• Smart Structures and Systems
• /
• v.26 no.3
• /
• pp.263-275
• /
• 2020

This research is dedicated to slope stability analysis using novel intelligent models. By coupling a neural network with spotted hyena optimizer (SHO), salp swarm algorithm (SSA), shuffled frog leaping algorithm (SFLA), and league champion optimization algorithm (LCA) metaheuristic algorithms, four predictive ensembles are built for predicting the factor of safety (FOS) of a single-layer cohesive soil slope. The data used to develop the ensembles are provided from a vast finite element analysis. After creating the proposed models, it was observed that the best population size for the SHO, SSA, SFLA, and LCA is 300, 400, 400, and 200, respectively. Evaluation of the results showed that the combination of metaheuristic and neural approaches offers capable tools for estimating the FOS. However, the SSA (error = 0.3532 and correlation = 0.9937), emerged as the most reliable optimizer, followed by LCA (error = 0.5430 and correlation = 0.9843), SFLA (error = 0.8176 and correlation = 0.9645), and SHO (error = 2.0887 and correlation = 0.8614). Due to the high accuracy of the SSA in properly adjusting the computational parameters of the neural network, the corresponding FOS predictive formula is presented to be used as a fast yet accurate substitution for traditional methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.spc
• /
• pp.39-53
• /
• 2023

Recently, the market competition has been fiercer due to the acceleration of technological change and the launch of intelligent products. In this situation, technology cooperation activities through networks rather than independent technological innovation activities of a single company or institution are recognized as a crucial strategy to gain competitiveness. Technology cooperation can take various forms depending on the target technology, and researchers have conducted performance analyses of technology cooperation types. However, there have not been data-based quantitative studies on the types and trends of technology cooperation for the target technology. In this paper, we explored the difference between the technology cooperation types by technology and time using the formal concept analysis method and co-patent information. In particular, the proposed methodology has been verified through the case study of electric vehicles, and it is intended to suggest the direction of technological cooperation according to specific technologies and cooperation targets in the future

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.15-37
• /
• 2004

With the growth in the size of datasets, data mining has recently become an important research topic. Especially, interests about spatio-temporal data mining has been increased which is a method for analyzing massive spatio-temporal data collected from a wide variety of applications like GPS data, trajectory data of surveillance system and earth geographic data. In the former approaches, conventional clustering algorithms are applied as spatio-temporal data mining techniques without any modification. In this paper, we focused to SOM that is the most common clustering algorithm applied to clustering analysis in data mining wet and develop the spatio-temporal data mining module based on it. In addition, we analyzed the clustering results of developed SOM module and compare them with those of K-means and Agglomerative Hierarchical algorithm in the aspects of homogeneity, separation, separation, silhouette width and accuracy. We also developed specialized visualization module fur more accurate interpretation of mining result.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.187-196
• /
• 2000

A lot of Internet shopping malls strive for obtaining a competitive advantage over others in an increasingly tighter electronic marketplace. To this end, understanding customer preference toward products (or services) and administering appropriate marketing strategy is essential for their continuous survival. However, only a few marketing researchers and practicioners focused on this issue, compared with academic and industry efforts devoted to traditional market segmentation. In this paper, we suggest a methodology of conjoint segmentation for electronic shopping malls. Traditional market segmentation methodologies based on customer's profile sometimes fail to utilize abundant information given while navigating around cyber shopping malls. In this methodology, we do not impose information overload to the customer for preference elicitation, but this methodology, we do not impose information overload to the customer for preference elicitation, but capture automatically generated surfing or buying data and analyze them to get useful market segmentation information. The methodology consists of 4-stages: 1) analyzing legacy homepages, 2) data preparation, 3) estimating and interpreting the result, and 4) developing marketing mix. Our methodology was to give useful guidelines for market segmentation to companies working in the electronic marketplace.

• Journal of Multimedia Information System
• /
• v.5 no.1
• /
• pp.27-34
• /
• 2018

In recent years, with the blooming of Internet of Things (IoT) and Cloud Computing (CC), researchers have begun to discover new methods of technological support in all areas (e.g. health, transport, education, etc.). In this paper, in order to achieve a type of network that will provide more intelligent media-data transfer new technologies were studied. Additionally, we have been studied the use of various open source tools, such as CC analyzers and simulators. These tools are useful for studying the collection, the storage, the management, the processing, and the analysis of large volumes of data. The simulation platform which have been used for our research is CloudSim, which runs on Eclipse software. Thus, after measuring the network performance with CloudSim, we also use the Cooja emulator of the Contiki OS, with the aim to confirm and access more metrics and options. More specifically, we have implemented a network topology from a small section of the script of CloudSim with Cooja, so that we can test a single network segment. The results of our experimental procedure show that there are not duplicated packets received during the procedure. This research could be a start point for better and more efficient media data transmission.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.445-453
• /
• 2002

