• Korean Journal of Radiology
• /
• v.22 no.12
• /
• pp.2017-2025
• /
• 2021

Objective: To evaluate the accuracy and clinical efficacy of a hybrid Greulich-Pyle (GP) and modified Tanner-Whitehouse (TW) artificial intelligence (AI) model for bone age assessment. Materials and Methods: A deep learning-based model was trained on an open dataset of multiple ethnicities. A total of 102 hand radiographs (51 male and 51 female; mean age ± standard deviation = 10.95 ± 2.37 years) from a single institution were selected for external validation. Three human experts performed bone age assessments based on the GP atlas to develop a reference standard. Two study radiologists performed bone age assessments with and without AI model assistance in two separate sessions, for which the reading time was recorded. The performance of the AI software was assessed by comparing the mean absolute difference between the AI-calculated bone age and the reference standard. The reading time was compared between reading with and without AI using a paired t test. Furthermore, the reliability between the two study radiologists' bone age assessments was assessed using intraclass correlation coefficients (ICCs), and the results were compared between reading with and without AI. Results: The bone ages assessed by the experts and the AI model were not significantly different (11.39 ± 2.74 years and 11.35 ± 2.76 years, respectively, p = 0.31). The mean absolute difference was 0.39 years (95% confidence interval, 0.33-0.45 years) between the automated AI assessment and the reference standard. The mean reading time of the two study radiologists was reduced from 54.29 to 35.37 seconds with AI model assistance (p < 0.001). The ICC of the two study radiologists slightly increased with AI model assistance (from 0.945 to 0.990). Conclusion: The proposed AI model was accurate for assessing bone age. Furthermore, this model appeared to enhance the clinical efficacy by reducing the reading time and improving the inter-observer reliability.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.119-130
• /
• 2024

Universities are open systems that aim to prepare students to meet academic and industrial programs' expectations. It is important for universities to recognize these expectations and to make sure that they are achievable. To do so, graduates' progression tracking system is an essential tool for universities' development to ensure graduate students meet the market requirements. The purpose of this paper is to create automatic tracing system that captures information about students after graduation and creates annual report that represents the status of university students in term of employment or completing their study. It mainly assists graduates to find appropriate jobs that meet their desires or enabling them to complete their higher education by providing all these opportunities in one platform. The system main objective is to improve communication between graduate students, the university and companies. It also aims to identify the difficulties associated with graduate employability and changes are required to serve current students in term of creating new programs or activities. This helps universities to identify and address the existing curriculums and program's strengths and weaknesses and their adequacy, quality and competencies of a graduate in the labor market, which enhances the quality of higher education. we analyzed and implemented the tracing system using PHP language, which speeds up custom web application development and MySQL database, which guarantee data security, high performance, and other features. Graduate students found the proposed system usable and valuable.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.65-72
• /
• 2023

This paper proposes a method for detecting malicious domains considering human habitual characteristics by building a Deep Learning model based on LSTM (Long Short-Term Memory). DGA (Domain Generation Algorithm) malicious domains exploit human habitual errors, resulting in severe security threats. The objective is to swiftly and accurately respond to changes in malicious domains and their evasion techniques through typosquatting to minimize security threats. The LSTM-based Deep Learning model automatically analyzes and categorizes generated domains as malicious or benign based on malware-specific features. As a result of evaluating the model's performance based on ROC curve and AUC accuracy, it demonstrated 99.21% superior detection accuracy. Not only can this model detect malicious domains in real-time, but it also holds potential applications across various cyber security domains. This paper proposes and explores a novel approach aimed at safeguarding users and fostering a secure cyber environment against cyber attacks.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.7
• /
• pp.680-685
• /
• 2009

