• Journal of radiological science and technology
• /
• v.47 no.1
• /
• pp.29-37
• /
• 2024

This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1797-1808
• /
• 2021

Objective: To determine whether volumetric CT texture analysis (CTTA) using fully automatic tumor segmentation can help predict recurrence-free survival (RFS) in patients with intrahepatic mass-forming cholangiocarcinomas (IMCCs) after surgical resection. Materials and Methods: This retrospective study analyzed the preoperative CT scans of 89 patients with IMCCs (64 male; 25 female; mean age, 62.1 years; range, 38-78 years) who underwent surgical resection between January 2005 and December 2016. Volumetric CTTA of IMCCs was performed in late arterial phase images using both fully automatic and semi-automatic liver tumor segmentation techniques. The time spent on segmentation and texture analysis was compared, and the first-order and second-order texture parameters and shape features were extracted. The reliability of CTTA parameters between the techniques was evaluated using intraclass correlation coefficients (ICCs). Intra- and interobserver reproducibility of volumetric CTTAs were also obtained using ICCs. Cox proportional hazard regression were used to predict RFS using CTTA parameters and clinicopathological parameters. Results: The time spent on fully automatic tumor segmentation and CTTA was significantly shorter than that for semi-automatic segmentation: mean ± standard deviation of 1 minutes 37 seconds ± 50 seconds vs. 10 minutes 48 seconds ± 13 minutes 44 seconds (p < 0.001). ICCs of the texture features between the two techniques ranged from 0.215 to 0.980. ICCs for the intraobserver and interobserver reproducibility using fully automatic segmentation were 0.601-0.997 and 0.177-0.984, respectively. Multivariable analysis identified lower first-order mean (hazard ratio [HR], 0.982; p = 0.010), larger pathologic tumor size (HR, 1.171; p < 0.001), and positive lymph node involvement (HR, 2.193; p = 0.014) as significant parameters for shorter RFS using fully automatic segmentation. Conclusion: Volumetric CTTA parameters obtained using fully automatic segmentation could be utilized as prognostic markers in patients with IMCC, with comparable reproducibility in significantly less time compared with semi-automatic segmentation.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.85-95
• /
• 2009

In the binaural synthesis environments, wide varieties of the head-related transfer functions (HRTFs) that have measured with a various direction would be desirable to obtain the accurate and various spatial sound images. To reduce the size' of HRTFs, interpolation has been often employed, where the HRTF for any direction is obtained by a limited number of the representative HRTFs. In this paper, we study on the distortion measures for interpolation, which has an important role in interpolation. With lhe various objective distortion metrics, the differences between the interpolated and the measured HRTFs were computed. These were then compared and analyzed with the results from the listening tests. From the results, the objective distortion measures were selected, that reflected the perceptual differences in spatial sound image. This measure was employed in a practical interpolation technique. We applied the proposed method to four kinds of an HRTF set, measured from three human heads and one mannequin. As a result, the Mel-frequency cepstral distortion was shown to be a good predictor for the differences in spatial sound location, when three HRTF measured from human, and the time-domain signal to distortion ratio revealed good prediction results for the entire four HRTF sets.

• Journal of Navigation and Port Research
• /
• v.47 no.6
• /
• pp.376-385
• /
• 2023

Fishing boat capsizing accidents account for more than half of all capsize accidents. These can occur for a variety of reasons, including inexperienced operation, bad weather, and poor maintenance. Due to the size and influence of the industry, technological complexity, and regional diversity, fishing ships are relatively under-researched compared to commercial ships. This study aimed to predict the rolling motion time series of fishing boats using an image-based deep learning model. Image-based deep learning can achieve high performance by learning various patterns in a time series. Three image-based deep learning models were used for this purpose: Xception, ResNet50, and CRNN. Xception and ResNet50 are composed of 177 and 184 layers, respectively, while CRNN is composed of 22 relatively thin layers. The experimental results showed that the Xception deep learning model recorded the lowest Symmetric mean absolute percentage error(sMAPE) of 0.04291 and Root Mean Squared Error(RMSE) of 0.0198. ResNet50 and CRNN recorded an RMSE of 0.0217 and 0.022, respectively. This confirms that the models with relatively deeper layers had higher accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.577-582
• /
• 2024

