• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.459-460
• /
• 2001

In this paper, we analyze algorithms for diagnosing of VEP(visual evoked potential) signal. We used wavelet transform for the preprocessing of VEP signal data and back propagation neural network for the pattern recognition. We used several wavelets to study their effects and efficiency in the preprocessing of VEP. The diagnosis system led to good results. We obtained the noise reduced and compressed signal with the wavelet transform of the training VEP signal. So it is possible to train the neural network faster and exact diagnosis processing is possible in the neural network. From the experimental results, we know that the discrimination ability of the neural network is changed by the type of basis vector and the proposed system is good to the diagnosis of VEP.

• 한국군사과학기술학회지
• /
• 제6권3호
• /
• pp.36-43
• /
• 2003

Multi-target away signal simulator which can simulate the radiated noises of maneuvering targets in a specified ocean range is an essential equipment for the validation of developed towed array sonar system. This simulator should provide realistic multi-channel signals those are required for beamforming on the signal processing unit of towed away system. This paper describes the overall system configuration and signal synthesis techniques for the target radiated noise. And this paper considers why the time delays between target and individual sensors are caused and how to compensate these time delays to individual sensors output. This multi-purpose target simulator could be used for the training of TASS operators.

• Journal of Information Processing Systems
• /
• 제16권1호
• /
• pp.145-154
• /
• 2020

Maximum likelihood (ML) is the best estimator asymptotically as the number of training samples approaches infinity. This paper deduces an adaptive algorithm for blind signal processing problem based on gradient optimization criterion. A parametric density model is introduced through a parameterized generalized distribution family in ML framework. After specifying a limited number of parameters, the density of specific original signal can be approximated automatically by the constructed density function. Consequently, signal separation can be conducted without any prior information about the probability density of the desired original signal. Simulations on classical biomedical signals confirm the performance of the deduced technique.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.149-155
• /
• 2023

In urban areas it can be difficult to utilize global navigation satellite systems (GNSS) due to signal reflections and blockages. It is thus crucial to detect reflected or blocked signals because they lead to significant degradation of GNSS positioning accuracy. In a previous study, a classifier for global positioning system (GPS) signal reception conditions was developed using three features and the support vector machine (SVM) algorithm. However, this classifier had limitations in its classification performance. Therefore, in this study, we developed an improved machine learning based method of classifying GPS signal reception conditions by including an additional feature with the existing features. Furthermore, we applied various machine learning classification algorithms. As a result, when tested with datasets collected in different environments than the training environment, the classification accuracy improved by nine percentage points compared to the existing method, reaching up to 58%.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.746-751
• /
• 1991

Deafs train articulation by observing mouth of a tutor. sensing tactually the notions of the vocal organs, or using speech training aids. Present speech training aids for deafs can measure only single speech ter, or display only frequency spectra in histogrm or pseudo-color. In this study, a speech training aids that can display subject's articulation in the form of a cross section of the vocal organs and other speech parameters together in a single system Is aimed to develop and this system makes a subject to know where to correct. For our objective, first, speech production mechanism is assumed to be AR model in order to estimate articulatory notions of the vocal tract from speech signal. Next, a vocal tract profile mode using LPC analysis is made up. And using this model, articulatory notions for Korean vowels are estimated and displayed in the vocal tract profile graphics.

• 한국통신학회논문지
• /
• 제34권3C호
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2003년도 추계 학술발표회논문집
• /
• pp.13-19
• /
• 2003

Discriminant method using seismic signal was studied for discrimination of surface explosion. By means of the seismic spectral characteristics, multi-variate discriminant analysis was performed. Four single discriminant techniques - Pg/Lg, Lg1/Lg2, Pg1/Pg2, and Rg/Lg - based on seismic source theory were applied to explosion and earthquake training data sets. The Pg/Lg discriminant technique was most effective among the four techniques. Nevertheless, it could not perfectly discriminate the samples of the training data sets. In this study, a compound linear discriminant analysis was defined by using common characteristics of the training data sets for the single discriminants. The compound linear discriminant analysis was used for the single discriminant as an independent variable. From this analysis, all the samples of the training data sets were correctly discriminated, and the probability of misclassification was lowered to 0.7％.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.982-986
• /
• 1997

A method using cutting force signal and neural network for detection tool damage is proposed. Cutting force signal is gained by tool dynamometer and the signal is prepocessed to normalize. Cutting force signal is changed by tool state. When tool damage is occurred, cutting force signal goes up in comparison with that in normal state. However,the signal goes down in case of catastrophic fracture. These features are memorized in neural network through nomalizing couse. A new nomalizing method is introduced in this paper. Fist, cutting forces are sumed up except data smaller than threshold value, which is the cutting force during non-cutting action. After then, the average value is found by dividing by the number of data. With backpropagation training process, the neural network memorizes the feature difference of cutting force signal between with and without tool damage. As a result, the cutting force can be used in monitoring the condition of cutting tool and neural network can be used to classify the cutting force signal with and without tool damage.

• 인터넷정보학회논문지
• /
• 제18권4호
• /
• pp.19-25
• /
• 2017

In this paper, we designed and implemented IoT sensors based badminton motion analysis and training system that can be readily used by badminton players with PC. Unlike the traditional badminton training system which uses signals of the flags by coach, the proposed electronic training system used IoT sensors to automatically detect and analysis the motions for badminton players. The proposed badminton motion analysis and training system has the advantage with low power, because it communicates with the program through BLE communication. The badminton motion analysis system automatically measures the training time according to the player's movement, so it is possible to collect objective result data with less errors than the conventional flag signal based method by coach. In this paper, training data of 5 athletes were collected and it provides the feedback function through the visualization of each section of the training results by the players which can enable the effective training. For the weakness section of each player, the coach and the player can selectively and repeatedly perform the training function with the proposed training system. Based on this, it is possible to perform the repeated training on weakness sections and they can improve the response speed for these sections. Continuous research is expected to be able to compare more various players' agility and physical fitness.

• 한국정보통신학회논문지
• /
• 제6권4호
• /
• pp.567-573
• /
• 2002

본 논문에서는 보간 방식을 사용하는 OFDM(Orthogonal Frequency Division Multiplexing) 통신 시스템에 적합한 새로운 심볼 시간동기 처리 방법을 제시한다. 제안된 방법은 다음과 같은 과정을 거친다 먼저, 수신되는 포락선 신호의 평균 전력을 연속적으로 측정함으로서, 대략적인 심볼 시간동기 절차를 수행한다. 이 절차에 의해, 동기 가능여부에 대한 판정을 한다. 만약 동기가 가능하다고 판단되는 경우, 이어서, 짧은 길이의 훈련신호와 수신된 포락선신호간의 상관성을 측정하는 방범을 사용하여, 정확한 심볼 동기 과정을 수행하도록 한다. 마지막으로, 긴 훈련 신호를 사용한 주파수 동기절차를 수행하도록 하는데, 이 것은 심볼 시간 동기 과정에서 발생되는 미세한 심볼 동기 오차에 의한 성상도의 회전 효과를 교정할 수 있도록 하기 위함이다. 시뮬레이션 결과로부터, 제안된 동기방법이 주파수 선택적 페이딩 채 널 하에서도 우수한 동기특성을 제공함을 알 수 있다.