• Smart Media Journal
• /
• v.5 no.3
• /
• pp.35-41
• /
• 2016

In this paper, we propose hand-gesture signal recognition based on EPS(Electronic Potential Sensor) using Deep learning model. Extracted signals which from Electronic field based sensor, EPS have much of the noise, so it must remove in pre-processing. After the noise are removed with filter using frequency feature, the signals are reconstructed with dimensional transformation to overcome limit which have just one-dimension feature with voltage value for using convolution operation. Then, the reconstructed signal data is finally classified and recognized using multiple learning layers model based on deep learning. Since the statistical model based on probability is sensitive to initial parameters, the result can change after training in modeling phase. Deep learning model can overcome this problem because of several layers in training phase. In experiment, we used two different deep learning structures, Convolutional neural networks and Recurrent Neural Network and compared with statistical model algorithm with four kinds of gestures. The recognition result of method using convolutional neural network is better than other algorithms in EPS gesture signal recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.4
• /
• pp.337-346
• /
• 2021

Detection of abnormal signal generally can be done by using features of normal signals as main information because of data imbalance. This paper propose an efficient method for abnormal signal detection using parallel AutoEncoder (AE) which can use features of abnormal signals as well. The proposed Parallel AE (PAE) is composed of a normal and an abnormal reconstructors having identical AE structure and train features of normal and abnormal signals, respectively. The PAE can effectively solve the imbalanced data problem by sequentially training normal and abnormal data. For further detection performance improvement, additional binary classifier can be added to the PAE. Through experiments using public acoustic data, we obtain that the proposed PAE shows Area Under Curve (AUC) improvement of minimum 22 % at the expenses of training time increased by 1.31 ~ 1.61 times to the single AE. Furthermore, the PAE shows 93 % AUC improvement in detecting abnormal underwater acoustic signal when pre-trained PAE is transferred to train open underwater acoustic data.

• Journal of Ocean Engineering and Technology
• /
• v.28 no.6
• /
• pp.552-559
• /
• 2014

In general, the number of underwater transient signals is very limited for research on automatic recognition. Data-dependent feature extraction is one of the most effective methods in this case. Therefore, we suggest WPCC (Wavelet packet ceptsral coefficient) as a feature extraction method. A wavelet packet best tree for each data set is formed using an entropy-based cost function. Then, every terminal node of the best trees is counted to build a common wavelet best tree. It corresponds to flexible and non-uniform filter bank reflecting characteristics for the data set. A GMM (Gaussian mixture model) is used to classify five classes of underwater transient data sets. The error rate of the WPCC is compared using MFCC (Mel-frequency ceptsral coefficients). The error rates of WPCC-db20, db40, and MFCC are 0.4%, 0%, and 0.4%, respectively, when the training data consist of six out of the nine pieces of data in each class. However, WPCC-db20 and db40 show rates of 2.98% and 1.20%, respectively, while MFCC shows a rate of 7.14% when the training data consists of only three pieces. This shows that WPCC is less sensitive to the number of training data pieces than MFCC. Thus, it could be a more appropriate method for underwater transient recognition. These results may be helpful to develop an automatic recognition system for an underwater transient signal.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.751-753
• /
• 2017

In this paper, we implement remote training kit using camera, Arduino and AVR practice kit so that AVR practice kit can be practiced remotely. Implemented systems can be practiced by a large number of users one at a time from a remote location. The practitioner creates the AVR Studio program using the PC remote control method and downloads it to the AVR training kit. When a computer program is created and a mouse is clicked or dragged, the input signal is transmitted to the Arduino and the Arduino transmits the actual button input signal or the analog voltage to the AVR kit. When the AVR kit is activated by receiving the input signal, you can check the operation through the camera. Therefore, using the implemented system, a plurality of users can perform AVR training using one kit.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.167-175
• /
• 2021

Semi-supervised learning uses both labeled data and unlabeled data. Recently consistency regularization is very popular in semi-supervised learning. Unsupervised data augmentation (UDA) that uses unlabeled data augmentation is also based on the consistency regularization. The Kullback-Leibler divergence is used for the loss of unlabeled data and cross-entropy for the loss of labeled data through UDA learning. UDA uses techniques such as training signal annealing (TSA) and confidence-based masking to promote performance. In this study, we propose to use Jensen-Shannon divergence instead of Kullback-Leibler divergence, reverse-TSA and not to use confidence-based masking for performance improvement. Through experiment, we show that the proposed technique yields better performance than those of UDA.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.114-117
• /
• 1996

