• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.257-260
• /
• 2020

본 논문은 단일의 옷감 이미지로 가상의 그래픽 렌더링을 위해 Pix2Pix 방법을 이용하여 Normal map 을 생성하는 방법을 제시한다. 구체적으로 단일의 이미지를 이용해서 Normal map 를 생성하기 위해, Color image 와 Normal map 쌍의 training dataset 을 Pix2Pix 방법을 이용해서 학습시킨다 또한, test dataset 의 Color image 를 입력으로 넣어 생성된 Normal map 결과를 확인한다. 그리고 선행연구에서 사용되어오던 U-Net 방식의 방법과 본 논문에서 사용한 Pix2Pix 를 이용한 Normal map 생성 결과를 SSIM(Structural Similarity Index)으로 비교 평가한다. 또한, 생성된 Normal map 을 렌더링하고자 하는 가상 객체의 사이즈에 맞게 사이즈를 조정하여 OpenGL 로 렌더링한 결과를 확인한다. 본 논문을 통해서 단일의 패턴 이미지를 Pix2Pix 로 생성한 Normal map 으로 옷감의 디테일을 사실감 있게 표현할 수 있음을 확인할 수 있었다.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.127-128
• /
• 2023

The construction industry is increasingly adopting vision AI technologies to improve efficiency and safety management. However, the complex and dynamic nature of construction sites can pose challenges to the accuracy of vision AI models trained on datasets that do not consider the background. This study investigates the effect of background on object recognition for vision AI in construction sites by constructing a learning dataset and a test dataset with varying backgrounds. Frame scaffolding was chosen as the object of recognition due to its wide use, potential safety hazards, and difficulty in recognition. The experimental results showed that considering the background during model training significantly improved the accuracy of object recognition.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• ETRI Journal
• /
• v.46 no.4
• /
• pp.633-647
• /
• 2024

In e-commerce platforms, sentiment analysis on an enormous number of user reviews efficiently enhances user satisfaction. In this article, an automated product recommendation system is developed based on machine and deep-learning models. In the initial step, the text data are acquired from the Amazon Product Reviews dataset, which includes 60 000 customer reviews with 14 806 neutral reviews, 19 567 negative reviews, and 25 627 positive reviews. Further, the text data denoising is carried out using techniques such as stop word removal, stemming, segregation, lemmatization, and tokenization. Removing stop-words (duplicate and inconsistent text) and other denoising techniques improves the classification performance and decreases the training time of the model. Next, vectorization is accomplished utilizing the term frequency-inverse document frequency technique, which converts denoised text to numerical vectors for faster code execution. The obtained feature vectors are given to the modified convolutional neural network model for sentiment analysis on e-commerce platforms. The empirical result shows that the proposed model obtained a mean accuracy of 97.40% on the APR dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.21-30
• /
• 2024

In this paper, we propose a method to build a sample dataset of the features of eight sensor-only facilities built as infrastructure for autonomous cooperative driving. The feature extracted from point cloud data acquired by LiDAR and build them into the sample dataset for recognizing the facilities. In order to build the dataset, eight sensor-only facilities with high-brightness reflector sheets and a sensor acquisition system were developed. To extract the features of facilities located within a certain measurement distance from the acquired point cloud data, a cylindrical projection method was applied to the extracted points after applying DBSCAN method for points and then a modified OTSU method for reflected intensity. Coordinates of 3D points, projected coordinates of 2D, and reflection intensity were set as the features of the facility, and the dataset was built along with labels. In order to check the effectiveness of the facility dataset built based on LiDAR data, a common CNN model was selected and tested after training, showing an accuracy of about 90% or more, confirming the possibility of facility recognition. Through continuous experiments, we will improve the feature extraction algorithm for building the proposed dataset and improve its performance, and develop a dedicated model for recognizing sensor-only facilities for autonomous cooperative driving.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.29-37
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the Gradient Descent Optimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.7
• /
• pp.2397-2404
• /
• 2011

Variable selection k nearest neighbor QSAR modeling approach was applied to a data set of 80 3-arylisoquinolines exhibiting cytotoxicity against human lung tumor cell line (A-549). All compounds were characterized with molecular topology descriptors calculated with the MolconnZ program. Seven compounds were randomly selected from the original dataset and used as an external validation set. The remaining subset of 73 compounds was divided into multiple training (56 to 61 compounds) and test (17 to 12 compounds) sets using a chemical diversity sampling method developed in this group. Highly predictive models characterized by the leave-one out cross-validated $R^2$ ($q^2$) values greater than 0.8 for the training sets and $R^2$ values greater than 0.7 for the test sets have been obtained. The robustness of models was confirmed by the Y-randomization test: all models built using training sets with randomly shuffled activities were characterized by low $q^2{\leq}0.26$ and $R^2{\leq}0.22$ for training and test sets, respectively. Twelve best models (with the highest values of both $q^2$ and $R^2$) predicted the activities of the external validation set of seven compounds with $R^2$ ranging from 0.71 to 0.93.

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.535-545
• /
• 2004

The clustering method suggested in this paper produces clusters based on the 'rules of variables' by merging the 'training' and the identically structured reference data and then by filtering it to obtain the clusters of the 'training data' through the use of the 'tree classification model'. The reference dataset is generated by spatially contrasting it to the 'training data' through the 'reverse arcing' algorithm to effectively identify the clusters. The strength of this method is that it can be applied even to the mixture of continuous and discrete types of 'training data' and the performance of this algorithm is illustrated by applying it to the simulated data as well as to the actual data.

• ETRI Journal
• /
• v.39 no.5
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.695-706
• /
• 2022

Medium and high-resolution optical satellites have proven their effectiveness in detecting wildfire areas. However, smoke plumes generated by wildfire scatter visible light incidents on the surface, thereby interrupting accurate monitoring of the area where wildfire occurs. Therefore, a technology to extract smoke in advance is required. Deep learning technology is expected to improve the accuracy of smoke extraction, but the lack of training datasets limits the application. However, for clouds, which have a similar property of scattering visible light, a large amount of training datasets has been accumulated. The purpose of this study is to develop a smoke extraction technique using deep learning, and the limits due to the lack of datasets were overcome by using a cloud dataset on transfer learning. To check the effectiveness of transfer learning, a small-scale smoke extraction training set was made, and the smoke extraction performance was compared before and after applying transfer learning using a public cloud dataset. As a result, not only the performance in the visible light wavelength band was enhanced but also in the near infrared (NIR) and short-wave infrared (SWIR). Through the results of this study, it is expected that the lack of datasets, which is a critical limit for using deep learning on smoke extraction, can be solved, and therefore, through the advancement of smoke extraction technology, it will be possible to present an advantage in monitoring wildfires.