• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.1-8
• /
• 2010

In this paper, we propose a scheduling strategy for grid environment that reduces resource cost. This strategy considers resource cost and job failure rate to efficiently allocate local computing resources. The key idea of our strategy is that we use two-level scheduling using remote and local scheduler. The remote scheduler determines the expected total execution times of jobs using the current network and local system status maintained in its resource database and allocates jobs with minimum total execution time to local systems. The local scheduler recalculates the waiting time and execution time of allocated job and uses it to determine whether the job can be processed within the specified deadline. If it cannot finish in time, the job is migrated other local systems, through simulation, we show that it is more effective to reduce the resource cost than the previous Greedy strategy. We also show that the proposed strategy improves the performance compared to previous Greedy strategy.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.813-824
• /
• 2021

To improve educational performance by analyzing the learning trends of adult learners of Open High Schools, various algorithm models using artificial intelligence were designed and performance was evaluated by applying them to real data. We analyzed Log data of 115 adult learners in the cyber education system of Open High Schools. Most adult learners of Open High Schools learned more than recommended learning time, but at the end of the semester, the actual learning time was significantly reduced compared to the recommended learning time. In the second half of learning, the participation rate of VODs, formation assessments, and learning activities also decreased. Therefore, in order to improve educational performance, learning time should be supported to continue in the second half. In the latter half, we developed an artificial intelligence algorithm models using Tensorflow to predict learning time by data they started taking the course. As a result, when using CNN(Convolutional Neural Network) model to predict single or multiple outputs, the mean-absolute-error is lowest compared to other models.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.10 no.1
• /
• pp.73-80
• /
• 2010

The optimal design of water distribution system have started with the least cost design of single objective function using fixed hydraulic variables, eg. fixed water demand and pipe roughness. However, more adequate design is accomplished with considering uncertainties laid on water distribution system such as uncertain future water demands, resulting in successful estimation of real network's behaviors. So, many researchers have suggested a variety of approaches to consider uncertainties in water distribution system using uncertainties quantification methods and the optimal design of multi-objective function is also studied. This paper suggests the new approach of a multi-objective optimization seeking the minimum cost and maximum robustness of the network based on two uncertain variables, nodal demands and pipe roughness uncertainties. Total design procedure consists of two folds: least cost design and final optimal design under uncertainties. The uncertainties of demands and roughness are considered with Latin Hypercube sampling technique with beta probability density functions and multi-objective genetic algorithms (MOGA) is used for the optimization process. The suggested approach is tested in a case study of real network named the New York Tunnels and the applicability of new approach is checked. As the computation time passes, we can check that initial populations, one solution of solutions of multi-objective genetic algorithm, spread to lower right section on the solution space and yield Pareto Optimum solutions building Pareto Front.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.11B
• /
• pp.946-955
• /
• 2004

It is shown that the do Bruijn graph (dBG) can be used as an architecture for interconnection network and a suitable structure for parallel computation. Recent works have classified dBG based routing algorithms into shortest path routing and fault tolerant routing but investigation into fault free shortest path (FFSP) on dBG has been non-existent. In addition, as the size of the network increase, more faults are to be expected and therefore shortest path dBG algorithms in fault free mode may not be suitable routing algorithms for real interconnection networks, which contain several failures. Furthermore, long fault free path may lead to high traffic, high delay time and low throughput. In this paper we investigate routing algorithms in the condition of existing failure, based on the Bidirectional do Bruijn graph (BdBG). Two FFSP routing algorithms are proposed. Then, the performances of the two algorithms are analyzed in terms of mean path lengths and discrete set mean sizes. Our study shows that the proposed algorithms can be one of the candidates for routing in real interconnection networks based on dBG.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.2
• /
• pp.28-36
• /
• 2022

As port structures are exposed to various extreme external loads such as wind (typhoons), sea waves, or collision with ships; it is important to evaluate the structural safety periodically. To monitor the port structure, especially the rubber fender, a fender segmentation system using a vision sensor and deep learning method has been proposed in this study. For fender segmentation, a new deep learning network that improves the encoder-decoder framework with the receptive field block convolution module inspired by the eccentric function of the human visual system into the DenseNet format has been proposed. In order to train the network, various fender images such as BP, V, cell, cylindrical, and tire-types have been collected, and the images are augmented by applying four augmentation methods such as elastic distortion, horizontal flip, color jitter, and affine transforms. The proposed algorithm has been trained and verified with the collected various types of fender images, and the performance results showed that the system precisely segmented in real time with high IoU rate (84%) and F1 score (90%) in comparison with the conventional segmentation model, VGG16 with U-net. The trained network has been applied to the real images taken at one port in Republic of Korea, and found that the fenders are segmented with high accuracy even with a small dataset.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.101-108
• /
• 2024

