• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Smart Structures and Systems
• /
• v.6 no.2
• /
• pp.115-133
• /
• 2010

A modal filter is a tool used to extract the modal coordinates of each individual mode from a system's output. This is achieved by mapping the response vector from the physical space to the modal space. It decomposes the system's responses into modal coordinates, and thus, on the output of the filter, the frequency response with only one peak corresponding to the natural frequency to which the filter was tuned can be obtained. As was shown in the paper (Deraemecker and Preumont 2006), structural modification (e.g. a drop in stiffness or mass due to damage) causes the appearance of spurious peaks on the output of the modal filter. A modal filter is, therefore, a great indicator of damage detection, with such advantages as low computational effort due to data reduction, ease of automation and lack of sensitivity to environmental changes. This paper presents the application of modal filters for the detection of stiffness changes. Two experiments were conducted: the first one using the simulation data obtained from the numerical 7DOF model, and the second one on the experimental data from a laboratory stand in 4 states of damage.

• Bulletin of the Korean Space Science Society
• /
• 2008.10a
• /
• pp.36.1-36.1
• /
• 2008

An Unscented Kalman Filter(UKF) for estimation of attitude and rate of a spacecraft using only magnetometer vector measurement is presented. The dynamics used in the filter is nonlinear rotational equation which is augmented by the quaternion kinematics to construct a process model. The filter is designed for low Earth orbit satellite, so the disturbance torques include gravity-gradient torque, magnetic disturbance torque, and aerodynamic drag. The magnetometer measurements are simulated based on time-varying position of the spacecraft. The filter has been tested not only in the standby mode but also in the detumbling mode. To stabilize the attitude, linear PD controller is applied and the actuator is assumed to be thruster. A Monte-Carlo simulation has been done to guarantee the stability of the filter performance to the various initial conditions. The UKF performance is compared to that of EKF and it reveals that UKF outperforms EKF.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.1
• /
• pp.38-50
• /
• 2018

Spatio-temporal load forecasting (STLF) is a foundation for building the prediction-based power map, which could be a useful tool for the visualization and tendency assessment of urban energy application. Constructing one point-forecasting model for each electricity cell in the geographic space is possible; however, it is unadvisable and insufficient, considering the aggregation features of electricity cells and uncertainties in input variables. This paper presents a new STLF method, with a data-driven framework consisting of 3 subroutines: multi-level clustering of cells considering their aggregation features, load regression for each category of cells based on SLS-SVRNs (sparse least squares support vector regression networks), and interval forecasting of spatio-temporal load with sampled blind number. Take some area in Pudong, Shanghai as the region of study. Results of multi-level clustering show that electricity cells in the same category are clustered in geographic space to some extent, which reveals the spatial aggregation feature of cells. For cellular load regression, a comparison has been made with 3 other forecasting methods, indicating the higher accuracy of the proposed method in point-forecasting of spatio-temporal load. Furthermore, results of interval load forecasting demonstrate that the proposed prediction-interval construction method can effectively convey the uncertainties in input variables.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2143-2145
• /
• 2003

In the linear system identification using the discrete time constant coefficients, there is a subspace method based on 4SID recently much suggested instead of the parametric method like as the maximum likelihood method. The subspace method is not related with the impulse response and difference equation in its input-output equation, but with the system matrix of the direct state space model from the input-output data. The subspace method is a very useful tool to adopt in the multivariable system identification, but it has a shortage unable to adopt in the closed-loop system identification. In this paper, we are suggested the methods to get rid of the shortage of the subspace method in the closed-loop system identification. The subspace method is used in the estimate of the output prediction values from the estimating of the state space vector. And we have compared the results with the outputs of the recursive least square method in the numerical simulation.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1156-1165
• /
• 2018

This paper presents a detailed realization of direct torque controlled induction motor drive for elevator applications. The drive is controlled according to the well-known space vector modulated direct control scheme (SVM-DTC). As the elevator drives are usually equipped with speed sensors, flux estimation is carried out using a current model where two stator currents are measured and accurate instantaneous rotor speed measurement is used to overcome the need for measuring stator voltages. Speed profiling for a comfortable elevator ride and other supervisory control activities to provide smooth operation are also explained. The drive performance is examined and controllers' parameters are fine-tuned using MATLAB/SIMULINK. The blocks used for flux and torque estimation and control in the offline simulation are compiled for real-time using dSPACE Microlabox. The performance of the drive has been verified experimentally. The results show good performance under transient and steady state conditions.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.12
• /
• pp.981-988
• /
• 2021

This paper presents a decentralized guidance algorithm for swarm flight of fixed-wing UAVs (Unmanned Aerial Vehicles). Considering swarm flight missions, we assume four representative swarm tasks: gathering, loitering, waypoint/path following, and individual task. Those tasks require several distinct maneuvers such as path following, flocking, and collision avoidance. In order to deal with the required maneuvers, this paper proposes an integrated guidance algorithm based on vector field, augmented Cucker-Smale model, and potential field methods. Integrated guidance command is synthesized with heuristic weights designed for each guidance method. The proposed algorithm is verified through flight tests using up to 19 small fixed-wing UAVs.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.329-341
• /
• 2014

Kernel-based mean-shift object tracking has gained more interests nowadays, with the aid of its feasibility of reliable real-time implementation of object tracking. This algorithm calculates the best mean-shift vector based on the color histogram similarity between target model and target candidate models, where the color histograms are usually produced after uniform color-space quantization for the implementation of real-time tracker. However, when the image of target model has a reduced contrast, such uniform quantization produces the histogram model having large values only for a few histogram bins, resulting in a reduced accuracy of similarity comparison. To solve this problem, a non-uniform quantization algorithm has been proposed, but it is hard to apply to real-time tracking applications due to its high complexity. Therefore, this paper proposes a fast non-uniform color-space quantization method using the histogram equalization, providing an adjusted histogram distribution such that the bins of target model histogram have as many meaningful values as possible. Using the proposed method, the number of bins involved in similarity comparison has been increased, resulting in an enhanced accuracy of the proposed mean-shift tracker. Simulations with various test videos demonstrate the proposed algorithm provides similar or better tracking results to the previous non-uniform quantization scheme with significantly reduced computation complexity.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.