• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.281-291
• /
• 2022

Surmounting complexities in analyzing the mechanical parameters of concrete entails selecting an appropriate methodology. This study integrates a novel metaheuristic technique, namely satin bowerbird optimizer (SBO) with artificial neural network (ANN) for predicting uniaxial compressive strength (UCS) of concrete. For this purpose, the created hybrid is trained and tested using a relatively large dataset collected from the published literature. Three other new algorithms, namely Henry gas solubility optimization (HGSO), sunflower optimization (SFO), and vortex search algorithm (VSA) are also used as benchmarks. After attaining a proper population size for all algorithms, the Utilizing various accuracy indicators, it was shown that the proposed ANN-SBO not only can excellently analyze the UCS behavior, but also outperforms all three benchmark hybrids (i.e., ANN-HGSO, ANN-SFO, and ANN-VSA). In the prediction phase, the correlation indices of 0.87394, 0.87936, 0.95329, and 0.95663, as well as mean absolute percentage errors of 15.9719, 15.3845, 9.4970, and 8.0629%, calculated for the ANN-HGSO, ANN-SFO, ANN-VSA, and ANN-SBO, respectively, manifested the best prediction performance for the proposed model. Also, the ANN-VSA achieved reliable results as well. In short, the ANN-SBO can be used by engineers as an efficient non-destructive method for predicting the UCS of concrete.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.393-405
• /
• 2023

Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.6
• /
• pp.28-39
• /
• 2010

The study aims at offering a solution to the problems of transmission delay and data throughput decrease as the number of contending On-Board Units (OBU) increases by applying CSMA medium access control protocol based upon IEEE 802.11p. In a competition-based medium, contention probability becomes high as OBU increases. In order to improve the performance of this medium access layer, the author proposes EDCA which a adaptive adjustment of the Contention Windows (CW) considering traffic density and data type. EDCA applies fixed values of Minimum Contention Window (CWmin) and Maximum Contention Window (CWmax) for each of four kinds of Access Categories (AC) for channel-specific service differentiation. EDCA does not guarantee the channel-specific features and network state whereas it guarantees inter-AC differentiation by classifying into traffic features. Thus it is not possible to actively respond to a contention caused by network congestion occurring in a short moment in channel. As a solution, CWminAS(CWmin Adaptation Scheme) and ACATICT(Adaptive Contention window Adjustment Technique based on Individual Class Traffic) are proposed as active CW control techniques. In previous researches, the contention probabilities for each value of AC were not examined or a single channel based AC value was considered. And the channel-specific demands of IEEE 802.11p and the corresponding contention probabilities were not reflected in the studies. The study considers the collision number of a previous service section and the current network congestion proposes a dynamic control technique ACCW(Adaptive Control of Contention windows in considering the WAVE situation) for CW of the next channel.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.78-87
• /
• 2011

A variety of intelligent application using the sensor network system is being studied. In general, the sensor network consists of nodes which equipped with a variety of sensing module and is utilized to collect environment information. Recently, the demands of multimedia data are increasing due to the demands of more detailed environmental monitoring or high-quality data. In this paper, we overcome the limitations of low bandwidth in Zigbee-based sensor networks and propose a routing algorithm for real-time multimedia data transmission. In the previously proposed algorithm for multimedia data transmission occurs delay time of routing setup phase and has a low data transmission speed due to bandwidth limitations of Zigbee. In this paper, we propose the hybrid routing algorithm that consist of Zigbee and Bluetooth and solve the bandwidth problem of existing algorithm. We also propose the disjointed multipath setup algorithm based on competition that overcome delay time of routing setup phase in existing algorithm. To evaluate the superiority of the proposed algorithm, we compare it with the existing algorithm. Our experimental results show that the latency was reduced by approximately 78% and the communication speed is increased by approximately 6.9-fold.

• BMB Reports
• /
• v.41 no.4
• /
• pp.287-293
• /
• 2008

In a yeast two-hybrid screen, we identified the microtubule-destabilizing protein SCG10 as a potential effector protein of $BRI_3$. The association was verified using GST pull-down, Co-IP, and their perinuclear co-localization. The analysis of in vitro microtubule polymerization/depolymerization showed that the binding of $BRI_3$ to SCG10 effectively blocked the ability of SCG10 to induce microtubule disassembly, as determined by turbidimetric assays. In intact PC12 cells, $BRI_3$ exhibited the ability to stabilize the microtubule network and attenuate the microtubule-destabilizing activity of SCG10. Furthermore, co-expression of $BRI_3$ with SCG10 attenuated SCG10-mediated PC12 cell neurite outgrowth induced by NGF. These results identify a novel connection between a neuron-specific BRI protein and the cytoskeletal network, suggesting possible roles of BRI3 in the process of neuronal differentiation.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.15 no.9
• /
• pp.896-905
• /
• 2004

