• Smart Structures and Systems
• /
• 제20권6호
• /
• pp.669-682
• /
• 2017

The normalised version of bispectrum, the so-called bicoherence, has often proved a reliable method of damage detection on engineering applications. Indeed, higher-order spectral analysis (HOSA) has the advantage of being able to detect non-linearity in the structural dynamic response while being insensitive to ambient vibrations. Skewness in the response may be easily spotted and related to damage conditions, as the majority of common faults and cracks shows bilinear effects. The present study tries to extend the application of HOSA to damage localisation, resorting to a neural network based classification algorithm. In order to validate the approach, a non-linear finite element model of a 4-meters-long cantilever beam has been built. This model could be seen as a first generic concept of more complex structural systems, such as aircraft wings, wind turbine blades, etc. The main aim of the study is to train a Neural Network (NN) able to classify different damage locations, when fed with bispectra. These are computed using the dynamic response of the FE nonlinear model to random noise excitation.

• International Journal of Automotive Technology
• /
• 제7권3호
• /
• pp.361-367
• /
• 2006

This paper describes a novel stereo vision based localization of free parking site, which recognizes the target position of automatic parking system. Pixel structure classification and feature based stereo matching extract the 3D information of parking site in real time. The pixel structure represents intensity configuration around a pixel and the feature based stereo matching uses step-by-step investigation strategy to reduce computational load. This paper considers only parking site divided by marking, which is generally drawn according to relevant standards. Parking site marking is separated by plane surface constraint and is transformed into bird's eye view, on which template matching is performed to determine the location of parking site. Obstacle depth map, which is generated from the disparity of adjacent vehicles, can be used as the guideline of template matching by limiting search range and orientation. Proposed method using both the obstacle depth map and the bird's eye view of parking site marking increases operation speed and robustness to visual noise by effectively limiting search range.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권10호
• /
• pp.4072-4091
• /
• 2015

A separation of text and non-text elements plays an important role in document layout analysis. A number of approaches have been proposed but the quality of separation result is still limited due to the complex of the document layout. In this paper, we present an efficient method for the classification of text and non-text components in document image. It is the combination of whitespace analysis with multi-layer homogeneous regions which called recursive filter. Firstly, the input binary document is analyzed by connected components analysis and whitespace extraction. Secondly, a heuristic filter is applied to identify non-text components. After that, using statistical method, we implement the recursive filter on multi-layer homogeneous regions to identify all text and non-text elements of the binary image. Finally, all regions will be reshaped and remove noise to get the text document and non-text document. Experimental results on the ICDAR2009 page segmentation competition dataset and other datasets prove the effectiveness and superiority of proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.658-672
• /
• 2021

Since the signal with strong power need be demodulated first for successive interference cancellation (SIC) receiver in non-orthogonal multiple access (NOMA) systems, the base station (BS) need inform the near user terminal (UT), which has allocated higher power, of the far UT's modulation mode. To avoid unnecessary signaling overhead of control channel, a blind detection algorithm of NOMA signal modulation mode is designed in this paper. Taking the joint constellation density diagrams of NOMA signal as the detection features, the deep residual network is built for classification, so as to detect the modulation mode of NOMA signal. In view of the fact that the joint constellation diagrams are easily polluted by high intensity noise and lose their real distribution pattern, the wavelet denoising method is adopted to improve the quality of constellations. The simulation results represent that the proposed algorithm can achieve satisfactory detection accuracy in NOMA systems. In addition, the factors affecting the recognition performance are also verified and analyzed.

• 로봇학회논문지
• /
• 제13권4호
• /
• pp.265-271
• /
• 2018

The recent prosthetic technologies pursue to control multi-DOFs (degrees-of-freedom) hand and wrist. However, challenges such as high cost, wear-ability, and motion intent recognition for feedback control still remain for the use in daily living activities. The paper proposes a multi-channel knit band sensor to worn easily for surface EMG-based prosthetic control. The knitted electrodes were fabricated with conductive yarn, and the band except the electrodes are knitted using non-conductive yarn which has moisture wicking property. Two types of the knit bands are fabricated such as sixteen-electrodes for eight-channels and thirty-two electrodes for sixteen-channels. In order to substantiate the performance of the biopotential signal acquisition, several experiments are conducted. Signal to noise ratio (SNR) value of the knit band sensor was 18.48 dB. According to various forearm motions including hand and wrist, sixteen-channels EMG signals could be clearly distinguishable. In addition, the pattern recognition performance to control myoelectric prosthesis was verified in that overall classification accuracy of the RMS (root mean squares) filtered EMG signals (97.84%) was higher than that of the raw EMG signals (87.06%).

