• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1415-1425
• /
• 2018

Kompsat-5 is the first Earth Observation Satellite which is equipped with an SAR in Korea. SAR images are generated by receiving signals reflected from an object by microwaves emitted from a SAR antenna. Because the wavelengths of microwaves are longer than the size of particles in the atmosphere, it can penetrate clouds and fog, and high-resolution images can be obtained without distinction between day and night. However, there is no color information in SAR images. To overcome these limitations of SAR images, colorization of SAR images using Cycle GAN, a deep learning model developed for domain translation, was conducted. Training of Cycle GAN is unstable due to the unsupervised learning based on unpaired dataset. Therefore, we proposed MS Cycle GAN applying multi-scale discriminator to solve the training instability of Cycle GAN and to improve the performance of colorization in this paper. To compare colorization performance of MS Cycle GAN and Cycle GAN, generated images by both models were compared qualitatively and quantitatively. Training Cycle GAN with multi-scale discriminator shows the losses of generators and discriminators are significantly reduced compared to the conventional Cycle GAN, and we identified that generated images by MS Cycle GAN are well-matched with the characteristics of regions such as leaves, rivers, and land.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.197-212
• /
• 2022

The purpose of this study is to develop an automatic software system for bone age evaluation and to evaluate its accuracy in testing and feasibility in clinical practice. 20394 left-hand radiographs of healthy children (2-18 years old) were collected from China Skeletal Development Survey data of 1998 and China Skeletal Development Survey data of 2005. Three experienced radiologists and China-05 standard maker jointly evaluate the stages of bone development and the reference bone age was determined by consensus. 1020 from 20394 radiographs were picked randomly as test set and the remaining 19374 radiographs as training set and validation set. Accuracy of the automatic software system for bone age assessment is evaluated in test set and two clinical test sets. Compared with the reference standard, the automatic software system based on RUS-CHN for bone age assessment has a 0.04 years old mean difference, ±0.40 years old in 95% confidence interval by single reading, a 85.6% percentage agreement of ratings, a 93.7% bone age accuracy rate, 0.17 years old of MAD, 0.29 years old of RMS; Compared with the reference standard, the automatic software system based on TW3-C RUS has a 0.04 years old mean difference, a ±0.38 years old in 95% confidence interval by single reading, a 90.9% percentage agreement of ratings, a 93.2% bone age accuracy rate, a 0.16 years of MAD, and a 0.28 years of RMS. Automatic software system, AI-China-05 showed reliably accuracy in bone age estimation and steady determination in different clinical test sets.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.9
• /
• pp.273-282
• /
• 2023

Recently, various technologies such as logistics automation and port operations automation with ICT technology are being developed to build smart ports. However, there is a lack of technology development for port safety and safety accident prevention. This paper proposes an AI-based shipping container loading safety management system for the prevention of safety accidents at container loading fields in ports. The system consists of an AI-based shipping container safety accident risk classification and storage function and a real-time safety accident monitoring function. The system monitors the accident risk at the site in real-time and can prevent container collapse accidents. The proposed system is developed as a prototype, and the system is ecaluated by direct application in a port.

• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.505-516
• /
• 2022

Objective: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms. Materials and Methods: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated. Results: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001). Conclusion: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.6
• /
• pp.403-408
• /
• 2021

Currently, in the design process of civil structures such as bridges, it is common to make final products by repeating the process of redesigning, if the initial design is found to not meet the standards after a structural review. This iterative process extends the design time, and causes inefficient consumption of engineering manpower, which should be put into higher-level design, on simple repetitive mechanical work. This problem can be resolved by automating the design process, but the external analysis program used in the design process has been the biggest obstacle to such automation. In this study, we constructed an AI-based automation system for the bridge design process, including an interface that could control both a reinforcement learning algorithm, and an external analysis program, to replace the repetitive tasks in the current design process. The prototype of the system built in this study was developed for a 2-span RC Rahmen bridge, which is one of the simplest bridge systems. In the future, it is expected that the developed interface system can be utilized as a basic technology for linking the latest AI with other types of bridge designs.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.3
• /
• pp.134-139
• /
• 2023

