• Journal of Sensor Science and Technology
• /
• v.33 no.5
• /
• pp.248-254
• /
• 2024

Artificial intelligence techniques have improved fire-detection methods; however, false alarms still occur. Conventional methods detect fires using current sensors, which can lead to detection errors due to temporary environmental changes or noise. Thus, fire-detection methods must include a trend analysis of past information. We propose a deep-learning-based fire detection method using multi-sensor data and Kendall's tau. The proposed system used a BiLSTM model to predict fires using pre-processed multi-sensor data and extracted trend information. Kendall's tau indicates the trend of a time-series data as a score; therefore, it is easy to obtain a target pattern. The experimental results showed that the proposed system with trend values recorded an accuracy of 99.93% for BiLSTM and GRU models in a 20-tap moving average filter and 40% fire threshold. Thus, the proposed trend approach is more accurate than that of conventional approaches.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.315-318
• /
• 2015

in recently the world trend of security system for shipping transport is much more important and stronger, so following the world trend, there is development to security system of shipping transport for national security logistics system construction. it is still ongoing. For the world trend of security system, there is attempt of portable radiation detection, which is possible to get detection of nuclide in south Korea. in this Paper, it will shows about Full-digital system to portable radiation detection platform.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.6
• /
• pp.1436-1442
• /
• 2015

In recently the world trend of security system for shipping transport is much more important and stronger, so following the world trend, there is development to security system of shipping transport for national security logistics system construction. it is still ongoing. For the world trend of security system, there is attempt of portable radiation detection, which is possible to get detection of nuclide in south Korea.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.236-243
• /
• 2009

With advances in topic detection and tracking(TDT), automatic trend analysis from a collection of time-stamped documents, like patents, news papers, and blog pages, is a challenging research problem. Past research in this area has mainly focused on showing a trend line over time of a given concept by measuring the strength of trend-associated term frequency information. for detection of emerging trends, either a simple criterion such as frequency change was used, or an overall comparison was made against a training data. We note that in order to show most salient trends detected among many possibilities, it is critical to devise a ranking function. To this end, we define four properties(change, persistency, stability and volume) of trend lines drawn from frequency information, to quantify various aspects of trends, and propose a method by which trend lines can be ranked. The properties are examined individually and in combination in a series of experiments for their validity using the ranking algorithm. The results show that a judicious combination of the four properties is a better indicator for salient trends than any single criterion used in the past for ranking or detecting emerging trends.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.562-565
• /
• 2018

A wide range of IoT applications use information collected from networks of sensors for monitoring and controlling purposes. However, the frequent appearance of fault data makes it difficult to extract correct information, thereby sending incorrect commands to actuators that can threaten human privacy and safety. For this reason, it is necessary to have a mechanism to detect fault data collected from sensors. In this paper, we present a trend-adaptive multi-scale principal component analysis (Trend-adaptive MS-PCA) model for data fault detection. The proposed model inherits advantages of Discrete Wavelet Transform (DWT) in capturing time-frequency information and advantages of PCA in extracting correlation among sensors' data. Experimental results on a real dataset show the high effectiveness of the proposed model in data fault detection.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.507-517
• /
• 1997

As structures are higher, large-sized and more complex, we should detect the fire at the beginning and cope with it to reduce the loss of mankind and the physical damage due to fire. So we have investigated and developed various kinds of fire detection system, and do the efforts for minimizing the nonfire alarm. As there exists a close relationship between the technology development and the market potential, a comparison between the number of fires in special buildings and detection types were made to find out market potential based on the annual statistics on fire products inspection. In addition, we have discussed the causes of nonfire alarm and the fire detection system and prospect the research trend of the fire detection system.

• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.371-384
• /
• 2022

The fused LASSO signal approximator (FLSA) can be applied to find change points from the data having piecewise constant mean structure. It is well-known that the FLSA is inconsistent in change points detection. This inconsistency is due to a total-variation denoising penalty of the FLSA. ℓ₁ trend filter, one of the popular tools for finding an underlying trend from data, can be used to identify change points of piecewise linear trends. Since the ℓ₁ trend filter applies the sum of absolute values of slope differences, it can be inconsistent for change points recovery as the FLSA. However, there are few studies on the inconsistency of the ℓ₁ trend filtering. In this paper, we demonstrate the inconsistency of the ℓ₁ trend filtering with a numerical study.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.149-154
• /
• 2022

In recent years, the application of deep learning method to computer vision has shown to achieve great performances. Thus, many research projects have also applied deep learning technology to railroad defect detection. In this paper, we have reviewed the researches that applied computer vision based deep learning method to railroad defect detection and inspection, and have discussed the current trend and the direction of those researches. Many research projects were targeted to operate automatically without visual inspection of human and to work in real-time. Therefore, methods to speed up the computation were also investigated. The reduction of the number of learning parameters was considered important to improve computation efficiency. In addition to computation speed issue, the problem of annotation was also discussed in some research projects. To alleviate the problem of time consuming annotation, some kinds of automatic segmentation of the railroad defect or self-supervised methods have been suggested.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2002.05a
• /
• pp.1066-1070
• /
• 2002

We propose a neural network based up-trend detector. An auto-associative neural network was trained with 'up-trend' data obtained from the KOSPI 200 future price. It was then used to predict an up-trend Simple investment strategies based on the detector achieved a two year return of $19.8\%$ with no leverage.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.12 no.6
• /
• pp.1-6
• /
• 2008

This work proposes a fuzzy trend monitoring method for the fault detection of a gas turbine engine through analyzing measured performance data trend. The proposed trend monitoring technique can diagnose the engine status by monitoring major engine measured parameters such as fuel flow rate, exhaust gas temperature, rotor rotational speed and vibration, and then analyzing their time deppendent changes. In order to perform this, firstly the measured engine performance data variation is formulated using Linear Regression, and then faults are isolated and identified using fuzzy logic.