• Korean Journal of Radiology
• /
• v.21 no.4
• /
• pp.431-441
• /
• 2020

Objective: To compare the diagnostic performance and interobserver variability of strain ratio obtained from one or two regions of interest (ROI) on breast elastography. Materials and Methods: From April to May 2016, 140 breast masses in 140 patients who underwent conventional ultrasonography (US) with strain elastography followed by US-guided biopsy were evaluated. Three experienced breast radiologists reviewed recorded US and elastography images, measured strain ratios, and categorized them according to the American College of Radiology breast imaging reporting and data system lexicon. Strain ratio was obtained using the 1-ROI method (one ROI drawn on the target mass), and the 2-ROI method (one ROI in the target mass and another in reference fat tissue). The diagnostic performance of the three radiologists among datasets and optimal cut-off values for strain ratios were evaluated. Interobserver variability of strain ratio for each ROI method was assessed using intraclass correlation coefficient values, Bland-Altman plots, and coefficients of variation. Results: Compared to US alone, US combined with the strain ratio measured using either ROI method significantly improved specificity, positive predictive value, accuracy, and area under the receiver operating characteristic curve (AUC) (all p values < 0.05). Strain ratio obtained using the 1-ROI method showed higher interobserver agreement between the three radiologists without a significant difference in AUC for differentiating breast cancer when the optimal strain ratio cut-off value was used, compared with the 2-ROI method (AUC: 0.788 vs. 0.783, 0.693 vs. 0.715, and 0.691 vs. 0.686, respectively, all p values > 0.05). Conclusion: Strain ratios obtained using the 1-ROI method showed higher interobserver agreement without a significant difference in AUC, compared to those obtained using the 2-ROI method. Considering that the 1-ROI method can reduce performers' efforts, it could have an important role in improving the diagnostic performance of breast US by enabling consistent management of breast lesions.

• 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.

• Journal of Environmental Impact Assessment
• /
• v.33 no.1
• /
• pp.9-17
• /
• 2024

The purpose of this study is to select and predict optimal heatwave indices for describing and predicting heat-related illnesses. Regression analysis was conducted using Heat-related illness surveillance system data for a number of heat-related illnesses and meteorological data from the Korea Meteorological Administration's Automatic Weather Station (AWS) for the period from 2021 to 2023. Daily average temperature, daily maximum temperature, daily average Wet Bulb Globe Temperature (WBGT), and daily maximum WBGT values were calculated and analyzed. The results indicated that among the four indicators, the daily maximum WBGT showed the highest suitability with an R² value of 0.81 and RMSE of 0.98, with a threshold of 29.94 Celsius. During the entire analysis period, there were a total of 91 days exceeding this threshold, resulting in 339 cases of heat-related illnesses. Predictions of heat-related illness cases from 2021 to 2023 using the regression equation for daily maximum WBGT showed an accuracy with less than 10 cases of error annually, demonstrating a high level of precision. Through continuous research and refinement of data and analysis methods, it is anticipated that this approach could contribute to predicting and mitigating the impact of heatwaves.

• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.57-67
• /
• 2024

This paper explores the potential of electromyography (EMG) as a means of gesture recognition for user input in gesture-based interaction. EMG utilizes small electrodes within muscles to detect and interpret user movements, presenting a viable input method. To classify user gestures based on EMG data, machine learning techniques are employed, necessitating the preprocessing of raw EMG data to extract relevant features. EMG characteristics can be expressed through formulas such as Integrated EMG (IEMG), Mean Absolute Value (MAV), Simple Square Integral (SSI), Variance (VAR), and Root Mean Square (RMS). Additionally, determining the suitable time for gesture classification is crucial, considering the perceptual, cognitive, and response times required for user input. To address this, segment sizes ranging from a minimum of 100ms to a maximum of 1,000ms are varied, and feature extraction is performed to identify the optimal segment size for gesture classification. Notably, data learning employs overlapped segmentation to reduce the interval between data points, thereby increasing the quantity of training data. Using this approach, the paper employs four machine learning models (KNN, SVC, RF, XGBoost) to train and evaluate the system, achieving accuracy rates exceeding 96% for all models in real-time gesture input scenarios with a maximum segment size of 200ms.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.150-157
• /
• 2024

