• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.357-372
• /
• 2001

In this paper, we present the concept of generalization in constructing windows for subsequence matching and propose a new subsequence matching method. GeneralMatch, based on the generalization. The earlier work of Faloutsos et al.(FRM in short) causes a lot of false alarms due to lack of the point-filtering effect. DualMatch, which has been proposed by the authors, improves performance significantly over FRM by exploiting the point filtering effect, but it has the problem of having a smaller maximum window size (half that FRM) given the minimum query length. GeneralMatch, an improvement of DualMatch, offers advantages of both methods: it can use large windows like FRM and, at the same time, can exploit the point-filtering effect like DualMatch. GeneralMatch divides data sequences into J-sliding windows (generalized sliding windows) and the query sequence into J-disjoint windows (generalized disjoint windows). We formally prove that our GeneralMatch is correct, i.e., it incurs no false dismissal. We also prove that, given the minimum query length, there is a maximum bound of the window size to guarantee correctness of GeneralMatch. We then propose a method of determining the value of J that minimizes the number of page accesses, Experimental results for real stock data show that, for low selectivities ($10^{-6}~10^{-4}$), GeneralMatch improves performance by 114% over DualMatch and by 998% iver FRM on the average; for high selectivities ($10^{-6}~10^{-4}$), by 46% over DualMatch and by 65% over FRM on the average.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.10
• /
• pp.2461-2469
• /
• 1997

Target detection and recognition problems, in which neural networks are widely used, require translation invariant and real-time processing in addition to the requirements that general pattern recognition problems need. This paper presents a novel architecture that meets the requirements and explains effective methodology to train the network. The proposed neural network is an architectural extension of the shared-weight neural network that is composed of the feature extraction stage followed by the pattern recognition stage. Its feature extraction stage performs correlational operation on the input with a weight kernel, and the entire neural network can be considered a nonlinear correlation filter. Therefore, the output of the proposed neural network is correlational plane with peak values at the location of the target. The architecture of this neural network is suitable for implementing with parallel or distributed computers, and this fact allows the application to the problems which require realtime processing. Net training methodology to overcome the problem caused by unbalance of the number of targets and non-targets is also introduced. To verify the performance, the proposed network is applied to detection and recognition problem of a specific automobile driving around in a parking lot. The results show no false alarms and fast processing enough to track a target that moves as fast as about 190 km per hour.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.13 no.2 s.54
• /
• pp.231-242
• /
• 2009

The baseline distribution of a structure represents the statistical distribution of dynamic response feature from the healthy state of the structure. Generally, damage-sensitive dynamic response feature of a structure manifest themselves near the tail of a baseline statistical distribution. In this regard, some researchers have paid attention to extreme value distribution for modeling the tail of a baseline distribution. However, few researches have been conducted to theoretically understand the extreme value distribution from a perspective of statistical damage assessment. This study investigates the asymptotic convergence of domain of attraction in extreme value distribution through parameter estimation, which is needed for reliable statistical damage assessment. In particular, the asymptotic convergence of a domain of attraction is quantified with respect to the sample size out of which each extreme value is extracted. The effect of the sample size on false positive alarms in statistical damage assessment is quantitatively investigated as well. The validity of the proposed method is demonstrated through numerically simulated acceleration data on a two span continuous truss bridge.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.9-18
• /
• 2015

In recent years, the number of applications embedded in the various devices such as a smart phone is getting larger. Due to the frequent changes of states in the execution environment, various malfunctions may occur. In order to handle the issue, this paper suggests an approach to detecting method-level failures in the legacy software systems. We can determine if the software executes the abnormal behavior based on the behavior model. However, when we apply the context-sensitive behavior model to the method-level, several problems happen such as false alarms and monitoring overhead. To tackle those issues, we propose CIBFD (Context-Insensitive Behavior Model-based Failure Detection) method. Through the case studies, we compare CIBFD method with the existing method. In addition, we analyze the effectiveness of the method for each application domains.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.87-94
• /
• 2008

