• Fire Science and Engineering
• /
• v.11 no.2
• /
• pp.25-33
• /
• 1997

Fire hazards in an apartment building that represents the average households in Korean were investigated by conducting a full-scale experiment. This experiment attempts to analyze fire hazards using materials, and furnishings common to Korean housing stock. Experimental results are compared to the predictions of the C-FAST and smoke transport computer model. Comparisons between experimental data and C-FAST data are performed only to a living-room fire. Flashover occurred at approximately 380 seconds in a fire experinent, and at approximately 420 seconds in Zone-Model. Based on all of data between experimental data between experimental data and Zone-Model data, it is concluded that the safe egress time is at least 250 seconds.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3989-4006
• /
• 2020

The intelligent agriculture monitoring is based on the perception and analysis of environmental data, which enables the monitoring of the production environment and the control of environmental regulation equipment. As the scale of the application continues to expand, a large amount of data will be generated from the perception layer and uploaded to the cloud service, which will bring challenges of insufficient bandwidth and processing capacity. A fog-based offline and real-time hybrid data analysis architecture was proposed in this paper, which combines offline and real-time analysis to enable real-time data processing on resource-constrained IoT devices. Furthermore, we propose a data process-ing algorithm based on the incremental principal component analysis, which can achieve data dimensionality reduction and update of principal components. We also introduce the concept of Squared Prediction Error (SPE) value and realize the abnormal detection of data through the combination of SPE value and data fusion algorithm. To ensure the accuracy and effectiveness of the algorithm, we design a regular-SPE hybrid model update strategy, which enables the principal component to be updated on demand when data anomalies are found. In addition, this strategy can significantly reduce resource consumption growth due to the data analysis architectures. Practical datasets-based simulations have confirmed that the proposed algorithm can perform data fusion and exception processing in real-time on resource-constrained devices; Our model update strategy can reduce the overall system resource consumption while ensuring the accuracy of the algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.2
• /
• pp.152-159
• /
• 2005

This paper describes the application of a model-based system design method critical to complex intelligent systems, PSARE, to a welding robot development to define its top level architecture. The PSARE model consists of requirement model which describes the core processes(function) of the system, enhanced requirement model which adds technology specific processes to requirement model and allocates them to architecture model, and architecture model which describes the structure and interfaces and flows of the modules of the system. This paper focuses on the detailed procedure and method rather than the detailed domain model of the welding robot. In this study, only the top level architecture of a welding robot was defined using the PSARE method. However, the method can be repeatedly applied to the lower level architecture of the robot until the process which the robot should perform can be clearly defined. The enhanced data flow diagram in this model separates technology independent processes and technology specific processes. This approach will provide a useful base not only for improvement of a class of welding robots but also for development of increasingly complex intelligent real-time systems.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.369-374
• /
• 2022

Purpose: Focused ultrasound is an emerging technology for treating the brain locally in a noninvasive manner. In this study, we have investigated the influence of skull properties on simulating transcranial pressure field. Methods: A 3D computational model of transcranial focused ultrasound was constructed using female and male CT data to solve for intracranial pressure. For heterogeneous model, the acoustic properties were calculated from CT Hounsfield units based on a porosity. The homogeneous model assigned constant acoustic properties for the single-layered skull. Results: A computational model was validated against empirical data. The homogeneous models were then compared with the heterogeneous model, resulted in 10.87% and 7.19% differences in peak pressure for female and male models respectively. For the focal volume, homogeneous model demonstrated more than 94% overlap compared with the heterogeneous model. Conclusion: Homogeneous model can be constructed using MR images that are commonly used for the segmentation of the skull. We propose the possibility of the homogeneous model for the simulating transcranial pressure field owing to comparable focal volume between homogeneous model and heterogeneous model.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.324-329
• /
• 2009

Hand Motion Modeling and Recognition (HMR) are a fundamental technology in the field of proactive computing for designing a human computer interaction system. In this paper, we present a 3D HMR system including data glove based on 3-axis accelerometer sensor and 3D Hand Modeling. Data glove as a device is capable of transmitting the motion signal to PC through wireless communication. We have implemented a 3D hand model using kinematic chain theory. We finally utilized the rule based algorithm to recognize hand gestures namely, scissor, rock and papers using the 3-D hand model.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.1-11
• /
• 2023

