• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.745-753
• /
• 2021

Recently, a large fire occurred in a multi-use facility used by a large number of citizens, including the vulnerable, resulting in a lot of injuries and damages. Although several pilot studies have been conducted to reduce such incidents, the development of advanced disaster response technology using the latest spatial information and IoT technology is still insufficient. In this study, a pilot test bed is built to demonstrate detailed technologies derived through the first stage of realistic fire management technology research for the development of applied technology in the field. In detail, the building conditions and candidate sites of the test bed were first investigated and analyzed to derive satisfactory conditions and candidate target buildings. A second pilot test bed was then selected, and the necessary sensor and facility infrastructure were built to demonstrate the outcomes. Finally, a scenario was produced for technology verification, and a test bed system was developed. The pilot test bed is expected to contribute to verifying intermediate outcomes of realistic fire management research projects, enhancing the quality of the developed technologies.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.2
• /
• pp.121-129
• /
• 2015

This paper presents a multiple vehicle recognition algorithm based on radar and vision sensor fusion for lane change assistance. To determine whether the lane change is possible, it is necessary to recognize not only a primary vehicle which is located in-lane, but also other adjacent vehicles in the left and/or right lanes. With the given sensor configuration, two challenging problems are considered. One is that the guardrail detected by the front radar might be recognized as a left or right vehicle due to its genetic characteristics. This problem can be solved by a guardrail recognition algorithm based on motion and shape attributes. The other problem is that the recognition of rear vehicles in the left or right lanes might be wrong, especially on curved roads due to the low accuracy of the lateral position measured by rear radars, as well as due to a lack of knowledge of road curvature in the backward direction. In order to solve this problem, it is proposed that the road curvature measured by the front vision sensor is used to derive the road curvature toward the rear direction. Finally, the proposed algorithm for multiple vehicle recognition is validated via field test data on real roads.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.915-922
• /
• 2006

Recently, the requirements of the embedded software are getting diverse as the diversity of embedded software application fields increases. The systematic development methods are issued to deal with the dependency between hardware and software. However, the existing development methods have not considered the software's close connection to hardware and the high-level reusability for common requirements of several similar domains. In this paper, we propose a design method of development process model of product lines to support an efficient development method for embedded software. For this, we firstly suggest a domain scoping method and an IDEF0(Integration DEFinition)-based business model for extracting the efficient requirements. Next, we present a component deriving method based on the service architecture and an architecture design method after considering the hardware dependency. And we explain the artifacts of MSDFS(Multi Sensor Data Fusion System) at each design step in order to show how the proposed model can be applied to the embedded software development.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.483-490
• /
• 2019

Assessing the effect of forest fires and measuring the gas concentration around a fire has received little attention. Therefore, the concentrations of various gases in areas surrounding a fire need to be measured by the development of a suitable device. Unlike conventional portable devices, the AQS (Air Quality System) proposed in this paper is a portable instrument that measures five types of gases simultaneously, including CO, CO2, NOx, VOCs, and NH3, and has high durability through sensor protection algorithms. A PC-based program with an AQS connection was developed to monitor the real-time changes in the gas concentration. The reliability of the developed device was proven through a comparison of the results with other commercial gas analyzers. Measurements of the concentration due to indoor and outdoor fires were performed around a fire area to review the applicability and the predicted results were obtained.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.433-443
• /
• 2022

Purpose: In this paper, we propose a study of deep learning algorithms that estimate and predict sarcopenia by exploiting the high penetration rate of smart devices. Method: To utilize deep learning techniques, experimental data were collected by using the inertial sensor embedded in the smart device. We implemented a smart device application for data collection. The data are collected by labeling normal and abnormal gait and five states of running, falling and squat posture. Result: The accuracy was analyzed by comparative analysis of LSTM, CNN, and RNN models, and binary classification accuracy of 99.87% and multiple classification accuracy of 92.30% were obtained using the CNN-LSTM fusion algorithm. Conclusion: A study was conducted using a smart sensoring device, focusing on the fact that gait abnormalities occur for people with sarcopenia. It is expected that this study can contribute to strengthening the safety issues caused by sarcopenia.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.89-94
• /
• 2024

