• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1001-1019
• /
• 2017

The signal processing is a field of the electrical engineering but it is very much related with the time series analysis. Thesedays the commercial softwares are widely used by the reseachers. We have attempted to make a guide for using the R-package in the digital signal processing. It would be good to read the materials in each section first and to follow the plots in the section 8 and to run the attached R-codes. The article consists of (1) Fourier transform and Fourier inverse transform, (2) spectral analysis (3) parametric and non-parametric estimation for the period (4) filter design. Simple theoretical explanations are provided and R implementations are added.

• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.62-66
• /
• 2022

Recently, there have been many research efforts based on data-based deep learning technologies to deal with the interference problem between heterogeneous wireless communication devices in unlicensed frequency bands. However, existing approaches are commonly based on the use of complex neural network models, which require high computational power, limiting their efficiency in resource-constrained network interfaces and Internet of Things (IoT) devices. In this study, we address the problem of classifying heterogeneous wireless technologies including Wi-Fi and ZigBee in unlicensed spectrum bands. We focus on a data-driven approach that employs a supervised-learning method that uses received signal strength indicator (RSSI) data to train Deep Convolutional Neural Networks (CNNs). We propose a simple measurement methodology for collecting RSSI training data which preserves temporal and spectral properties of the target signal. Real experimental results using an open-source 2.4 GHz wireless development platform Ubertooth show that the proposed sampling method maintains the same accuracy with only a 10% level of sampling data for the same neural network architecture.

• Journal of the Institute of Convergence Signal Processing
• /
• v.25 no.1
• /
• pp.7-14
• /
• 2024

This study conducted a comparative experiment on the continuity of time series data and the classification performance of artificial intelligence models. In BCI research using EEG signals, the performance of behavior and thought classification improved as the continuity of the data decreased. In particular, LSTM achieved a high performance of 0.8728 on data with low continuity, and DNN showed a performance of 0.9178 when continuity was not considered. This suggests that data without continuity may perform better. Additionally, data without continuity showed better performance in task classification. These results suggest that BCI research based on EEG signals can perform better by showing various data characteristics through shuffling rather than considering data continuity.

• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.1-10
• /
• 2020

In this paper, we propose a new pornographic content detection scheme using bi-directional relationships between neighboring auditory signals in order to accurately detect sound-centered obscene contents that are rapidly spreading via the Internet. To capture the bi-directional relationships between neighboring signals, we design a multilayered bi-directional dilated-causal convolution network by stacking several dilated-causal convolution blocks each of which performs bi-directional dilated-causal convolution operations. To verify the performance of the proposed scheme, we compare its accuracy to those of the previous two schemes each of which uses simple auditory feature vectors with a support vector machine and uses only the forward relationships in audio signals by a previous stack of dilated-causal convolution layers. As the results, the proposed scheme produces an accuracy of up to 84.38% that is superior performance up to 25.80% than other two comparison schemes.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.10
• /
• pp.166-174
• /
• 1998

Neural networks, having highly nonlinear dynamics by virtue of the distributed nonlinearities and the learing ability, have the potential for the adaptive prediction of nonstationary signals. This paper describes the nonlinear prediction of these signals in two ways; using a nonlinear module and the cascade combination of nonlinear and linear modules. Fully-connected recurrent neural networks (RNNs) and a conventional tapped-delay-line (TDL) filter are used as the nonlinear and linear modules respectively. The dynamic behavior of the proposed predictors is demonstrated for chaotic time series adn speech signals. For the relative comparison of prediction performance, the proposed predictors are compared with a conventional ARMA linear prediction model. Experimental results show that the neural networks based adaptive predictor ourperforms the traditional linear scheme significantly. We also find that the cascade combination predictor is well suitable for the prediction of the time series which contain large variations of signal amplitude.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.166-166
• /
• 2017

