• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.350-351
• /
• 2018

최근 의료 현장에 인공지능 기술의 도입이 가속화 되고 있다. 특히, 의료영상 분석 분야의 관련된 기 시스템 및 소프트웨어의 패러다임을 변화시키고 있다. 본 연구는 인공지능 기술을 적용하기 위한 학습의료영상 구성을 제안하고 이를 기반으로 X-ray 영상 중 손부위에 적용하여 오른손과 왼손을 판별하는 응용에 적용하였다. 그리고 Deep Learning Algorithm의 CNN을 개선하여 개발한 Advanced GoogLeNet를 적용하여 97%이상의 정확도를 보였다. 본 연구를 통해 얻어진 인공지능에 적용하기 위한 학습데이터 셋 구성과 개선된 알고리즘은 다양한 의료영상분석에 적용하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1004-1006
• /
• 2019

Different scale of information is an important component in computer vision systems. Recently, there are considerable researches on utilizing multi-scale information to solve the scale-invariant problems, such as GoogLeNet and FPN. In this paper, we introduce the notion of different scale information fusion (DSIF) and show that it has a significant effect on the performance of object recognition systems. We analyze the DSIF in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to clear suggestions for ways of the DSIF to choose.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.2
• /
• pp.125-133
• /
• 2022

This paper proposes a fault detection method for a Unmanned Surface Vehicle (USV) with overactuated system. Current status information for fault detection is expressed as a scalogram image. The scalogram image is obtained by wavelet-transforming the USV's control input and sensor information. The fault detection scheme is based on Convolutional Neural Network (CNN) algorithm. The previously generated scalogram data was transferred learning to GoogLeNet algorithm. The data are generated as scalogram images in real time, and fault is detected through a learning model. The result of fault detection is very robust and highly accurate.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.3
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.3
• /
• pp.129-136
• /
• 2021

Cavitation erosion is one of the major factors causing damage by lowering the structural strength of the marine propeller and the risk of it has been qualitatively evaluated by each institution with their own criteria based on the experiences. In this study, in order to quantitatively evaluate the risk of cavitation erosion on the propeller, we implement a deep learning algorithm based on a convolutional neural network. We train and verify it using the model tests results, including cavitation characteristics of various ship types. Here, we adopt the validated well-known networks such as VGG, GoogLeNet, and ResNet, and the results are compared with the expert's qualitative prediction results to confirm the feasibility of the prediction algorithm using a convolutional neural network.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.67-75
• /
• 2018

According to Symantec's Internet Security Threat Report(2018), Internet security threats such as Cryptojackings, Ransomwares, and Mobile malwares are rapidly increasing and diversifying. It means that detection of malwares requires not only the detection accuracy but also versatility. In the past, malware detection technology focused on qualitative performance due to the problems such as encryption and obfuscation. However, nowadays, considering the diversity of malware, versatility is required in detecting various malwares. Additionally the optimization is required in terms of computing power for detecting malware. In this paper, we present Stream Order(SO)-CNN and Incremental Coordinate(IC)-CNN, which are malware detection schemes using CNN(Convolutional Neural Network) that effectively detect intelligent and diversified malwares. The proposed methods visualize each malware binary file onto a fixed sized image. The visualized malware binaries are learned through GoogLeNet to form a deep learning model. Our model detects and classifies malwares. The proposed method reveals better performance than the conventional method.

• Nutrition Research and Practice
• /
• v.13 no.6
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.417-423
• /
• 2017

Recently, many embedded devices that have the computing capability required for deep learning have become available; hence, many new applications using these devices are emerging. However, these embedded devices have an architecture different from that of PCs and high-performance servers. In this paper, we propose a method that improves the performance of deep-learning framework by considering the architecture of an embedded device that shares memory between the CPU and the GPU. The proposed method is implemented in Caffe, an open-source deep-learning framework, and is evaluated on an NVIDIA Jetson TK1 embedded device. In the experiment, we investigate the image recognition performance of several state-of-the-art deep-learning networks, including AlexNet, VGGNet, and GoogLeNet. Our results show that the proposed method can achieve significant performance gain. For instance, in AlexNet, we could reduce image recognition latency by about 33% and energy consumption by about 50%.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.5
• /
• pp.407-414
• /
• 2020

SVM (Support vector machine) analysis was performed after applying a deep learning technique based on an Inception-based model (GoogLeNet). The accuracy of automatic image classification was analyzed using an SVM with multiple virtual grid sizes. Six classes were selected from a standard land cover map. Cars were added as a separate item to increase the classification accuracy of roads. The virtual grid size was 2-5 m for natural areas, 5-10 m for traffic areas, and 10-15 m for building areas, based on the size of items and the resolution of input images. The results demonstrate that automatic classification accuracy can be increased by adopting an integrated approach that utilizes weighted virtual grid sizes for different classes.

• Anatomy and Cell Biology
• /
• v.56 no.1
• /
• pp.86-93
• /
• 2023

Age at death estimation has always been a crucial yet challenging part of identification process in forensic field. The use of human skeletons have long been explored using the principle of macro and micro-architecture change in correlation with increasing age. The clavicle is recommended as the best candidate for accurate age estimation because of its accessibility, time to maturation and minimal effect from weight. Our study applies pre-trained convolutional neural network in order to achieve the most accurate and cost effective age estimation model using clavicular bone. The total of 988 clavicles of Thai population with known age and sex were radiographed using Kodak 9000 Extra-oral Imaging System. The radiographs then went through preprocessing protocol which include region of interest selection and quality assessment. Additional samples were generated using generative adversarial network. The total clavicular images used in this study were 3,999 which were then separated into training and test set, and the test set were subsequently categorized into 7 age groups. GoogLeNet was modified at two layers and fine tuned the parameters. The highest validation accuracy was 89.02% but the test set achieved only 30% accuracy. Our results show that the use of medial clavicular radiographs has a potential in the field of age at death estimation, thus, further study is recommended.