• 전자공학회논문지B
• /
• 제31B권5호
• /
• pp.141-148
• /
• 1994

Both the neural network classifier utilizing multi-layer perceptron and the linear tree classifier composed of hierarchically structured linear discriminating functions can form arbitrarily complex decision boundaries in the feature space and have very similar decision making processes. In this paper, a new method for automatically choosing the number of neurons in the hidden layers and for initalzing the connection weights between the layres and its supporting theory are presented by mapping the sequential structure of the linear tree classifier to the parallel structure of the neural networks having one or two hidden layers. Experimental results on the real data obtained from the military ship images show that this method is effective, and that three exists no siginificant difference in the classification acuracy of both classifiers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.109.3-109
• /
• 2002

1. Introduction 2. Vision system 3. Effect of brightness variations 4. Color classifier using multi-layer neural network 5. Experimental result of color classifier 6. Applications for robot soccer system 7. Conclusion

• 대한공간정보학회지
• /
• 제8권2호
• /
• pp.47-60
• /
• 2000

본 연구에서는 인공위성영상을 이용한 토지피복 분류방법 중 파라메트릭한 분류와 비-파라메트릭한 분류의 대표성을 띤 최대우도 분류법과 신경망을 이용한 분류방법을 사용하여 분류정확도를 비교하였다. 분류정확도의 평가에 있어서 일반적인 분석가들이 사용하는 훈련지역에 대한 분류 정확도의 분석뿐만 아니라, 시험지역에 대한 정확도분석을 하였다. 그 결과, 최대우도분류기에 비하여 신경망의 분류기가 일반적인 훈련데이터의 분류에 있어서 약 3% 우월하였으며, 지상검증데이터를 사용한 분류결과에서는 시험에 사용된 두 분류기 모두 빈약한 분류결과를 나타내었으나, 신경망에 의한 분류가 최대우도에 비하여 약 10%정도 보다 신뢰할 수 있는 결과를 얻을 수 있었다.

• 한국시뮬레이션학회논문지
• /
• 제5권1호
• /
• pp.1-12
• /
• 1996

We propose a new approach to classifying a time series data into one of the autoregressive moving-average (ARMA) models. It is bases on two pattern recognition concepts for solving time series identification. The one is an extended sample autocorrelation function (ESACF). The other is a neural network-driven decision tree classifier(NNDTC) in which two pattern recognition techniques are tightly coupled : neural network and decision tree classfier. NNDTc consists of a set of nodes at which neural network-driven decision making is made whether the connecting subtrees should be pruned or not. Therefore, time series identification problem can be stated as solving a set of local decisions at nodes. The decision values of the nodes are provided by neural network functions attached to the corresponding nodes. Experimental results with a set of test data and real time series data show that the proposed approach can efficiently identify the time seires patterns with high precision compared to the previous approaches.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1261-1267
• /
• 2015

The problem of underwater target detection and classification has been attracted a substantial amount of attention and studied from many researchers for both military and non-military purposes. The difficulty is complicate due to various environmental conditions. In this paper, we study classifier ensemble methods for active sonar target classification to improve the classification performance. In general, classifier ensemble method is useful for classifiers whose variances relatively large such as decision trees and neural networks. Bagging, Random selection samples, Random subspace and Rotation forest are selected as classifier ensemble methods. Using the four ensemble methods based on 31 neural network classifiers, the classification tests were carried out and performances were compared.

• 전기학회논문지
• /
• 제64권9호
• /
• pp.1337-1346
• /
• 2015

In this paper, pattern classifier is designed to classify precipitation and non-precipitation events from weather radar data. The proposed classifier is based on Fuzzy Neural Network(FNN) and consists of three FNNs which operate in parallel. In the proposed network, the connection weights of the consequent part of fuzzy rules are expressed as two polynomial types such as constant or linear polynomial function, and their coefficients are learned by using Least Square Estimation(LSE). In addition, parametric as well as structural factors of the proposed classifier are optimized through Differential Evolution(DE) algorithm. After event classification between precipitation and non-precipitation echo, non-precipitation event is to get rid of all echo, while precipitation event including non-precipitation echo is to get rid of non-precipitation echo by classifier that is also based on Fuzzy Neural Network. Weather radar data obtained from meteorological office is to analysis and discuss performance of the proposed event and echo patter classifier, result of echo pattern classifier compare to QC(Quality Control) data obtained from meteorological office.

• International journal of advanced smart convergence
• /
• 제10권3호
• /
• pp.51-58
• /
• 2021

In this paper, we propose a deep learning classifier for estimating the number of layers in the Earth's structure. When installing a grounding system, knowledge of the subsurface in the area is absolutely necessary. The subsurface structure can be modeled by the earth parameters. Knowing the exact number of layers can significantly reduce the amount of computation to estimate these parameters. The classifier consists of a feedforward neural network. Apparent resistivity curves were used to train the deep learning classifier. The apparent resistivity at 20 equally spaced log points in each curve are used as the features for the input of the deep learning classifier. Apparent resistivity curve data sets are collected either by theoretical calculations or by Wenner's measurement method. Deep learning classifiers are coded by Keras, an open source neural network library written in Python. This model has been shown to converge with close to 100% accuracy.

• 한국음향학회지
• /
• 제14권1호
• /
• pp.13-21
• /
• 1995

본 논문에서는 신경망 학습에 의한 영상분류 알고리즘을 개선하였으며, 이것은 입력패턴 생성부와 분류을 위한 역전파 알고리즘에 의한 광역신경망으로 구성된다. 입력패턴을 위한 특징값으로는 자기조직화 형상지도 학습에 의해 얻은 코드북 데이타를 특징벡터로 이용한다. 이것은 입력벡터로서 원영상에 충실하면서 입력 뉴런수를 감소시킨다. 분류기에 사용된 광역망 알고리즘은 가중치와 유니트 오프셋 제어가 가능하도록 역전파 알고리즘에 제어부와 어드레스 메모리부를 삽입하였다. 실험결과 이들 분류기는 학습시 국소최소점에 빠지지 않게 되며, 대규모 신경망을 구현하고자 할 때 망구조를 간단히 할 수 있다. 또한 이것은 동작속도를 크게 개선할 수 있다.