• 한국음향학회지
• /
• 제38권1호
• /
• pp.120-127
• /
• 2019

수동 소나 시스템에서 음원 깊이를 구분하는 연구는 수 십 년 동안 진행되어 왔다. 그 이유는 음원 깊이 구분을 통해 표적이 수상함인지 잠수함인지 식별할 수 있기 때문이다. 본 논문은 표적으로부터 수신된 소음 (또는 신호)의 채널 임펄스 응답을 이용하여 음원 깊이를 구분하였다. 송신신호에 대한 정보가 없는 상황에서 채널 임펄스 응답을 추정하기 위해 음선 기반 블라인드 디컨벌루션 기법이 사용되었다. 추정된 채널 임펄스 응답의 패턴에서 교차점은 음선의 상대적 도달 시간에 의하여 결정되며, 이는 표적 깊이 구분에 이용된다. 제안된 알고리즘은 시뮬레이션과 실험 데이터를 통하여 검증하였다.

• Current Optics and Photonics
• /
• 제3권5호
• /
• pp.466-472
• /
• 2019

A system for continuous-wave coherent Doppler lidar (CW lidar), made up of all-fiber structures and a coaxial transmission telescope, was set up for wind measurement in Hefei (31.84 N, 117.27 E), Anhui province of China. The lidar uses a fiber laser as a light source at a wavelength of $1.55{\mu}m$, and focuses the laser beam on a location 80 m away from the telescope. Using the CW lidar, radial wind measurement was carried out. Subsequently, the spectra of the atmospheric backscattered signal were analyzed. We tested the noise and obtained the lower limit of wind velocity as 0.721 m/s, through the Rayleigh criterion. According to the number of Doppler peaks in the radial wind spectrum, a classification retrieval algorithm (CRA) combining a Gaussian fitting algorithm and a spectral centroid algorithm is designed to estimate wind velocity. Compared to calibrated pulsed coherent wind lidar, the correlation coefficient for the wind velocity is 0.979, with a standard deviation of 0.103 m/s. The results show that CW lidar offers satisfactory performance and the potential for application in wind measurement.

• 방송공학회논문지
• /
• 제26권7호
• /
• pp.844-854
• /
• 2021

Semi-supervised learning (SSL) and few-shot learning (FSL) have shown impressive performance even then the volume of labeled data is very limited. However, SSL and FSL can encounter a significant performance degradation if the diversity gap between the labeled and unlabeled data is high. To reduce this diversity gap, we propose a novel scheme that relies on an autoencoder for generating pseudo examples. Specifically, the autoencoder is trained on a specific class using the available labeled data and the decoder of the trained autoencoder is then used to generate N samples of that specific class based on N random noise, sampled from a standard normal distribution. The above process is repeated for all the classes. Consequently, the generated data reduces the diversity gap and enhances the model performance. Extensive experiments on MNIST and FashionMNIST datasets for SSL and FSL verify the effectiveness of the proposed approach in terms of classification accuracy and robustness against adversarial attacks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.95-99
• /
• 2023

Recently Machine Learning has been considered as one of the active research areas of Computer Science. The various Artificial Intelligence techniques are used to solve the classification problems of environmental sciences, biological sciences, and medical sciences etc. Due to the heterogynous and malfunctioning weather sensors a considerable amount of noisy data with missing is generated, which is alarming situation for weather prediction stockholders. Filling of these missing values with proper method is really one of the significant problems. The data must be cleaned before applying prediction model to collect more precise & accurate results. In order to solve all above stated problems, this research proposes a novel weather forecasting system which consists upon two steps. The first step will prepare data by reducing the noise; whereas a decision model is constructed at second step using regression algorithm. The Confusion Matrix will be used to evaluation the proposed classifier.