In 2007, the first domestic pet insurance policies were introduced, and by 2023, numerous insurance products had been developed. The pet insurance market has been expanding steadily. However, as of 2022, only 0.8% of all pet owners have subscribed to pet insurance. Pet owners hesitate to enroll in pet insurance due to expensive premiums, unclear coverage details, and strict enrollment criteria. This paper proposes a model capable of detecting pet eye diseases and predicting their health age. Initially, EfficientNet is employed to identify the pet's eye disease, while OpenCV is utilized to locate and measure the size of the disease, enabling the calculation of the pet's healthy age. By leveraging the calculated health age, the aim is to aid insurance companies in determining pet insurance premiums. This model can facilitate the calculation of reasonable pet insurance rates based on the pet's eye condition and health age. Ultimately, the objective is to implement a system capable of detecting pet eye conditions and predicting their health age.

• Herbal Formula Science
• /
• v.32 no.1
• /
• pp.11-28
• /
• 2024

Objectives : GunRyeong-Tang(GRT) is a traditional herbal prescription that combines Oryeongsan and Sagunja-tang. This study employed network analysis methods on the components of GRT and target genes related to diabetes complications to predict the improvement effects of GRT on diabetes complications. Methods : The collection of active compounds of GRT and related target genes involved the utilization of public databases and the PubChem database. We selected diabetes complication-related genes using GeneCards and confirmed their correlation through comparative analysis with the target genes of GRT. We constructed a network using Cytoscape 3.9.1 and conducted topological analysis. To predict the mechanism, we performed functional enrichment analysis based on Gene Ontology (GO) biological processes and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. Results : Through network analysis, 234 active compounds and 1361 related genes were collected from GRT. A total of 9,136 genes related to diabetes complications were collected, and 1,039 target genes overlapping with the components of GRT were identified. The core genes of this network were TP53, INS, AKT1, ALB, and EGFR. In addition, GRT significantly reduced the H9c2 cell size and the expression of myocardial hypertrophy biomarkers (ANP, BNP), which were increased by high glucose (HG). Conclusions : Through this study, we were able to predict the activity and mechanism of action of GRT on diabetes and diabetic complications, and confirmed the potential of GRT as a treatment for diabetes complications through the effect of GRT on improving myocardial hypertrophy for diabetic cardiomyopathy.

• Computers and Concrete
• /
• v.34 no.2
• /
• pp.151-168
• /
• 2024

This research aimed to appraise the effectiveness of four optimization approaches - cuckoo optimization algorithm (COA), multi-verse optimization (MVO), particle swarm optimization (PSO), and teaching-learning-based optimization (TLBO) - that were enhanced with an artificial neural network (ANN) in predicting the bearing capacity of shallow foundations located on cohesionless soils. The study utilized a database of 97 laboratory experiments, with 68 experiments for training data sets and 29 for testing data sets. The ANN algorithms were optimized by adjusting various variables, such as population size and number of neurons in each hidden layer, through trial-and-error techniques. Input parameters used for analysis included width, depth, geometry, unit weight, and angle of shearing resistance. After performing sensitivity analysis, it was determined that the optimized architecture for the ANN structure was 5×5×1. The study found that all four models demonstrated exceptional prediction performance: COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP. It is worth noting that the MVO-MLP model exhibited superior accuracy in generating network outputs for predicting measured values compared to the other models. The training data sets showed R² and RMSE values of (0.07184 and 0.9819), (0.04536 and 0.9928), (0.09194 and 0.9702), and (0.04714 and 0.9923) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively. Similarly, the testing data sets produced R² and RMSE values of (0.08126 and 0.07218), (0.07218 and 0.9814), (0.10827 and 0.95764), and (0.09886 and 0.96481) for COA-MLP, MVO-MLP, PSO-MLP, and TLBO-MLP methods respectively.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.3
• /
• pp.166-177
• /
• 2006

The cache size tends to grow in the embedded processor as technology scales to smaller transistors and lower supply voltages. However, larger cache size demands more energy. Accordingly, the ratio of the cache energy consumption to the total processor energy is growing. Many cache energy schemes have been proposed for reducing the cache energy consumption. However, these previous schemes are concerned with one side for reducing the cache energy consumption, dynamic cache energy only, or static cache energy only. In this paper, we propose a hybrid scheme for reducing dynamic and static cache energy, simultaneously. for this hybrid scheme, we adopt two existing techniques to reduce static cache energy consumption, drowsy cache technique, and to reduce dynamic cache energy consumption, way-prediction technique. Additionally, we propose a early wake-up technique based on program counter to reduce penalty caused by applying drowsy cache technique. We focus on level 1 data cache. The hybrid scheme can reduce static and dynamic cache energy consumption simultaneously, furthermore our early wake-up scheme can reduce extra program execution cycles caused by applying the hybrid scheme.