In this paper, we propose a new vision-based fire detection method for a real-life application. Most previous vision-based methods using color information and temporal variation of pixel produce frequent false alarms because they used a lot of heuristic features. Furthermore there is also computation delay for accurate fire detection. To overcome these problems, we first detected candidated fire regions by using background modeling and color model of fire. Then we made probabilistic models of fire by using a fact that fire pixel values of consecutive frames are changed constantly and applied them to a Bayesian Network. In this paper we used two level Bayesian network, which contains the intermediate nodes and uses four skewnesses for evidence at each node. Skewness of R normalized with intensity and skewnesses of three high frequency components obtained through wavelet transform. The proposed system has been successfully applied to many fire detection tasks in real world environment and distinguishes fire from moving objects having fire color.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.1 s.307
• /
• pp.31-38
• /
• 2006

In this paper, we consider one-step-ahead control of waveform parameters (pulse amplitudes and lengths, and FM sweep rate) as well as detection thresholds for optimal range and range-rate tracking in clutter. The optimal control of the combined parameter set minimizes a tracking performance index under a set of parameter constraints. The performance index includes the probability of track loss and a function of estimation error covariances. The track loss probability and the error covariance are predicted using a hybrid conditional average algorithm The effect of the false alarms and clutter interference is taken into account in the prediction. Tracking performance of the one-step-ahead control is presented for several examples and compared with a control strategy heuristically derived from a finite horizon optimization.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.5
• /
• pp.62-68
• /
• 2010

This study is to identify target locations with low false alarms on thermal infrared images obtained from natural environment. The proposed method is different from the previous researches because it uses morphology filters for Gabor response images instead of an intensity image in initial detection stage. This method does not need precise extracting a target silhouette to distinguish true targets or clutters. It comprises three distinct stages. First, morphological operations and adaptive thresholding are applied to the summation image of four Gabor responses of an input image to find out salient regions. The locations of extracted regions can be classified into targets or clutters. Second, local texture features are computed from salient regions of an input image. Finally, the local texture features are compared with the training data to distinguish between true targets and clutters. The multi-layer perceptron having three layers is used as a classifier. The performance of the proposed method is proved by using natural infrared images. Therefore it can be applied to real automatic target detection systems.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.609-620
• /
• 2016

Recently, there are active studies on a forward collision warning system to prevent the accidents and improve convenience of drivers. For collision evasion, the vehicle detection system is required. In general, existing learning-based vehicle detection methods use the entire appearance of the vehicles from rear-view images, so that each vehicle types should be learned separately since they have distinct rear-view appearance regarding the types. To overcome such shortcoming, we learn Haar-like features from the lower part of the vehicles which contain tail lights to detect vehicles leveraging the fact that the lower part is consistent regardless of vehicle types. As a verification procedure, we detect tail lights to distinguish actual vehicles and non-vehicles. If candidates are too small to detect the tail lights, we use HOG(Histogram Of Gradient) feature and SVM(Support Vector Machine) classifier to reduce false alarms. The proposed forward vehicle detection method shows accuracy of 95% even in the complicated images with many buildings by the road, regardless of vehicle types.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1131-1138
• /
• 2006

This paper proposes a novel method for grading of underground communication conduits by laser projection image analysis. The equipment thrust into conduit consists of a laser diode, a light emitting diode and a camera, the laser diode is utilized for generating projection image onto pipe wall, the light emitting diode for lighting environment and the image of conduit is acquired by the camera. In order to segment profile region, we used a novel color difference model and multiple thresholds method. The shape of profile ring is represented as a minimum diameter and the Fourier descriptor, and then the pipe status is graded by the rule-based method. Both local and global features of the segmented ring shaped, the minimum diameter and the Fourier descriptor, are utilized, therefore injured and distorted pipes can be correctly graded. From the experimental results, the classification is measured with accuracy such that false alarms are less than 2% under the various conditions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.427-430
• /
• 2007

Many victims and property damages are caused in fires every year. In this paper, flame and smoke detection algorithm by using image processing technique is proposed to early alarm fires. The first decision of proposed algorithms is to check candidate of flame region with its unique color distribution distinguished from artificial lights. If it is not a flame region then we can check to candidate of smoke region by measuring difference of brightness and chroma at present frame. If we just check flame and smoke with only simple brightness and hue, we will occasionally get false alarms. Therefore we also use motion information about candidate of flame and smoke regions. Finally, to determine the flame after motion detection, activity information is used. And in order to determine the smoke, edges detection method is adopted. As a result of simulation with real CCTV video signal, it is shown that the proposed algorithm is useful for early fire recognition.