In this paper, we propose a efficient noise power estimation technique for an integrated acoustic echo and noise suppression system in a frequency domain. The proposed method uses speech absence probability (SAP) derived from the microphone input signal as the smoothing parameter updating noise power to reduce the noise power estimation error resulted from the distortions in the unified structure where the noise suppression (NS) operation is placed after the acoustic echo suppression (AES) algorithm. Therefore, in the proposed approach, the smoothing parameter based on SAP derived from the input signal instead of echo-suppressed signal should stop updating noise power estimates during the distorted noise spectrum periods. The performance of the proposed algorithm is evaluated by the objective test under various environments and yields better results compared with the conventional scheme.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.3
• /
• pp.1-14
• /
• 2024

Gaining an accurate 3D stream geometry has become feasible with Unmanned Aerial Vehicle (UAV), which is crucial for better understanding stream hydrodynamic processes. The objective of this study was to investigate series of filters to remove stream vegetation and propose the best method for generating Digital Terrain Models (DTMs) using UAV-based point clouds. A stream reach approximately 500 m of the Bokha stream in Icheon city was selected as the study area. Point clouds were obtained in August 1st, 2023, using Phantom 4 multispectral and Zenmuse L1 for Structure from Motion (SfM) and Light Detection And Ranging (LiDAR) respectively. Three vegetation filters, two morphological filters, and six composite filters which combined vegetation and morphological filters were applied in this study. The Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used to assess each filters comparing with the two cross-sections measured by leveling survey. The vegetation filters performed better in SfM, especially for short vegetation areas, while the morphological filters demonstrated superior performance on LiDAR, particularly for taller vegetation areas. Overall, the composite filters combining advantages of two types of filters performed better than single filter application. The best method was the combination of Progressive TIN (PTIN) and Color Indicies of Vegetation Extraction (CIVE) for SfM, showing the smallest MAE of 0.169 m. The proposed method in this study can be utilized for constructing DTMs of stream and thus contribute to improving the accuracy of stream hydrodynamic simulations.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.325-332
• /
• 2006

In this paper. we Propose the noise suppressor with the Perceptual model and wavelet packet transform. The objective is to enhance speech corrupted colored or non-stationary noise. If corrupted noise is colored. subband approach would be more efficient than whole band one. To avoid serious residual noise and speech distortion, we must adjust the Wavelet Coefficient Threshold (WCT). In this Paper. the subband is designed matching with the critical band and WCT is adapted noise masking threshold (NMT) and segmental signal to noise ratio (seg_SNR). Consequently. it has similar Performance with EVRC in PESQ-MOS. But it's better than wavelet packet transform using universal threshold about 0.289 in PESQ-MOS. The important thing is that it's more useful than EVRC in coded speech. In coded speech. PESQ-MOS is higher than EVRC about 0.23.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.6
• /
• pp.402-409
• /
• 2010

In this paper, we propose an efficient integrated suppression algorithm based on combined power of acoustic echo and background noise. The proposed method combines the acoustic echo and noise power by the weighting parameter derived from the decision rule based on the estimated echo to noise power ratio. Therefore, in the proposed approach, the acoustic echo and noise signal are able to be reduced through only one suppression filter based on the estimated combined power. The proposed unified structure improves the problems of the residual echo and noise resulted from the conventional unified structure where the noise suppression (NS) operation is placed after the acoustic echo suppression (AES) algorithm or vice versa. The performance of the proposed algorithm is evaluated by the objective test under various environments and yields better results compared with the conventional scheme.

