• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.20-25
• /
• 2009

The maximum likelihood detection with QR decomposition and M-algorithm (QRM-MLD) has been presented as a suboptimum multiple-input multiple-output (MIMO) detection scheme which can provide almost the same performance as the optimum maximum likelihood (ML) MIMO detection scheme but with the reduced complexity. However, due to the lack of parallelism and the regularity in the decoding structure, the conventional QRM-MLD which uses the tree-structure still has very high complexity for the very large scale integration (VLSI) implementation. In this paper, we modify the tree-structure of conventional QRM-MLD into trellis-structure in order to obtain high operational parallelism and regularity and then apply the Viterbi algorithm to the QRM-MLD to ease the burden of the VLSI implementation.We show from our selected numerical examples that, by using the QRM-MLD with our proposed trellis-structure, we can reduce the complexity significantly compared to the tree-structure based QRM-MLD while the performance degradation of our proposed scheme is negligible.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11C
• /
• pp.932-939
• /
• 2008

Recently lattice-reduction (LR) has been used in signal detection for multiple-input multiple-output (MIMO) systems. The conventional LR aided detection schemes are combinations of LR and signal detection methods such as zero-forcing (ZF) and minimum mean square error (MMSE) detection. In this paper, we propose the Lattice-Reduction-aided scheme based on extended noise variance matrix to search good candidate symbol set in quantization step. Then this scheme estimates transmitted symbol with Semidefinite Relaxation by candidate symbol set. Simulation results in a random MIMO system show that the proposed scheme exhibits improved performance and a slight increase in complexity.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.37-44
• /
• 2002

In this paper, the Viterbi decoder containing new branch metrics of the squared Euclidean distance with multiple order phase differences is introduced in order to improve the bit error rate (BER) in the differential detection of the trellis-coded MDPSK-DFDM. The proposed Viterbi decoder is conceptually same as the sliding multiple phase differential detection method that uses the branch metric with multiple phase differences. Also, we describe the Viterbi algorithm in order to use this branch metrics. Our study shows that such a Viterbi decoder improves BER peformance without sacrificing bandwidth and power efficiency. Also, the proposed algorithm can be used in the single carrier modulation.

• Journal of Communications and Networks
• /
• v.15 no.3
• /
• pp.283-291
• /
• 2013

In this paper, we propose new multiuser detectors (MUDs) based on compressed sensing approaches for the large-scale multiple antenna systems equipped with dozens of low-power antennas. We consider the scenarios where the number of receiver antennas is smaller than the total number of users, but the number of active users is relatively small. This prior information motivates sparsity-embracing MUDs such as sparsity-embracing linear/nonlinear MUDs where the detection of active users and their symbol detection are employed. In addition, sparsity-embracing MUDs with maximum a posteriori probability criterion (MAP-MUDs) are presented. They jointly detect active users and their symbols by exploiting the probability of user activity, and it can be solved efficiently by introducing convex relaxing senses. Furthermore, it is shown that sparsity-embracing MUDs exploiting common users' activity across multiple symbols, i.e., frame-by-frame, can be considered to improve performance. Also, in multiple multiple-input and multiple-output networks with aggressive frequency reuse, we propose the interference cancellation strategy for the proposed sparsity-embracing MUDs. That first cancels out the interference induced by adjacent networks and then recovers the desired users' information by exploiting the low user activity. In simulation studies for binary phase shift keying modulation, numerical evidences establish the effectiveness of our proposed MUDs exploiting low user activity, as compared with the conventional MUD.

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.481-493
• /
• 2011

As the development of mobile devices, mobile phones are equipped with many features. Video-call feature is one of them. In this paper, we present distance measurement between speaker and smart-phone using multiple color spaces and multiple thresholds. first, detect face based on skin color information. and second, measure distance between speaker and smart-phone using the detected face region. Especially, the first considering point in the development of face area detection is real-time processing and the second point is robustness to solve the problems of face detection errors due to rapid change of object movement, lighting and background between adjacent frames.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.3
• /
• pp.471-479
• /
• 2019

This research proposes a indoor magnetic map matching algorithm that improves the position accuracy by employing multiple magnetic sensors and probabilistic candidate weighting function. Since the magnetic field is easily distorted by the surrounding environment, the distorted magnetic field can be used for position mapping, and multiple sensor configuration is useful to improve mapping accuracy. Nevertheless, the position error is likely to increase because the external magnetic disturbances have repeated pattern in indoor environment and several points have similar magnetic field distortion characteristics. Those errors cause large position error, which reduces the accuracy of the position detection. In order to solve this problem, we propose a method to reduce the error using multiple sensors and likelihood boundaries that uses human walking characteristics. Also, to reduce the maximum position error, we propose an algorithm that weights according to their importance. We performed indoor walking tests to evaluate the performance of the algorithm and analyzed the position detection error rate and maximum distance error. From the results we can confirm that the accuracy of position detection is greatly improved.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.2
• /
• pp.407-414
• /
• 2007

A sensor fault detection scheme(SFDS) for a class of nonlinear systems that can be represented by Takagi-Sugeno fuzzy model is proposed. Basically, the SFDS may be considered as a multiple observer scheme(MOS) in which the bank of state observers and the detection & isolation logic are included. However, the proposed scheme has two great differences from the conventional MOSs. First, the proposed scheme includes fuzzy fault detection observers(FFDO) that are constructed based on the T-S fuzzy model that provides very good approximation to nonlinear dynamic systems. Secondly, unlike the conventional MOS, the FFDOS are driven not parallelly but sequentially according to the predetermined sequence to avoid the massive computational burden, which is known to be the biggest obstacle to the practical application of the multiple observer based FDI schemes. During the operating time, each FFDO generates the residuals carrying the information of a specified fault, and the corresponding fault detection logic unit performs the logical operations to detect and isolate the fault of interest. The proposed scheme is applied to an inverted pendulum control system for sensor fault detection/isolation. Simulation study shows the practical feasibility of the proposed scheme.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.502-510
• /
• 2016

Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.447-450
• /
• 2009

In this paper, binary pulse-antipodal modulation (2PAM) direct-sequence (DS) ultra-wideband (UWB) system is applied to multiple input multiple output (MIMO) system using vertical bell lab layered space-time (V-BLAST) structure to achieve high-data-rate communications over indoor wireless channels. The relationship between antenna dimension and BER performance of 2PAM DS UWB MIMO system is discussed. In the receiver of UWB-MIMO system, various MIMO detection algorithms such as zero-forcing (ZF), ZF-ordered successive interference cancellation (OSIC), minimum-mean-square-error (MMSE), MMSE-OSIC and maximum likelihood (ML) are comparatively studied.