• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.455-457
• /
• 2019

In this paper we study the effect of decomposed spatiotemporal convolutions for action recognition in videos. Our motivation emerges from the empirical observation that spatial convolution applied on solo frames of the video provide good performance in action recognition. In this research we empirically show the accuracy of factorized convolution on individual frames of video for action classification. We take 3D ResNet-18 as base line model for our experiment, factorize its 3D convolution to 2D (Spatial) and 1D (Temporal) convolution. We train the model from scratch using Kinetics video dataset. We then fine-tune the model on UCF-101 dataset and evaluate the performance. Our results show good accuracy similar to that of the state of the art algorithms on Kinetics and UCF-101 datasets.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.1-6
• /
• 2021

Recently, pre-trained convolutional neural network CNNs have been widely used and applied for medical image classification. These models can utilised in three different ways, for feature extraction, to use the architecture of the pre-trained model and to train some layers while freezing others. In this study, the ResNet18 pre-trained CNNs model is used for feature extraction, followed by the support vector machine for multiple classes to classify medical images from multi-classes, which is used as the main classifier. Our proposed classification method was implemented on Kvasir and PH2 medical image datasets. The overall accuracy was 93.38% and 91.67% for Kvasir and PH2 datasets, respectively. The classification results and performance of our proposed method outperformed some of the related similar methods in this area of study.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.643-646
• /
• 2020

본 논문에서는 직전 연구였던 비트 평면 분할과 디더링을 통한 다중 학습 통합 신경망 구축에서의 한계점을 분석하고, 향상시킨 방법을 제시한다. 통합 신경망을 구축하는 방법에 대해 최근까지 시도되었던 방법들은 신경망을 구성하는 가중치(weight)나 층(layer)를 공유하거나 태스크 별로 구분하는 것들이 있다. 이와 같은 선상에서 본 연구는 더 작은 단위인 가중치의 비트 평면을 태스크 별로 할당하여 보다 효율적인 통합 신경망을 구축한다. 실험은 이미지 분류 문제에 대해 수행하였다. 대중적인 신경망 구조인 ResNet18 에 대해 적용한 결과 데이터셋 CIFAR10 과 CIFAR100 에서 이론적인 압축률 50%를 달성하면서 성능 저하가 거의 발견되지 않았다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.912-913
• /
• 2023

이미지 처리에 관한 인공지능 모델의 발전에 따라 개인정보 유출 문제가 가속화되고 있다. 인공지능은 다방면으로 삶에 편리함을 제공하지만, 딥러닝 기술은 적대적 예제에 취약성을 보이기 때문에, 개인은 보안에 취약한 대상이 된다. 본 연구는 ResNet18 신경망 모델에 얼굴이미지를 학습시킨 후, Shadow Attack을 사용하여 입력 이미지에 대한 AI 분류 정확도를 의도적으로 저하시켜, 허가받지 않은 이미지의 인식율을 낮출 수 있도록 구현하였으며 그 성능을 실험을 통해 입증하였다.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.90-97
• /
• 2024

This paper focuses on detecting Alzheimer's Disease (AD). The most usual form of dementia is Alzheimer's disease, which causes permanent cause memory cell damage. Alzheimer's disease, a neurodegenerative disease, increases slowly over time. For this matter, early detection of Alzheimer's disease is important. The purpose of this work is using Magnetic Resonance Imaging (MRI) to diagnose AD. A Convolution Neural Network (CNN) model, Reset, and VGG the pre-trained learning models are used. Performing analysis and validation of layers affects the effectiveness of the model. T1-weighted MRI images are taken for preprocessing from ADNI. The Dataset images are taken from the Alzheimer's Disease Neuroimaging Initiative (ADNI). 3D MRI scans into 2D image slices shows the optimization method in the training process while achieving 96% and 94% accuracy in VGG 16 and ResNet 18 respectively. This study aims to classify AD from brain 3D MRI images and obtain better results.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.17-24
• /
• 2022

With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.559-565
• /
• 2024

Research on autonomous vehicles is being actively conducted. As autonomous vehicles emerge, there will be a transitional period in which traditional and autonomous vehicles coexist, potentially leading to a higher accident rate. Currently, when a traffic accident occurs, the fault ratio is determined according to the criteria set by the General Insurance Association of Korea. However, the time required to investigate the type of accident is substantial. Additionally, there is an increasing trend in fault ratio disputes, with requests for reconsideration even after the fault ratio has been determined. To reduce these temporal and material costs, we propose a deep learning model that automatically determines fault ratios. In this study, we aimed to determine fault ratios based on accident video through a image classification model based on ResNet-18 and video action recognition using TSN. If this model commercialized, could significantly reduce the time required to measure fault ratios. Moreover, it provides an objective metric for fault ratios that can be offered to the parties involved, potentially alleviating fault ratio disputes.

• Imaging Science in Dentistry
• /
• v.52 no.3
• /
• pp.239-244
• /
• 2022

Purpose: Despite the proliferation of numerous morphometric and anthropometric methods for sex identification based on linear, angular, and regional measurements of various parts of the body, these methods are subject to error due to the observer's knowledge and expertise. This study aimed to explore the possibility of automated sex determination using convolutional neural networks(CNNs) based on lateral cephalometric radiographs. Materials and Methods: Lateral cephalometric radiographs of 1,476 Iranian subjects (794 women and 682 men) from 18 to 49 years of age were included. Lateral cephalometric radiographs were considered as a network input and output layer including 2 classes(male and female). Eighty percent of the data was used as a training set and the rest as a test set. Hyperparameter tuning of each network was done after preprocessing and data augmentation steps. The predictive performance of different architectures (DenseNet, ResNet, and VGG) was evaluated based on their accuracy in test sets. Results: The CNN based on the DenseNet121 architecture, with an overall accuracy of 90%, had the best predictive power in sex determination. The prediction accuracy of this model was almost equal for men and women. Furthermore, with all architectures, the use of transfer learning improved predictive performance. Conclusion: The results confirmed that a CNN could predict a person's sex with high accuracy. This prediction was independent of human bias because feature extraction was done automatically. However, for more accurate sex determination on a wider scale, further studies with larger sample sizes are desirable.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.63-75
• /
• 2022

The raw data collected by structural health monitoring (SHM) systems may suffer multiple patterns of anomalies, which pose a significant barrier for an automatic and accurate structural condition assessment. Therefore, the detection and classification of these anomalies is an essential pre-processing step for SHM systems. However, the heterogeneous data patterns, scarce anomalous samples and severe class imbalance make data anomaly detection difficult. In this regard, this study proposes a convolutional neural network-based data anomaly detection method. The time and frequency domains data are transferred as images and used as the input of the neural network for training. ResNet18 is adopted as the feature extractor to avoid training with massive labelled data. In addition, the focal loss function is adopted to soften the class imbalance-induced classification bias. The effectiveness of the proposed method is validated using acceleration data collected in a long-span cable-stayed bridge. The proposed approach detects and classifies data anomalies with high accuracy.