• 전자공학회논문지 IE
• /
• v.47 no.4
• /
• pp.10-17
• /
• 2010

There is no general method to find out from signals of the channel outputs of ICA(Independent Component Analysis) which is what you want. Assuming speech signals contaminated with the sound from the muffler of a car, this paper presents the method which shows what you want, It is anticipated that speech signals will show larger correlation coefficients for speech signals than others. Batch, maximum and average method were proposed using 'ah', 'oh', 'woo' vowels whose signals were spoken by the same person who spoke the speech signals and using the same vowels whose signals are by another person. With the correlation coefficients which were calculated for each vowel, voting and summation methods were added. This paper shows what the best is among several methods tried.

• Sleep Medicine and Psychophysiology
• /
• v.8 no.1
• /
• pp.67-71
• /
• 2001

Independent Component Analysis (ICA) is a blind source separation method using unsupervised learning and mutual information theory created in the late eighties and developed in the nineties. It has already succeeded in separating eye movement artifacts from human scalp EEG recording. Several characteristic sleep waves such as sleep spindle, K-complex, and positive occipital sharp transient of sleep (POSTS) can be recorded during sleep EEG recording. They are used as stage determining factors of sleep staging and might be reflections of unknown neural sources during sleep. We applied the ICA method to sleep EEG for sleep waves separation. Eighteen channel scalp longitudinal bipolar montage was used for the EEG recording. With the sampling rate of 256Hz, digital EEG data were converted into 18 by n matrix which was used as a original data matrix X. Independent source matrix U (18 by n) was obtained by independent component analysis method ($U=W{\timex}X$, where W is an 18 by 18 matrix obtained by ICA procedures). ICA was applied to the original EEG containing sleep spindle, K-complex, and POSTS. Among the 18 independent components, those containing characteristic shape of sleep waves could be identified. Each independent component was reconstructed into original montage by the product of inverse matrix of W (inv(W)) and U. The reconstructed EEG might be a separation of sleep waves without other components of original EEG matrix X. This result (might) demonstrates that characteristic sleep waves may be separated from original EEG of unknown mixed neural origins by the Independent Component Analysis (ICA) method.

• Steel and Composite Structures
• /
• v.42 no.6
• /
• pp.733-745
• /
• 2022

This study proposed a robust artificial intelligence (AI) model based on the social behaviour of the imperialist competitive algorithm (ICA) and artificial neural network (ANN) for modelling the deflection of reinforced concrete beams, abbreviated as ICA-ANN model. Accordingly, the ICA was used to adjust and optimize the parameters of an ANN model (i.e., weights and biases) aiming to improve the accuracy of the ANN model in modelling the deflection reinforced concrete beams. A total of 120 experimental datasets of reinforced concrete beams were employed for this aim. Therein, applied load, tensile reinforcement strength and the reinforcement percentage were used to simulate the deflection of reinforced concrete beams. Besides, five other AI models, such as ANN, SVM (support vector machine), GLMNET (lasso and elastic-net regularized generalized linear models), CART (classification and regression tree) and KNN (k-nearest neighbours), were also used for the comprehensive assessment of the proposed model (i.e., ICA-ANN). The comparison of the derived results with the experimental findings demonstrates that among the developed models the ICA-ANN model is that can approximate the reinforced concrete beams deflection in a more reliable and robust manner.

• Investigative Magnetic Resonance Imaging
• /
• v.8 no.1
• /
• pp.1-8
• /
• 2004

Purpose : Information about electrical activity inside the brain during fMRl scans is very useful in monitoring physiological function of the patient or locating the spatial position of the activated region in the brain. However, many additional noises appear in the EEG signal acquired during the MRI scan. Gradient induced noise is the biggest one among the noises. In this work, we propose a gradient noise reduction method using the independent component analysis (ICA) method. Materials and Methods : We used a 29-channel MR-compatible EEG measurement system and a 3.0 Tesla MRI system. We measured EEG signals on a subject lying inside the magnet during EPI scans. We selectively removed the gradient noise from the measured EEG signal using the ICA method. We compared the results with the ones obtained with conventional averaging method and PCA method. Results : All the noise reduction methods including the averaging and PCA methods were effective in removing the noise in some extent. However, the proposed ICA method was found to be superior to the other methods. Conclusion : Gradient noise in EEG signals acquired during fMRI scans can be effectively reduced by the ICA method. The noise-reduced EEG signal can be used in fMRI studies of epileptic patients or combinatory studies of fMRI and EEG.

• Journal of the Microelectronics and Packaging Society
• /
• v.18 no.3
• /
• pp.33-37
• /
• 2011

In this study, the degradation mechanism of mounted chip resistors with Ag-epoxy isotropic conductive adhesives (ICAs) under the humidity exposure ($85^{\circ}C$/85%RH) was examined by electrical resistance change and microstructural study. The effect of the chloride content in Ag-epoxy ICA on joint stability was also examined. The increasing range of the electrical resistance in the typical ICA joint was greater than that in the low Cl content ICA joint. In the case of the typical ICA joint, Sn oxides such as SnO, $SnO_2$, and Sn-Cl-O were formed inhomogeneously on the surface of the Sn plating during the $85^{\circ}C$/85%RH test. In contrast, no Sn-Cl-O was found in the low Cl content ICA joint during the $85^{\circ}C$/85%RH. It is suggested that Cl in Ag-epoxy ICA accelerate the electrical degradation of Sn plated chip components joined with Ag-epoxy ICA.

