• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.255-258
• /
• 2022

As environmental pollution continues, attention on renewable energy is on the constant rise in recent days. Although various kinds of renewable energy such as solar, wind power and biomass energy have been generated in Jeju, opening and analyzing cases on related data seem insufficient. Therefore, this study is being conducted to deduce the variables which have high relation with solar panel&s output and to understand machine learning methods that can be applied to solar power generation data by utilizing Kaggle platform, which is actively used by a number of scientists. Then, it is planned to propose a form of solar power generation dataset by researching machine learning methods that could be applied to the data. To be specific, analyzing solar power generation data with the Kaggle platform, this study will provide complements on gathering solar power data in Jeju. This study is anticipated to be utilized on data analysis for developing the solar power industry in Jeju. That is, this study is expected to reveal the room for improvement inherent in existing open datasets in Jeju, so that they could be constructed in a suitable form for machine learning for AI analytics. Through this process, a method to increase efficiency of solar power generation is anticipated to be prepared.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.9
• /
• pp.1373-1384
• /
• 1997

There have been a number of expert systems which are concerned with the design of machine elements such as gear, shaft, bearing and so on. However the design of more complicated systems such as gear dreives are still difficult. Thus, in consideration of the integrative nature of the system, we develop a design support system for gear drives which is composed of various machine elements-gear, shaft, bearing, key and so on. Design systems for each machine element are developed and integrated through object-oriented approach. Databases essential for data reference and/or data control in the design process are built up independently and interface to the main program. Expert systems are also developed and integrated for intelligent support to the designer, in those of the determination of gear specification and the selection of bearing types. Through the integration of design environment for each machine element, it is expected to increase the convenience in the design process and the stability of the design solution. And also the system management, including addition of various design/analysis modules and expansion to the gear drives of other types, can be conveniently achieved since the system has developed under due consideration of its efficiency and expandability through object-oriented programming approach.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.3
• /
• pp.127-143
• /
• 2016

This study explored the variability in the accuracy of dasymetric population estimation with different grid cell sizes. Dasymetric population maps for Fulton County, Georgia in the US were generated from 30m to 420m at intervals of 30m using an automated intelligent dasymetric mapping technique, population data, and original and simulated land use and cover data. The accuracies of dasymetric population maps were evaluated using RMSE and adjusted RMSE statistics. Lumped fractal dimension values were calculated for the dasymetric population maps generated from resolutions of 30m to 420m using the triangular prism surface area (TPSA) method. The results show that a grid cell size of 210m or smaller is required to estimate population more accurately in terms of thematic accuracy, but a grid cell size of 30m is required to meet an acceptable spatial accuracy of dasymetric population estimation in the study area. The fractal analysis also indicates that a grid cell size of 120m is the optimal resolution for dasymetric population estimation in the study area.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.35-49
• /
• 2009

In electronic warfare settings, battlefield helicopters identify various threats based upon threat data, which are acquired using their multi-sensors of aircraft survivability equipment (ASE). To continually function despite of potential threats and successfully execute their missions, the battlefield helicopters have to repeatedly report threats in simulated battlefield situations. Toward this ends, the paper presents threat unification using multi-sensor simulator and its implementation. The simulator consists of (1) threat attributes generator, which models threats against battlefield helicopters and defines their specific attributes, (2) threat data generator, which generates threats, being similar to real ones, using normal, uniform, and exponential distributions, and (3) graphic display for threat analysis and unification, which shows unified threat information, for example, threat angle and its level. We implement a multi-sensor threat simulator that can be repeatedly operable in various simulated battlefield settings. Further, we report experimental results that, in addition to tangibly modeling the threats to battlefield helicopters, test the capabilities of threat unification using our simulator.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.5
• /
• pp.761-770
• /
• 2004

