• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1496-1521
• /
• 2012

Uncertainty is ubiquitous in target tracking wireless sensor networks due to environmental noise, randomness of target mobility and other factors. Sensing results are always unreliable. This paper considers unreliability as it occurs in wireless sensor networks and its impact on target-tracking accuracy. Firstly, we map intersection pairwise sensors' uncertain boundaries, which divides the monitor area into faces. Each face has a unique signature vector. For each target localization, a sampling vector is built after multiple grouping samplings determine whether the RSS (Received Signal Strength) for a pairwise nodes' is ordinal or flipped. A Fault-Tolerant Target-Tracking (FTTT) strategy is proposed, which transforms the tracking problem into a vector matching process that increases the tracking flexibility and accuracy while reducing the influence of in-the-filed factors. In addition, a heuristic matching algorithm is introduced to reduce the computational complexity. The fault tolerance of FTTT is also discussed. An extension of FTTT is then proposed by quantifying the pairwise uncertainty to further enhance robustness. Results show FTTT is more flexible, more robust and more accurate than parallel approaches.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.65-72
• /
• 2019

Data augmentation is a method that increases the amount of data through various algorithms based on a small amount of sample data. When machine learning and deep learning techniques are used to solve real-world problems, there is often a lack of data sets. The lack of data is at greater risk of underfitting and overfitting, in addition to the poor reflection of the characteristics of the set of data when learning a model. Thus, in this paper, through the layer-wise data augmenting method at each layer of deep neural network, the proposed method produces augmented data that is substantially meaningful and shows that the method presented by the paper through experimentation is effective in the learning of the model by measuring whether the method presented by the paper improves classification accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1623-1629
• /
• 2022

Matrix multiplication is a fundamental operation widely used in science and engineering. There is an approximate matrix multiplication method as a way to reduce the amount of computation of matrix multiplication. Approximate matrix multiplication determines an appropriate probability distribution for selecting columns and rows of matrices, and performs approximate matrix multiplication by selecting columns and rows of matrices according to this distribution. Probability distributions are generated by considering both matrices A and B participating in matrix multiplication. In this paper, we propose a method to generate a probability distribution that selects columns and rows of matrices to be used for approximate matrix multiplication, targeting only matrix A. Approximate matrix multiplication was performed on 1000×1000 ~ 5000×5000 matrices using existing and proposed methods. The approximate matrix multiplication applying the proposed method compared to the conventional method has been shown to be closer to the original matrix multiplication result, averaging 0.02% to 2.34%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.39-47
• /
• 2010

A research of image-based articulated pose estimation has some problems such as detection of human feature, precise pose estimation, and real-time performance. In particular, various methods are currently presented for recovering many joints of human body. We propose the novel numerical inverse kinematics improved with the UKF(unscented Kalman filter) in order to estimate the human pose in real-time. An existing numerical inverse kinematics is required many iterations for solving the optimal estimation and has some problems such as the singularity of jacobian matrix and a local minima. To solve these problems, we combine the UKF as a tool for optimal state estimation with the numerical inverse kinematics. Combining the solution of the numerical inverse kinematics with the sampling based UKF provides the stability and rapid convergence to optimal estimate. In order to estimate the human pose, we extract the interesting human body using both background subtraction and skin color detection algorithm. We localize its 3D position with the camera geometry. Next, through we use the UKF based numerical inverse kinematics, we generate the intermediate joints that are not detect from the images. Proposed method complements the defect of numerical inverse kinematics such as a computational complexity and an accuracy of estimation.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.149-157
• /
• 2012

In this thesis, the problem of computing approximate answers to continuous sliding-window joins over data streams when the available memory may be insufficient to keep the entire join state. One approximation scenario is to provide a maximum subset of the result, with the objective of losing as few result tuples as possible. An alternative scenario is to provide a random sample of the join result, e.g., if the output of the join is being aggregated. It is shown formally that neither approximation can be addressed effectively for a sliding-window join of arbitrary input streams. Previous work has addressed only the maximum-subset problem, and has implicitly used a frequency based model of stream arrival. There exists a sampling problem for this model. More importantly, it is shown that a broad class of applications for which an age-based model of stream arrival is more appropriate, and both approximation scenarios under this new model are addressed. Finally, for the case of multiple joins being executed with an overall memory constraint, an algorithm for memory allocation across the join that optimizes a combined measure of approximation in all scenarios considered is provided.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.9
• /
• pp.1065-1071
• /
• 2012

Wind energy is becoming one of the most preferable alternatives to conventional sources of electric power that rely on fossil fuels. For stable electric power generation, constant rotating speed control of a wind turbine is performed through pitch control and stall control of the turbine blades. Recently, variable pitch control has been implemented in modern wind turbines to harvest more energy at variable wind speeds that are even lower than the rated one. Although wind turbine pitch controllers are currently optimized using a step response via the Ziegler-Nichols auto-tuning process, this approach does not satisfy the requirements of variable pitch control. In this study, the variable pitch controller was optimized by a genetic algorithm using a neural network model that was constructed by the Latin Hypercube sampling method to improve the Ziegler-Nichols auto-tuning process. The optimized solution shows that the root mean square error, rise time, and settle time are respectively improved by more than 7.64%, 15.8%, and 15.3% compared with the corresponding initial solutions obtained by the Ziegler-Nichols auto-tuning process.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.607-615
• /
• 2020

The purpose of this study was to analyze the research status and trends related to the industrial mathematics based on text mining techniques with a sample of 4910 papers collected in the SIAM Journal on Applied Mathematics from 1970 to 2019. The R program was used to collect titles, abstracts, and key words from the papers and to analyze topic modeling techniques based on LDA algorithm. As a result of the coherence score on the collected papers, 20 topics were determined optimally using the Gibbs sampling methods. The main results were as follows. First, studies on industrial mathematics were conducted in a variety of mathematics fields, including computational mathematics, geometry, mathematical modeling, topology, discrete mathematics, probability and statistics, with a focus on analysis and algebra. Second, 5 hot topics (mathematical biology, nonlinear partial differential equation, discrete mathematics, statistics, topology) and 1 cold topic (probability theory) were found based on time series regression analysis. Third, among the fields that were not reflected in the 2015 revised mathematics curriculum, numeral system, matrix, vector in space, and complex numbers were extracted as the contents to be covered in the high school mathematical curriculum. Finally, this study suggested strategies to activate industrial mathematics in Korea, described the study limitations, and proposed directions for future research.