• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.6
• /
• pp.545-550
• /
• 2004

Recent natural disasters like flooding and slope collapse have shown the need for natural risk management system, as they endanger directly public health and cause severe damages on the national economy. In order to improve the efficiency of risk management systems, this management system based on AANN(Auto-Associative Neural Network)is proposed in this paper. AANN can be effectively used for identification of abnormal data and data compression. The proposed AANN-based risk management system collects and stores measurement data from sensors and transmits them to remote server for web-monitoring. Generally, it is desirable to transmit the compressed data instead of raw data in normal state. However, if dangerous situation happens, rapid tramission of measurement data should be required. These requirements are easily satisfied by using AANN. In order to verify the feasibilities of the proposed system, The AANN-based risk management system is applied to slope collapse monitoring system.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.778-789
• /
• 2021

Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.84-85
• /
• 2019

MPEG-NNR (Compression of Neural Network for Multimedia Content Description and Analysis) aims to define a compressed and interoperable representation of trained neural networks. In this paper, we present a low-rank approximation to compress a CNN used for image compression, which is one of MPEG-NNR use cases. In the presented method, the low-rank approximation decomposes one 2D kernel matrix of weights into two 1D kernel matrix values in each convolution layer to reduce the data amount of weights. The evaluation results show that the model size of the original CNN is reduced to half as well as the inference runtime is reduced up to about 30% with negligible loss in PSNR.

• Computers and Concrete
• /
• v.8 no.5
• /
• pp.491-510
• /
• 2011

Before deciding if structures exposed to high temperature are to be repaired or demolished, their final state should be carefully examined. Destructive and non-destructive testing methods are generally applied for this purpose. Compressive strength and color change in mortars are observed as a result of the effects of high temperature. In this study, ordinary and pozzolan-added mortar samples were produced using different aggregates, and exposed to 100, 200, 300, 600, 900 and $1200^{\circ}C$. The samples were divided into two groups and cooled to room temperature in water and air separately. Compression tests were carried out on these samples, and the color change was evaluated by the Munsell Color System. The relationships between the change in compressive strength and color of mortars were determined by using a multi-layered feed-forward Neural Network model trained with the back-propagation algorithm. The results showed that providing accurate estimates of compressive strength by using the color components and ultrasonic pulse velocity design parameters were possible using the approach adopted in this study.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.383-386
• /
• 1997

In this paper, We proposed a parallel structure of the Neural Network model to nonlinear complex system. Neural Network was used as basic model which has learning ability and high tolerence level. This paper, we used Neural Network which has BP(Error Back Propagation Algorithm) model. But it sometimes has difficulty to append characteristic of input data to nonlinear system. So that, I used HCM(hard c-Means) method of clustering technique to append property of input data. Clustering Algorithms are used extensively not only to organized categorize data, but are also useful for data compression and model construction. Gas furance, a sewage treatment process are used to evaluate the performance of the proposed model and then obtained higher accuracy than other previous medels.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.4
• /
• pp.374-381
• /
• 1991

As a diagnostic image of hospitl, the utilization of digital image is steadily increasing. Image coding is indispensable for storing and compressing an enormous amount of diagnostic images economically and effectively. In this paper adaptive two stage vector quantization based on Kohonen's neural network for the compression of cardioangiography among typical angiography of radiographic image sequences is presented and the performance of the coding scheme is compare and gone over. In an attempt to exploit the known characteristics of changes in cardioangiography, relatively large blocks of image are quantized in the first stage and in the next stage the bloks subdivided by the threshold of quantization error are vector quantized employing the neural network of frequency sensitive competitive learning. The scheme is employed because the change produced in cardioangiography is due to such two types of motion as a heart itself and body motion, and a contrast dye material injected. Computer simulation shows that the good reproduction of images can be obtained at a bit rate of 0.78 bits/pixel.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.56 no.1
• /
• pp.28-36
• /
• 2007

Sensor networks are usually composed of tens or thousands of tiny devices with limited resources. Because of their limited resources, many researchers have studied on the energy management in the WSNs(Wireless Sensor Networks), especially taking into account communications efficiency. For effective data transmission and sensor fault detection in sensor network environment, a new remote monitoring system based on PCA(Principle Component Analysis) and AANN(Auto Associative Neural Network) is proposed. PCA and AANN have emerged as a useful tool for data compression and identification of abnormal data. Proposed system can be effectively applied to sensor network working in LEA2C(Low Energy Adaptive Connectionist Clustering) routing algorithms. To verify its applicability, some simulation studies on the data obtained from real WSNs are executed.

• Journal of the Korean Geotechnical Society
• /
• v.19 no.4
• /
• pp.287-298
• /
• 2003

The feasibility of using neural networks to model the complex relationship between piezocone measurements and the undrained shear strength of clays has been investigated. A three layered back propagation neural network model was developed based on actual undrained shear strengths, which were obtained from the isotrpoically and anisotrpoically consolidated triaxial compression test(CIUC and CAUC), and piezocone measurements compiled from various locations around the world. It was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was compared with conventional empirical method, direct correlation method, and theoretical method. It was found that the neural network model is not only capable of inferring a complex relationship between piezocone measurements and the undrained shear strength of clays but also gives a more precise and reliable undrained shear strength than theoretical and empirical approaches. Furthermore, neural network model has a possibility to be a generalized relationship between piezocone measurements and undrained shear strength over the various places and countries, while the present empirical correlations present the site specific relationship.

• Journal of Korea Multimedia Society
• /
• v.22 no.7
• /
• pp.790-803
• /
• 2019

The effects of different heat treatments on the sensory characteristics of abalones are studied in this study. In this paper, the sensory evaluation of abalone samples under different heat treatment conditions is carried out, and the evaluation results are analyzed. The three-dimensional (3D) scanning and reverse engineering are used in tooth modeling of the sensory evaluation of abalone samples under different heat treatment conditions. Besides, the chewing movement models are simplified into three modes, including the cutting mode, compressing mode and grinding mode, which are simulated using finite element simulation. The elastic modulus of the abalone samples is obtained through the compression testing using a texture analyzer to distinguish their material properties under different heat treatments and to obtain simulated mechanical parameters. Finally, taking the mechanical parameters of the finite element simulation of abalone chewing as input and sensory evaluation parameters as the output, BP neural network is established in which the sensory texture evaluation model of abalone samples is obtained. Through verification, the neural network prediction model can meet the requirements of food texture evaluation, with an average error of 9.12%.