• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.1-8
• /
• 2021

In this paper, we propose reinforced VGG style network structure for low performance embedded system to classify low resolution infrared image. The combination of reinforced VGG style network structure and global average pooling makes lower computational complexity and higher accuracy. The proposed method classify the synthesize image which have 9 class 3,723,328ea images made from OKTAL-SE tool. The reinforced VGG style network structure composed of 4 filters on input and 16 filters on output from max pooling layer shows about 34% lower computational complexity and about 2.4% higher accuracy then the first parameter minimized network structure made for embedded system composed of 8 filters on input and 8 filters on output from max pooling layer. Finally we get 96.1% accuracy model. Additionally we confirmed the about 31% lower inference lead time in ported C code.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.529-536
• /
• 2022

In the past two years, Severe Acute Respiratory Syndrome Coronavirus-2(SARS-CoV-2) has been hitting more and more to people. This paper proposes a novel U-Net Convolutional Neural Network to classify and segment COVID-19 lung CT images, which contains Sub Coding Block (SCB), Atrous Spatial Pyramid Pooling(ASPP) and Attention Gate(AG). Three different models such as FCN, U-Net and U-Net-SCB are designed to compare the proposed model and the best optimizer and atrous rate are chosen for the proposed model. The simulation results show that the proposed U-Net-MMFE has the best Dice segmentation coefficient of 94.79% for the COVID-19 CT scan digital image dataset compared with other segmentation models when atrous rate is 12 and the optimizer is Adam.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.9-15
• /
• 2023

Metaverse is a modern new technology that is advancing quickly. The goal of this study is to investigate this technique from the perspective of computer vision as well as general perspective. A thorough analysis of computer vision related Metaverse topics has been done in this study. Its history, method, architecture, benefits, and drawbacks are all covered. The Metaverse's future and the steps that must be taken to adapt to this technology are described. The concepts of Mixed Reality (MR), Augmented Reality (AR), Extended Reality (XR) and Virtual Reality (VR) are briefly discussed. The role of computer vision and its application, advantages and disadvantages and the future research areas are discussed.

• Information and Communications Magazine
• /
• v.33 no.10
• /
• pp.49-56
• /
• 2016

본 논문에서는 패턴 인식 및 회귀 문제를 풀기 위해 쓰이는 기계학습에 대한 전반적인 이론과 설계방법에 대해 알아본다. 대표적인 기계학습 방법인 신경회로망과 기저벡터머신 등에 대해 소개하고 이러한 기계학습 모델을 선택하고 구축하는 데에 있어 고려해야 하는 문제점들에 대해 이야기 한다. 그리고 특징 추출 과정이 기계학습 모델의 성능에 어떻게 영향을 미치는지, 일반적으로 특징 추출을 위해 어떤 방법들이 사용되는 지에 대해 알아본다. 또한, 최근 새로운 패러다임으로 대두되고 있는 딥러닝에 대해 소개한다. 자가인코더, 제한볼츠만기계, 컨볼루션신경회로망, 회귀신경회로망과 같이 딥러닝 기술이 적용된 대표적인 신경망 구조에 대해 설명하고 기존의 기계학습 모델과 비교하여 딥러닝이 가지고 있는 특장점을 알아본다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.5
• /
• pp.801-808
• /
• 2022

Research on how to embed knowledge in large-scale Linked Data and apply neural network models for entity matching is relatively scarce. The most fundamental problem with this is that different labels lead to lexical heterogeneity. In this paper, we propose an extended GCN (Graph Convolutional Network) model that combines re-align structure to solve this lexical heterogeneity problem. The proposed model improved the performance by 53% and 40%, respectively, compared to the existing embedded-based MTransE and BootEA models, and improved the performance by 5.1% compared to the GCN-based RDGCN model.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.2
• /
• pp.170-178
• /
• 2019

Classification of radar signals in the field of electronic warfare is a problem of discriminating threat types by analyzing enemy threat radar signals such as aircraft, radar, and missile received through electronic warfare equipment. Recent radar systems have adopted a variety of modulation schemes that are different from those used in conventional systems, and are often difficult to analyze using existing algorithms. Also, it is necessary to design a robust algorithm for the signal received in the real environment due to the environmental influence and the measurement error due to the characteristics of the hardware. In this paper, we propose a radar signal classification method which are not affected by radar signal modulation methods and noise generation by using deep learning techniques.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.805-809
• /
• 2018

In this paper, we analyze the change of accuracy when fixed point arithmetic is used instead of floating point arithmetic in binary weight network(BWN). We observed the change of accuracy by varying total bit size and fraction bit size. If the integer part is not changed after fixed point approximation, there is no significant decrease in accuracy compared to the floating-point operation. When overflow occurs in the integer part, the approximation to the maximum or minimum of the fixed point representation minimizes the decrease in accuracy. The results of this paper can be applied to the minimization of memory and hardware resource requirement in the implementation of FPGA-based BWN accelerator.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.135-142
• /
• 2023

In addressing the prominent issues of climate change, resource scarcity, and environmental pollution associated with household waste, extensive research has been conducted on intelligent waste classification methods. These efforts range from traditional classification algorithms to machine learning and neural networks. However, challenges persist in effectively classifying waste in diverse environments and conditions due to insufficient datasets, increased complexity in neural network architectures, and performance limitations for real-world applications. Therefore, this paper proposes i-YOLOX as a solution for rapid classification and improved accuracy. The proposed model is evaluated based on network parameters, detection speed, and accuracy. To achieve this, a dataset comprising 10,000 samples of household waste, spanning 17 waste categories, is created. The i-YOLOX architecture is constructed by introducing the Involution channel convolution operator and the Convolution Branch Attention Module (CBAM) into the YOLOX structure. A comparative analysis is conducted with the performance of the existing YOLO architecture. Experimental results demonstrate that i-YOLOX enhances the detection speed and accuracy of waste objects in complex scenes compared to conventional neural networks. This confirms the effectiveness of the proposed i-YOLOX architecture in the detection and classification of multiple household waste objects.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.