• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.31-41
• /
• 2018

Text classification has been studied for a long time in the Natural Language Processing field. In this paper, we propose an article- and paragraph-level genre classification system using Word2Vec-based LSTM, GRU, and CNN models for large-scale English corpora. Both article- and paragraph-level classification performed best in accuracy with LSTM, which was followed by GRU and CNN in accuracy performance. Thus, it is to be confirmed that in evaluating the classification performance of LSTM, GRU, and CNN, the word sequential information for articles is better than the word feature extraction for paragraphs when the pre-trained Word2Vec-based word embeddings are used in both deep learning-based article- and paragraph-level classification tasks.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.205-211
• /
• 2021

Plants are important for humanity. They intervene in several areas of human life: medicine, nutrition, cosmetics, decoration, etc. The large number of varieties of these plants requires an efficient solution to identify them for proper use. The ease of recognition of these plants undoubtedly depends on the classification of these species into family; however, finding the relevant characteristics to achieve better automatic classification is still a huge challenge for researchers in the field. In this paper, we have developed a new automatic plant classification technique based on artificial neural networks. Our model uses leaf texture characteristics as parameters for plant family identification. The results of our model gave a perfect classification of three plant families of the Ivorian flora, with a determination coefficient (R2) of 0.99; an error rate (RMSE) of 1.348e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and an accuracy (Accuracy) of 100%. The same technique was applied on Flavia: the international basis of plants and showed a perfect identification regression (R2) of 0.98, an error rate (RMSE) of 1.136e-14, a sensitivity of 84.85%, a specificity of 100%, a precision of 100% and a trueness (Accuracy) of 100%. These results show that our technique is efficient and can guide the botanist to establish a model for many plants to avoid identification problems.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.133-136
• /
• 1997

The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room or improving the accuracy of chromosome classification. In this paper, We propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of multi-step multi-layer neural network(MMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted three morphological features parameters such as centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.). This Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results show that the chromosome classification error is reduced much more than that of the other classification methods.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.653-655
• /
• 2005

More than 70 percent of terrestrial territory of Korea is mountainous areas where degradation becomes serious year by year due to illegal tombs, expanding golf courses and stone mine development. We elaborate the potential usage of high resolution image for the monitoring of the phenomena. We made the classification of tombs and the statistical radiometric characteristics of graves were identified from this project. The graves could be classified to 4 groups from the field survey. As compared with grouping data after clustering and discriminant analysis, the two results coincided with each other. Object-oriented classification algorithm for feature extraction was theoretically researched in this project. And we did a pilot project, which was performed with mixed methods. That is, the conventional methods such as unsupervised and supervised classification were mixed up with the new method for feature extraction, object-oriented classification method. This methodology showed about $60\%$ classification accuracy for extracting tombs from satellite imagery. The extraction of tombs' geographical coordinates and graves themselves from satellite image was performed in this project. The stone mines and golf courses are extracted by NDVI and GVI. The accuracy of classification was around 89 percent. The location accuracy showed extraction of tombs from one-meter resolution image is cheaper and quicker way than GPS method. Finally we interviewed local government officers and made analyses on the current situation of mountainous area management and potential usage of KOMPSAT-II images. Based on the requirement analysis, we developed software, which is to management and monitoring system for mountainous area for local government.

• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.1060-1071
• /
• 2014

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.388-393
• /
• 2002

Remote sensing data is collected and analyzed to enhance understanding of the terrestrial surface. Since Landsat satellite was launched in 1972, many researches using multispectral data has been achieved. Recently, with the availability of airborne and satellite hyperspectral data, the study on hyperspectral data are being increased. It is known that as the number of spectral bands of high-spectral resolution data increases, the ability to detect more detailed cases should also increase, and the classification accuracy should increase as well. In this paper, we classified the hyperspectral and multispectral data and tested the classification accuracy. The MASTER(MODIS/ASTER Airborne Simulator, 50channels, 0.4~13$\mu$m) and Landsat TM(7channels) imagery including Yeong-Gwang area were used and we adjusted the classification items in several cases and tested their classification accuracy through statistical comparison. As a result of this study, it is shown that hyperspectral data offer more information than multispectral data.

