• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.510-512
• /
• 2022

컴퓨터 비전 분야에서 오랫동안 사용되었던 CNN(Convolution Neural Network)은 오분류를 일으키기 위해 악의적으로 추가된 섭동에 매우 취약하다. ViT(Vision Transformer)는 입력 이미지의 전체적인 특징을 탐색하는 어텐션 구조를 적용함으로 CNN의 국소적 특징 탐색보다 특성 픽셀에 섭동을 추가하는 적대적 공격에 강건한 특성을 보이지만 최근 어텐션 구조에 대한 강건성 분석과 다양한 공격 기법의 발달로 보안 취약성 문제가 제기되고 있다. 본 논문은 ViT가 CNN 대비 강건성을 가지는 구조적인 특징을 분석하는 연구와 어텐션 구조에 대한 최신 공격기법을 소개함으로 향후 등장할 ViT 파생 모델의 강건성을 유지하기 위해 중점적으로 다루어야 할 부분이 무엇인지 소개한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.214-216
• /
• 2022

비디오 프레임 보간 기술은 시간 해상도를 증가시키는 기술로 최근 Convolutional Neural Network(이하 CNN) 기반의 다양한 연구가 진행되고 있다. 하지만 일부 시각에서는 CNN 기반의 연구가 동일한 커널을 모든 화소에 적용하는 것과 객체의 움직임을 예측하기 위해 장기간의 데이터를 활용하는 것에 한계점이 있다고 주장한다. 이에 따라 장기간의 데이터 활용에 특화된 트랜스포머 기반의 비디오 프레임 보간 기술이 제안되었다. 본 논문에서는 트랜스포머 기반의 기존 연구에서 합성 네트워크의 성능을 향상시키기 위해 광학 흐름 안내 기반의 새로운 학습 방법을 제안한다 실험 결과를 통해 평균 PSNR 0.09dB와 SSIM 0.0031 성능 향상을 확인한다.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.351-358
• /
• 2024

In Japan, bridge inspections are mandated every five years. The inspection database for bridges under the jurisdiction of the Ministry of Land, Infrastructure, Transport, and Tourism enables the acquisition of damage progression data for each structural element. This study develops a methodology for predicting the deterioration of girder bridges, employing a novel approach where inspection drawings are processed using Optical Character Recognition (OCR) to extract element numbers and their spatial relationships, subsequently creating a comprehensive graph of these elements. A key feature of this prediction methodology is its ability to consider the adjacency relationships between different bridge members, made possible by the detailed analysis of drawing information and a Graph Transformer model. The research examines and compares the accuracy of predictions made with and without considering adjacency relationships, highlighting the effectiveness of incorporating detailed structural information in the predictive analysis of bridge deterioration.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.539-542
• /
• 2003

A motor is the workhorse of our industry. The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. Different internal motor faults (e.g., inter-turn short circuits, broken bearings, broken rotor bars) along with external motor faults (e.g., phase failure, mechanical overload, blocked rotor) are expected to happen sooner or later. This paper introduces the fault detection technique of induction motors based upon the stator current. The fault motors have rotor bar broken or rotor unbalance defect, respectively. The stator currents are measured by the current meters and stored by the time domain. The time domain is not suitable to represent the current signals, so the frequency domain is applied to display the signals. The Fourier Transformer is used for the conversion of the signal. After the conversion of the signals, the features of the signals have to be extracted by the signal processing methods like a wavelet analysis, a spectrum analysis, etc. The discovered features are entered to the pattern classification model such as a neural network model, a polynomial neural network, a fuzzy inference model, etc. This paper describes the fault detection results that use wavelet decomposition. The wavelet analysis is very useful method for the time and frequency domain each. Also it is powerful method to detect the features in the signals.

• 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 Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.17-27
• /
• 2023

Recently, automatic text summarization, which automatically summarizes only meaningful information for users, is being studied steadily. Especially, research on text summarization using Transformer, an artificial neural network model, has been mainly conducted. Among various studies, the GSG method, which trains a model through sentence-by-sentence masking, has received the most attention. However, the traditional GSG has limitations in selecting a sentence to be masked based on the degree of overlap of tokens, not the meaning of a sentence. Therefore, in this study, in order to improve the quality of text summarization, we propose SbGSG (Semantic-based GSG) methodology that selects sentences to be masked by GSG considering the meaning of sentences. As a result of conducting an experiment using 370,000 news articles and 21,600 summaries and reports, it was confirmed that the proposed methodology, SbGSG, showed superior performance compared to the traditional GSG in terms of ROUGE and BERT Score.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.570-573
• /
• 2022

This paper presents the identification of void diameters for a cast-resin transformer using an artificial neural network (ANN) model. A PD signal was measured by the Rogowski coil sensor which has the planar and thin structures fabricated on a printed circuit board (PCB), and the PD electrode system was fabricated to simulate a PD defect by a void. In addition, void samples with different diameters were fabricated by injecting air in a cylindrical aluminum frame using a syringe during the epoxy curing process. To identify the diameter of void defects, PD characteristics such as the discharge magnitude, pulse count, and phase angle were extracted and back propagation algorithm (BPA) was designed using virtual instrument (VI) based on the Labview program. From the experimental results, the BPA algorithm proposed in this paper has over 90% accurate rate to identify the diameter of void defects and is expected to use reference data of maintenance and replacement of insulation for cast-resin transformers in the on-site PD measurement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1726-1748
• /
• 2024

Trajectory planning is vital for autonomous systems like robotics and UAVs, as it determines optimal, safe paths considering physical limitations, environmental factors, and agent interactions. Recent advancements in trajectory planning and future location prediction stem from rapid progress in machine learning and optimization algorithms. In this paper, we proposed a novel framework for Spatial-temporal transformer-based feed-forward neural networks (STTFFNs). From the traffic flow local area point of view, skip-gram model is trained on trajectory data to generate embeddings that capture the high-level features of different trajectories. These embeddings can then be used as input to a transformer-based trajectory planning model, which can generate trajectories for new objects based on the embeddings of similar trajectories in the training data. In the next step, distant regions, we embedded feedforward network is responsible for generating the distant trajectories by taking as input a set of features that represent the object's current state and historical data. One advantage of using feedforward networks for distant trajectory planning is their ability to capture long-term dependencies in the data. In the final step of forecasting for future locations, the encoder and decoder are crucial parts of the proposed technique. Spatial destinations are encoded utilizing location-based social networks(LBSN) based on visiting semantic locations. The model has been specially trained to forecast future locations using precise longitude and latitude values. Following rigorous testing on two real-world datasets, Porto and Manhattan, it was discovered that the model outperformed a prediction accuracy of 8.7% previous state-of-the-art methods.