Federated learning (FL) is a ground breaking machine learning paradigm that allow smultiple participants to collaboratively train models in a cloud environment, all while maintaining the privacy of their raw data. This approach is in valuable in applications involving sensitive or geographically distributed data. However, one of the challenges in FL is dealing with heterogeneous and non-independent and identically distributed (non-IID) data across participants, which can result in suboptimal model performance compared to traditionalmachine learning methods. To tackle this, we introduce FedGCD, a novel FL algorithm that employs Graph Neural Network (GNN)-based community detection to enhance model convergence in federated settings. In our experiments, FedGCD consistently outperformed existing FL algorithms in various scenarios: for instance, in a non-IID environment, it achieved an accuracy of 0.9113, a precision of 0.8798,and an F1-Score of 0.8972. In a semi-IID setting, it demonstrated the highest accuracy at 0.9315 and an impressive F1-Score of 0.9312. We also introduce a new metric, nonIIDness, to quantitatively measure the degree of data heterogeneity. Our results indicate that FedGCD not only addresses the challenges of data heterogeneity and non-IIDness but also sets new benchmarks for FL algorithms. The community detection approach adopted in FedGCD has broader implications, suggesting that it could be adapted for other distributed machine learning scenarios, thereby improving model performance and convergence across a range of applications.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.9-16
• /
• 2023

In the recommendation system of the credit card company, it is necessary to understand the customer patterns to predict a customer's next merchant based on their histories. The data we want to model is much more complex and there are various patterns that customers choose. In such a situation, it is necessary to use an effective model that not only shows the relevance of the merchants, but also the relevance of the customers relative to these merchants. The proposed model aims to predict the next merchant for the customer. To improve prediction performance, we propose a novel model, called Customer-based Recommendation Model (CRM), to produce a more efficient representation of customers. For the next merchant recommendation system, we use a synthetic credit card usage dataset, BC'17. To demonstrate the applicability of the proposed model, we also apply it to the next item recommendation with another real-world transaction dataset, IJCAI'16.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.75-80
• /
• 2018

In this paper, we propose heterogeneous lifelog mining model in health big-data platform. It is an ontology-based mining model for collecting user's lifelog in real-time and providing healthcare services. The proposed method distributes heterogeneous lifelog data and processes it in real time in a cloud computing environment. The knowledge base is reconstructed by an upper ontology method suitable for the environment constructed based on the heterogeneous ontology. The restructured knowledge base generates inference rules using Jena 4.0 inference engines, and provides real-time healthcare services by rule-based inference methods. Lifelog mining constructs an analysis of hidden relationships and a predictive model for time-series bio-signal. This enables real-time healthcare services that realize preventive health services to detect changes in the users' bio-signal by exploring negative or positive correlations that are not included in the relationships or inference rules. The performance evaluation shows that the proposed heterogeneous lifelog mining model method is superior to other models with an accuracy of 0.734, a precision of 0.752.

• Journal of Wetlands Research
• /
• v.19 no.1
• /
• pp.132-143
• /
• 2017

It is essential to obtain periodic sediment discharge data in a river in order to minimize problems that may arise from the erosion, transport, and deposition of sediment. However, it is difficult to estimate sediment discharge by the sediment discharge measurement plan in Korea at present, and empirical fomulas or numerical models are used to replace them. This paper has applied the K-DRUM model, a grid-based rainfall-runoff-sediment model, to estimate sediment discharge and ensure the continuity of the data in the watershed. Discharge and sediment load in 17 watersheds were estimated and the applicability of the model was analyzed through comparisons with measured data. For quantitative evaluation, NSE, PBIAS and RSR items were used, and discharge results reflected the tendency of rainfall and showed high statistical value. In case of sediment discharge, the soil erosion process of the watershed is physically well reflected. When the calibration was performed using the measure data, the applicability seems to be excellent in estimating the continuous sediment discharge data in the real watershed.