• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.179-193
• /
• 2023

This study explores an alternative to the existing centralized process for data anomaly detection in modern Internet of Things (IoT)-based structural health monitoring (SHM) systems. An edge intelligence framework is proposed for the early detection and classification of various data anomalies facilitating quality enhancement of acquired data before transmitting to a central system. State-of-the-art deep neural network pruning techniques are investigated and compared aiming to significantly reduce the network size so that it can run efficiently on resource-constrained edge devices such as wireless smart sensors. Further, depthwise separable convolution (DSC) is invoked, the integration of which with advanced structural pruning methods exhibited superior compression capability. Last but not least, quantization-aware training (QAT) is adopted for faster processing and lower memory and power consumption. The proposed edge intelligence framework will eventually lead to reduced network overload and latency. This will enable intelligent self-adaptation strategies to be employed to timely deal with a faulty sensor, minimizing the wasteful use of power, memory, and other resources in wireless smart sensors, increasing efficiency, and reducing maintenance costs for modern smart SHM systems. This study presents a theoretical foundation for the proposed framework, the validation of which through actual field trials is a scope for future work.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1946-1952
• /
• 1999

A new image compression method to preserve edge characteristics in reconstructed images using an unsupervised learning neural is proposed in this paper. By the unsupervised competitive learning which generalizes previously proposed Centroid Neural Network(CNN) algorithm with the geometric characteristics of edge area and statistical characteristics of image data, more codevectors are allocated in the edge areas to provide the more accurate edges in reconstructed image. Experimental results show that the proposed method gives improved edge in reconstructed images when compared with SOM, Modified SOM and M/R-CNN.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.6
• /
• pp.95-101
• /
• 2001

This work is concerned with construction of the intelligence stress predictor far compression strength evaluation using neural network-ultrasonic waves. The contact pressure in jointed plates was measured by using ultrasonic technique. Neural network is used to evaluate and predict contact pressure from the results of the calibration curves. The organized neural system was leaned with the accuracy of 99%, as a result of learning the ultrasonic echo ratio to the contact pressure measurement between SM45C and STS410 materials. And it could be evaluated and predicted with the accuracy of 90% in the evaluation of ultrasonic echo ratio difference in the same surface roughness and contact pressure, and 85% in the prediction of virtual ultrasonic echo ratio. Thus the proposed stress predictor is very useful for the evaluation and prediction of the contact pressure between SM45C and STS410 materials.

• Journal of the Korean Geotechnical Society
• /
• v.17 no.6
• /
• pp.25-36
• /
• 2001

The purpose of this paper is to discuss the effects of soil properties such as liquid limit, water content, etc. on the compression index and to propose the empirical equation of compression index far regional clay and to verify the application Back Propagation Neural Network(BPNN). The compression index values obtained from laboratory tests are in the range of 0.01 to 3.06 for clay soils sampled in eleven regions. As the compare with the results of laboratory test and the predicted compression index value from the proposed empirical equations, the results of empirical equations including single soil parameter have a possibility to be overestimated. Also, the results of empirical equations including multiple soil parameters closed to the measured value more than that of empirical equations including single soil parameter, but the standard error for measured value obtained larger than 0.05. For these reasons, the empirical equations including single or multiple soil parameters proposed base on the results of laboratory test and the determination coefficient is up to 0.89. The result of BPNN shows that correlation coefficient and standard error between test and neural network result is larger than 0.925 and smaller than 0.0196, which means high correlativity, respectively. Especially, the estimated result by neural network, using only three parameters such as natural water content, dry unit weight and in-situ void ratio among various factors is available to the estimation of compression index and the correlation coefficient is 0.974. This result verified the possibility that if BPNN use, the compression index can be predicted by the parameters, which obtained from simplex field test.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.129-133
• /
• 2023

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.112-115
• /
• 2022

The process of deep learning usually needs to deal with massive data which has greatly limited the development of deep learning technologies today. Convolutional Neural Network (CNN) structure is often used to solve image classification problems. However, a large number of images may be required in order to train an image in CNN, which is a heavy burden for existing computer systems to handle. If the image data can be compressed under the premise that the computer hardware system remains unchanged, it is possible to train more datasets in deep learning. However, image compression usually adopts the form of lossy compression, which will lose part of the image information. If the lost information is key information, it may affect learning performance. In this paper, we will analyze the effect of image compression on deep learning performance on CNN-based cat and dog classification. Through the experiment results, we conclude that the compression of images does not have a significant impact on the accuracy of deep learning.

• Journal of Broadcast Engineering
• /
• v.26 no.7
• /
• pp.868-876
• /
• 2021

Deploying deep neural network model training performs remarkable performance in the fields of Object detection and Instance segmentation. To train these models, features are first extracted from the input image using a backbone network. The extracted features can be reused by various tasks. Research has been actively conducted to serve various tasks by using these learned features. In this process, standardization discussions about encoding, decoding, and transmission methods are proceeding actively. In this scenario, it is necessary to analyze the response characteristics of features against various distortions that may occur in the data transmission or data compression process. In this paper, experiment was conducted to inject various distortions into the feature in the object recognition task. And analyze the mAP (mean Average Precision) metric between the predicted value output from the neural network and the target value as the intensity of various distortions was increased. Experiments have shown that features are more robust to distortion than images. And this points out that using the feature as transmission means can prevent the loss of information against the various distortions during data transmission and compression process.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Tunnel and Underground Space
• /
• v.28 no.3
• /
• pp.277-291
• /
• 2018

LSTM (Long Short-Term Memory) algorithm which is a kind of recurrent neural network was used to establish a model to predict the stress-strain curve of an material under uniaxial compression. The model was established from the stress-strain data from uniaxial compression tests of silica-gypsum specimens. After training the model, it can predict the behavior of the material up to the failure state by using an early stage of stress-strain curve whose stress is very low. Because the LSTM neural network predict a value by using the previous state of data and proceed forward step by step, a higher error was found at the prediction of higher stress state due to the accumulation of error. However, this model generally predict the stress-strain curve with high accuracy. The accuracy of both LSTM and tangential prediction models increased with increased length of input data, while a difference in performance between them decreased as the amount of input data increased. LSTM model showed relatively superior performance to the tangential prediction when only few input data was given, which enhanced the necessity for application of the model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.11
• /
• pp.1173-1178
• /
• 2011

The power generated by wind turbines changes rapidly because of the continuous fluctuation of wind speed and direction. It is important for the power industry to have the capability to predict the changing wind power. In this paper, neural network based wind power prediction scheme which uses wind speed and direction is considered. In order to get a better prediction result, compression function which can be applied to the measurement data is introduced. Empirical data obtained from wind farm located in Kunsan is considered to verify the performance of the compression function.