• Information and Communications Magazine
• /
• v.24 no.11
• /
• pp.25-36
• /
• 2007

Deep packet inspection is widely recognized as a powerful way which is used for intrusion detection systems for inspecting, deterring and deflecting malicious attacks over the network. Fundamentally, almost intrusion detection systems have the ability to search through packets and identify contents that match with known attach. In this paper we survey the deep packet inspection implementations techniques, research challenges and algorithm. Finally, we provide a comparison between the different applied system.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.44-50
• /
• 2003

Even though algorithm of intrusion detection is superior to other algorithm in intrusion detection system, it is supposed that captured packet happened hostly lead to lose packet in system architecture when a buffer is full. If packet lost concerned to be hacked, it might impact to system all over. In this paper, try to focus on performance improvement of detection system. Buffer with threshold value could classify normal packet and hacked packet. The buffer accept normal packet and supposed to be hacked packet until critical value. When buffer reached at threshold value, destroyed packet is only normal packet. Proposed method can complement weakness that bypass hacked packet.

• Journal of information and communication convergence engineering
• /
• v.4 no.4
• /
• pp.174-179
• /
• 2006

In this paper we present a text detection method inspired by wavelet packet analysis and improved fuzzy clustering algorithm(IAFC).This approach assumes that the text and non-text regions are considered as two different texture regions. The text detection is achieved by using wavelet packet analysis as a feature analysis. The wavelet packet analysis is a method of wavelet decomposition that offers a richer range of possibilities for document image. From these multi scale features, we adapt the improved fuzzy clustering algorithm based on the unsupervised learning rule. The results show that our text detection method is effective for document images scanned from newspapers and journals.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.4C
• /
• pp.330-335
• /
• 2008

This paper proposes a packet detection algorithm for IEEE802.11n system. IEEE802.11n is a multiple input multiple output (MIMO) system and we have to consider several combining techniques which are used in multiple receive antenna system. In this paper, we propose a hybrid packet detection algorithm which combines double sliding window algorithm or delay and correlation algorithm, that is used in single input single output (SISO) system, and multiple receive antenna combining algorithms, and simulated their performances in Iin system environments and shows the results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1880-1884
• /
• 2004

The wavelet packet transform has been applied for QRS detection with squaring, window integration, and impulse filter techniques to cut down the false detection of QRS complex. This real time QRS detection has been performed on Simulink and Matlab. The correct QRS detection rates have reached to 99.75% in the experiment with 15 sets of ECG data from European ST-T database which are kept in Physionet.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.3
• /
• pp.655-659
• /
• 2016

In this paper, we propose new detection and detour methods against packet drop attacks for availability in the Internet of Things (IoT) based on the IEEE 802.15.4e and RPL protocol standards that employ IPv6. We consider the rank value of RPL and the consecutive packet drops to improve the detection metrics, and also take into account the use of both sibling and child nodes on a RPL routing path to construct the detour method. Our simulation results show that the proposed detection method is faster than the previous result, and the detour method improves the detour success rate.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.49 no.7
• /
• pp.30-38
• /
• 2012

This paper presents packet detection, frequency offset estimation architecture and performance analysis for OFDM-based wireless personal area network (WPAN) systems. Packet detection structure is used to find the start point of a packet exactly in WPAN system as the correlation value passes the constant threshold value. The applied autocorrelation structure of the algorithm can be implemented simply compared to conventional packet detection algorithms. The proposed frequency offset estimation architecture is designed for phase rotation process structure, internal bit reduction to reduce hardware size and the frequency offset adjustment block to reduce look-up table size unlike the conventional structure. If the received signal can be compensated by estimated frequency offset through the correction block, it can reduce the impact on the frequency offset. Through the performance result, the proposed structure has lower hardware complexity and gate count compared to the conventional structure. Thus, the proposed structure for OFDM-based WPAN systems can be applied to the initial synchronization process and high-speed low-power WPAN chips.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.2
• /
• pp.139-145
• /
• 2014

In this paper, a feature parameter is obtained by applying the Teager energy to the WPD(Wavelet Packet Decomposition) coefficients. The threshold value is obtained based on means and standard deviations of nonspeech frames. Experimental results by using TIMIT speech and NOISEX-92 noise databases show that the proposed algorithm is superior to the typical VAD algorithm. The ROC(Receiver Operating Characteristics) curves are used to compare performance of VAD's for SNR values of ranging from 10 to -10 dB.

• The KIPS Transactions:PartC
• /
• v.9C no.4
• /
• pp.473-480
• /
• 2002

Although many researches on IDS (Intrusion Detection System) have been performed, the most of them are limited to the algorithm of detection software. However, even an IDS with superior algorithm can not detect intrusion, if it loses packets which nay have a clue of intrusions. In this paper, we suggest an efficient wav to improve the performance of IDS by reducing packet losses occurred due to hardware limitation and abundant processing overhead introduced by massive detection software itself. The reduction in packet losses is achieved by dropping hacking-free packets. The result shows that this decrease of packet losses leads an IDS to improve the detection rate of real attack.

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.14-21
• /
• 2005

Even though mainly statistical methods have been used in anomaly network intrusion detection, to detect various attack types, machine learning based anomaly detection was introduced. Machine learning based anomaly detection started from research applying traditional learning algorithms of artificial intelligence to intrusion detection. However, detection rates of these methods are not satisfactory. Especially, high false positive and repeated alarms about the same attack are problems. The main reason for this is that one packet is used as a basic learning unit. Most attacks consist of more than one packet. In addition, an attack does not lead to a consecutive packet stream. Therefore, with grouping of related packets, a new approach of group-based learning and detection is needed. This type of approach is similar to that of multiple-instance problems in the artificial intelligence community, which cannot clearly classify one instance, but classification of a group is possible. We suggest group generation algorithm grouping related packets, and a learning algorithm based on a unit of such group. To verify the usefulness of the suggested algorithm, 1998 DARPA data was used and the results show that our approach is quite useful.