANOVA tests has a single or doubly noncentral F distribution and the noncentral F distribution is applied to the calculation of the power functions of tests of general linear hypotheses. Although various approximations of noncentral F distribution are suggested, they are troublesome to compute. In this paper, the calculation of noncentral F distribution is applied to the neural network theory, to solve the computation problem. The neural network consists of the multi-layer perceptron structure and learning process has the algorithm of the backpropagation. Using fables and figs, comparisons are made between the results obtained by neural network theory and the Patnaik's values. Regarding of accuracy and calculation, the results by neural network are efficient than the Patnaik's values.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.818-823
• /
• 2008

In this paper, we propose a feature extraction method which extracts directional features of handwritten numerals by using the projection runlength. Our directional featrures are obtained from four directional images, each of which contains horizontal, vertical, right-diagonal and left-diagonal lines in entire numeral shape respectively. A conventional method which extracts directional features by using Kirsch masks generates edge-shaped double line directional images for four directions, whereas our method uses the projections and their runlengths for four directions to produces single line directional images for four directions. To obtain the directional projections for four directions from a numeral image, some preprocessing steps such as thinning and dilation are required, but the shapes of resultant directional lines are more similar to the numeral lines of input numerals. Four [$4{\times}4$] directional features of a numeral are obtained from four directional line images through a zoning method. By using a hybrid feature which is made by combining our feature with the conventional features of a mesh features, a kirsch directional feature and a concavity feature, higher recognition rates of the handwrittern numerals can be obtained. For recognition test with given features, we use a multi-layer perceptron neural network classifier which is trained with the back propagation algorithm. Through the experiments with the handwritten numeral database of Concordia University, we have achieved a recognition rate of 97.85%.

• Smart Structures and Systems
• /
• v.26 no.3
• /
• pp.263-275
• /
• 2020

This research is dedicated to slope stability analysis using novel intelligent models. By coupling a neural network with spotted hyena optimizer (SHO), salp swarm algorithm (SSA), shuffled frog leaping algorithm (SFLA), and league champion optimization algorithm (LCA) metaheuristic algorithms, four predictive ensembles are built for predicting the factor of safety (FOS) of a single-layer cohesive soil slope. The data used to develop the ensembles are provided from a vast finite element analysis. After creating the proposed models, it was observed that the best population size for the SHO, SSA, SFLA, and LCA is 300, 400, 400, and 200, respectively. Evaluation of the results showed that the combination of metaheuristic and neural approaches offers capable tools for estimating the FOS. However, the SSA (error = 0.3532 and correlation = 0.9937), emerged as the most reliable optimizer, followed by LCA (error = 0.5430 and correlation = 0.9843), SFLA (error = 0.8176 and correlation = 0.9645), and SHO (error = 2.0887 and correlation = 0.8614). Due to the high accuracy of the SSA in properly adjusting the computational parameters of the neural network, the corresponding FOS predictive formula is presented to be used as a fast yet accurate substitution for traditional methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.447-452
• /
• 2005

기존의 단층 퍼셉트론은 출력 노드가 선형 분리 가능한 패턴들만을 분류할 수 있고 Exclusive OR와 같은 비선형 문제에 대해서는 분류할 수 없는 단점이 있다. 그러나 퍼지 단층 퍼셉트론은 퍼지소속 함수(fuzzy membership function)를 적용하여 단층 구조로 Exclusive OR 문제와 같은 고전적인 문제를 개선하였다. 그러나 퍼지 단층 퍼셉트론은 기존의 단층 퍼셉트론과 마찬가지로 결정 경계선이 진동하는 경우가 생기며 초기 가중치의 범위와 학습률에 따라 수렴성이 매우 낮아지는 단점이 있다. 따라서 본 논문에서는 바이어스항을 도입하여 결정 경계선이 진동하는 것을 방지하여 수렴성을 개선시키고 선형 활성화 함수를 제안하고 학습률과 모멘텀 개념을 도입하여 학습 시간을 단축시키는 개선된 퍼지 단층 퍼셉트론 알고리즘을 제안한다. 제안된 방법과 퍼지 단층 퍼셉트론간의 학습 성능을 분석하기 위하여 인공 신경망에서 벤치마크로 사용되는 exclusive OR 문제와 문자 패턴 분류에 적용하여 epoch 수와 수렴성을 비교한 결과, 제안된 방법이 기존의 퍼지 단층 퍼셉트론보다 학습 시간이 적게 소요되고 수렴성이 개선된 것을 확인하였다.