• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.190-199
• /
• 2014

In this paper, the vestibular hair bundle feature model and integrated vestibular hair cell model were proposed. In conventional modeling studies of vestibular system, only partial mechanisms were modeled, such as the characteristics of the vestibular hair bundles without external forces or the action potential of synapse, and the study about action potential of vestibular afferent considering the characteristics of the vestibular hair bundle was not performed. The proposed integrated vestibular hair cell model reflects external forces considering negative stiffness features of each hair bundles with different regularities of hair cells and our model was compared with conventional model without external forces. As a result, irregular afferent and intermediate afferent with high ratio of firing frequency variations to the changes of external stimulation had small width of negative stiffness section, but the width of the negative stiffness of regular afferent with low ratio was similar to that of conventional negative stiffness features. And the proposed integrated vestibular hair cell model showed almost same results with conventional data with animal experiments in 11 chosen frequency bands. It is verified that our proposed hair bundle feature model is adequately modeled.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• IE interfaces
• /
• v.18 no.1
• /
• pp.1-9
• /
• 2005

A new logistics concept is needed through the sharing information between suppliers and consumers, which maximizes the customers service and its flexibility by changing functional- oriented to process-oriented. As in many other industries, communication and data manipulation technology have led to systematical change to the logistics industry. One of the biggest changes of the industry that lies ahead is Consolidated Transportation. To improve this systematically false logistical environment, developing an integrated logistics information system with consolidated transportation, framework, standardization, and data integration is essential. However, no party outstands as the leading party for nationwide improvement of logistics, nor does the right analysis and design for it. Therefore, successful nationwide logistics model is yet to exist. This paper provides individual parties, which consider efficient consolidated transportation as their business models, with instructions for logistics information system so that they could be competitive in the market. It also helps companies collect user requirements for efficient consolidated transportation, and utilize it for its development. Finally, this paper extracts the design of algorithm for the efficient consolidated transportation.

• The Journal of Korean Association of Computer Education
• /
• v.10 no.2
• /
• pp.101-113
• /
• 2007

In this paper, we present an object-based modeling and language for an object-oriented spatio-temporal database system. For handling the structure of spatio-temporal objects and the spatio-temporal operators, we propose the two layers of data modeling: a spatio-temporal object model (STOM) and an spatio_temporal internal description model (STIM). We then propose STOQL, a spatio-temporal object-oriented query language. STOQL provides an integrated mechanism for the graphical display of spatial objects and the retrieval of spatio-temporal and aspatial objects.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.410-415
• /
• 2005

Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits at a wide range of scales - Self-similarity. Self-similarity is expressed by long term dependency, this is contradictory concept with Poisson model that have relativity short term dependency. Therefore, first of all for design and dimensioning of next generation communication network, traffic model that are reflected burstness and self-similarity is required. Here self-similarity can be characterized by Hurst parameter. In this paper, when different many data traffic being integrated under various environments is arrived to communication network, Hurst Parameter's change is analyzed and compared with simulation results.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2005.04a
• /
• pp.316-319
• /
• 2005

Contaminated area should be identified for designing polluted groundwater cleanup plan. A methodology was suggested to identify a contaminant plume distribution geostatistically. James & Gorelick (1994) suggested a methodology to evaluate data worth as expected reducing remediation cost. In this study, their methodology was modified to evaluate data worth as expected reducing uncertainty of the contaminant plume distribution. In suggested methodology, the source identification model by Mahar & Datta (2001) using a forward solute transport model is integrated. Suggested methodology was assessed by two simple example problems and its result represented reducing uncertainties of contaminant plume distribution successfully.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.233-244
• /
• 2016

Smart grid is called it as a system of systems. There are diverse types of systems in smart grid environment. Therefore, one of key factors to achieve smart grid successfully is interoperability among diverse systems. To secure interoperability, smart grid operating system should be developed complied with standards in terms of the data representation and communication. Common Information Model (CIM) and OLE Process for Control - Unified Architecture (OPC-UA) are the representative international standards in smart grid domain. Each standard defines data representation and communication by providing common information model and the unified architecture. In this paper, we explain a smart grid platform that we have developed to comply with CIM and OPC-UA standards for secure interoperability among numerous legacy systems.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.285-295
• /
• 2004

Statistical process control(SPC) and engineering process control(EPC) are two complementary strategies for quality improvement. An integrated process control(IPC) can use EPC to reduce the effect of predictable quality variations and SPC to monitor the process for detection of special causes. In this paper we assume an IMA(1,1) model as a disturbance process and an occurrence of a level shift in the process, and we consider the economic performance for applying an EWMA chart to monitor MMSE-controlled processes. The numerical results suggest that the IPC scheme in an IMA(1,1) disturbance model does not give additional advantages in the economic aspect.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.904-915
• /
• 2018

We demonstrate how social media content can be used to predict the unemployment rate, a real-world indicator. We present a novel method for predicting the unemployment rate using social media analysis based on natural language processing and statistical modeling. The system collects social media contents including news articles, blogs, and tweets written in Korean, and then extracts data for modeling using part-of-speech tagging and sentiment analysis techniques. The autoregressive integrated moving average with exogenous variables (ARIMAX) and autoregressive with exogenous variables (ARX) models for unemployment rate prediction are fit using the analyzed data. The proposed method quantifies the social moods expressed in social media contents, whereas the existing methods simply present social tendencies. Our model derived a 27.9% improvement in error reduction compared to a Google Index-based model in the mean absolute percentage error metric.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.44 no.2
• /
• pp.148-160
• /
• 2002

Lake water quality assessment information is useful to anyone involved in lake management, from lakeshore owners to lake associations. 11 provides lake water quality, which can improve how to manage lake resources and how to measure current conditions. It also provides a knowledge base that can be used to protect and restore lakes. SWMM was applied to simulate the discharge and pollutant loads from Boryeong watershed, and WASP5 was applied to analyze the changes of water quality in Boryeong freshwater lake. In each model, the most suitable parameters were calculated through sensitive analysis and some parameters used default data. Simulated in SWMM and measured discharge showed the accuracy of 88.6%. T-N and T-P exceeds the criteria in the simulation of water quality in Boryeong freshwater lake, and control of pollutant loads in the main stream showed the most effective way. Integrated water quality management system was developed to give convenience in the operation of SWMM and WASP5 and data acquisition.