• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.173-178
• /
• 2007

Recently, fires happen to occur owing to various factors. However, the demage caused by the fire is eyer increasing because timely actions could not be taken. To reduce the demage, a development of fire detection system which makes it possible to take adequate actions is requited. In this work, a sensor network-based fire detection system which utilizes both sensor nodes equipped with smoke sensor and unmaned helicopter is proposed. The proposed system is composed of unmaned helicopter which can gather the measurement data from the deployed sensor nodes and the embedded system which can get visual information on the firing spot and transmit these images to a remote server computer. The proposed system is applied to actual test bed to verify its feasibility.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.153-159
• /
• 2014

In this paper, we propose the Distributed Power Saving Control System that enables the active and intelligent control(on/off and/or dimming control) of the lightning device using sensors and mobile agents. The proposed system is effective for energy saving and induces cost reductions in design and development of power saving control system as adding remote-monitoring or controlling functions is easier with the application of a variety of active rules. Moreover, the system improves the effectiveness of the acquired sensing data by real-time event handling and device controlling using a mobile agent based sensor network middleware that regularize the contextual information or a user's emotion. The results of this paper present the potential applicability of the proposed distributed control system using mobile agent in various active sensor network applications.

• Steel and Composite Structures
• /
• v.29 no.6
• /
• pp.703-716
• /
• 2018

Rapid detection of damages in civil engineering structures, in order to assess their possible disorders and as a result produce competent decision making, are crucial to ensure their health and ultimately enhance the level of public safety. In traditional intelligent health monitoring methods, the features are manually extracted depending on prior knowledge and diagnostic expertise. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed here for intelligent health monitoring of civil engineering structures. In the first stage, $Nystr{\ddot{o}}m$ method is used for automatic feature extraction from structural vibration signals. In the second stage, Moving Kernel Principal Component Analysis (MKPCA) is employed to classify the health conditions based on the extracted features. In this paper, KPCA has been implemented in a new form as Moving KPCA for effectively segmenting large data and for determining the changes, as data are continuously collected. Numerical results revealed that the proposed health monitoring system has a satisfactory performance for detecting the damage scenarios of a three-story frame aluminum structure. Furthermore, the enhanced version of KPCA methods exhibited a significant improvement in sensitivity, accuracy, and effectiveness over conventional methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12B
• /
• pp.1670-1679
• /
• 2011

In the area of wireless sensor networks, sensor coverage and network connectivity problems are caused by a limited detection range and the communication distance of the nodes. To solve the coverage and connectivity problems, many studies are suggested, but most research is restricted to apply into the real environment because they didn't consider various environmental factors on wireless sensor network deployment. So in this paper, we propose a node deployment strategy considering environmental factors and the number of nodes in surveillance and reconnaissance sensor networks(SRSN). The proposed node deployment method divides the installation of the surveillance and reconnaissance sensor networks system into four steps such as identification of influences factors for node placement through IPB process, sensor node deployment based on sensing range, selection of monitoring site, and relay node deployment based on RF communication range. And it deploys the sensor nodes and relay nodes considered the features of the surveillance and reconnaissance sensor network system and environmental factors. The result of simulation indicates that the proposed node deployment method improves sensor coverage and network connectivity.

• Journal of Soil and Groundwater Environment
• /
• v.21 no.4
• /
• pp.30-41
• /
• 2016

The amount of groundwater related data is drastically increasing domestically from various sources since 2000. To justify the more expansive continuation of the data acquisition and to derive valuable implications from the data, continued employments of sophisticated and state-of-the-arts statistical tools in the analyses and predictions are important issue. In the present study, we employed a well established machine learning technique of Gaussian Process Regression (GPR) model in the trend analyses of groundwater level for the long-term change. The major benefit of GPR model is that the model provide not only the future predictions but also the associated uncertainty. In the study, the long-term predictions of groundwater level from the stations of National Groundwater Monitoring Network located within Han River Basin were exemplified as prediction cases based on the GPR model. In addition, a few types of groundwater change patterns were delineated (i.e., increasing, decreasing, and no trend) on the basis of the statistics acquired from GPR analyses. From the study, it was found that the majority of the monitoring stations has decreasing trend while small portion shows increasing or no trend. To further analyze the causes of the trend, the corresponding precipitation data were jointly analyzed by the same method (i.e., GPR). Based on the analyses, the major cause of decreasing trend of groundwater level is attributed to reduction of precipitation rate whereas a few of the stations show weak relationship between the pattern of groundwater level changes and precipitation.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.379-392
• /
• 2023

