• MALSORI
• /
• no.54
• /
• pp.73-83
• /
• 2005

The goal of our research is to build a text-independent speaker identification system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severely degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(principal component analysis) can improve the performance in the situation. We also propose an augmented PCA process, which augments class discriminative information to the original feature vectors before PCA transformation and selects the best direction for each pair of highly confusable speakers. The proposed method reduced the relative recognition error by 21%.

• Smart Structures and Systems
• /
• v.17 no.3
• /
• pp.445-470
• /
• 2016

In this study, the Bayesian probabilistic framework is investigated for modal identification and modal identifiability based on the field measurements provided in the structural health monitoring benchmark problem of an instrumented cable-stayed bridge named Ting Kau Bridge (TKB). The comprehensive structural health monitoring system on the cable-stayed TKB has been operated for more than ten years and it is recognized as one of the best test-beds with readily available field measurements. The benchmark problem of the cable-stayed bridge is established to stimulate investigations on modal identifiability and the present paper addresses this benchmark problem from the Bayesian prospective. In contrast to deterministic approaches, an appealing feature of the Bayesian approach is that not only the optimal values of the modal parameters can be obtained but also the associated estimation uncertainty can be quantified in the form of probability distribution. The uncertainty quantification provides necessary information to evaluate the reliability of parametric identification results as well as modal identifiability. Herein, the Bayesian spectral density approach is conducted for output-only modal identification and the Bayesian model class selection approach is used to evaluate the significance of different modes in modal identification. Detailed analysis on the modal identification and modal identifiability based on the measurements of the bridge will be presented. Moreover, the advantages and potentials of Bayesian probabilistic framework on structural health monitoring will be discussed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.12 no.2
• /
• pp.79-88
• /
• 2017

One of the important applications of activity sensing in the home is energy monitoring. Many previous methodologies for detecting and recognizing household appliances have been proposed. This paper presents an approach that uses an energy metering circuit (EMC) to classify and identify the various electrical devices in home based on root-mean-square (RMS) consumed current value. EMC gathers the RMS current values created by appliance state transition (e.g., on to off) and apparatus operating process. In this paper, an identification algorithm is proposed to detect a change in current levels using the standard deviation of current signals and their average values. In addition, characteristic of the appliance is extracted concerning four feature parameters concerning the number of current levels, the minimum level, the maximum level, and signal-to-noise ratio (SNR) of them. Experiment results validate the reliable performance of the proposed identification method for 11 representative appliances.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4E
• /
• pp.156-163
• /
• 2002

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

• Smart Structures and Systems
• /
• v.15 no.2
• /
• pp.259-281
• /
• 2015

In this study, a structural identification method is proposed to assess the integrity of gravity-type caisson structures by analyzing vibration features. To achieve the objective, the following approaches are implemented. Firstly, a simplified structural model with a few degrees-of-freedom (DOFs) is formulated to represent the gravity-type caisson structure that corresponds to the sensors' DOFs. Secondly, a structural identification algorithm based on the use of vibration characteristics of the limited DOFs is formulated to fine-tune stiffness and damping parameters of the structural model. Finally, experimental evaluation is performed on a lab-scaled gravity-type caisson structure in a 2-D wave flume. For three structural states including an undamaged reference, a water-level change case, and a foundation-damage case, their corresponding structural integrities are assessed by identifying structural parameters of the three states by fine-tuning frequency response functions, natural frequencies and damping factors.

• Journal of Power Electronics
• /
• v.11 no.4
• /
• pp.418-423
• /
• 2011

This paper presents a simulation model and a parameter identification scheme of an induction motor drive for electric vehicle. The induction motor in automotive applications should operate in very high efficiency and achieve the maximum-torque-per-ampere (MTPA) feature even with saturated magnetic flux under very high torque. The indirect vector control which is typically adopted in traction drive system requires precise information of motor parameters, particularly rotor time constants. This work models an induction motor considering magnetic saturation and proposes an empirical identification method using the current controller in the synchronous reference frame. The proposed method is applied to a 22kW-rated induction motor for electric vehicle.

• International Journal of Aeronautical and Space Sciences
• /
• v.5 no.1
• /
• pp.39-45
• /
• 2004

The vibration characteristics of rotating machinery are directly related withits condition such as rotor types, thereby it should be acquired the information fromthe vibration signal so that operating conditions may be rationally decided.Accordingly, the study is to focus on developing the analysis for identifying theoperational feature of rotor systems. For this purpose the complex frequencyanalysis for identification, which utilizes the directionaI spectrum for effectiveidentification of rotor systems, is introduced. From this proposed method, theanalysis of dynamic model of the rotors is performed including the stabilitybehavior of the general rotor by Ftoquet theory. Through this process theexcitation methodology to identify the types of rotors is investigated and theeffective way to identification is also suggested.

• Speech Sciences
• /
• v.2
• /
• pp.57-66
• /
• 1997

This paper studies the effects of the method, CMS(Cepstral Mean Subtraction), (which compensates for some of the speech distortion. caused by telephone channels), on the performance of the text-dependent speaker identification system. This system is based on the VQ(Vector Quantization) and HMM(Hidden Markov Model) method and chooses the LPC-Cepstrum and Mel-Cepstrum as the feature vectors extracted from the speech data transmitted through telephone channels. Accordingly, we can compare the correct recognition rates of the speaker identification system between the use of LPC-Cepstrum and Mel-Cepstrum. Finally, from the experiment results table, it is found that the Mel-Cepstrum parameter is proven to be superior to the LPC-Cepstrum and that recognition performance improves by about 10% when compensating for telephone channel using the CMS.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.156-156
• /
• 2002

We apply independent component analysis (ICA) for extracting an optimal basis to the problem of finding efficient features for representing speech signals of a given speaker The speech segments are assumed to be generated by a linear combination of the basis functions, thus the distribution of speech segments of a speaker is modeled by adapting the basis functions so that each source component is statistically independent. The learned basis functions are oriented and localized in both space and frequency, bearing a resemblance to Gabor wavelets. These features are speaker dependent characteristics and to assess their efficiency we performed speaker identification experiments and compared our results with the conventional Fourier-basis. Our results show that the proposed method is more efficient than the conventional Fourier-based features in that they can obtain a higher speaker identification rate.

• Journal of Korea Multimedia Society
• /
• v.18 no.1
• /
• pp.1-8
• /
• 2015

In recent years, ear has emerged as a new biometric trait, because it has advantage of higher user acceptance than fingerprint and can be captured at remote distance in an indoor or outdoor environment. This paper proposes an individual identification method using ear region based on SIFT(shift invariant feature transform). Unlike most of the previous studies using rectangle shape for extracting a region of interest(ROI), this study sets an ROI as a flexible expanded region including ear. It also presents an effective extraction and matching method for SIFT keypoints. Experiments for evaluating the performance of the proposed method were performed on IITD public database. It showed correct identification rate of 98.89%, and it showed 98.44% with a deformed dataset of 20% occlusion. These results show that the proposed method is effective in ear recognition and robust to occlusion.