• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.230-238
• /
• 2024

The refractive index is a key material-design parameter, especially for high-refractive-index glasses, which are used for precision optics and devices. Increased demand for high-precision optical lenses produced by the glass-mold-press (GMP) process has spurred extensive studies of proper glass materials. B₂O₃, SiO₂, and multiple heavy-metal oxides such as Ta₂O₅, Nb₂O₅, La₂O₃, and Gd₂O₃ mostly compose the high-refractive-index glasses for GMP. However, due to many oxides including up to 10 components, it is hard to predict the refractivity solely from the composition of the glass. In this study, the refractive index of optical glasses based on the B₂O₃-La₂O₃-Ta₂O₅-SiO₂ system is predicted using machine learning (ML) and compared to experimental data. A dataset comprising up to 271 glasses with 10 components is collected and used for training. Various ML algorithms (linear-regression, Bayesian-ridge-regression, nearest-neighbor, and random-forest models) are employed to train the data. Along with composition, the polarizability and density of the glasses are also considered independent parameters to predict the refractive index. After obtaining the best-fitting model by R² value, the trained model is examined alongside the experimentally obtained refractive indices of B₂O₃-La₂O₃-Ta₂O₅-SiO₂ quaternary glasses.

• Geomechanics and Engineering
• /
• v.37 no.4
• /
• pp.307-321
• /
• 2024

This paper delves into the critical assessment of predicting sidewall displacement in underground caverns through the application of nine distinct machine learning techniques. The accurate prediction of sidewall displacement is essential for ensuring the structural safety and stability of underground caverns, which are prone to various geological challenges. The dataset utilized in this study comprises a total of 310 data points, each containing 13 relevant parameters extracted from 10 underground cavern projects located in Iran and other regions. To facilitate a comprehensive evaluation, the dataset is evenly divided into training and testing subset. The study employs a diverse array of machine learning models, including recurrent neural network, back-propagation neural network, K-nearest neighbors, normalized and ordinary radial basis function, support vector machine, weight estimation, feed-forward stepwise regression, and fuzzy inference system. These models are leveraged to develop predictive models that can accurately forecast sidewall displacement in underground caverns. The training phase involves utilizing 80% of the dataset (248 data points) to train the models, while the remaining 20% (62 data points) are used for testing and validation purposes. The findings of the study highlight the back-propagation neural network (BPNN) model as the most effective in providing accurate predictions. The BPNN model demonstrates a remarkably high correlation coefficient (R2 = 0.99) and a low error rate (RMSE = 4.27E-05), indicating its superior performance in predicting sidewall displacement in underground caverns. This research contributes valuable insights into the application of machine learning techniques for enhancing the safety and stability of underground structures.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.111-118
• /
• 2024

In general network-based intrusion detection system is designed to detect malicious behavior directed at a network or its resources. The key goal of this paper is to look at network data and identify whether it is normal traffic data or anomaly traffic data specifically for accounting information systems. In today's world, there are a variety of principles for detecting various forms of network-based intrusion. In this paper, we are using supervised machine learning techniques. Classification models are used to train and validate data. Using these algorithms we are training the system using a training dataset then we use this trained system to detect intrusion from the testing dataset. In our proposed method, we will detect whether the network data is normal or an anomaly. Using this method we can avoid unauthorized activity on the network and systems under that network. The Decision Tree and K-Nearest Neighbor are applied to the proposed model to classify abnormal to normal behaviors of network traffic data. In addition to that, Logistic Regression Classifier and Support Vector Classification algorithms are used in our model to support proposed concepts. Furthermore, a feature selection method is used to collect valuable information from the dataset to enhance the efficiency of the proposed approach. Random Forest machine learning algorithm is used, which assists the system to identify crucial aspects and focus on them rather than all the features them. The experimental findings revealed that the suggested method for network intrusion detection has a neglected false alarm rate, with the accuracy of the result expected to be between 95% and 100%. As a result of the high precision rate, this concept can be used to detect network data intrusion and prevent vulnerabilities on the network.

• Journal of Aerospace System Engineering
• /
• v.18 no.5
• /
• pp.73-80
• /
• 2024

A deep neural network (DNN) was employed to predict the spring-back of a CFRP composite spar induced by the curing process. A total of 816 spring-back data points, derived from varying stacking angles, layer counts, and flange radii, were generated through finite element method (FEM)-based curing analysis to train the DNN model. The trained model demonstrated an R-squared value of 0.99 and a mean squared error of 0.00093, indicating excellent performance. For untrained flange radii, the spring-back predicted by the DNN exhibited a mean relative error of 2.18% when compared to FEM results. Additionally, while FEM analysis required approximately 20 minutes, the DNN-based prediction required only about 14 milliseconds. These results highlight the potential of using DNNs for the rapid prediction of process-induced deformation in CFRP composites.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.999-1004
• /
• 2005

