• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.6
• /
• pp.1-11
• /
• 2021

To develop an efficient procedure related to the flamelet library, the machine learning process based on artificial neural network(ANN) is applied for the gaseous hydrogen/liquid oxygen combustor under a supercritical pressure condition. For hidden layers, 25 combinations based on Rectified Linear Unit(ReLU) and hyperbolic tangent are adopted to find an optimum architecture in terms of the computational efficiency and the training performance. For activation functions, the hyperbolic tangent is proper to get the high learning performance for accurate properties. A transformation learning data is proposed to improve the training performance. When the optimal node is arranged for the 4 hidden layers, it is found to be the most efficient in terms of training performance and computational cost. Compared to the interpolation procedure, the ANN procedure reduces computational time and system memory by 37% and 99.98%, respectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.6
• /
• pp.1045-1057
• /
• 2022

Recently, the National Institute of Standards and Technology (NIST) announced four cryptographic algorithms as a standard candidates of Post-Quantum Cryptography (PQC). In this paper, we show that private key can be exposed by a non-profiling-based power analysis attack such as Correlation Power Analysis (CPA) and Differential Deep Learning Analysis (DDLA) on CRYSTALS-KYBER algorithm, which is decided as a standard in the PKE/KEM field. As a result of experiments, it was successful in recovering the linear polynomial coefficient of the private key. Furthermore, the private key can be sufficiently recovered with a 13.0 Normalized Maximum Margin (NMM) value when Hamming Weight of intermediate values is used as a label in DDLA. In addition, these non-profiling attacks can be prevented by applying countermeasures that randomly divides the ciphertext during the decryption process and randomizes the starting point of the coefficient-wise multiplication operation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1853-1858
• /
• 2021

O-rings fill the gaps between mechanical parts. Until now, the sorting of defective products has been performed visually and manually, so classification errors often occur. Therefore, a camera-based defect classification system without human intervention is required. However, a binarization process is required to separate the required region from the background in the camera input image. In this paper, an adaptive binarization technique that considers the surrounding pixel values is applied to solve the problem that single-threshold binarization is difficult to apply due to factors such as changes in ambient lighting or reflections. In addition, the convex hull technique is also applied to compensate for the missing pixel part. And the learning model to be applied to the separated region applies the residual error-based deep learning neural network model, which is advantageous when the defective characteristic is non-linear. It is suggested that the proposed system through experiments can be applied to the automation of O-ring defect detection.

• The Korean Journal of Pain
• /
• v.35 no.3
• /
• pp.345-352
• /
• 2022

Background: Optimal needle depth in transforaminal epidural injection (TFEI) is determined by body measurements and is influenced by the needle entry angle. Physician can choose the appropriate needle length and perform the procedure more effectively if depth is predicted in advance. Methods: This retrospective study included patients with lumbosacral pain from a single university hospital. The skin depth from the target point was measured using magnetic resonance imaging transverse images. The depth was measured bilaterally for L4 and L5 TFEIs at 15°, 20°, and 25° oblique angles from the spinous process. Results: A total of 4,632 measurements of 386 patients were included. The lengths of the left and right TFEI at the same level and oblique angle were assessed, and no statistical differences were identified. Therefore, linear regression analysis was performed for bilateral L4 and L5 TFEIs. The R-squared values of height and weight combined were higher than the height, weight, and body mass index (BMI). The following equation was established: Depth (mm) = a - b (height, cm) + c (weight, kg). Based on the equation, maximal BMI capable with a 23G, 3.5-inch, Quincke-type point spinal needle was presented for three different angles (15°, 20°, and 25°) at lumbar levels L4 and L5. Conclusions: The maximal BMI that derived from the formulated equation is listed on the table, which can help in preparations for morbid obesity. If a patient has bigger BMI than the one in the table, the clinician should prepare longer needle than the usual spinal needle.

• Journal of the Korea Society for Simulation
• /
• v.19 no.3
• /
• pp.109-117
• /
• 2010

In this study, we consider stationary waiting times in a simple fork-and-join type queue which consists of three single-server machines, Machine 1, Machine 2, and Assembly Machine. We assume that the queue has a renewal arrival process and that independent service times at each node are either deterministic or non-overlapping. We also assume that the Machines 1 and 2 have an infinite buffer capacity whereas the Assembly Machine has two finite buffers, one for each machine. Services at each machine are given by FIFO service discipline and a communication blocking policy. We derive the explicit expressions for stationary waiting times at all nodes as a function of finite buffer capacities by using (max,+)-algebra. Various characteristics of stationary waiting times such as mean, higher moments, and tail probability can be computed from these expressions.