In this paper, the design, fabrication and experiment on a planar array antenna with a flat-topped radiation pattern for a mobile base station antenna were described. The current distribution of an antenna aperture, which is easily realizable in a feeding network compared with the conventional one of sin(x)/x was optimized for shaping a desired flat-topped radiation pattern. The planar array antenna designed in this paper has a rectangular lattice and is composed of array elements of 16${\times}$8. Each radiating element, which is a microstrip element fed coaxially, has a linear vertical polarization and the feed network which use a Wilkinson power divider and a 180$^{\circ}$ ring hybrid coupler as a base element is designed. The flat-topped radiation pattern with 90$^{\circ}$ is shaped by 16 array elements with the element spacing of 0.55 λ$_{ο}$ in the azimuth plane, and the normal radiation pattern with 10$^{\circ}$ is shaped by 8 array elements with the element spacing of 0.65 λ$_{ο}$ in the elevation plane. Also, the planar array antenna is symmetrically divided into four parts. It consists of one hundred-twenty-eight radiating elements, thirty-two 1-4 column dividers, low 1-8 row dividers and one 1-4 input power divider. In order to verify electrical performances of the planar way antenna proposed in this paper, the experimental breadboard operated in tile band of 1.92～2.17 GHz(IMT2000 band) was fabricated, and its experimental results were a good agreement with simulation ones.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.349-356
• /
• 2005

Artificial Organism-used application areas are expanding at a break-neck speed with a view to getting things done in a dynamic and Informal environment. A use of general programming or traditional hi methods as the representation of Artificial Organism behavior knowledge in these areas can cause problems related to frequent modifications and bad response in an unpredictable situation. Strategies aimed at solving these problems in a machine-learning fashion includes Genetic Programming and Evolving Neural Networks. But the learning method of Artificial-Organism is not good yet, and can't represent life in the environment. With this in mind, this research is designed to come up with a new behavior evolution model. The model represents behavior knowledge with Classification Rules and Enhanced Backpropation Neural Networks and discriminate the denomination. To evaluate the model, the researcher applied it to problems with the competition of Artificial-Organism in the Simulator and compared with other system. The survey shows that the model prevails in terms of the speed and Qualify of learning. The model is characterized by the simultaneous learning of classification rules and neural networks represented on chromosomes with the help of Genetic Algorithm and the consolidation of learning ability caused by the hybrid processing of the classification rules and Enhanced Backpropagation Neural Network.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.45-52
• /
• 2008

As the recent development of the IT services, there is a urgent need of effective diagnosis system to present appropriate solution for the complicated problems of breakdown control, a cause analysis of breakdown and others. So we propose an intelligent diagnosis system that integrates the case-based reasoning and the artificial neural network to improve the system performance and to achieve optimal diagnosis. The case-based reasoning is a reasoning method that resolves the problems presented in current time through the past cases (experience). And it enables to make efficient reasoning by means of less complicated knowledge acquisition process, especially in the domain where it is difficult to extract formal rules. However, reasoning by using the case-based reasoning alone in diagnosis problem domain causes a problem of suggesting multiple causes on a given symptom. Since the suggested multiple causes of given symptom has the same weight, the unnecessary causes are also examined as well. In order to resolve such problems, the back-propagation learning algorithm of the artificial neural network is used to train the pairs of the causes and associated symptoms and find out the cause with the highest weight for occurrence to make more clarified and reliable diagnosis.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.113-124
• /
• 2020

Social movements to improve the performance of buildings through remodeling of aging apartment houses are being captured. To this end, the remodeling construction cost analysis, structural analysis, and political institutional review have been conducted to suggest ways to activate the remodeling. However, although the method of analyzing construction cost for remodeling apartment houses is currently being proposed for research purposes, there are limitations in practical application possibilities. Specifically, In order to be used practically, it is applicable to cases that have already been completed or in progress, but cases that will occur in the future are also used for construction cost analysis, so the sustainability of the analysis method is lacking. For the purpose of this, we would like to suggest an automated estimating method. For the sustainability of construction cost estimates, Deep-Learning was introduced in the estimating procedure. Specifically, a method for automatically finding the relationship between design elements, work types, and cost increase factors that can occur in apartment remodeling was presented. In addition, Monte Carlo Simulation was included in the estimation procedure to compensate for the lack of uncertainty, which is the inherent limitation of the Deep Learning-based estimation. In order to present higher accuracy as cases are accumulated, a method of calculating higher accuracy by comparing the estimate result with the existing accumulated data was also suggested. In order to validate the sustainability of the automated estimates proposed in this study, 13 cases of learning procedures and an additional 2 cases of cumulative procedures were performed. As a result, a new construction cost estimating procedure was automatically presented that reflects the characteristics of the two additional projects. In this study, the method of estimate estimate was used using 15 cases, If the cases are accumulated and reflected, the effect of this study is expected to increase.