• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.6-13
• /
• 2024

This paper proposes an approach to detect abnormal data in automotive controller area network (CAN) using an unsupervised learning model, i.e. autoencoder and Gaussian kernel density estimation function. The proposed autoencoder model is trained with only message ID of CAN data frames. Afterwards, by employing the Gaussian kernel density estimation function, it effectively detects abnormal data based on the trained model characterized by the optimally determined number of frames and a loss threshold. It was verified and evaluated using four types of attack data, i.e. DoS attacks, gear spoofing attacks, RPM spoofing attacks, and fuzzy attacks. Compared with conventional unsupervised learning-based models, it has achieved over 99% detection performance across all evaluation metrics.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1
• /
• pp.25-31
• /
• 1999

This paper proposes a new wide-band beamforming algorithm which has Gaussian weighting at nested linear array for acoustic measurement. The beamforming is performed one-shot by using all sensors simultaneously, not octave-by-octave. Gaussian weighting of frequency-dependent function is applied to each sensor before time-delay compensation so as to control the frequency receiving band of each sensor. As the results of the simulations, it is confirmed that the proposed algorithm can form the one-shot beams having uniform directivity index and also it can be applied to the broad-band acoustic measurement.

• The Journal of Engineering Geology
• /
• v.16 no.3 s.49
• /
• pp.245-254
• /
• 2006

Using a natural gradient tracer test, the characteristics of hydrodynamic dispersion according to each depth of a fractured rock were studied, and the effective porosity and longitudinal dispersivity of the fractured rock were estimated. The difference of vertical hydrodynamic dispersion was identified by concentration breakthrough curves linear regression analyses of bromide concentrations according to depths versus time, and hydraulic fracture characteristics at two intervals of the monitoring well. Higher concentration and faster arrival time at GL- 18 m depth (RQD 13%, average joint spacing 2 cm, TCR 100%) than at GL- 25 m depth (RQD 41%, average joint spacing 7 cm, TCR 100%) resulted from shorter distance and more fractures. Tracer was transported through the 1 st fractures until the arrival of its peak concentration and through the 2nd fractures or matrix diffusion after the arrival of its peak concentration. The increase/decrease slopes of bromide concentration versus time were 3.46/-1.57 at GL-18 m depth and 3.l9/-0.47 at GL- 25 m depth of the monitoring well. So the faster bromide transport was confirmed at GL- 18 m depth with more fractures. The concentration increment of bromide was fitted by a Gaussian function and the concentration decrement of bromide was fitted by an exponential function. Effective porosity and longitudinal dispersivity estimated by CATTI code were 10.50% and 0.85 m, respectively.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1997.06a
• /
• pp.5-8
• /
• 1997

음성신호는 성대를 통과한 공기 흐름의 성질에 따라 유성음과 무성음으로 구분될 수 있다. 그 중 유성음에서는 성대의 규칙적인 지동이 존재하게 된는 데 이때 성대가 닫히는 순간을 GCI(Glotal Closure Instant)라 하며 성대 진동의 기본주기를 피치라고 한다. 이러한 피치는 음성합성, 음성인식, 피치동기 음성신호의 분석등에 중요한 파라미터 중의 하나이다. 본 논문에서는 가우시안 함수의 일차미분형태를 갖는 웨이브렛 함수를 사용할 경우 신호의 급격한 변화부분을 검출할 수 있다는 성질을 이용하여 음성 신호의 GCI를 찾아내고 이를 이용하여 피치를 검출하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.3
• /
• pp.140-148
• /
• 2014

In this paper, We proposed Gaussian function as a basis of hybrid method. Hybrid method is to extrapolate late time and high frequency data using early time and low frequency data. This method takes advantages of both MOT and MOM as well as having shorter running time and smaller error. For this method a better basis function is required. We compared the performance of the result with proposed function and conventional basis including Hermite and Laguerre polynomial.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2158-2165
• /
• 2007