• Clinics in Shoulder and Elbow
• /
• v.26 no.2
• /
• pp.162-168
• /
• 2023

Background: Reverse shoulder arthroplasty (RSA) has evolved continuously over recent years, with expanded indications and better outcomes. YouTube is one of the most popular sources globally for health-related information available to patients. Evaluating the reliability of YouTube videos concerning RSA is important to ensure proper patient education. Methods: YouTube was queried for the term "reverse shoulder replacement." The first 50 videos were evaluated using three different scores: Journal of the American Medical Association (JAMA) benchmark criteria, the global quality score (GQS), and the reverse shoulder arthroplasty-specific score (RSAS). Multivariate linear regression analyses were conducted to determine the presence of a relationship between video characteristics and quality scores. Results: The average number of views was 64,645.78±264,160.9 per video, and the average number of likes was 414 per video. Mean JAMA, GQS, and RSAS scores were 2.32±0.64, 2.31±0.82, and 5.53±2.43, respectively. Academic centers uploaded the highest number of videos, and surgical techniques/approach videos was the most common video content. Videos with lecture content predicted higher JAMA scores whereas videos uploaded by industry predicted lower RSAS scores. Conclusions: Despite its massive popularity, YouTube videos provide a low quality of information on RSA. Introducing a new editorial review process or developing a new platform for patients' medical education may be necessary. Level of evidence: Not applicable.

• Geomechanics and Engineering
• /
• v.34 no.6
• /
• pp.697-726
• /
• 2023

Brittleness as an important property of rock plays a crucial role both in the failure process of intact rock and rock mass response to excavation in engineering geological and geotechnical projects. Generally, rock brittleness indices are calculated from the mechanical properties of rocks such as uniaxial compressive strength, tensile strength and modulus of elasticity. These properties are generally determined from complicated, expensive and time-consuming tests in laboratory. For this reason, in the present research, an attempt has been made to predict the rock brittleness indices from simple, inexpensive, and quick laboratory test results namely dry unit weight, porosity, slake-durability index, P-wave velocity, Schmidt rebound hardness, and point load strength index using multiple linear regression, exponential regression, support vector machine (SVM) with various kernels, generating fuzzy inference system, and regression tree ensemble (RTE) with boosting framework. So, this could be considered as an innovation for the present research. For this purpose, the number of 39 rock samples including five igneous, twenty-six sedimentary, and eight metamorphic were collected from different regions of Iran. Mineralogical, physical and mechanical properties as well as five well known rock brittleness indices (i.e., B₁, B₂, B₃, B₄, and B₅) were measured for the selected rock samples before application of the above-mentioned machine learning techniques. The performance of the developed models was evaluated based on several statistical metrics such as mean square error, relative absolute error, root relative absolute error, determination coefficients, variance account for, mean absolute percentage error and standard deviation of the error. The comparison of the obtained results revealed that among the studied methods, SVM is the most suitable one for predicting B₁, B₂ and B₅, while RTE predicts B₃ and B₄ better than other methods.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.110-117
• /
• 2023

Reconstructing underwater geometry in real time with forward-looking sonar is critical for applications such as localization, mapping, and path planning. Geometrical data must be repeatedly calculated and overwritten in real time because the reliability of the acoustic data is affected by various factors. Moreover, scattering of signal data during the coordinate conversion process may lead to geometrical errors, which lowers the accuracy of the information obtained by the sensor system. In this study, we propose a three-step data processing method with low computational cost for real-time operation. First, the number of data points to be interpolated is determined with respect to the distance between each point and the size of the data grid in a Cartesian coordinate system. Then, the data are processed with a nonlinear interpolation so that they exhibit linear properties in the coordinate system. Finally, the data are transformed based on variations in the position and orientation of the sonar over time. The results of an evaluation of our proposed approach in a simulation show that the nonlinear interpolation operation constructed a continuous underwater geometry dataset with low geometrical error.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.2
• /
• pp.91-100
• /
• 2023

The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.187-192
• /
• 2022

Even the announcing date for the staring date of "With Corona" has been decided, still many people have not completed vaccination, the most important condition for starting the With Corona, because of concerns for its side effects. In addition, although the economy may can be recovered by the With Corona, but the number of infected people may can be surged. In this paper, in order to awaken the people for the awareness of Corona 19 in advance of the With Corona, the Corona 19 is predicted through a non-linear probability process. Here, among the deep learning RNN, BI-LSTM, which is a bidirectional LSTM, and GRU, gates decreased than LSTM have been used. And this has been compared and analyzed through train set, test set, loss function, residual analysis, normal distribution, and autocorrelation, and compared and predicted for which has a better performance.