• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.461-464
• /
• 1998

Lateral Information Propagation Neural Networks (LIPN) is proposed for on-line interpolation. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. Information propagates among neighbor nodes laterally and inter-node interpolation is achieved. Through several simulation experiments, real time reconstruction of the nonlinear image information is processed. 1-D LIPN hardware has been implemented with general purpose analog ICs to test the interpolation capability of the proposed neural networks. Experiments with static and dynamic signals have been done upon the LIPN hardware.

• Journal of Web Engineering
• /
• v.20 no.8
• /
• pp.2413-2432
• /
• 2021

Recently, the demand for high-quality video content has rapidly been increasing, led by the development of network technology and the growth in video streaming platforms. In particular, displays with a high refresh rate, such as 120 Hz, have become popular. However, the visual quality is only enhanced if the video stream is produced at the same high frame rate. For the high quality, conventional videos with a low frame rate should be converted into a high frame rate in real time. This paper introduces a bidirectional intermediate flow estimation method for real-time video frame interpolation. A bidirectional intermediate optical flow is directly estimated to predict an accurate intermediate frame. For real-time processing, multiple frames are interpolated with a single intermediate optical flow and parts of the network are implemented in 16-bit floating-point precision. Perceptual loss is also applied to improve the cognitive performance of the interpolated frames. The experimental results showed a high prediction accuracy of 35.54 dB on the Vimeo90K triplet benchmark dataset. The interpolation speed of 84 fps was achieved for 480p resolution.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.

• Geophysics and Geophysical Exploration
• /
• v.25 no.3
• /
• pp.140-161
• /
• 2022

Seismic data with missing traces are often obtained regularly or irregularly due to environmental and economic constraints in their acquisition. Accordingly, seismic data interpolation is an essential step in seismic data processing. Recently, research activity on machine learning-based seismic data interpolation has been flourishing. In particular, convolutional neural network (CNN) and generative adversarial network (GAN), which are widely used algorithms for super-resolution problem solving in the image processing field, are also used for seismic data interpolation. In this study, CNN-based algorithm, U-Net and GAN-based algorithm, and conditional Wasserstein GAN (cWGAN) were used as seismic data interpolation methods. The results and performances of the methods were evaluated thoroughly to find an optimal interpolation method, which reconstructs with high accuracy missing seismic data. The work process for model training and performance evaluation was divided into two cases (i.e., Cases I and II). In Case I, we trained the model using only the regularly sampled data with 50% missing traces. We evaluated the model performance by applying the trained model to a total of six different test datasets, which consisted of a combination of regular, irregular, and sampling ratios. In Case II, six different models were generated using the training datasets sampled in the same way as the six test datasets. The models were applied to the same test datasets used in Case I to compare the results. We found that cWGAN showed better prediction performance than U-Net with higher PSNR and SSIM. However, cWGAN generated additional noise to the prediction results; thus, an ensemble technique was performed to remove the noise and improve the accuracy. The cWGAN ensemble model removed successfully the noise and showed improved PSNR and SSIM compared with existing individual models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2581-2594
• /
• 2018

The microcell terrain is the most common wireless network terrain in our life. In order to solve wireless network optimization of weak coverage in the microcell terrain, improve call quality and reduce the cost of the premise, power amplifiers in base stations should be adjusted according to user volume. In this paper, characteristics of microcell topography are obtained after analysis. According to the topography characteristics of different microcells, changes in the number of users at different times have been estimated, meanwhile, the number of scatter users are also obtained by monitoring the PCCPCH RSCP and other parameters. Then B-Spline interpolation method has been applied to scatter users to obtain the continuous relationship between the number of users and time. On this basis, power amplification can be chosen according to changes in the number of users. The methods adopted by this paper are also applied in the engineering practice, sampling and interpolation are used to obtain the number of users at all times, so that the power amplification can be adjusted by the number of users in a microcell. Such a method is able to optimize wireless network and achieve a goal of expanding the area of base stations, reduce call drop rate and increase capacity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3690-3713
• /
• 2019

