• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.243-252
• /
• 2024

Among the Foley sound generation models that have recently begun to be studied, a sound generation technique using the Vector Quantized-Variational AutoEncoder (VQ-VAE) structure and generation model such as Pixelsnail are one of the important research subjects. On the other hand, in the field of deep learning-based acoustic signal compression, residual vector quantization technology is reported to be more suitable than the conventional VQ-VAE structure. Therefore, in this paper, we aim to study whether residual vector quantization technology can be effectively applied to the Foley sound generation. In order to tackle the problem, this paper applies the residual vector quantization technique to the conventional VQ-VAE-based Foley sound generation model, and in particular, derives a model that is compatible with the existing models such as Pixelsnail and does not increase computational resource consumption. In order to evaluate the model, an experiment was conducted using DCASE2023 Task7 data. The results show that the proposed model enhances about 0.3 of the Fréchet audio distance. Unfortunately, the performance enhancement was limited, which is believed to be due to the decrease in the resolution of time-frequency domains in order to do not increase consumption of the computational resources.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.

• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.261-282
• /
• 2024

This study proposed and evaluated electroencephalography (EEG)-based and eye-tracking-based methods to determine relevance by utilizing users' implicit relevance feedback while navigating content in a digital library. For this, EEG/eye-tracking experiments were conducted on 32 participants using video, image, and text data. To assess the usefulness of the proposed methods, deep learning-based artificial intelligence (AI) techniques were used as a competitive benchmark. The evaluation results showed that EEG component-based methods (av_P600 and f_P3b components) demonstrated high classification accuracy in selecting relevant videos and images (faces/emotions). In contrast, AI-based methods, specifically object recognition and natural language processing, showed high classification accuracy for selecting images (objects) and texts (newspaper articles). Finally, guidelines for implementing a digital library interface based on EEG, eye-tracking, and artificial intelligence technologies have been proposed. Specifically, a system model based on implicit relevance feedback has been presented. Moreover, to enhance classification accuracy, methods suitable for each media type have been suggested, including EEG-based, eye-tracking-based, and AI-based approaches.

• Journal of Radiation Industry
• /
• v.17 no.1
• /
• pp.19-32
• /
• 2023

The amount of radioactive waste is expected to dramatically increase with decommissioning of nuclear power plants such as Kori-1, the first nuclear power plant in South Korea. Accurate nuclide analysis is necessary to manage the radioactive wastes safely, but research on verification of radionuclide analysis has yet to be well established. This study aimed to develop the technology that can verify the results of radionuclide analysis based on artificial intelligence. In this study, we propose an anomaly detection algorithm for inspecting the analysis error of radionuclide. We used the data from 'Updated Scaling Factors in Low-Level Radwaste' (NP-5077) published by EPRI (Electric Power Research Institute), and resampling was performed using SMOTE (Synthetic Minority Oversampling Technique) algorithm to augment data. 149,676 augmented data with SMOTE algorithm was used to train the artificial neural networks (classification and anomaly detection networks). 324 NP-5077 report data verified the performance of networks. The anomaly detection algorithm of radionuclide analysis was divided into two modules that detect a case where radioactive waste was incorrectly classified or discriminate an abnormal data such as loss of data or incorrectly written data. The classification network was constructed using the fully connected layer, and the anomaly detection network was composed of the encoder and decoder. The latter was operated by loading the latent vector from the end layer of the classification network. This study conducted exploratory data analysis (i.e., statistics, histogram, correlation, covariance, PCA, k-mean clustering, DBSCAN). As a result of analyzing the data, it is complicated to distinguish the type of radioactive waste because data distribution overlapped each other. In spite of these complexities, our algorithm based on deep learning can distinguish abnormal data from normal data. Radionuclide analysis was verified using our anomaly detection algorithm, and meaningful results were obtained.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.326-334
• /
• 2024