In this paper, a Modified Fuzzy C-Means algorithm with Gaussian Weights(MFCM_GW) is presented for nonlinear blind channel equalization. The proposed algorithm searches the optimal channel output states of a nonlinear channel from the received symbols, based on the Bayesian likelihood fitness function and Gaussian weighted partition matrix instead of a conventional Euclidean distance measure. Next, the desired channel states of a nonlinear channel are constructed with the elements of estimated channel output states, and placed at the center of a Radial Basis Function(RBF) equalizer to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with those of a simplex genetic algorithm(GA), a hybrid genetic algorithm(GA merged with simulated annealing(SA): GASA), and a previously developed version of MFCM. It is shown that a relatively high accuracy and fast search speed has been achieved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1818-1825
• /
• 2017

An Acoustic Doppler Current Profiler(ADCP) measures the current velocity and analyzes the degree of turbulence using Doppler effects of ultrasonic waves. Therefore, the autocorrelation or FFT spectrum estimates are obtained for extraction of current velocity in each spatial region. However, if the correlation method does not satisfy the assumption that the return signal spectra are symmetric Gaussian, the large bias errors can occur. Also, the accurate estimation of autocorrelation or FFT spectrum is difficult due to the short acquisition interval when the rapid changes of current velocity occur. Thus, in this paper, the estimation method of the autoregressive spectrum peak is suggested for the accurate current velocity measurement of both symmetric and asymmetric spectra. It is shown that estimation quality can be improved using the suggested method comparing with the conventional methods. Many return signals under the various environment are simulated and the results are compared and analyzed for evaluation of the suggested method.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.1
• /
• pp.22-34
• /
• 1992

There exists a transform trellis code that is optimal for stationary Gaussian sources and the squared-error distortion measure at all rates. In this paper, we train an asymptotically optimal version of such a code to obtain one which is matched better to the statistics of real world data. The training algorithm uses the M algorithm to search the trellis codebook and the LBG algorithm to update the trellis codebook. We investigate the trained transform trellis coding scheme for the first-order AR(autoregressive) Gaussian source whose correlation coefficient is 0.9 and actual speech sentences. For the first-order AR source, the achieved SNR for the test sequence is from 0.6 to 1.4 dB less than the maximum achievable SNR as given by Shannon's rate-distortion function for this source, depending on the rate and surpasses all previous known results for this source. For actual speech data, to achieve improved performance, we use window functions and gain adaptation at rate 1.0 bits/sample.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.395-406
• /
• 2017

The purpose of this study is to identify the pattern of daily electricity demand through clustering and classification. The hourly data was collected by KPS (Korea Power Exchange) between 2008 and 2012. The time trend was eliminated for conducting the pattern of daily electricity demand because electricity demand data is times series data. We have considered k-means clustering, Gaussian mixture model clustering, and functional clustering in order to find the optimal clustering method. The classification analysis was conducted to understand the relationship between external factors, day of the week, holiday, and weather. Data was divided into training data and test data. Training data consisted of external factors and clustered number between 2008 and 2011. Test data was daily data of external factors in 2012. Decision tree, random forest, Support vector machine, and Naive Bayes were used. As a result, Gaussian model based clustering and random forest showed the best prediction performance when the number of cluster was 8.

• ETRI Journal
• /
• v.7 no.4
• /
• pp.3-10
• /
• 1985

After the light from an incoherent LED was transmitted through the multimode fibers which were linked over 10 km, the nearfield power distribution reached the steady-state independent of launching conditions. It has been also found that the steady-state output power distribution showed the pattern of Gaussian function. In this steady-state Gaussian function pattern, the measured losses of fibers were very repeatable values. In case of using LD source, the speckle phenomena in near -field power distribution appeared until the distance of 10 km. And the output power distribution did not reach the steady-state shown in LED even over 20km on account of the coherence and the nonuniform lasing modes of LD. But the measured losses of fibers were nearly stable in this long distance.