The multicarrier direct sequence code-division (MC-DS/CDMA) is a well-known multiple access and data transmission scheme that is applicable for various mobile and wireless communications. Particularly for modern, smart vehicles equipped with multiple sensors, MC-DS/CDMA is one of the possible means for giving the sensors to get connected one another for sending and receiving messages and control information. For intra-vehicalur communicaiton and networking applications, we have proposed a novel MC-DS/CDMA multiple access and data transmission scheme incorporating a new idea of inserting sub-symbol based cyclic prefixes for compromising inter-symbol interference. In the performance investigation of our MC-DS/CDMA, we have looked into system performances related to bandwidth utiltzation, coding gain, and multiple number of sensors. Since the channel delay is comparatively shorter inside of vehicle than any other general mobile channels, the proposed scheme can be a successful candidate for networking wireless sensors simultaneously operting in an intelligent vehicle.

• Journal of Internet of Things and Convergence
• /
• v.5 no.2
• /
• pp.73-79
• /
• 2019

Research is underway on services and systems that provide real-time alerts for suffocating gases and potentially explosive materials, but currently smart bend type services are lacking. This study supports real-time identification of explosion hazards due to static electricity in the workplace and immediate elimination of accident occurrence factors, real-time monitoring of worker status and workplace hazards (oxygen, hazardous chemical concentration), and immediate warning and data in case of danger. We propose a method of establishing an accident prevention system through analysis. In this way, various accidents that may occur in industrial sites are monitored using IoT-based intelligent sensor nodes, wireless network technology, data processing middleware, and integrated control system, and real-time risk information at the industrial sites is prevented and accidents are prevented. By supporting a safe working environment, the company can significantly reduce costs compared to post-procurement costs.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2013

This study examined that how precisely MFCC, LPC, energy, and pitch related parameters of the speech data, which have been used mainly for voice recognition system could predict the vocal emotion categories as well as dimensions of vocal emotion. 110 college students participated in this experiment. For more realistic emotional response, we used well defined emotion-inducing stimuli. This study analyzed the relationship between the parameters of MFCC, LPC, energy, and pitch of the speech data and four emotional dimensions (valence, arousal, intensity, and potency). Because dimensional approach is more useful for realistic emotion classification. It results in the best vocal cue parameters for predicting each of dimensions by stepwise multiple regression analysis. Emotion categorizing accuracy analyzed by LDA is 62.7%, and four dimension regression models are statistically significant, p<.001. Consequently, this result showed the possibility that the parameters could also be applied to spontaneous vocal emotion recognition.

• Information and Communications Magazine
• /
• v.11 no.6
• /
• pp.37-54
• /
• 1994

Technical innovation on multimedia data processing brings us new multimedia services. Multimedia services are classified into five groups : TVs, computers, telecommunications, periperals, and softwares. This paper surveys on the services in various aspects and, in particular, computer areas are discussed in detail. To provide the services, major subsystems such as highspeed networks, operating systems, intelligent agent based user interfaces are discussed. In particular, multimedia operating systems are the most actively investigating research area as an infrastructure of multimedia computer systems to provide integrated multimedia services. So, the trends of new multimedia operating systems are analyzed and COSMOS (Collaborative Object Sharing for Multimedia Operating System) multimedia group presentation is discussed. The characteristics, model and abstract data structure of COSMOS is described. The performance analysis of 3 person conference system using audio, video and shared graphic editor on COSMOS shows that taking integrated multimedia operating system approach leads changing of new multimedia service environments.

• Journal of Convergence for Information Technology
• /
• v.10 no.1
• /
• pp.139-148
• /
• 2020

As the internet and computer technology are developed, there is a need for service of traditional culture that can effectively search and create culture, history, and tradition-related materials in online contents. In this paper, we developed an RDF-based ontology retrieval service platform and verified usability and validity. This platform is divided into triple search, keyword search, network graph search, story search and management, curation management module. Based on this, the search results can be visualized based on the relationship between data, network graph search and story search can be used to easily understand the relationship between the keywords. An platform evaluation was conducted for verification, and it was evaluated that an intelligent search that can easily identify the relationship between information and shorten the analysis and search time than the existing search function.