• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.6-11
• /
• 2011

In this paper, we propose a gait-based human identification system using eigenfeature regularization and extraction (ERE). First, a gait feature for human identification which is called gait energy image (GEI) is generated from walking sequences acquired from a camera sensor. In training phase, regularized transformation matrix is obtained by applying ERE to the gallery GEI dataset, and the gallery GEI dataset is projected onto the eigenspace to obtain galley features. In testing phase, the probe GEI dataset is projected onto the eigenspace created in training phase and determine the identity by using a nearest neighbor classifier. Experiments are carried out on the CASIA gait dataset A to evaluate the performance of the proposed system. Experimental results show that the proposed system is better than previous works in terms of correct classification rate.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2003.05a
• /
• pp.87-91
• /
• 2003

It has well known that MUSIC and ESPRIT algorithms estimate angle of arrival(AOA) with high resolution by eigenvalue decomposition of the covariance matrix which were obtained from the array antennas. However, the disadvantage of MUSIC and ESPRIT is that they are computationally ineffective, and then they are difficult to implement in real time. The other problem of MUSIC and ESRPIT is to require calibrated antennas with uniform features, and are sensitive to the manufacturing facult and other physical uncertainties. To overcome these disadvantages, several method using neural model have been study. For multiple signals, those require huge training data prior to AOA estimation. This paper proposes the algorithm for AOA estimation by interconnected hopfield neural model. Computer simulations show the validity of the proposed algorithm. The proposed method does not require huge training procedure and only assigns interconnected coefficients to the neural network prior to AOA estimation.

• Journal of Navigation and Port Research
• /
• v.27 no.4
• /
• pp.465-469
• /
• 2003

It has well known that MUSIC and ESPRIT algorithms estimate angle of arrival(AOA) with high resolution by eigenvalue decomposition of the covariance matrix which were obtained from the array antennas, However, the disadvantage of MUSIC and ESPRIT is that they are computationally ineffective, and then they are difficult to implement in real time. the other problem of MUSIC and ESPRIT is to require calibrated antennas with uniform features, and are sensitive ti the manufacturing fault and other physical uncertainties. To overcome these disadvantages, several method using neural model have been study. For multiple signals, those methods require huge training data prior to AOA estimation. This paper proposes the algorithm for AOA estimation by interconnected Hopfield neural model. Computer simulations show the validity of the proposed algorithm. It follows that the proposed method yields better AOA estimates than MUSIC. Moreover, out method does not require huge training procedure and only assigns interconnected coefficients to the neural network prior to AOA estimation.

• Journal of Internet Computing and Services
• /
• v.20 no.4
• /
• pp.73-79
• /
• 2019

Selecting a proper journal to submit a research paper is a difficult task for researchers since there are many journals and various decision factors to consider during the decision process. For this reason, journal recommendation services are exist as a kind of intelligent research assistant which recommend potential journals. The existing services are executing a recommendation based on topic similarity and numerical filtering. However, it is impossible to calculate topic similarity when a researcher does not input paper data, and difficult to input clear numerical values for researchers. Therefore, the journal recommendation method which consider the importance of decision factors is proposed by constructing the preference matrix based on the paper publication history of a researcher. The proposed method was evaluated by using the actual publication history of researchers. The experiment results showed that the proposed method outperformed the compared methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.33-38
• /
• 2019

This paper proposes an effective recognition method of VPI patient's speech employing DNN-HMM-based speech recognition system, and evaluates the recognition performance compared to GMM-HMM-based system. The proposed method employs speaker adaptation technique to improve VPI speech recognition. This paper proposes to use simulated VPI speech for generating a prior model for speaker adaptation and selective learning of weight matrices of DNN, in order to effectively utilize the small size of VPI speech for model adaptation. We also apply Linear Input Network (LIN) based model adaptation technique for the DNN model. The proposed speaker adaptation method brings 2.35% improvement in average accuracy compared to GMM-HMM based ASR system. The experimental results demonstrate that the proposed DNN-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM system.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.23-29
• /
• 2019

In this paper, the mood of images was classified into eight categories through a deep convolutional neural network and video was automatically generated using proper background music. Based on the collected image data, the classification model is learned using a multilayer perceptron (MLP). Using the MLP, a video is generated by using multi-class classification to predict image mood to be used for video generation, and by matching pre-classified music. As a result of 10-fold cross-validation and result of experiments on actual images, each 72.4% of accuracy and 64% of confusion matrix accuracy was achieved. In the case of misclassification, by classifying video into a similar mood, it was confirmed that the music from the video had no great mismatch with images.

• Journal of The Korean Association For Science Education
• /
• v.29 no.8
• /
• pp.812-823
• /
• 2009

The purpose of this study is to search effective assessments methods by using the Fusion model of Cognitive diagnosis theory. Attributes are skills or cognitive processes that are required to perform correctly on a particular item. After test items were developed, item's attributes were decided and Q-matrix about item's attributes was made. After testing, the result was analyzed according to gender and achievement level. The results of the analysis showed that students mastered 'Interpreting data' best, and 'synthesizing' worst among the five attributes. Female students showed higher ability than male students in 'recalling.' Students of high achievement level mastered more scientific attributes than students of low achievement level. Conventional assessments only provided a single summary score but Cognitive diagnosis modeling provided useful information by estimating individual knowledge states by assessing whether an examinee has mastered specific attributes measured by the science test. The skill profiles can offer a skill level of strong, weak, or mixed for each student for each skill. Therefore, the skill profiles will provide useful diagnostic information in addition to single overall scores.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.1-11
• /
• 2021

Detection of surface water features including river, wetland, reservoir from the satellite imagery can be utilized for sustainable management and survey of water resources. This research compared the water indices derived from the multispectral bands and the machine learning technique for detecting the surface water features from he Landsat-8 satellite image acquired in Daegu through the following steps. First, the NDWI(Normalized Difference Water Index) image and the MNDWI(Modified Normalized Difference Water Index) image were separately generated using the multispectral bands of the given Landsat-8 satellite image, and the two binary images were generated from these NDWI and MNDWI images, respectively. Then SVM(Support Vector Machine), the widely used machine learning techniques, were employed to generate the land cover image and the binary image was also generated from the generated land cover image. Finally the error matrices were used for measuring the accuracy of the three binary images for detecting the surface water features. The statistical results showed that the binary image generated from the MNDWI image(84%) had the relatively low accuracy than the binary image generated from the NDWI image(94%) and generated by SVM(96%). And some misclassification errors occurred in all three binary images where the land features were misclassified as the surface water features because of the shadow effects.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.411-417
• /
• 2022

This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.