• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.114-121
• /
• 2019

This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in 'tfrecords' format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.9
• /
• pp.125-139
• /
• 2014

In this paper, I propose a response modeling with a Semi-Supervised Support Vector Regression (SS-SVR) algorithm. In order to increase the accuracy and profit of response modeling, unlabeled data in the customer dataset are used with the labeled data during training. The proposed SS-SVR algorithm is designed to be a batch learning to reduce the training complexity. The label distributions of unlabeled data are estimated in order to consider the uncertainty of labeling. Then, multiple training data are generated from the unlabeled data and their estimated label distributions with oversampling to construct the training dataset with the labeled data. Finally, a data selection algorithm, Expected Margin based Pattern Selection (EMPS), is employed to reduce the training complexity. The experimental results conducted on a real-world marketing dataset showed that the proposed response modeling method trained efficiently, and improved the accuracy and the expected profit.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.200-209
• /
• 2019

When forecasting future values, a model estimated after minimizing training errors can yield test errors higher than the training errors. This result is the over-fitting problem caused by an increase in model complexity when the model is focused only on a given dataset. Some regularization and resampling methods have been introduced to reduce test errors by alleviating this problem but have been designed for use with only a given dataset. In this paper, we propose a new optimization approach to reduce test errors by transforming a test error minimization problem into a training error minimization problem. To carry out this transformation, we needed additional data for the given dataset, termed pseudo data. To make proper use of pseudo data, we used three types of missing data imputation techniques. As an optimization tool, we chose the least squares method and combined it with an extra pseudo data instance. Furthermore, we present the numerical results supporting our proposed approach, which resulted in less test errors than the ordinary least squares method.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.31-36
• /
• 2019

Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.104-109
• /
• 2022

For autonomous driving research using AI, datasets collected from road environments play an important role. In other countries, various datasets such as CityScapes, A2D2, and BDD have already been released, but datasets suitable for the domestic road environment still need to be provided. This paper analyzed and verified the dataset reflecting the Korean driving environment. In order to verify the training dataset, the class imbalance was confirmed by comparing the number of pixels and instances of the dataset. A similar A2D2 dataset was trained with the same deep learning model, ConvNeXt, to compare and verify the constructed dataset. IoU was compared for the same class between two datasets with ConvNeXt and mIoU was compared. In this paper, it was confirmed that the collected dataset reflecting the driving environment of Korea is suitable for learning.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.167-173
• /
• 2023

Hangul is unique compared to other Asian languages because of its simple letter forms that combine to create syllabic shapes. There are 24 basic letters that can be combined to form 27 additional complex letters. This produces 51 graphemes. Hangul optical character recognition has been a research topic for some time; however, handwritten Hangul recognition continues to be challenging owing to the various writing styles, slants, and cursive-like nature of the handwriting. In this study, a dataset containing thousands of samples of 51 Hangul graphemes was gathered from 110 freshmen university students to create a robust dataset with high variance for training an artificial neural network. The collected dataset included 2200 samples for each consonant grapheme and 1100 samples for each vowel grapheme. The dataset was normalized to the MNIST digits dataset, trained in three neural networks, and the obtained results were compared.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.580-581
• /
• 2024

고령화 사회에 접어들면서 황반 변성과 당뇨 망막 병증 등 시야결손을 동반하는 안구 질환의 발병률은 증가하지만 이러한 질환의 조기 발견에 인공지능을 접목시킨 연구는 부족한 실정이다. 본 논문은 안구 질환 자가 검사용 인공 신경망을 학습시키기 위한 데이터 베이스 구축 방법을 제안한다. MNIST와 CIFAR-10을 합성하여 중첩 이미지 데이터셋인 G-Dataset을 생성하였고, 7개의 인공신경망에 학습시켜 최종적으로 90% 이상의 정확도를 얻음으로 그 유효성을 입증하였다. G-Dataset을 안구 질환 자가 검사용 딥러닝 모델에 학습시켜 모바일 어플에 적용하면 사용자가 주기적인 검사를 통해 안구 질환을 조기에 진단하고 치료할 수 있을 것으로 기대된다.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.61.1-61.1
• /
• 2017

As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT $195{\AA}$, and $304{\AA}$ from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We consider other input images which consist of last two images and their difference image. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the over-fitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). All statistical parameters do not strongly depend on the number of input data sets. Our model can immediately be applied to automatic forecasting service when image data are available.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.39-46
• /
• 2019

In this study, before system development for the elimination of foreign fish species, we propose an algorithm to classify fish species by training fish images with CNN. The raw data for CNN learning were directly captured images for each species, Dataset 1 increases the number of images to improve the classification of fish species and Dataset 2 realizes images close to natural environment are constructed and used as training and test data. The classification performance of four CNNs are over 99.97% for dataset 1 and 99.5% for dataset 2, in particular, we confirm that the learned CNN using Data Set 2 has satisfactory performance for fish images similar to the natural environment. And among four CNNs, AlexNet achieves satisfactory performance, and this has also the shortest execution time and training time, we confirm that it is the most suitable structure to develop the system for the elimination of foreign fish species.