Structural health monitoring is used to ensure the well-being of civil structures by detecting damage and estimating deterioration. Wind flow applies external loads to high-rise buildings, with the horizontal force component of the wind causing structural displacements in high-rise buildings. This study proposes a deep learning-based predictive model for measuring lateral displacement response in high-rise buildings. The proposed long short-term memory model functions as a sequence generator to generate displacements on building floors depending on the displacement statistics collected on the top floor. The model was trained with wind-induced displacement data for the top floor of a high-rise building as input. The outcomes demonstrate that the model can forecast wind-induced displacement on the remaining floors of a building. Further, displacement was predicted for each floor of the high-rise buildings at wind flow angles of 0° and 45°. The proposed model accurately predicted a high-rise building model's story drift and lateral displacement. The outcomes of this proposed work are anticipated to serve as a guide for assessing the overall lateral displacement of high-rise buildings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.4
• /
• pp.1751-1767
• /
• 2016

Home security has become the prime concern for everyone in present scenario. In this work an attempt has been made to develop a home security system which is accessible, affordable and yet effective.The proposed system is based on 'Remote Embedded Control System' (RECS) which works both on the web and gsm platform for authentication and monitoring. This system is therefore cost effective as it relies on existing network infrastructure. As PCA is most popular and efficient algorithm for face recognition, it has been usedin this work. Next to it an interface has been developed for communication purpose in the embedded security system through the ZigBee module. Based on this embedded system, automated control of door movement has been implemented through electromagnetic door lock technology. This helps the users to monitor the real-time activities through web services/SMS. The web service consists of either web browser command or e-mail provision. The system establishes the communication between the system and authenticated user. The e-mail received by the system from the authorized person will monitor and control the real-time operation and door lock. The entire control system is reinforced using ARM1176JZF-S microcontroller and tested for actual use in the home environment. The result shows the experimental verification of the proposed system.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.181-187
• /
• 2011

Since 2003, state transportation study core technology development is being promoted as part of the bimodal trams operating in accordance with the development of refractive vehicle as research infrastructure for building high-tech road transport system has been the research and development. Bimodal trams of refraction as the vehicle for him to introduce domestic first ever operation management system also developed in Korea according to case-based technology system, but most of the country, and, in this study, mainly those based on technology integration building management system and the bimodal trams of refraction of a vehicle operated was to highlight the features and benefits. Bimodal tram station itself is the way the exclusive properties and to operate the route with large transport capacity has the characteristics of the railway, but the only routes such as railroad lines is not of closed roads under certain circumstances, the flexibility to use has to be integrated operations management system of bimodal trams characteristics of the railroads and public transportation by combining the characteristics of a flexible, convenient and secure services to users with the aim of providing research and will denote the system developed. In this study, bimodal integration system required for the operation of the tram station around the wired and wireless network management center, applying the organic integration into one system so that you have to be centrally managed. In addition, the existing traffic management system operates as a unidirectional rather than monitoring all system-wide management via the interactive network through real-time requests and responses were configured to allow management and control. These findings of the existing traffic operation management system that you can jump step can be based on future unmanned vehicles and related systems through control of the operation management system will be offered as a basis.

• Journal of Digital Contents Society
• /
• v.15 no.2
• /
• pp.219-225
• /
• 2014

Competition between corporations is getting more intense, so they need customer feedback in order to fulfill an effective management. Recently, SNS (Social Network Service) such as Twitter and Facebook has grown dramatically because of smart phones. Social media like Twitter and Facebook let customers to express their needs, and using big data such as data on SNS is a very effective method for getting customer's feedback. Collecting and analyzing social big data are operated by Buzz monitoring system. This research suggests how to utilize big data for getting customer's feedback on hotel CRM(Customer Relationship Management), which considers customer itself as asset of business. This paper demonstrates the research of buzz monitoring system that analyzes big data, and presents results of hotel customer reputation using buzz monitoring system. It would analyze the result from the hotel customer reputation, and research the implication in this paper.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.