Rehabilitators perform outpatient treatment and daily rehabilitation exercises to recover physical function with the aim of quickly returning to society after surgical treatment. Unlike performing exercises in a hospital with the help of a professional therapist, there are many difficulties in performing rehabilitation exercises by the patient on a daily basis. In this paper, we propose a CNN-LSTM-based upper limb rehabilitation real-time monitoring system so that patients can perform rehabilitation efficiently and with correct posture on a daily basis. The proposed system measures biological signals through shoulder-mounted hardware equipped with EMG and IMU, performs preprocessing and normalization for learning, and uses them as a learning dataset. The implemented model consists of three polling layers of three synthetic stacks for feature detection and two LSTM layers for classification, and we were able to confirm a learning result of 97.44% on the validation data. After that, we conducted a comparative evaluation with the Teachable machine, and as a result of the comparative evaluation, we confirmed that the model was implemented at 93.6% and the Teachable machine at 94.4%, and both models showed similar classification performance.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.75-82
• /
• 2023

Automatic speech recognition (ASR) has been revolutionized with deep learning-based approaches, among which self-supervised learning methods have proven to be particularly effective. In this study, we aim to enhance the performance of OpenAI's Whisper model, a multilingual ASR system on the Korean language. Whisper was pretrained on a large corpus (around 680,000 hours) of web speech data and has demonstrated strong recognition performance for major languages. However, it faces challenges in recognizing languages such as Korean, which is not major language while training. We address this issue by fine-tuning the Whisper model with an additional dataset comprising about 1,000 hours of Korean speech. We also compare its performance against a Transformer model that was trained from scratch using the same dataset. Our results indicate that fine-tuning the Whisper model significantly improved its Korean speech recognition capabilities in terms of character error rate (CER). Specifically, the performance improved with increasing model size. However, the Whisper model's performance on English deteriorated post fine-tuning, emphasizing the need for further research to develop robust multilingual models. Our study demonstrates the potential of utilizing a fine-tuned Whisper model for Korean ASR applications. Future work will focus on multilingual recognition and optimization for real-time inference.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.382-384
• /
• 2021

In this study, we implement a system that automatically classifies types of plastics using YOLO (You Only Look Once), a real-time object recognition algorithm. The system consists of Nvidia jetson nano, a small computer for deep learning and computer vision, with model trained to recognize plastic separation emission marks using YOLO. Using a webcam, recycling marks of plastic waste were recognized as PET, HDPE, and PP, and motors were adjusted to be classified according to the type. By implementing this automatic classifier, it is convenient in that it can reduce the labor of separating and discharging plastic separation marks by humans and increase the efficiency of recycling through accurate recycling.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.301-307
• /
• 2018

The most of the IR focus on the method for searching the document, so the keyword-based IR system is not able to reflect the feature information of the image. In order to overcome these limitations, we have developed a system that can search similar images based on the vector information of images, and it can search for similar images based on sketches. The proposed system uses the GAN to up sample the sketch to the image level, convert the image to the vector through the CNN, and then retrieve the similar image using the vector space model. The model was learned using fashion image and the image retrieval system was developed. As a result, the result is showed meaningful performance.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2023

The problem of classifying a non-line-of-sight (NLOS) signal in a multipath channel is important to improve global navigation satellite system (GNSS) positioning accuracy in urban areas. Conventional deep learning-based NLOS signal classifiers use GNSS satellite measurements such as the carrier-to-noise-density ratio (CN_0), pseudorange, and elevation angle as inputs. However, there is a computational inefficiency with use of these measurements and the NLOS signal features expressed by the measurements are limited. In this paper, we propose a Convolutional Neural Network (CNN)-based NLOS signal classifier that receives successive Auto-correlation function (ACF) outputs according to a time-series, which is the most primitive output of GNSS signal processing. We compared the proposed classifier to other DL-based NLOS signal classifiers such as a multi-layer perceptron (MLP) and Gated Recurrent Unit (GRU) to show the superiority of the proposed classifier. The results show the proposed classifier does not require the navigation data extraction stage to classify the NLOS signals, and it has been verified that it has the best detection performance among all compared classifiers, with an accuracy of up to 97%.