• Journal of Veterinary Science
• /
• v.25 no.3
• /
• pp.37.1-37.10
• /
• 2024

Importance: The portal vein to aorta (PV/Ao) ratio is used to assess the clinical significance of extrahepatic portosystemic shunt (EHPSS). Previous studies using computed tomography (CT) were conducted in dogs but not in cats. Objective: This study aimed to establish normal reference values for PV indices (PV/Ao ratio and PV diameter) in cats and determine the usefulness of these for predicting symptomatic EHPSS. Methods: This study included 95 dogs and 114 cats that underwent abdominal CT. The canine normal (CN) group included dogs without EHPSS. The cats were classified into feline normal (FN, 88/114), feline asymptomatic (FA, 16/114), and feline symptomatic (FS, 10/114) groups. The PV and Ao diameters were measured in axial cross-sections. Results: The group FN had a higher PV/Ao ratio than the group CN (p < 0.001). Within the feline groups, the PV indices were in the order FN > FA > FS (both p < 0.001). The mean PV diameter and PV/Ao ratio for group FN were 5.23±0.77 mm and 1.46±0.19, respectively. The cutoff values between groups FN and FS were 4.115 mm for PV diameter (sensitivity, 100%; specificity, 97.7%) and 1.170 for PV/Ao ratio (90%, 92.1%). The cutoff values between group FA and FS were 3.835 mm (90%, 93.8%) and 1.010 (70%, 100%), respectively. Conclusions and Relevance: The results demonstrated significant differences in PV indices between dogs and cats. In cats, the PV/Ao ratio demonstrated high diagnostic performance for symptomatic EHPSS. The PV diameter also performed well, in contrast to dogs.

• Computers and Concrete
• /
• v.33 no.2
• /
• pp.175-193
• /
• 2024

Researchers have embarked on an active investigation into the feasibility of adopting alternative materials as a solution to the mounting environmental and economic challenges associated with traditional concrete-based construction materials, such as reinforced concrete. The examination of concrete's mechanical properties using laboratory methods is a complex, time-consuming, and costly endeavor. Consequently, the need for models that can overcome these drawbacks is urgent. Fortunately, the ever-increasing availability of data has paved the way for the utilization of machine learning methods, which can provide powerful, efficient, and cost-effective models. This study aims to explore the potential of twelve machine learning algorithms in predicting the tensile strength of geopolymer concrete (GPC) under various curing conditions. To fulfill this objective, 221 datasets, comprising tensile strength test results of GPC with diverse mix ratios and curing conditions, were employed. Additionally, a number of unseen datasets were used to assess the overall performance of the machine learning models. Through a comprehensive analysis of statistical indices and a comparison of the models' behavior with laboratory tests, it was determined that nearly all the models exhibited satisfactory potential in estimating the tensile strength of GPC. Nevertheless, the artificial neural networks and support vector regression models demonstrated the highest robustness. Both the laboratory tests and machine learning outcomes revealed that GPC composed of 30% fly ash and 70% ground granulated blast slag, mixed with 14 mol of NaOH, and cured in an oven at 300°F for 28 days exhibited superior tensile strength.

• Steel and Composite Structures
• /
• v.51 no.1
• /
• pp.25-41
• /
• 2024

The measurement of pile bearing capacity is crucial for the design of pile foundations, where in-situ tests could be costly and time needed. The primary objective of this research was to investigate the potential use of fuzzy-based techniques to anticipate the maximum weight that concrete driven piles might bear. Despite the existence of several suggested designs, there is a scarcity of specialized studies on the exploration of adaptive neuro-fuzzy inference systems (ANFIS) for the estimation of pile bearing capacity. This paper presents the introduction and validation of a novel technique that integrates the fire hawk optimizer (FHO) and equilibrium optimizer (EO) with the ANFIS, referred to as ANFIS_FHO and ANFIS_EO, respectively. A comprehensive compilation of 472 static load test results for driven piles was located within the database. The recommended framework was built, validated, and tested using the training set (70%), validation set (15%), and testing set (15%) of the dataset, accordingly. Moreover, the sensitivity analysis is performed in order to determine the impact of each input on the output. The results show that ANFIS_FHO and ANFIS_EO both have amazing potential for precisely calculating pile bearing capacity. The R² values obtained for ANFIS_FHO were 0.9817, 0.9753, and 0.9823 for the training, validating, and testing phases. The findings of the examination of uncertainty showed that the ANFIS_FHO system had less uncertainty than the ANFIS_EO model. The research found that the ANFIS_FHO model provides a more satisfactory estimation of the bearing capacity of concrete driven piles when considering various performance evaluations and comparing it with existing literature.