In this study, remote articulation training system which connects the hearing disabled trainee and the speech therapist via B-ISDN is introduced. The hearing disabled does not have the hearing feedback of his own pronunciation, and the chance of watching his speech organs' movement trajectory will offer him the self-training of articulation. So the system has two purposes of self articulation training and trainer's on-line checking in remote place. We estimate the vocal tract articulatory movements from the speech signal using inverse modelling and display the movement trajectory on the sideview of human face graphically. The trajectories of trainees' articulation is displayed along with the reference trajectories, so the trainee can control his articulating to make the two trajectories overlapped. For on-line communication and ckecking training record, the system has the function of video conferencing and transferring articulatory data.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.20 no.5
• /
• pp.1211-1216
• /
• 2006

The effect of a chronic programme of either low- or moderate-to-high-intensity treadmill running on the activation of the Extracellular-signal regulated protein kinase (ERK1/2), Phosphorylated ERK 1/2(pERK1/2) and the Phosphorylated c-Jun N-terminal kinase(pJNK) pathways was determined in rat Back skin Hair follicle. Sprague-Dawley rats were assigned to one of three groups: (i) sedentary group(NE; n=10); (ii) low-intensity exercise group (Bm/min; LIE; n=10); and (iii) moderate-high-intensity exercise group(28m1min; HIE; n=10). The training regimens were planned so that animals covered the same distance and had similar utilization for both LIE and HIE exercise sessions. The report runs as follows; A single bout of LIE or HIE following 4 weeks of exercise led to a twofold increase in the phosphorylation of ERK2, pERK2 and a threefold increase in pJNKl, pERKl. ERKI phosphorylation in LIE Back skin sampled and pJNK2 in HIE Back skin sampled 48h after the last exercise bout was similar to sedentary values, while pJNK2 phosphorylation in LIE Back skin sampled was 70-80% lower than sedentary. 48h after the last exercise bout of LIE or HIE increased ERK2, pERKl and pJNKl expression, with the magnitude of this increase being independent of prior exercise intensity or duration. PERK1/2, pJNKl expression was increased Three- to fourfold in Back skin Hair follicle sampled 48h after the last exercise bout irrespective of the prior exercise programme, but ERKI expression in HIE Back skin sampled was approximately 90% lower than sedentary values. In conclusion, exercise-training of different jntensities/durations results in selective postexercise activation of intracellular signal pathways, which may be one mechanism regulating specific adaptations induced by diverse training programmes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.5
• /
• pp.980-987
• /
• 2009

A timing synchronization method is presented for IEEE 802.11a wireless OFDM system. First the signal detection is achieved by measuring the moving energy of the received OFDM signal in two consecutive windows. By measuring the correlation between the short training signal and received envelope signal, fine OFDM symbol synchronization can be acquired. The variance and average value of the correlation value is acquired. And the theoretical values are compared with computer simulation results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6B
• /
• pp.629-637
• /
• 2002

RLS a1gorithm is a kind of the adaptive a1gorithms in smart antennas and adapts the weight vector using the difference between the output signal of array antennas and the known training sequence. In this paper, we propose a new algorithm based on the RLS algorithm. It calculates the error signal with reference signal derived from blind scheme. Simulation results show that the proposed algorithm yields more user capacity by 67∼74% than other blind adaptive algorithms(LS-DRMTA, LS-DRMTCMA) at the same BER and the beamformer forms null beams toward interference signals and the main beam toward desired signal.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1586-1589
• /
• 2002

RLS algorithm is a kind of the adaptive algorithms in smart antennas and adapts the weight vector using the difference between the output signal of array antennas and the known training sequence. In this paper, we propose a new algorithm based on the RLS algorithm. It calculates the error signal with reference signal derived from blind scheme. Simulation results show that the proposed algorithm yields more user capacity by 67∼74% than other blind adaptive algorithms(LS-DRMTA, LS-DRMTCMA) at the same BER and the beamformer forms null beams toward interference signals and the main beam toward desired signal.