• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.3
• /
• pp.1-8
• /
• 2000

In this paper, we formulate an optimal control problem to obtain the optimal signal strength and detection threshold for tracking with NN filter, First, we predict the tracking performance of NN filter by using the HYCA method. Based on this method, the predicted tracking performance is represented with respect to signal strength and detection threshold. Using this relation, we find the optimal parameters for following three examples： 1) the sequence of optimal detection threshold which minimizes sum of position estimation error； 2) the sequence of optimal detection threshold which minimizes sum of validation gate volume； and 3) the sequence of optimal signal strength and detection threshold which minimizes sum of signal strength.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4814-4832
• /
• 2019

Plagiarism detection is increasingly exploiting text alignment. Text alignment involves extracting the plagiarism passages in a pair of the suspicious document and its source document. The heuristics have achieved excellent performance in text alignment. However, the further improvements of the heuristic methods mainly depends more on the experiences of experts, which makes the heuristics lack of the abilities for continuous improvements. To address this problem, machine learning maybe a proper way. Considering the position relations and the context of text segments pairs, we formalize the text alignment task as a problem of sequence labeling, improving the current methods at the model level. Especially, this paper proposes to use the probabilistic graphical model to tag the observed sequence of pairs of text segments. Hence we present the sequence labeling approach for text alignment in plagiarism detection based on Conditional Random Fields. The proposed approach is evaluated on the PAN@CLEF 2012 artificial high obfuscation plagiarism corpus and the simulated paraphrase plagiarism corpus, and compared with the methods achieved the best performance in PAN@CLEF 2012, 2013 and 2014. Experimental results demonstrate that the proposed approach significantly outperforms the state of the art methods.

• The KIPS Transactions:PartC
• /
• v.10C no.2
• /
• pp.119-124
• /
• 2003

Although there have been many studies on using finite automata for intrusion detection, it has been a difficult problem to generate compact finite automata automatically. In a previous research an approach to profile normal behaviors using finite automata was proposed. They divided the system call sequence of each process into three parts prefix, main portion, and suffix, and then substituted macros for frequently occurring substrings. However, the procedure was not automatic. In this paper we present algorithms to automatically generate intrusion detection automata from the sequence of system calls resulting from the normal runs of the programs. We also show the effectiveness of the proposed method through experiments.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.96-102
• /
• 2003

Video copy detection is a complementary approach to watermarking. As opposed to watermarking, which relies on inserting a distinct pattern into the video stream, video copy detection techniques match content-based signatures to detect copies of video. Existing typical content-based copy detection schemes have relied on image matching. This paper proposes two new sequence matching techniques for copy detection and compares the performance with color techniques that is the existing techniques. Motion, intensity and color-based signatures are compared in the context of copy detection. Comparison of experimental results are reported on detecting copies of movie clips.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.31-32
• /
• 2007

In this paper, a fault section detection method is proposed for ungrounded system in the case of a single line-to-ground fault. A conventional method is used for faulted feeder selection according to the angular relationship between zero-sequence currents of the feeders and zero-sequence voltage of the system. Fault section detection is based on the comparison of phase angle of zero-sequence current. Proposed method has been testified in a demo system by Matlab/Simulink simulations. Based on Distribution Automation System(DAS), Feeder Remote Terminal Unit(FRTU) is used to collect those necessary data, at present a demo system is under developing using Manufacturing Message Specification (MMS) in IEC61850 standard.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.11
• /
• pp.637-644
• /
• 2014

This paper investigates the detection performance of fault location using STDR(sequence time domain reflectometry) and SSTDR(spread spectrum time domain reflectometry) with various length and types of sequences, and then, proposes an improved detection technique by eliminating the injected signal in SSTDR. The detection error rates are compared and analyzed in power line channel model with various fault locations, fault types, and spreading sequences such as m-sequence, binary Barker sequence, and 4-phase Frank sequence. It is shown that the proposed technique is able to improve the detection performance obviously when the reflected signal is weak or the fault location is extremely close.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.652-661
• /
• 2017

A mention has a noun or noun phrase as its head and constructs a chunk that defines any meaning, including a modifier. Mention detection refers to the extraction of mentions from a document. In mentions, coreference resolution refers to determining any mentions that have the same meaning. Pointer networks, which are models based on a recurrent neural network encoder-decoder, outputs a list of elements corresponding to an input sequence. In this paper, we propose mention detection using pointer networks. This approach can solve the problem of overlapped mention detection, which cannot be solved by a sequence labeling approach. The experimental results show that the performance of the proposed mention detection approach is F1 of 80.75%, which is 8% higher than rule-based mention detection, and the performance of the coreference resolution has a CoNLL F1 of 56.67% (mention boundary), which is 7.68% higher than coreference resolution using rule-based mention detection.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.7
• /
• pp.85-91
• /
• 2016

Typically, radar systems change the pulse repetition interval of their modulated signal in order to avoid detection. On the other hand the radar-signal detection system tries to detect the modulation pattern. The histogram or auto-correlation methods are usually used to detect the PRI pattern of the radar signal. However these methods tend to lost the sequence information of the PRI pulses. This paper proposes a PRI-sequence detection algorithm based on the finite-state machine that could detect not only the PRI pattern but also their sequence.

• Journal of Korea Game Society
• /
• v.13 no.6
• /
• pp.85-94
• /
• 2013

Repackaging of mobile games is serious problem in the Android environment. In this paper, we propose a repackaging detection technique using shortened instruction sequence. By using shortened instruction sequence, the proposed technique can be applicable to a mobile device and can block repackaged apps coming from various sources. In the experiment, our technique showed high accuracy of repackaging detection.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1025-1033
• /
• 2004

This paper covers the detection of covert direct sequence spread spectrum signal without the PN(Pseudo Noise) code information. Due to its low probability of interception, the difficulty of spectrum surveillance increases. Detection parameters are the signal existence of given bandwidth, the length of spreading sequence used by transmitter, and the identification of spreading code for detected chip length. The triple correlation function(TCF) value which is one of the higher order statistical signal processing techniques can be used to detect spread spectrum signal without a prior knowledge, but, it has weakness that TCF results depend on the spread data sequence in actual application. This paper proposes the new scheme that not only overcomes the weakness but also presents better performance than the traditional TCF scheme. The performance comparison of conventional TCF with proposed technique shows that the triple correlation estimator(TCE) has better detection capability.