• Korean Journal of Soil Science and Fertilizer
• /
• v.42 no.5
• /
• pp.399-407
• /
• 2009

Laser induced breakdown spectroscopy(LIBS) is an simple analysis method for directly quantifying many kinds of soil micro-elements on site using a small size of laser without pre-treatment at any property of materials(solid, liquid and gas). The purpose of this study were to find an optimum condition of the LIBS measurement including wavelengths for quantifying soil elements, to relate spectral properties to the concentration of soil elements using LIBS as a simultaneous un-breakdown quantitative analysis technology, which can be applied for the safety assessment of agricultural products and precision agriculture, and to compare the results with a standardized chemical analysis method. Soil samples classified as fine-silty, mixed, thermic Typic Hapludalf(Memphis series) from grassland and uplands in Tennessee, USA were collected, crushed, and prepared for further analysis or LIBS measurement. The samples were measured using LIBS ranged from 200 to 600 nm(0.03 nm interval) with a Nd:YAG laser at 532 nm, with a beam energy of 25 mJ per pulse, a pulse width of 5 ns, and a repetition rate of 10 Hz. The optimum wavelength(${\lambda}nm$) of LIBS for estimating soil and plant elements were 308.2 nm for Al, 428.3 nm for Ca, 247.8 nm for T-C, 438.3 nm for Fe, 766.5 nm for K, 85.2 nm for Mg, 330.2 nm for Na, 213.6 nm for P, 180.7 nm for S, 288.2 nm for Si, and 351.9 nm for Ti, respectively. Coefficients of determination($r^2$) of calibration curve using standard reference soil samples for each element from LIBS measurement were ranged from 0.863 to 0.977. In comparison with ICP-AES(Inductively coupled plasma atomic emission spectroscopy) measurement, measurement error in terms of relative standard error were calculated. Silicon dioxide(SiO2) concentration estimated from two methods showed good agreement with -3.5% of relative standard error. The relative standard errors for the other elements were high. It implies that the prediction accuracy is low which might be caused by matrix effect such as particle size and constituent of soils. It is necessary to enhance the measurement and prediction accuracy of LIBS by improving pretreatment process, standard reference soil samples, and measurement method for a reliable quantification method.

• The korean journal of orthodontics
• /
• v.30 no.1 s.78
• /
• pp.115-126
• /
• 2000

Dental arch expansion is one of the method used to solve the dental crowding problem by non-extraction. Many formulae using tooth size have been suggested to predict ideal inter-premolar and inter-molar width. The purpose of this study was to evaluate the adequacy of some upper dental arch width prediction methods, namely Pont's method, Schmuth's method and Cha's method. The sample consisted of the casts of 119 Korean young adults who had no muscular abnormality, no skeletal discrepancy, and Angle's Class I molar relationships. Measurements were obtained directly from plaster casts; they Included mesiodistal crown diameters of the four maxillary incisors, as well as maxillary inter-first-premolar and inter-first-molar arch widths as specified by Pont. The correlation coefficients between the sum of incisors(SI) and upper dental arch width were calculated. The differences between predicted width and actual width were classified as overestimated, properestimated, and underestimated. The data obtained from each group were analyzed for statistical differences. The results were as follows : 1. Upper dental arch width indices were calculated from SI in normal occlusion (81.96 : premolar index, 62.55 : molar index). 2. Low correlations between SI and arch width were noted in normal occlusion (0.50 in the inter-premolar width, 0.39 in the inter-molar width). 3. Pont's formula and Schmuth's formula tended to overestimate the inter-premolar width. A more even distribution of estimates was noted in Cha's fomula. 4. Cases within $\pm$1 mm range of observed inter-premolar width were $45\%$ in the Cha's formula, $40\%$ in the Pont's formula, and $39\%$ in the Schmuth's formula. 5. All formulae had a tendency to underestimate the inter-molar width, but Cha's formula had better predictability than others. 6. Cases within $\pm$1 mm range of observed inter-molar width were $40\%$ in the Cha's formula, $29\%$ in the Pont's formula, and $13\%$ of Schmuth's formula. The data presented in this study does not support the clinical usefulness of ideal arch width prediction methods using the mesiodistal width of maxillary incisors.