• The Journal of Korean Physical Therapy
• /
• v.32 no.2
• /
• pp.70-74
• /
• 2020

Purpose: This study examined whether 1) the motor inhibition response as cognitive-behavioral component is learning though a stop signal task using stop-signal paradigm, and 2) whether there is a difference in the learning degree according to imagery training and actual practice training. Methods: Twenty young adults (males: 9, females: 11) volunteered to participate in this study, and were divided randomly into motor imagery training (IT, n=10) and practice training (PT, n=10) groups. The PT group performed an actual practice stop-signal task, while the IT group performed imagery training, which showed a stop-signal task on a monitor of a personal computer. The non-signal reaction time and stop-signal reaction time of both groups were assessed during the stop-signal task. Results: In the non-signal reaction time, there were no significant intra-group and inter-group differences between pre- and post-intervention in both groups (p>0.05). The stop-signal reaction time showed a significant difference in the PT group in the intra-group analysis (p<0.05). On the other hand, there was no significant intra-group difference in the IT group and inter-group difference between pre- and post-intervention (p>0.05). Conclusion: These results showed that the motor inhibition response could be learned through a stop-signal task. Moreover, these findings suggest that actual practice is a more effective method for learning the motor inhibition response.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• Near Infrared Analysis
• /
• v.1 no.2
• /
• pp.1-8
• /
• 2000

Using the net analyte signal, hybrid linear analysis was proposed to predict chemical concentration. In this paper, we select a sample from training set and apply orthogonal signal correction to obtain an improved pseudo unit spectrum for hybrid least analysis. using the mean spectrum of a calibration training set, we first show the calibration by hybrid least analysis is effective to the prediction of not only chemical concentrations but also physical property variables. Then, a pseudo unit spectrum from a training set is also tested with and without orthogonal signal correction. We use two data sets, one including five chemical concentrations and the other including ten physical property variables, to compare the performance of partial least squares and modified hybrid least analysis calibration methods. The results show that the hybrid least analysis with a selected training spectrum instead of well-measured pure spectrum still gives good performances, which is a little better than partial least squares.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.3C
• /
• pp.331-337
• /
• 2007

In this paper, we propose a novel Walsh coded training signal design and Walsh decoding method to estimate the channel response in MIMO-OFDM systems. The Walsh coded training signals are designed to have orthogonal property in time domain. Using the orthogonal property, the Walsh decoding process makes it possible to separate the desired training signal from the received signal and to estimate the channel response. The computer simulation results show that the proposed method exhibits almost the same performance as Li's original method using the optimal training sequence, even though the proposed method has much lower complexity.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.90-96
• /
• 2023

Securing large amounts of training data in deep learning neural networks, including convolutional neural networks, is of importance for avoiding overfitting phenomenon or for the excellent performance. However, securing labeled training data in deep learning neural networks is very limited in reality. To overcome this, several augmentation methods have been proposed in the literature to generate an additional large amount of training data through transformation or manipulation of the already acquired traing data. However, unlike training data such as images and texts, it is barely to find an augmentation method in the literature that additionally generates bio-signal training data for convolutional neural network based human activity recognition. Thus, this study proposes a simple but effective augmentation method of bio-signal training data for convolutional neural network based human activity recognition. The usefulness of the proposed augmentation method is validated by showing that human activity is recognized with high accuracy by convolutional neural network trained with its augmented bio-signal training data.

• Proceedings of the KIPE Conference
• /
• 2008.06a
• /
• pp.437-439
• /
• 2008

This paper presents the training system of myoelectric hand prosthesis controlling according to myoelectric signal generated in the human muscle. The training system consist of a trainer, a program for training. The experimental results proved the reliability of proposed training system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.10
• /
• pp.799-807
• /
• 2002

The vibration signal can give an indication of the condition of rotating machinery, highlighting potential faults such as unbalance, misalignment and bearing defects. The features in the vibration signal provide an important source of information for the faults diagnosis of rotating machinery. When additional training data become available after the initial training is completed, the conventional neural networks (NNs) must be retrained by applying total data including additional training data. This paper proposes the fault diagnostics algorithm using the ART-Kohonen network which does not destroy the initial training and can adapt additional training data that is suitable for the classification of machine condition. The results of the experiments confirm that the proposed algorithm performs better than other NNs as the self-organizing feature maps (SOFM) , learning vector quantization (LYQ) and radial basis function (RBF) NNs with respect to classification quality. The classification success rate for the ART-Kohonen network was 94 o/o and for the SOFM, LYQ and RBF network were 93 %, 93 % and 89 % respectively.

• Journal of Biomedical Engineering Research
• /
• v.15 no.4
• /
• pp.465-474
• /
• 1994

This study is concerned with a method which helps human to generate EMG signals accurately and consistently to make reliable design samples of function discriminator for prosthetic arm control. We intend to ensure a signal accuracy and consistency by training human as a signal generation source. For the purposes, we construct a human training system using a digital computer, which generates visual graphes to compare real target motion trajectory with the desired one, to observe EMG signals and their features. To evaluate the effect which affects a feature variance and a feature separability between motion classes by the human training system, we select 4 features such as integral absolute value, zero crossing counts, AR coefficients and LPC cepstrum coefficients. We perform a experiment four times during 2 months. The experimental results show that the hu- man training system is effective for accurate and consistent EMG signal generation and reduction of a feature variance, but is not correlated for a feature separability, The cepstrum coefficient is the most preferable among the used features for reduction of variance, class separability and robustness to a time varing property of EMG signals.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.42-46
• /
• 2009

Superimposed training (SIT) design for estimating of time-varying multipath channels is investigated for mobile orthogonal frequency division multiplexing (OFDM) systems. The design of optimum SIT consists of two parts: The optimal SIT sequence is derived by minimizing the channel estimates' mean square error (MSE); the optimal power allocation between training and information data is developed by maximizing the averaged signal to interference plus noise ratio (SINR) under the condition of equal powered paths. The theoretical analysis is verified by simulations. For the metric of the averaged SINR against signal to noise ratio (SNR), the theoretical result matches the simulation result perfectly. In contrast to an interpolated frequency-multiplexing training (FMT) scheme or an SIT scheme with random pilot sequence, the SIT scheme with proposed optimal sequence achieves higher SINR. The analytical solution of the optimal power allocation is demonstrated by the simulation as well.