Since Ultra-Short BaseLine (USBL) uses an array with narrow sensor spacing, precise synchronization is required to improve source localization performances. However, in the underwater environment, synchronization errors occur due to relatively strong noise and underwater acoustic channels such as multipath and Doppler, which deteriorates the source localization performances. This paper proposes a covariance-based synchronization compensation method to improve the source localization performances of the underwater USBL systems. The proposed method arranges the received signals through cross-correlation and calculates the covariance of the arranged signals. The synchronization error is related to the phase difference in the covariance. Thus, the phase difference is estimated as the covariance and compensated. Computer simulations demonstrate that the proposed method has better source localization performances than the conventional cross-correlation method.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.4
• /
• pp.1-11
• /
• 2019

With the development of remote sensing sensor technology, it has become possible to acquire satellite images with various spectral information. In particular, since the hyperspectral image is composed of continuous and narrow spectral wavelength, it can be effectively used in various fields such as land cover classification, target detection, and environment monitoring. Change detection techniques using remote sensing data are generally performed through differences of data with same dimensions. Therefore, it has a disadvantage that it is difficult to apply to heterogeneous sensors having different dimensions. In this study, we have developed a change detection method applicable to hyperspectral image and high spat ial resolution satellite image with different dimensions, and confirmed the applicability of the change detection method between heterogeneous images. For the application of the change detection method, the dimension of hyperspectral image was reduced by using correlation analysis and principal component analysis, and the change detection algorithm used CVA. The ROC curve and the AUC were calculated using the reference data for the evaluation of change detection performance. Experimental results show that the change detection performance is higher when using the image generated by adequate dimensionality reduction than the case using the original hyperspectral image.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Journal of the Korean Institute of Gas
• /
• v.25 no.3
• /
• pp.27-38
• /
• 2021

We devised the system to automatically shutdown the boiler and to fundamentally block the harmful gases, including carbon monoxide, into the indoor when the exhaust system swerves: (1) The discharge pressure of the exhaust gas decreases when the exhaust pipe is disconnected. The monitoring system of the exhaust pipe is implemented by measuring the output voltage of APS(Air Pressure Sensor) installed to control the amount of combustion air. (2) The operating software was modified so that when the system recognizes the fault condition of a flue pipe, the boiler control unit displays the fault status on the indoor regulator while shutting down the boiler. In accordance with the ventilation facility standards in the "Rules for Building Equipment Standards" by the Ministry of Land, Infrastructure and Transport, experiments were conducted to ventilate indoor air. When carbon monoxide leaked in worst-case scenario, it was possible to prevent poisoning accidents. However, since 2013, the number of indoor air exchange times has been mitigated from 0.7 to 0.5 times per hour. We observed the concentration exceeding TWA 30 ppm occasionally and thus recommend to reinforce this criterion. In conclusion, if the flue pipe fault detection and the indoor air ventilation system are introduced, carbon monoxide poisoning accidents are expected to decrease significantly. Also when the manufacturing and inspection steps, the correct installation and repair are supplemented with the user's attention in missing flue, it will be served to prevent human casualties from carbon monoxide poisoning.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.754-761
• /
• 2008

As the automobile industry and technologies are developed, driver's tend to more concern about service matters than mechanical matters. For this reason, interests about recognition of human knowledge and emotion to make safe and convenient driving environment for driver are increasing more and more. recognition of human knowledge and emotion are emotion engineering technology which has been studied since the late 1980s to provide people with human-friendly services. Emotion engineering technology analyzes people's emotion through their faces, voices and gestures, so if we use this technology for automobile, we can supply drivels with various kinds of service for each driver's situation and help them drive safely. Furthermore, we can prevent accidents which are caused by careless driving or dozing off while driving by recognizing driver's gestures. the purpose of this paper is to develop a system which can recognize states of driver's emotion and attention for safe driving. First of all, we detect a signals of driver's emotion by using bio-motion signals, sleepiness and attention, and then we build several types of databases. by analyzing this databases, we find some special features about drivers' emotion, sleepiness and attention, and fuse the results through Multi-Modal method so that it is possible to develop the system.