• Journal of information and communication convergence engineering
• /
• 제19권2호
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• 대한원격탐사학회지
• /
• 제28권5호
• /
• pp.489-499
• /
• 2012

이 논문에서는 원격탐사 자료의 분류를 목적으로 서로 다른 훈련 집단들과 분류자들로부터 생성된 분류 결과들을 결합하는 분류 틀을 제안하였다. 제안 분류 틀의 핵심 부분은 서로 다른 훈련 집단과 분류자들을 이용함으로써 분류 결과 사이의 다양성을 증가시켜서 결과적으로 분류 정확도를 향상시키는데 있다. 제안 분류 틀에서는 우선 서로 다른 샘플링 밀도를 가지는 서로 다른 훈련 집단들을 생성한 후에, 이들을 서로 다른 구분 능력을 나타내는 분류자들의 입력 훈련 자료로 사용한다. 그리고 초기 분류 결과들에 다수결 규칙을 적용하여 최종 분류 결과를 얻게 된다. 다중 시기 ENVISAT ASAR 자료를 이용한 토지 피복 분류사례 연구를 통해 제안 방법론의 적용 가능성을 검토하였다. 사례 연구에서 3개의 훈련 집단과 최대우도 분류자, 다층 퍼셉트론 분류자, support vector machine 등과 같은 3개의 분류자를 이용한 9개의 분류 결과를 결합하였다. 사례 연구 결과, 제안 분류 틀 안에서 토지 피복 구분에 관한 상호 보완적인 정보의 이용이 가능해져서 가장 높은 분류 정확도를 나타내었다. 서로 다른 결합들을 비교하였을 때, 다양성이 크지 않은 분류 결과들을 결합한 경우에는 분류 정확도의 향상이 나타나지 않았다. 따라서 다중 분류 시스템의 설계시 분류자들의 다양성을 확보하는 것이 중요함을 확인할 수 있었다.

• 대한원격탐사학회지
• /
• 제25권3호
• /
• pp.215-223
• /
• 2009

The noise removal as a preprocessing was tried with various kinds of wavelet pairs. Wavelet transform for 2D images generally uses the same wavelets as basis functions in horizontal and vertical directions. A method with different wavelets was tried for each direction separately, which gives more precise interpretation of the classification. Total 486 pairs of wavelets from nine basis functions were tried to remove image noises. The classification accuracies before and after the noise removal were compared. Although all kinds of wavelet pairs showed the increased accuracies in classification, there were best and worst wavelet pairs depending on the data sets. Wavelet pairs with low energy percentage of LL band showed the high classification accuracy. A pattern was found in the results that very similar vertical accuracy was distributed for each horizontal ones. Since Haar is the shortest length filter, Haar could be a predictor wavelet to find the good wavelet pairs.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.169-172
• /
• 2008

Land-use or land-cover classification of satellite images is one of the important tasks in remote sensing application and many researchers have been tried to enhance classification accuracy. Previous studies show that the classification technique based on wavelet transform is more effective than that of traditional techniques based on original pixel values, especially in complicated imagery. Various wavelets can be used in wavelet transform. Wavelets are used as basis functions in representing other functions, like sinusoidal function in Fourier analysis. In these days, some basis functions such as Haar, Daubechies, Coiflets and Symlets are mainly used in 2D image processing. Selecting adequate wavelet is very important because different results could be obtained according to the type of basis function in classification. However, it is not easy to choose the basis function which is effective to improve classification accuracy. In this study, we computed the wavelet coefficients of satellite image using 10 different basis functions, and then classified test image. After evaluating classification results, we tried to ascertain which basis function is the most effective for image classification. We also tried to see if the optimum basis function is decided by energy parameter before classifying the image using all basis function. The energy parameter of signal is the sum of the squares of wavelet coefficients. The energy parameter is calculated by sub-bands after the wavelet decomposition and the energy parameter of each sub-band can be a favorable feature of texture. The decision of optimum basis function using energy parameter in the wavelet based image classification is expected to be helpful for saving time and improving classification accuracy effectively.