• Journal of KIISE:Software and Applications
• /
• v.36 no.7
• /
• pp.548-559
• /
• 2009

The cascade face detector learned by Adaboost algorithm, which was proposed by Viola and Jones, is state of the art face detector due to its great speed and accuracy. In spite of its great performance, it still suffers from false alarms, and more computation is required to reduce them. In this paper, we want to reduce false alarms with less computation using facial color. Using facial color information, proposed face detection model scans sub-window efficiently and adapts a fast face/non-face classifier at the first stage of cascade face detector. This makes face detection faster and reduces false alarms. For facial color filtering, we define a facial color membership function, and facial color filtering image is obtained using that. An integral image is calculated from facial color filtering image. Using this integral image, its density of subwindow could be obtained very fast. The proposed scanning method skips over sub-windows that do not contain possible faces based on this density. And the face/non-face classifier at the first stage of cascade detector rejects a non-face quickly. By experiment, we show that the proposed face detection model reduces false alarms and is faster than the original cascade face detector.

• Korean Journal of Remote Sensing
• /
• v.31 no.2
• /
• pp.111-125
• /
• 2015

In this study, the target detection using both high-resolution satellite SAR and Elecro-Optical (EO) images such as TerraSAR-X and WorldView-2 is performed, considering the characteristics of targets. The targets of our interest are featured by being stationary and appearing as cluster targets. After the target detection of SAR image by using Constant False Alarm Rate (CFAR) algorithm, a series of processes is performed in order to reduce false alarms, including pixel clustering, network clustering and coherence analysis. We extend further our algorithm by adopting the fast and effective ellipse detection in EO image using randomized hough transform, which is significantly reducing the number of false alarms. The performance of proposed algorithm has been tested and analyzed on TerraSAR-X SAR and WordView-2 EO images. As a result, the average false alarm for group of targets is 1.8 groups/$64km^2$ and the false alarms of single target range from 0.03 to 0.3 targets/$km^2$. The results show that groups of targets are successfully identified with very low false alarms.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2002.11a
• /
• pp.152-157
• /
• 2002

• Proceedings of the Korean Nuclear Society Conference
• /
• 2001.10a
• /
• pp.102.2-102
• /
• 2001

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.171-178
• /
• 2017

In this study, we propose an automated unit test generation technique for detecting vulnerabilities of Android kernel modules. The technique automatically generates unit test drivers/stubs and unit test inputs for each function of Android kernel modules by utilizing dynamic symbolic execution. To reduce false alarms caused by function pointers and missing pre-conditions of automated unit test generation technique, we develop false alarm reduction techniques that match function pointers by utilizing static analysis and generate pre-conditions by utilizing def-use analysis. We showed that the proposed technique could detect all existing vulnerabilities in the three modules of Android kernel 3.4. Also, the false alarm reduction techniques removed 44.9% of false alarms on average.

• Journal of Korean Academy of Nursing Administration
• /
• v.20 no.5
• /
• pp.535-544
• /
• 2014

Purpose: This study was done to develop a schematized alarm-managing manual for continuous renal replacement therapy (CRRT) and to investigate its effects in maintaining continuity in the patients' treatment and promptly resolving alarms when CRRT is being carried out. Methods: Sixtynurses from two medical intensive care units (ICUs) (one experimental and one control) at one hospital were asked to answer a questionnaire including their CRRT nursing competency and satisfaction with the manual. Data on alarm resolution rate were collected by analyzing existing data, such as the details of each alarm and the number of resolutions around the clock in the CRRT device. Results: The alarm resolution rate and some of CRRT nursing competency scores in the experimental group were higher than those in the control group. The experimental group was also satisfied with the manual. Conclusion: The study confirmed that the schematized alarm-managing manual can be useful for ICU nurses to resolve alarms and can be used as a guideline. Application of this manual to clinical practices and its use can therefore, be encouraged through continuous education and promotion.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1149-1151
• /
• 2003

We performed a validation study of the MODIS active fire detection algorithm using high resolution SPOT image as the reference data set. Fire with visible smoke plumes are detected in the SPOT scenes, while the hotspots in MODIS data are detected using NASA's new version 4 fire detection algorithm. The detection performance is characterized by the commission error rate (false alarms) and the omission error rate (undetected fires). In the Sumatra and Kalimantan study area, the commission rate and the omission rate are 27% and 34% respectively. False alarms are probably due to recently burnt areas with warm surfaces. False negative detection occur where there are long smoke plumes and where fires occur in densely vegetated areas.

• Nuclear Engineering and Technology
• /
• v.22 no.2
• /
• pp.128-138
• /
• 1990

This paper presents a prototype expert system (ESRCP) for Reactor Coolant Pumps. The purpose of this system is to diagnose RCP failures and to offer corrective operational guides to plant operators. The first symptoms for the diagnosis are the alarms which are related to the RCP domain. Alarm processing is required to find a primary causal alarm when multiple alarms occur. The system performs the alarm processing by rule-based deduction or priority factor operation. To diagnose the RCP failure, the system performs rule-based deduction or Bayesian inference. Various sensor readings are required as symptoms to infer a root cause. When the symptoms are insufficient or uncertain to diagnose accurately, Bayesian inference is performed.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.4
• /
• pp.92-99
• /
• 1997

This paper proposed a control method to improve the efficiency of monitoring method by applying the nural network for an alarm processing method(APM)in an elevator facility of apartment complex. This APM is based on the cumulative generalized delta rule of backpropagation in neural network.It was used to infer the minimum alarms among multi-fired alarms, and then the inferred alarm can be dis¬played maintenance information of facility by using a pre-defined troubleshoot knowledge base. For validating the proposed monitoring method of this thesis, simulation results are compared with the operation of existing monitoring system and the way of alarm processing. The simulation method used to the three case of virtual scenario. As comparison results, a proposed method in this paper could be proved the applied possibility of an neural network and the performance in fields of facilities maintenance.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.716-718
• /
• 2004

The false alarm data in intrusion detection systems are divided into false positive and false negative. The false positive makes bad effects on the performance of intrusion detection system. And the false negative makes bad effects on the efficiency of intrusion detection system. Recently, the most of works have been studied the data mining technique for analysis of alert data. However, the false alarm data not only increase data volume but also change patterns of alert data along the time line. Therefore, we need a tool that can analyze patterns that change characteristics when we look for new patterns. In this paper, we focus on the false positives and present a framework for analysis of false alarm pattern from the alert data. In this work, we also apply incremental data mining techniques to analyze patterns of false alarms among alert data that are incremental over the time. Finally, we achieved flexibility by using dynamic support threshold, because the volume of alert data as well as included false alarms increases irregular.