According to the main group key management schemes logical key hierarchy (LKH), exclusion basis systems (EBS) and other group key schemes are limited in network structure, collusion attack, high energy consumption, and the single point of failure, this paper presents a group key management scheme for wireless sensor networks based on Lagrange interpolation polynomial characteristic (AGKMS). That Chinese remainder theorem is turned into a Lagrange interpolation polynomial based on the function property of Chinese remainder theorem firstly. And then the base station (BS) generates a Lagrange interpolation polynomial function f(x) and turns it to be a mix-function f(x)' based on the key information m(i) of node i. In the end, node i can obtain the group key K by receiving the message f(m(i))' from the cluster head node j. The analysis results of safety performance show that AGKMS has good network security, key independence, anti-capture, low storage cost, low computation cost, and good scalability.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5955-5977
• /
• 2018

Performance of the interpolation algorithm used in the technique of bi-dimensional empirical mode decomposition directly affects its popularization and application, so that the researchers pay more attention to the algorithm reasonable, accurate and fast. However, it has been a lack of an adaptive interpolation algorithm that is relatively satisfactory for the bi-dimensional empirical mode decomposition (BEMD) and is derived from the image characteristics. In view of this, this paper proposes an image interpolation algorithm based on the particle swarm and fractal. Its procedure includes: to analyze the given image by using the fractal brown function, to pick up the feature quantity from the image, and then to operate the adaptive image interpolation in terms of the obtained feature quantity. All parameters involved in the interpolation process are determined by using the particle swarm optimization algorithm. The presented interpolation algorithm can solve those problems of low efficiency and poor precision in the interpolation operation of bi-dimensional empirical mode decomposition and can also result in accurate and reliable bi-dimensional intrinsic modal functions with higher speed in the decomposition of the image. It lays the foundation for the further popularization and application of the bi-dimensional empirical mode decomposition algorithm.

• Journal of the Korean Society of Mechanical Technology
• /
• v.20 no.6
• /
• pp.872-878
• /
• 2018

Steam tables including superheated, saturated and compressed region were simultaneously modeled using the neural networks. Pressure and temperature were used as two inputs for superheated and compressed region. On the other hand Pressure and dryness fraction were two inputs for saturated region. The outputs were specific volume, specific enthalpy and specific entropy. The neural network model were compared with the linear interpolation model in terms of the percentage relative errors. The criterion of judgement was selected with the percentage relative error of 1%. In conclusion the neural networks showed better results than the interpolation method for all data of superheated and compressed region and specific volume of saturated region, but similar for specific enthalpy and entropy of saturated region.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.3
• /
• pp.89-95
• /
• 1997

This paper examines the relation between multidimensional linear interpolation (MDI) and regularization net-works, and shows that an MDI is a special form of regularization networks. For this purpose we propose a triangular basis function(TBF) network. Also we verified the condition when our proposed TBF becomes a well-known radial basis function (RBF).

• Journal of applied mathematics & informatics
• /
• v.9 no.2
• /
• pp.879-890
• /
• 2002

In this paper we consider open queueing system with a Poisson arrival process which have a finite upper bound on the arrival rate for which the system is stable. Interpolation approximations for quantities of interest, such as moments of the sojourn time distribution, have previously been developed for such systems, utilizing exact light and heavy traffic limits. These limits cannot always be easily computed for complex systems. Thus we consider an interpolation approximation where all of the relevant information is estimated via simulation. We show that all the relevant information can in fact be simultaneously estimated in a single regenerative simulation at any arrival rate. In addition to light and heavy traffic limits, both the quantity of interest and its derivative (with respect to the arrival rate) are estimated at the arrival rate of the simulation. All of the estimates are then combined, using a least squares procedure, to provide an interpolation approximation.