• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.151-152
• /
• 2019

In this paper, we propose an improved learning method based on a small data set for animal image classification. First, CNN creates a training model for a small data set and uses the data set to expand the data set of the training set Second, a bottleneck of a small data set is extracted using a pre-trained network for a large data set such as VGG16 and stored in two NumPy files as a new training data set and a test data set, finally, learn the fully connected network as a new data set.

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.71-80
• /
• 2020

In order to provide realistic traffic to the cyber warfare training system, it is necessary to prepare a traffic distribution plan in advance and to create a training data set using normal/threat data sets. This paper presents the design and implementation results of a method for creating a traffic distribution plan and a training data set to provide background traffic like a real environment to a cyber warfare training system. We propose a method of a traffic distribution plan by using the network topology of the training environment to distribute traffic and the traffic attribute information collected in real and simulated environments. We propose a method of generating a training data set according to a traffic distribution plan using a unit traffic and a mixed traffic method using the ratio of the protocol. Using the implemented tool, a traffic distribution plan was created, and the training data set creation result according to the distribution plan was confirmed.

• Journal of KIISE:Software and Applications
• /
• v.31 no.7
• /
• pp.859-868
• /
• 2004

We propose a method of selecting initial training examples for active learning so that it can reach high accuracy faster with fewer further queries. Our method is based on the assumption that an active learner can reach higher performance when given an initial training set consisting of diverse and typical examples rather than similar and special ones. To obtain a good initial training set, we first cluster examples by using k-means clustering algorithm to find groups of similar examples. Then, a representative example, which is the closest example to the cluster's centroid, is selected from each cluster. After these representative examples are labeled by querying to the user for their categories, they can be used as initial training examples. We also suggest a method of using the centroids as initial training examples by labeling them with categories of corresponding representative examples. Experiments with various text data sets have shown that the active learner starting from the initial training set selected by our method reaches higher accuracy faster than that starting from randomly generated initial training set.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.142-149
• /
• 2013

In general, a color of an image is represented by using red, green, and blue channels in a RGB camera system. However, only information of three channels are limited to estimate a spectral reflectance of a real scene. Because of this, the RGB camera system can not accurately represent the color. To overcome this limitation and represent an accurate color, researches to estimate the spectral reflectance by using a multi-channel camera system are being actively proceeded. Recently, a reflectance estimation method adaptively constructing a similar training set from a traditional training set according to a camera response by using a spectral similarity was introduced. However, in this method, an accuracy of the similar training set is reduced because the spectral similarity based on an average and a maximum distances was applied. In this paper, a reflectance estimation method applied a spectral similarity based on a correlation coefficient is proposed to improve the accuracy of the similar training set. Firstly, the correlation coefficient between the similar training set and the spectral reflectance obtained by Wiener estimation method is calculated. Secondly, the similar training set is constructed from the traditional training set according to the correlation coefficient. Finally, Wiener estimation method applied the similar training set is performed to estimate the spectral reflectance. To evaluate a performance of the proposed method with previous methods, experimental results are compared. As a result, the proposed method showed the best performance.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.507-515
• /
• 2008

Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1
• /
• pp.104-109
• /
• 1997

This paper derives a new training alorithm for WHMM using the well-known MCE/GPD method with experimental results on the E-set. The derived algorithm generalizes the conventional adaptive training algorithm for WHMM, which means that HMMs of multiple competing classes can be trained at the same time. The recognition results on the E-set have shown about 15% and 12% improvement for training and test data, respectively.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.159-166
• /
• 2023

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.