• Journal of Korean Neurosurgical Society
• /
• v.41 no.5
• /
• pp.343-346
• /
• 2007

Hypoplasia of the internal carotid artery is a rare congenital anomaly. Agenesis, aplasia, and hypoplasia of the internal carotid artery [ICA] are frequently associated with cerebral aneurysms in the circle of Willis. Authors report two cases with congenital hypoplasia of the ICA accompanying with the aneurysms. Transfemoral cerebral angiography [TFCA] in one patient identified nonvisualization of the left ICA. Bilateral anterior cerebral artery [ACA] and middle cerebral artery [MCA] were supplied from the right ICA accompanying with two aneurysms at anterior communicating artery [AcoA] and A1 portion of the left ACA. TFCA in another patient demonstrated hypoplastic left ICA and left ACA filled from the right ICA accompanying with AcoA aneurysm. Left MCA was filled from basilar artery via posterior communicating artery [PcoA]. Skull base computed tomography [CT] in two patients showed hypoplastic carotid canal. Authors performed direct aneurysmal neck clipping. Follow up CT angiography [CTA] at one year after surgery did not show regrowth or new development of the aneurysm. In patients with hypoplastic ICA, neurosurgeons should be aware of the possibility of development of the aneurysms, presumably because of hemodynamic process. Direct aneurysmal neck clipping is a good treatment modality. After operation, regular CTA, magnetic resonance angiography [MRA] or TFCA is needed to find progressive lesion and to prevent cerebrovascular attack [CVA].

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.5A
• /
• pp.475-483
• /
• 2006

If channel coefficients errors exist in MIMO-OFDM systems, the performance degradation of systems will occurs. In order to improve the performance of MIMO-OFDM systems, the technique of obtaining accurate channel estimation in multipath fading channel is necessary. In this paper, we introduce and propose new channel estimation-modified ICA algorithm. Simulation results shows from BER and SER curves which compare the proposed algorithm under time-varying Rayleigh fading with perfect known channel. The result of channel estimation by the proposed algorithm in this simulation, it shows that PDF(amplitude of channel) are close to the case with perfect known channel at the receiver with respect to uncoded QPSK/16-QAM/64-QAM modulation. Also, we can see that BER and SER curves are very close to the case with perfect known channel. Therefore, we see that the proposed algorithm have a good performance in MIMO-OFDM systems.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.199-206
• /
• 2004

This paper proposes a hybrid independent component analysis(ICA) of fixed-point(FP) algorithm and robust algorithm. The FP algorithm is applied for improving the analysis speed and performance, and the robust algorithm is applied for preventing performance degradations by means of very small kurtosis and temporal correlations between components. And the adaptive adaptation of temporal correlations has been proposed for solving limits of the conventional robust algorithm dependent on the maximum time delay. The proposed ICA has been applied to the problems for separating the 4-mixed signals of 500 samples and 10-mixed images of $512\times512$pixels, respectively. The experimental results show that the proposed ICA has a characteristics of adaptively adapting the maximum time delay, and has a superior separation performances(speed, rate) to conventional FP-ICA and hybrid ICA of heuristic correlation. Especially, the proposed ICA gives the larger degree of improvement as the problem size increases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.8
• /
• pp.1596-1603
• /
• 2007

In this paper, we experimented by three kind of method for feature parameter, training method and recognition algorithm of most suitable for speech recognition system and considered. We decided speech recognition system of most suitable through two kind of experiment after we make speech recognizer. First, we did an experiment about three kind of feature parameter to evaluate recognition performance of it in speech recognizer using existent MFCC and MFCC new feature parameter that change characteristic space using PCA and ICA. Second, we experimented recognition performance or HMM, SVM and RVM by studying data number. By an experiment until now, feature parameter by ICA showed performance improvement of average 1.5% than MFCC by high linear discrimination from characteristic space. RVM showed performance improvement of maximum 3.25% than HMM in an experiment by decrease of studying data. As such result, effective method for speech recognition system to propose in this paper derives feature parameters using ICA and un recognition using RVM.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.2
• /
• pp.177-183
• /
• 2019

In this paper, we proposed an application method of ICA (Independent Component Analysis) to passive line array sonar to separate interferences from target signals in low frequency band and compared performance of three conventional ICA algorithms. Since the low frequency signals are received through larger bearing angles than other frequency bands, neighboring beam signals can be used to perform ICA as measurement signals of the ICA. We use three ICA algorithms such as Fast ICA, NNMF (Non-negative Matrix Factorization) and JADE (Joint Approximation Diagonalization of Eigen-matrices). Through experiments on real data obtained from passive line array sonar, it is verified that the interference can be separable from target signals by the suggested method and the JADE algorithm shows the best separation performance among the three algorithms.