• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.68-80
• /
• 2022

Since the launch of AI, technology development to implement complete and sophisticated AI functions has continued. In efforts to develop technologies for complete automation, Machine Learning techniques and deep learning techniques are mainly used. These techniques deal with supervised learning, unsupervised learning, and reinforcement learning as internal technical elements, and use the Big-data Analysis method again to set the cornerstone for decision-making. In addition, established decision-making is being improved through subsequent repetition and renewal of decision-making standards. In other words, big data analysis, which enables data classification and recognition/recognition, is important enough to be called a key technical element of AI function. Therefore, big data analysis itself is important and requires sophisticated analysis. In this study, among various tools that can analyze big data, we will use a Python program to find out what variables can affect addiction according to smartphone use in a decision tree environment. We the Python program checks whether data classification by decision tree shows the same performance as other tools, and sees if it can give reliability to decision-making about the addictiveness of smartphone use. Through the results of this study, it can be seen that there is no problem in performing big data analysis using any of the various statistical tools such as Python and R when analyzing big data.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.165-171
• /
• 2024

In this study, we present a novel approach for enhancing chest X-ray image classification (normal, Covid-19, edema, mass nodules, and pneumothorax) by combining contrastive learning and machine learning algorithms. A vast amount of unlabeled data was leveraged to learn representations so that data efficiency is improved as a means of addressing the limited availability of labeled data in X-ray images. Our approach involves training classification algorithms using the extracted features from a linear fine-tuned Momentum Contrast (MoCo) model. The MoCo architecture with a Resnet34, Resnet50, or Resnet101 backbone is trained to learn features from unlabeled data. Instead of only fine-tuning the linear classifier layer on the MoCopretrained model, we propose training nonlinear classifiers as substitutes for softmax in deep networks. The empirical results show that while the linear fine-tuned ImageNet-pretrained models achieved the highest accuracy of only 82.9% and the linear fine-tuned MoCo-pretrained models an increased highest accuracy of 84.8%, our proposed method offered a significant improvement and achieved the highest accuracy of 87.9%.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.318-331
• /
• 2022

With the recent development of hardware computing devices and software based frameworks, machine tasks using deep learning networks are expected to be utilized in various industrial fields and personal IoT devices. However, in order to overcome the limitations of high cost device for utilizing the deep learning network and that the user may not receive the results requested when only the machine task results are transmitted from the server, Collaborative Intelligence (CI) proposed the transmission of feature maps as a solution. In this paper, an efficient compression method for feature maps with vast data sizes to support the CI paradigm was analyzed and presented through experiments. This method increases redundancy by applying feature map reordering to improve compression efficiency in traditional video codecs, and proposes a feature map method that improves compression efficiency and maintains the performance of machine tasks by simultaneously utilizing image compression format and video compression format. As a result of the experiment, the proposed method shows 14.29% gain in BD-rate of BPP and mAP compared to the feature compression anchor of MPEG-VCM.

• Broadcasting and Media Magazine
• /
• v.25 no.1
• /
• pp.75-82
• /
• 2020

디지털 트윈이나 증강현실, 가상현실, 자율주행 등과 같이 현실 좌표계의 위치를 다루거나 현실과 가상세계를 융합하는 기술들에 있어 측위 기술은 상당히 주요하게 작용한다. 측위 기술은 그 목적과 타겟 디바이스에 따라 매우 다양하게 존재하며, 기존 측위 기술들에 인공지능을 융합하여 정밀도와 측위 주기를 개선시키는 등 다양한 연구가 진행되고 있는 분야이다. 본 고에서는 기존의 다양한 측위 기술들의 동향과 인공지능을 융합하여 성능을 높인 사례들에 대해 설명한다.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.64.3-64.3
• /
• 2017

For the detection of transient sources in optical wide field surveys like KMTNet Supernova Project, difference imaging technique is commonly used. As this method produces a fair amount of false positives, it is also common to utilize machine learning algorithms to screen likely true positives. While deep learning methods such as a convolutional neural network has been successfully applied recently, its application can be limited if the size of the training sample is small. I will discuss a variation of more conventional method that adopts the wavelet transform for feature engineering and its performance.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.634-636
• /
• 2018

최근 들어 Big Data를 활용한 기술들이 많이 개발되고 있다. 본 연구에서는 Machine Learning과 Deep Learning을 이용하여 음성 Big Data를 활용한 이미지 시각화를 통해 보이스 피싱 등 여러 범죄에 도움이 되게 하고 그 외의 음성과 얼굴 매칭을 통한 새로운 보안시스템 및 다양한 시너지 효과들을 기대하는 서비스를 기술한다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.526-527
• /
• 2023

Speech emotion recognition(SER) is one of the interesting topics in the machine learning field. By developing multi-modal speech emotion recognition system, we can get numerous benefits. This paper explain about fusing BERT as the text recognizer and CNN as the speech recognizer to built a multi-modal SER system.

• Korean Journal of Radiology
• /
• v.23 no.12
• /
• pp.1119-1125
• /
• 2022

• Convergence Security Journal
• /
• v.20 no.2
• /
• pp.111-121
• /
• 2020

Deep neural networks (DNNs) provide good performance for machine learning tasks such as image recognition and object recognition. However, DNNs are vulnerable to an adversarial example. An adversarial example is an attack sample that causes the neural network to recognize it incorrectly by adding minimal noise to the original sample. However, the disadvantage is that it takes a long time to generate such an adversarial example. Therefore, in some cases, an attack may be necessary that quickly causes the neural network to recognize it incorrectly. In this paper, we propose a fast misclassification sample that can rapidly attack neural networks. The proposed method does not consider the distortion of the original sample when adding noise. We used MNIST and CIFAR10 as experimental data and Tensorflow as a machine learning library. Experimental results show that the fast misclassification sample generated by the proposed method can be generated with 50% and 80% reduced number of iterations for MNIST and CIFAR10, respectively, compared to the conventional Carlini method, and has 100% attack rate.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.65-74
• /
• 2021

Recently, studies on Korean spelling correction have been actively conducted based on machine translation and automatic noise generation. These methods generate noise and use as train and data set. This has limitation in that it is difficult to accurately measure performance because it is unlikely that noise other than the noise used for learning is included in the test set In addition, there is no practical error type standard, so the type of error used in each study is different, making qualitative analysis difficult. This paper proposes new 'error type classification' for deep learning-based Korean spelling correction research, and error analysis perform on existing commercialized Korean spelling correctors (System A, B, C). As a result of analysis, it was found the three correction systems did not perform well in correcting other error types presented in this paper other than spacing, and hardly recognized errors in word order or tense.