In this paper, we propose a novel algorithm for predicting the number of apples on an apple tree using a deep learning-based object detection model and a polynomial regression model. Measuring the number of apples on an apple tree can be used to predict apple yield and to assess losses for determining agricultural disaster insurance payouts. To measure apple fruit load, we photographed the front and back sides of apple trees. We manually labeled the apples in the captured images to construct a dataset, which was then used to train a one-stage object detection CNN model. However, when apples on an apple tree are obscured by leaves, branches, or other parts of the tree, they may not be captured in images. Consequently, it becomes difficult for image recognition-based deep learning models to detect or infer the presence of these apples. To address this issue, we propose a two-stage inference process. In the first stage, we utilize an image-based deep learning model to count the number of apples in photos taken from both sides of the apple tree. In the second stage, we conduct a polynomial regression analysis, using the total apple count from the deep learning model as the independent variable, and the actual number of apples manually counted during an on-site visit to the orchard as the dependent variable. The performance evaluation of the two-stage inference system proposed in this paper showed an average accuracy of 90.98% in counting the number of apples on each apple tree. Therefore, the proposed method can significantly reduce the time and cost associated with manually counting apples. Furthermore, this approach has the potential to be widely adopted as a new foundational technology for fruit load estimation in related fields using deep learning.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.3
• /
• pp.173-178
• /
• 2024

This study presents a technique for assessing the dimensional quality of assembly parts in Prefabricated Steel Structures (PSS) using a stereo vision sensor. The stereo vision system captures images and point cloud data of the assembly area, followed by applying image processing algorithms such as fuzzy-based edge detection and Hough transform-based circular bolt hole detection to identify bolt hole locations. The 3D center positions of each bolt hole are determined by correlating 3D real-world position information from depth images with the extracted bolt hole positions. Principal Component Analysis (PCA) is then employed to calculate coordinate axes for precise measurement of distances between bolt holes, even when the sensor and structure orientations differ. Bolt holes are sorted based on their 2D positions, and the distances between sorted bolt holes are calculated to assess the assembly part's dimensional quality. Comparison with actual drawing data confirms measurement accuracy with an absolute error of 1mm and a relative error within 4% based on median criteria.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.4
• /
• pp.281-306
• /
• 2023

This study analyzed the legal deposit, acquisition, and donation status from 2020 to 2022, along with the deposit status of e-publications with issued ISBNs. Through this analysis, the study derived improvement measures to strengthen compliance with legal deposit obligations for domestic e-publications. The key findings are as follows: The collection methods were acquisition (57.07%), legal deposit (41.74%), and donation (1.19%). The file formats varied, including e-books (pdf, epub), webtoons (jpg), and audiobooks (mp3). Most e-publications collected were published from 2012 to 2022, with some from 1960 to 2011. Webtoons dominated acquired materials, while legal deposits mainly comprised e-books. Analyzing the status of e-publications with issued ISBNs, e-books (96.2%) were most common, with the literature field receiving the highest number of ISBNs. Most ISBNs were issued during 2020 to 2022. Looking at the top 10 publishers, the low legal deposit rate indicates the need for improvement. To address this, proposed improvement measures include enhancing publishers' awareness of legal deposits, strengthening incentives and sanctions, encouraging voluntary participation through transparent disclosure of the legal deposit status, and improving the accuracy of data in the ISBN issuance and deposit system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.317-326
• /
• 2024

Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.146-156
• /
• 2024

Objective: Automated breast ultrasound (ABUS) is a relevant imaging technique for early breast cancer diagnosis and is increasingly being used as a supplementary tool for mammography. This study compared the performance of ABUS and handheld ultrasound (HHUS) in detecting and characterizing the axillary lymph nodes (LNs) in patients with breast cancer. Materials and Methods: We retrospectively reviewed the medical records of women with recently diagnosed early breast cancer (≤ T2) who underwent both ABUS and HHUS examinations for axilla (September 2017-May 2018). ABUS and HHUS findings were compared using pathological outcomes as reference standards. Diagnostic performance in predicting any axillary LN metastasis and heavy nodal-burden metastases (i.e., ≥ 3 LNs) was evaluated. The ABUS-HHUS agreement for visibility and US findings was calculated. Results: The study included 377 women (53.1 ± 11.1 years). Among 385 breast cancers in 377 patients, 101 had axillary LN metastases and 30 had heavy nodal burden metastases. ABUS identified benign-looking or suspicious axillary LNs (average, 1.4 ± 0.8) in 246 axillae (63.9%, 246/385). According to the per-breast analysis, the sensitivity, specificity, positive and negative predictive values, and accuracy of ABUS in predicting axillary LN metastases were 43.6% (44/101), 95.1% (270/284), 75.9% (44/58), 82.6% (270/327), and 81.6% (314/385), respectively. The corresponding results for HHUS were 41.6% (42/101), 95.1% (270/284), 75.0% (42/56), 82.1% (270/329), and 81.0% (312/385), respectively, which were not significantly different from those of ABUS (P ≥ 0.53). The performance results for heavy nodal-burden metastases were 70.0% (21/30), 89.6% (318/355), 36.2% (21/58), 97.3% (318/327), and 88.1% (339/385), respectively, for ABUS and 66.7% (20/30), 89.9% (319/355), 35.7% (20/56), 97.0% (319/329), and 88.1% (339/385), respectively, for HHUS, also not showing significant difference (P ≥ 0.57). The ABUS-HHUS agreement was 95.9% (236/246; Cohen's kappa = 0.883). Conclusion: Although ABUS showed limited sensitivity in diagnosing axillary LN metastasis in early breast cancer, it was still useful as the performance was comparable to that of HHUS.

• Korean Journal of Radiology
• /
• v.23 no.2
• /
• pp.246-255
• /
• 2022

Objective: To determine the usefulness of Silent MR angiography (MRA) for evaluating intracranial aneurysms treated with stent-assisted coil embolization. Materials and Methods: Ninety-nine patients (101 aneurysms) treated with stent-assisted coil embolization (Neuroform atlas, 71 cases; Enterprise, 17; LVIS Jr, 9; and Solitaire AB, 4 cases) underwent time-of-flight (TOF) MRA and Silent MRA in the same session using a 3T MRI system within 24 hours of embolization. Two radiologists independently interpreted both MRA images retrospectively and rated the image quality using a 5-point Likert scale. The image quality and diagnostic accuracy of the two modalities in the detection of aneurysm occlusion were further compared based on the stent design and the site of aneurysm. Results: The average image quality scores of the Silent MRA and TOF MRA were 4.38 ± 0.83 and 2.78 ± 1.04, respectively (p < 0.001), with an almost perfect interobserver agreement. Silent MRA had a significantly higher image quality score than TOF MRA at the distal internal carotid artery (n = 57, 4.25 ± 0.91 vs. 3.05 ± 1.16, p < 0.001), middle cerebral artery (n = 21, 4.57 ± 0.75 vs. 2.19 ± 0.68, p < 0.001), anterior cerebral artery (n = 13, 4.54 ± 0.66 vs. 2.46 ± 0.66, p < 0.001), and posterior circulation artery (n = 10, 4.50 ± 0.71 vs. 2.90 ± 0.74, p = 0.013). Silent MRA had superior image quality score to TOF MRA in the stented arteries when using Neuroform atlas (4.66 ± 0.53 vs. 3.21 ± 0.84, p < 0.001), Enterprise (3.29 ± 1.59 vs. 1.59 ± 0.51, p = 0.003), LVIS Jr (4.33 ± 1.89 vs. 1.89 ± 0.78, p = 0.033), and Solitaire AB stents (4.00 ± 2.25 vs. 2.25 ± 0.96, p = 0.356). The interpretation of the status of aneurysm occlusion exhibited significantly higher sensitivity with Silent MRA than with TOF MRA when using the Neuroform Atlas stent (96.4% vs. 14.3%, respectively, p < 0.001) and LVIS Jr stent (100% vs. 20%, respectively, p = 0.046). Conclusion: Silent MRA can be useful to evaluate aneurysms treated with stent-assisted coil embolization, regardless of the aneurysm location and type of stent used.