An algorithm for a hybrid controller consists of a sliding mode control part and a fuzzy logic part which ar purposely for nonlinear systems. The sliding mode part of the solution is based on "eigenvalue/vector"-type controller is used as the backstepping approach for tracking errors. The fuzzy logic part is a Mamdani fuzzy model. This is designed by applying sliding mode control (SMC) method to the dynamic model. The main objective is to keep the update dynamics in a stable region by used SMC. After that the plant behavior is presented to train procedure of adaptive neuro-fuzzy inference systems (ANFIS). ANFIS architecture is determined and the relevant formulation for the approach is given. Using the error (e) and rate of error (de), occur due to the difference between the desired output value (yd) and the actual output value (y) of the system. A dynamic adaptation law is proposed and proved the particularly chosen form of the adaptation strategy. Subsequently VSC creates a sliding mode in the plant behavior while the parameters of the controller are also in a sliding mode (stable trainer). This study considers the ANFIS structure with first order Sugeno model containing nine rules. Bell shaped membership functions with product inference rule are used at the fuzzification level. Finally the Mamdani fuzzy logic which is depends on adaptive neuro-fuzzy inference systems structure designed. At the transferable stage from ANFIS to Mamdani fuzzy model is adjusted for the membership function of the input value (e, de) and the actual output value (y) of the system could be changed to trapezoidal and triangular functions through tuning the parameters of the membership functions and rules base. These help adjust the contributions of both fuzzy control and variable structure control to the entire control value. The application example, control of a mass-damper system is considered. The simulation has been done using MATLAB. Three cases of the controller will be considered: for backstepping sliding-mode controller, for hybrid controller, and for adaptive backstepping sliding-mode controller. A numerical example is simulated to verify the performances of the proposed control strategy, and the simulation results show that the controller designed is more effective than the adaptive backstepping sliding mode controller.

• Journal of the Korean Society for Railway
• /
• v.18 no.3
• /
• pp.175-185
• /
• 2015

Generally, in the train area, switch tracks have required high reliability because this system is directly associated with derailment. Especially, switch tracks of Maglev vehicles must be moved in terms of the whole geometric characteristics, in which the bogies are encased in the switch track. For this reason, switch track was constructed with steel lighter than concrete girders. But, the steel switch track was weak because of structural vibration as well as structural deformation. Therefore, it is important to predict the levitation stability when a vehicle passes over flexible switch track. The aims of this paper are to develop a coupled dynamic model to describe the relationship between a Maglev vehicle and switch track and to predict the levitation stability. In order to develop the coupled dynamic model, a three dimensional vehicle model was developed based on multibody dynamics; a switch model was made using the modal superposition method. And, the developed model was verified using comparison measured data.

• Journal of the Korea Society for Simulation
• /
• v.30 no.3
• /
• pp.1-9
• /
• 2021

Commander and staffs on the battlefield are aware of the situation and, based on the results, they perform military activities through their military decisions. Recently, with the development of information technology, the demand for artificial intelligence to support military decisions has increased. It is essential to identify, collect, and pre-process the data set for reinforcement learning to utilize artificial intelligence. However, data on enemies lacking in terms of accuracy, timeliness, and abundance is not suitable for use as AI learning data, so a training model is needed to collect AI learning data. In this paper, a methodology for learning artificial intelligence was presented using the constructive wargame model exercise data. First, the role and scope of artificial intelligence to support the commander and staff in the military decision-making process were specified, and to train artificial intelligence according to the role, learning data was identified in the Chang-Jo 21 model exercise data and the learning results were simulated. The simulation data set was created as imaginary sample data, and the doctrine of ROK Army, which is restricted to disclosure, was utilized with US Army's doctrine that can be collected on the Internet.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.121-132
• /
• 2018

Weather is an important factor affecting roadway transportation in many aspects such as traffic flow, driver 's driving patterns, and crashes. This study focuses on the relationship between weather and road surface condition and develops a model to estimate the road surface condition using machine learning. A road surface sensor was attached to the probe vehicle to collect road surface condition classified into three categories as 'dry', 'moist' and 'wet'. Road geometry information (curvature, gradient), traffic information (link speed), weather information (rainfall, humidity, temperature, wind speed) are utilized as variables to estimate the road surface condition. A variety of machine learning algorithms examined for predicting the road surface condition, and a two - stage classification model based on 'Random forest' which has the highest accuracy was constructed. 14 days of data were used to train the model and 2 days of data were used to test the accuracy of the model. As a result, a road surface state prediction model with 81.74% accuracy was constructed. The result of this study shows the possibility of estimating the road surface condition using the existing weather and traffic information without installing new equipment or sensors.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.