모돈의 건강 상태를 정량 지수화 하기 위한 연구를 수행 중이다. 지제이상, 섭식 불량, 수면 패턴 등의 운동 특성 분석을 위하여 복수의 초음파 센서를 이용하였다. 시계열 계측 신호를 분석하여 정량 지수화를 수행하는 과정에서 주파수 도메인 분석을 시도하였다. 이 과정에서 주파수 도메인의 분해능에 따른 편차 극복을 위한 비선형 모델링을 수행하였다. 또한 인접한 시계열 데이터 구간 간의 상관성 분석이 가능하면 대용량 데이터의 실시간 처리로 인한 지연 시간 극복 및 기대되는 예후에 대한 조기 진단이 가능할 것이다. 본 연구에서는 구글에서 제공하는 Tensorflow와 NVIDIA에서 제공하는 CUDA 엔진을 동시 적용한 심층 학습 시스템을 이용하였다. 전 처리를 위하여 주파수 분해능 (2분, 3분, 5분, 7분, 11분, 13분, 17분, 19분)에 따른 데이터 집합을 1단계로 두고, 상위 10 순위 안에 드는 파워 스펙트럼 밀도의 크기를 2단계로 하여, 총 2~10개의 입력 노드를 순차적으로 선정하였고, 동일한 방식으로 인접한 시계열의 파워 스펙터럼 밀도를 순위를 변화시켜 지정하였다. 대표적인 심층학습 모델인 Softmax regression with a multilayer convolutional network를 이용하여 Recursive feature selection 경우의 수를 $8{\times}9{\times}9$로 총 648 가지 선정하고, Epoch는 10,000회로 지정하였다. Calibration 모델링의 경우 Cost function이 10% 이하인 경우 해당 경우의 학습을 중단하였으며, 모델 간 상호 교차 검증을 수행하기 위하여 $_8C_2{\times}_8C_2{\times}_8C_2$ 경우의 수에 대한 Verification test를 수행하였다. Calibration 과정 상 모든 경우에 대하여 10% 이하의 Cost function 값을 보였으나, 검증 테스트 과정에서 모든 경우에 대하여 $r^2$ < 0.5 인 결정 계수 값이 나타났다. 단적으로 심층학습 모델의 과도한 적합(Over fitting) 방식의 한계를 보인 것이라 판단할 수 있다. 적합한 Feature selection 및 심층 학습 모델에 대한 지속적이고 추가적인 고려를 통해 과도적합을 해소함과 동시에 실효적이고 활용 가능한 Classification을 위한 입, 출력 노드 단의 전후 Indexing, Quantization에 대한 고려가 필요할 것이다. 이를 통해 모돈 생체 정보 정량화를 위한 지능형 현장 진단 기술 연구를 지속할 것이다.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.27 no.2
• /
• pp.87-95
• /
• 1990

Conventional methods to estimate natural frequencies and damping ratios of structures from measured response time series obtained during impact tests are reviewed. Maximum Entropy Method and Least Square Prony Method are introduced to alleviate the inherent limitation of the conventional methods. The performance of the methods are explored through computer simulation. As an example of application, they are applied to the time series obtained from an anchor drop-and-snup test of a container ship and the result is compared to that of conventional FFT method. As a result of the computer simulation, it is found that Maximum Entropy Method is very efficient to estimate natural frequencies of structures when two neighboring natural frequencies are close enough and short data records are only available, but it is not a reliable estimator for damping ratios. And it is also found that Least Square Prony Method is efficient to estimate the natural frequencies and damping ratios of highly damped structural system, but the estimation efficiency of damping ratios is significantly deteriorated in the presence of significant additive noise.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.197-200
• /
• 2000

최대 수용전력 시계열 데이터를 수집하여 카오스적 성질을 분석하고 퍼지 제어기로부터 추론되어진 제어 값으로 특정 플랜트의 단기예측을 수행하는 카오스 퍼지 제어기를 구성하고 시뮬레이션을 통하여 실제 데이터와의 오차 검토를 통하여 카오스 퍼지 제어기의 강인성을 검증하고 이 시스템을 통하여 얻어진 결과와 실제 데이터를 비교함으로써 제어기의 성능을 평가한다.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.431-436
• /
• 2005

This paper describes how to diagnose SBR plant equipment using time-series data mining. It shows the equipment diagnostics based upon vibration signals that are acquired front each device lot process control. Data transform techniques including two data preprocessing skills and data mining methods were employed in the data analysis. The proposed method is not only suitable for SBR equipment, but is also suitable for other Industrial devices. The experimental results performed on a lab-scale SBR plant show a good equip-ment-management performance.