• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.165-172
• /
• 2020

In this paper we propose an uses on-device-based edge computing technology and big data analysis methods through the use of on-device-based edge computing technology and analysis of big data, which are distributed computing paradigms that introduce computations and storage devices where necessary to solve problems such as transmission delays that occur when data is transmitted to central centers and processed in current general smart factories. However, even if edge computing-based technology is applied in practice, the increase in devices on the network edge will result in large amounts of data being transferred to the data center, resulting in the network band reaching its limits, which, despite the improvement of network technology, does not guarantee acceptable transfer speeds and response times, which are critical requirements for many applications. It provides the basis for developing into an AI-based facility prediction conservation analysis tool that can apply deep learning suitable for big data in the future by supporting intelligent facility management that can support productivity growth through research that can be applied to the field of facility preservation and smart factory industry with integrated hardware technology that can accommodate these requirements and factory management and control technology.

• The Journal of Korean Institute of Information Technology
• /
• v.15 no.12
• /
• pp.157-164
• /
• 2017

Mobile ECG signal measurement is a technique to measure small signals of several mV, and many studies have been conducted to remove noise including wandering scheme. Removal of the equipotential line noise caused by shaking or movement of the electrode cable is one of the core research contents for the electrocardiogram measurement. In this study, we proposed a modified step-size of combined NLMS(normalized least squares) and DLMS(delayed least squares) adaptive filter to eliminate baseline noise from ECG signals. The proposed method mainly adjusts initial filter step-size to reduce distortion of original ECG signals characteristic after eliminating baseline noise. The modified filter step-size is scaled by filter order size and distortion minimization factor. This method is suitable for portable ECG device with a small processor and less power consumption. This technique also decreases computation time which is essential for real-time filtering. The proposed filter also increase the signal to noise ratio (SNR) compared to conventional NLMS filter.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.49-55
• /
• 2021

Recently, a small tracking radar requires the development of a small millimeter wave tracking radar having a high range resolution that can acquire and track a target in various environments and disable the target system with a single blow. Small millimeter wave tracking radar with high range resolution needs to implement a signal processor that can process wide bandwidth signals in real time and meet the requirements of small tracking radar. In this paper, we designed a signal processor that can perform the role and function of a signal processor for a small millimeter wave tracking radar. The signal processor for the small millimeter wave tracking radar requires the real-time processing of input signal of OOOMHz center frequency and OOOMHz bandwidth from 8 channels. In order to satisfy the requirements of the signal processor, the signal processor was designed by applying the high-performance FPGA (Field Programmable Gate Array) and ADC (Analog-to-digital converter) for pre-processing operations, such as DDC (Digital Down Converter) and FFT (Fast Fourier Transform). Finally, the signal processor of the small millimeter wave tracking radar was verified via performance test.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.5
• /
• pp.901-909
• /
• 2021

Since mobile devices have limited computational resources, it tends to use the cloud to compute or store data. As real-time becomes more important due to 5G, many studies have been conducted on edge clouds that computes at locations closer to users than central clouds. The farther the user's physical distance from the edge cloud connected to base station is, the slower the network transmits. So applications should be migrated and re-run to nearby edge cloud for smooth service use. We run applications in docker containers, which is independent of the host operating system and has a relatively light images size compared to the virtual machine. Existing migration studies have been experimented by using network simulators. It uses fixed values, so it is different from the results in the real-world environment. In addition, the method of migrating images through shared storage was used, which poses a risk of packet content exposure. In this paper, Containers are migrated with Secure CoPy(SCP) method, a data encryption transmission, by establishing an edge computing environment in a real-world environment. It compares migration time with Network File System, one of the shared storage methods, and analyzes network packets to verify safety.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.485-492
• /
• 2021

In this paper, we propose the development of a defect inspection system for polygonal containers. Embedded board consists of main part, communication part, input/output part, etc. The main unit is a main arithmetic unit, and the operating system that drives the embedded board is ported to control input/output for external communication, sensors and control. The input/output unit converts the electrical signals of the sensors installed in the field into digital and transmits them to the main module and plays the role of controlling the external stepper motor. The communication unit performs a role of setting an image capturing camera trigger and driving setting of the control device. The input/output unit converts the electrical signals of the control switches and sensors into digital and transmits them to the main module. In the input circuit for receiving the pulse input related to the operation mode, etc., a photocoupler is designed for each input port in order to minimize the interference of external noise. In order to objectively evaluate the accuracy of the development of the proposed polygonal container defect inspection system, comparison with other machine vision inspection systems is required, but it is impossible because there is currently no machine vision inspection system for polygonal containers. Therefore, by measuring the operation timing with an oscilloscope, it was confirmed that waveforms such as Test Time, One Angle Pulse Value, One Pulse Time, Camera Trigger Pulse, and BLU brightness control were accurately output.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.7-14
• /
• 2019

In this paper, we propose a Cascade Classifier face detection method using the Haar-like feature, which is complemented by the Flood Fill algorithm for lossy areas due to illumination and shadow in YCbCr color space extraction. The Cascade Classifier using Haar-like features can generate noise and loss regions due to lighting, shadow, etc. because skin color extraction using existing YCbCr color space in image only uses threshold value. In order to solve this problem, noise is removed by erosion and expansion calculation, and the loss region is estimated by using the Flood Fill algorithm to estimate the loss region. A threshold value of the YCbCr color space was further allowed for the estimated area. For the remaining loss area, the color was filled in as the average value of the additional allowed areas among the areas estimated above. We extracted faces using Haar-like Cascade Classifier. The accuracy of the proposed method is improved by about 4% and the detection rate of the proposed method is improved by about 2% than that of the Haar-like Cascade Classifier by using only the YCbCr color space.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1179-1192
• /
• 2018

In order to detect the Antarctic Polar Front (PF) among the main fronts in the Southern Ocean, this study is based on the combinations of satellite-based sea surface temperature (SST) and height (SSH) observations. For accurate PF detection, we classified the signals as front or non-front grids based on the Bayesian decision theory from daily SST and SSH datasets, and then spatio-temporal synthesis has been performed to remove primary noises and to supplement geographical connectivity of the front grids. In addition, sea ice and coastal masking were employed in order to remove the noise that still remains even after performing the processes and morphology operations. Finally, we selected only the southernmost grids, which can be considered as fronts and determined as the monthly PF by a linear smoothing spline optimization method. The mean positions of PF in this study are very similar to those of the PFs reported by the previous studies, and it is likely to be well represents PF formation along the bottom topography known as one of the major influences of the PF maintenance. The seasonal variation in the positions of PF is high in the Ross Sea sector (${\sim}180^{\circ}W$), and Australia sector ($120^{\circ}E-140^{\circ}E$), and these variations are quite similar to the previous studies. Therefore, it is expected that the detection approach for the PF position applied in this study and the final composite have a value that can be used in related research to be carried out on the long term time-scale.