Extra-oral imaging techniques such as Panoramic X-rays (PXs) and Cone Beam Computed Tomography (CBCT) are the most preferred imaging modalities in dental clinics owing to its patient convenience during imaging as well as their ability to visualize entire teeth information. PXs are preferred for routine clinical treatments and CBCTs for complex surgeries and implant treatments. However, PXs are limited by the lack of third dimensional spatial information whereas CBCTs inflict high radiation exposure to patient. When a PX is already available, it is beneficial to reconstruct the 3D oral structure from the PX to avoid further expenses and radiation dose. In this paper, we propose 3DentAI - an U-Net based deep learning framework for 3D reconstruction of oral structure from a PX image. Our framework consists of three module - a reconstruction module based on attention U-Net for estimating depth from a PX image, a realignment module for aligning the predicted flattened volume to the shape of jaw using a predefined focal trough and ray data, and lastly a refinement module based on 3D U-Net for interpolating the missing information to obtain a smooth representation of oral cavity. Synthetic PXs obtained from CBCT by ray tracing and rendering were used to train the networks without the need of paired PX and CBCT datasets. Our method, trained and tested on a diverse datasets of 600 patients, achieved superior performance to GAN-based models even with low computational complexity.

• Journal of The Korean Institute of Defense Technology
• /
• v.5 no.3
• /
• pp.8-17
• /
• 2023

The current weapon system is operated as a complex weapon system with various standards and protocols applied, so there is a risk of failure in smooth information exchange during combined and joint operations on the battlefield. The interoperability of weapon systems to carry out precise strikes on key targets through rapid situational judgment between weapon systems is a key element in the conduct of war. Since the Korean military went into service, there has been a need to change the configuration and improve performance of a large number of software and hardware, but there is no verification system for the impact on interoperability, and there are no related test tools and facilities. In addition, during combined and joint training, errors frequently occur during use after arbitrarily changing the detailed operation method and software of the weapon/power support system. Therefore, periodic verification of interoperability between weapon systems is necessary. To solve this problem, rather than having people schedule an evaluation period and conduct the evaluation once, AI should continuously evaluate the interoperability between weapons and power support systems 24 hours a day to advance warfighting capabilities. To solve these problems, To this end, preliminary research was conducted to improve defense interoperability capabilities by applying natural language processing techniques (①Word2Vec model, ②FastText model, ③Swivel model) (using published algorithms and source code). Based on the results of this experiment, we would like to present a methodology (automated evaluation of interoperability requirements evaluation / level measurement through natural language processing model) to implement an automated defense interoperability evaluation tool without relying on humans.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.73-82
• /
• 2023

With 78% of current fisheries workers being elderly, there's a pressing need to address labor shortages. Consequently, active research on smart aquaculture technologies, centered on object detection and tracking algorithms, is underway. These technologies allow for fish size analysis and behavior pattern forecasting, facilitating the development of real-time monitoring and automated systems. Our study utilized video data from cameras outside aquaculture facilities and implemented fish detection and tracking algorithms. We aimed to tackle high maintenance costs due to underwater conditions and camera corrosion from ammonia and pH levels. We evaluated the performance of a real-time system using YOLOv7 for fish detection and the SORT algorithm for movement tracking. YOLOv7 results demonstrated a trade-off between Recall and Precision, minimizing false detections from lighting, water currents, and shadows. Effective tracking was ascertained through re-identification. This research holds promise for enhancing smart aquaculture's operational efficiency and improving fishery facility management.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.4
• /
• pp.17-34
• /
• 2023