Past and current customer behavior is the best predicator of future customer behavior. This paper introduces a procedure on personalized defection detection and prevention for an online game site. The basic idea for our defection detection and prevention is adopted from the observation that potential defectors have a tendency to take a couple of months or weeks to gradually change their behavior (i.e. trim-out their usage volume) before their eventual withdrawal. For this purpose, we suggest a SOM (Self-Organizing Map) based procedure to determine the possible states of customer behavior from past behavior data. Based on this representation of the state of behavior, potential defectors are detected by comparing their monitored trajectories of behavior states with frequent and confident trajectories of past defectors. The key feature of this study includes a defection prevention procedure which recommends the desirable behavior state for the ext period so as to lower the likelihood of defection. The defection prevention procedure can be used to design a marketing campaign on an individual basis because it provides desirable behavior patterns for the next period. The experiments demonstrate that our approach is effective for defection prevention and efficient for defection detection because it predicts potential defectors without deterioration of prediction accuracy compared to that of the MLP (Multi-Layer Perceptron) neural network.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.495-498
• /
• 2005

The study is aimed at searching algorithm upgrading which can automatically compose goods displayed according to the degree of popularity regarding customer's requests, for the purpose of design of an intellectual shopping mall on the net and putting it into force by using classified technical Data-mining and statical analysis including personal information , entrance records and purchase records. This is for the study of strategic marketing. The system can automate the conventional shopping mall system by manual and personal judgements and also suggest a new formation of marketing techniques to strengthen the competition in B2B market which is steeply increasing.

• Genomics & Informatics
• /
• v.3 no.3
• /
• pp.68-73
• /
• 2005

Pharmacogenomics research requires an intelligent integration of large-scale genomic and clinical data with public and private knowledge resources. We developed a web-based knowledge base for KPRN (Korea Pharmacogenomics Research Network, http://kprn.snubi. org/). Four major types of information is integrated; genetic variation, drug information, disease information, and literature annotation. Eighteen Korean pharmacogenomics research groups in collaboration have submitted 859 genotype data sets for 91 disease-related genes. Integrative analysis and visualization of the large collection of data supported by integrated biomedical path­ways and ontology resources are provided with a user-friendly interface and visualization engine empowered by Generic Genome Browser.

• Journal of the Korean Society of Visualization
• /
• v.20 no.2
• /
• pp.78-85
• /
• 2022

In these days, the rapid development in prediction technology using artificial intelligent is being applied in a variety of engineering fields. Especially, dimensionality reduction technologies such as autoencoder and convolutional neural network have enabled the classification and regression of high-dimensional data. In particular, pixel level prediction technology enables semantic segmentation (fine-grained classification), or physical value prediction for each pixel such as depth or surface normal estimation. In this study, the pressure distribution of the ship's surface was estimated at the pixel level based on the artificial neural network. First, a potential flow analysis was performed on the hull form data generated by transforming the baseline hull form data to construct 429 datasets for learning. Thereafter, a neural network with a U-shape structure was configured to learn the pressure value at the node position of the pretreated hull form. As a result, for the hull form included in training set, it was confirmed that the neural network can make a good prediction for pressure distribution. But in case of container ship, which is not included and have different characteristics, the network couldn't give a reasonable result.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.200-215
• /
• 2023

With the rapid advance of autonomous driving technology, the related vehicle market is experiencing explosive growth, and it is anticipated that the era of fully autonomous vehicles will arrive in the near future. However, along with the development of autonomous driving technology, questions regarding its safety and reliability continue to be raised. Concerns among technology adopters are increasing due to media reports of accidents involving autonomous vehicles. To promote the improvement of the safety of autonomous vehicles, it is essential to analyze previous accident cases and identify their causes. Therefore, in this study, we aimed to analyze the factors influencing the severity of autonomous vehicle accidents using previous accident cases and related data. The data used for this research primarily comprised autonomous vehicle accident reports collected and distributed by the California Department of Motor Vehicles (CA DMV). Spatial information on accident locations and additional traffic data were also collected and utilized. Given that the primary data used in this study were accident reports, a Poisson regression analysis was conducted to model the expected number of accidents. The research results indicated that the severity of autonomous vehicle accidents increases in areas with low lighting, the presence of bicycle or bus-exclusive lanes, and a history of pedestrian and bicycle accidents. These findings are expected to serve as foundational data for the development of algorithms to enhance the safety of autonomous vehicles and promote the installation of related transportation infrastructure.