Indoor localization is a critical component for numerous applications, ranging from navigation in large buildings to emergency response. This paper presents an enhanced Pedestrian Dead Reckoning (PDR) scheme using smartphone sensors, integrating neural network-aided motion recognition, Kalman filter-based error correction, and multi-sensor data fusion. The proposed system leverages data from the accelerometer, magnetometer, gyroscope, and barometer to accurately estimate a user's position and orientation. A neural network processes sensor data to classify motion modes and provide real-time adjustments to stride length and heading calculations. The Kalman filter further refines these estimates, reducing cumulative errors and drift. Experimental results, collected using a smartphone across various floors of University, demonstrate the scheme's ability to accurately track vertical movements and changes in heading direction. Comparative analyses show that the proposed CNN-LSTM model outperforms conventional CNN and Deep CNN models in angle prediction. Additionally, the integration of barometric pressure data enables precise floor level detection, enhancing the system's robustness in multi-story environments. Proposed comprehensive approach significantly improves the accuracy and reliability of indoor localization, making it viable for real-world applications.

• Journal of Internet Computing and Services
• /
• v.15 no.3
• /
• pp.101-107
• /
• 2014

With the development of online service, recent forms of databases have been changed from static database structures to dynamic stream database structures. Previous data mining techniques have been used as tools of decision making such as establishment of marketing strategies and DNA analyses. However, the capability to analyze real-time data more quickly is necessary in the recent interesting areas such as sensor network, robotics, and artificial intelligence. Landmark window-based frequent pattern mining, one of the stream mining approaches, performs mining operations with respect to parts of databases or each transaction of them, instead of all the data. In this paper, we analyze and evaluate the techniques of the well-known landmark window-based frequent pattern mining algorithms, called Lossy counting and hMiner. When Lossy counting mines frequent patterns from a set of new transactions, it performs union operations between the previous and current mining results. hMiner, which is a state-of-the-art algorithm based on the landmark window model, conducts mining operations whenever a new transaction occurs. Since hMiner extracts frequent patterns as soon as a new transaction is entered, we can obtain the latest mining results reflecting real-time information. For this reason, such algorithms are also called online mining approaches. We evaluate and compare the performance of the primitive algorithm, Lossy counting and the latest one, hMiner. As the criteria of our performance analysis, we first consider algorithms' total runtime and average processing time per transaction. In addition, to compare the efficiency of storage structures between them, their maximum memory usage is also evaluated. Lastly, we show how stably the two algorithms conduct their mining works with respect to the databases that feature gradually increasing items. With respect to the evaluation results of mining time and transaction processing, hMiner has higher speed than that of Lossy counting. Since hMiner stores candidate frequent patterns in a hash method, it can directly access candidate frequent patterns. Meanwhile, Lossy counting stores them in a lattice manner; thus, it has to search for multiple nodes in order to access the candidate frequent patterns. On the other hand, hMiner shows worse performance than that of Lossy counting in terms of maximum memory usage. hMiner should have all of the information for candidate frequent patterns to store them to hash's buckets, while Lossy counting stores them, reducing their information by using the lattice method. Since the storage of Lossy counting can share items concurrently included in multiple patterns, its memory usage is more efficient than that of hMiner. However, hMiner presents better efficiency than that of Lossy counting with respect to scalability evaluation due to the following reasons. If the number of items is increased, shared items are decreased in contrast; thereby, Lossy counting's memory efficiency is weakened. Furthermore, if the number of transactions becomes higher, its pruning effect becomes worse. From the experimental results, we can determine that the landmark window-based frequent pattern mining algorithms are suitable for real-time systems although they require a significant amount of memory. Hence, we need to improve their data structures more efficiently in order to utilize them additionally in resource-constrained environments such as WSN(Wireless sensor network).

• Progress in Medical Physics
• /
• v.20 no.3
• /
• pp.132-138
• /
• 2009

Studies on target motion in 4-dimensional radiotherapy are being world-widely conducted to enhance treatment record and protection of normal organs. Prediction of tumor motion might be very useful and/or essential for especially free-breathing system during radiation delivery such as respiratory gating system and tumor tracking system. Neural network is powerful to express a time series with nonlinearity because its prediction algorithm is not governed by statistic formula but finds a rule of data expression. This study intended to assess applicability of neural network method to predict tumor motion in 4-dimensional radiotherapy. Scaled Conjugate Gradient algorithm was employed as a learning algorithm. Considering reparation data for 10 patients, prediction by the neural network algorithms was compared with the measurement by the real-time position management (RPM) system. The results showed that the neural network algorithm has the excellent accuracy of maximum absolute error smaller than 3 mm, except for the cases in which the maximum amplitude of respiration is over the range of respiration used in the learning process of neural network. It indicates the insufficient learning of the neural network for extrapolation. The problem could be solved by acquiring a full range of respiration before learning procedure. Further works are programmed to verify a feasibility of practical application for 4-dimensional treatment system, including prediction performance according to various system latency and irregular patterns of respiration.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.