Camera trapping has been used as a non-invasive survey method that minimizes anthropogenic disturbance to ecosystems. Nevertheless, it is labor-intensive and time-consuming, requiring researchers to quantify species and populations. In this study, we aimed to improve the preprocessing of camera trapping data by utilizing an object detection algorithm. Wildlife monitoring using unmanned sensor cameras was conducted in a forested urban forest and a green space on a university campus in Cheonan City, Chungcheongnam-do, Korea. The collected camera trapping data were classified by a researcher to identify the occurrence of species. The data was then used to test the performance of the YOLO-X object detection algorithm for wildlife detection. The camera trapping resulted in 10,500 images of the urban forest and 51,974 images of green spaces on campus. Out of the total 62,474 images, 52,993 images (84.82%) were found to be false positives, while 9,481 images (15.18%) were found to contain wildlife. As a result of wildlife monitoring, 19 species of birds, 5 species of mammals, and 1 species of reptile were observed within the study area. In addition, there were statistically significant differences in the frequency of occurrence of the following species according to the type of urban greenery: Parus varius(t = -3.035, p < 0.01), Parus major(t = 2.112, p < 0.05), Passer montanus(t = 2.112, p < 0.05), Paradoxornis webbianus(t = 2.112, p < 0.05), Turdus hortulorum(t = -4.026, p < 0.001), and Sitta europaea(t = -2.189, p < 0.05). The detection performance of the YOLO-X model for wildlife occurrence was analyzed, and it successfully classified 94.2% of the camera trapping data. In particular, the number of true positive predictions was 7,809 images and the number of false negative predictions was 51,044 images. In this study, the object detection algorithm YOLO-X model was used to detect the presence of wildlife in the camera trapping data. In this study, the YOLO-X model was used with a filter activated to detect 10 specific animal taxa out of the 80 classes trained on the COCO dataset, without any additional training. In future studies, it is necessary to create and apply training data for key occurrence species to make the model suitable for wildlife monitoring.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.189-198
• /
• 2024

Research combining deep learning-based models and physical simulations is making important advances in the medical field. This extracts the necessary information from medical image data and enables fast and accurate prediction of deformation of the skeleton and soft tissue based on physical laws. This study proposes a system that integrates Neural Radiance Fields (NeRF), Position-Based Dynamics (PBD), and Parallel Resampling to generate 3D volume data, and deform and visualize them in real-time. NeRF uses 2D images and camera coordinates to produce high-resolution 3D volume data, while PBD enables real-time deformation and interaction through physics-based simulation. Parallel Resampling improves rendering efficiency by dividing the volume into tetrahedral meshes and utilizing GPU parallel processing. This system renders the deformed volume data using ray casting, leveraging GPU parallel processing for fast real-time visualization. Experimental results show that this system can generate and deform 3D data without expensive equipment, demonstrating potential applications in engineering, education, and medicine.

• Imaging Science in Dentistry
• /
• v.54 no.3
• /
• pp.271-275
• /
• 2024

Purpose: Recent advancements in artificial intelligence (AI), particularly tools such as ChatGPT developed by OpenAI, a U.S.-based AI research organization, have transformed the healthcare and education sectors. This study investigated the effectiveness of ChatGPT in answering dentistry exam questions, demonstrating its potential to enhance professional practice and patient care. Materials and Methods: This study assessed the performance of ChatGPT 3.5 and 4 on U.S. dental exams - specifically, the Integrated National Board Dental Examination (INBDE), Dental Admission Test (DAT), and Advanced Dental Admission Test (ADAT) - excluding image-based questions. Using customized prompts, ChatGPT's answers were evaluated against official answer sheets. Results: ChatGPT 3.5 and 4 were tested with 253 questions from the INBDE, ADAT, and DAT exams. For the INBDE, both versions achieved 80% accuracy in knowledge-based questions and 66-69% in case history questions. In ADAT, they scored 66-83% in knowledge-based and 76% in case history questions. ChatGPT 4 excelled on the DAT, with 94% accuracy in knowledge-based questions, 57% in mathematical analysis items, and 100% in comprehension questions, surpassing ChatGPT 3.5's rates of 83%, 31%, and 82%, respectively. The difference was significant for knowledge-based questions(P=0.009). Both versions showed similar patterns in incorrect responses. Conclusion: Both ChatGPT 3.5 and 4 effectively handled knowledge-based, case history, and comprehension questions, with ChatGPT 4 being more reliable and surpassing the performance of 3.5. ChatGPT 4's perfect score in comprehension questions underscores its trainability in specific subjects. However, both versions exhibited weaker performance in mathematical analysis, suggesting this as an area for improvement.