• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.66.2-66.2
• /
• 2020

We propose a deep learning analysis technique with a convolutional neural network (CNN) to predict the evolutionary track of the Epoch of Reionization (EoR) from the 21-cm differential brightness temperature tomography images. We use 21cmFAST, a fast semi-numerical cosmological 21-cm signal simulator, to produce mock 21-cm maps between z = 6 ~ 13. We then apply two observational effects, such as instrumental noise and limit of (spatial and depth) resolution somewhat suitable for realistic choices of the Square Kilometre Array (SKA), into the 21-cm maps. We design our deep learning model with CNN to predict the sliced-averaged neutral hydrogen fraction from the given 21-cm map. The estimated neutral fraction from our CNN model has great agreement with the true value even after coarsely smoothing with broad beam size and frequency bandwidth and heavily covered by noise with narrow beam size and frequency bandwidth. Our results show that the deep learning analyzing method has the potential to reconstruct the EoR history efficiently from the 21-cm tomography surveys in future.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.10
• /
• pp.884-892
• /
• 2014

In this paper, a meta model using neural network substituting for the simulator aerodynamic database is proposed to improve simulation fidelity near the critical flight area and real-time performance. It is shown that the accuracy of the meta model is relatively higher than the existing table lookup methods for arbitrary nonlinear database and the calculation speed is also improved for a specific F-16 maneuver simulation. The increase in the number of hidden nodes in the meta model for better accuracy of database representations causes a delay in function generation due to increased time required for computing exponential functions. In order to make up this drawback, we additionally study the fast exponential function method.

• Science of Emotion and Sensibility
• /
• v.5 no.2
• /
• pp.29-34
• /
• 2002

Our previous studies investigated that narrow field of view (FOV : 50˚) and slow navigation speed decreased the frequency of occurrence and severity of cybersickness during immersion in the virtual reality (VR). It would cause a significant reduction of cybersickness if it were provided cybersickness alleviating virtual environment (CAVE) using biofeedback method whenever subject underwent physiological agitation. For verifying the hypothesis, we constructed a real-time cybersickness detection and feedback system with artificial neural network whose inputs are electrophysiological parameters of blood pulse volume, skin conductance, eye blink, skin temperature, heart period, and EEG. The system temporary provided narrow FOV and decreased speed of navigation as feedback outputs whenever physiological measures signal the occurrence of cybersickness. We examined the frequency and severity of cybersickness from simulator sickness questionnaires and self-report in 36 subjects. All subjects experienced VR two times in CAVE and non-CAVE condition at one-month intervals. The frequency and severity of cybersickness were significantly reduced in CAVE than non-CAVE condition. Virtual environment of narrow FOV and slow navigation provided by electrophysiological features based artificial neural network caused a significant reduction of cybersickness symptoms. These results showed that efficiency of a cybersickness detection system we developed was relatively high and subjects expressed more comfortable in the virtual navigation environment.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.162-177
• /
• 2020

The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1255-1262
• /
• 2012

Look into the nuclear power plant of Wolsong currently, it is controlled in order to required operating pressure with PI controller. PI controller has a simple structure and satisfy design requirements to gain setting. However, It is difficult to control without changing the gain from produce changes in parameters such as loss of the valves and the pipes. To solve these problems, the dynamic change of the PI controller gain, or to compensate for the PI controller output is desirable to configure the controller. The aim of this research and development in the parameter variations can be controlled to a stable controller design which is reduced an error and a vibration. Proposed PI/NN control techniques is the PI controller and the neural network controller that combines a parallel and the neural network controller part is compensated output of the controller for changes in the parameters were designed to be robust. To directly evaluate the controller performance can be difficult to test in real processes to reflect the characteristics of the process. Therefore, we develope the simulator model using the real process data and simulation results when compared with the simulated process characteristics that showed changes in the parameters. As a result the PI/NN controller error and was confirmed to reduce vibrations.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.9-26
• /
• 2005

In the pursuit of ever higher levels of performance, recent computer systems have made use of deep pipeline, dynamic scheduling and multi-issue superscalar processor technologies. In this situations, branch prediction schemes are an essential part of modem microarchitectures because the penalty for a branch misprediction increases as pipelines deepen and the number of instructions issued per cycle increases. In this paper, we propose a novel branch prediction scheme, direction-gshare(d-gshare), to improve the prediction accuracy. At first, we model a neural network with the components that possibly affect the branch prediction accuracy, and analyze the variation of their weights based on the neural network information. Then, we newly add the component that has a high weight value to an original gshare scheme. We simulate our branch prediction scheme using Simple Scalar, a powerful event-driven simulator, and analyze the simulation results. Our results show that, compared to bimodal, two-level adaptive and gshare predictor, direction-gshare predictor(d-gshare. 3) outperforms, without additional hardware costs, by up to 4.1% and 1.5% in average for the default mont of embedded direction, and 11.8% in maximum and 3.7% in average for the optimal one.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1951-1975
• /
• 2023

Recent advances in Cognitive Radio Networks (CRN) have elevated them to the status of a critical instrument for overcoming spectrum limits and achieving severe future wireless communication requirements. Collaborative spectrum sensing is presented for efficient channel selection because spectrum sensing is an essential part of CRNs. This study presents an innovative cooperative spectrum sensing (CSS) model that is built on the Firefly Algorithm (FA), as well as machine learning artificial neural networks (ANN). This system makes use of user grouping strategies to improve detection performance dramatically while lowering collaboration costs. Cooperative sensing wasn't used until after cognitive radio users had been correctly identified using energy data samples and an ANN model. Cooperative sensing strategies produce a user base that is either secure, requires less effort, or is faultless. The suggested method's purpose is to choose the best transmission channel. Clustering is utilized by the suggested ANN-FA model to reduce spectrum sensing inaccuracy. The transmission channel that has the highest weight is chosen by employing the method that has been provided for computing channel weight. The proposed ANN-FA model computes channel weight based on three sets of input parameters: PU utilization, CR count, and channel capacity. Using an improved evolutionary algorithm, the key principles of the ANN-FA scheme are optimized to boost the overall efficiency of the CRN channel selection technique. This study proposes the Artificial Neural Network with Firefly Algorithm (ANN-FA) for cognitive radio networks to overcome the obstacles. This proposed work focuses primarily on sensing the optimal secondary user channel and reducing the spectrum handoff delay in wireless networks. Several benchmark functions are utilized We analyze the efficacy of this innovative strategy by evaluating its performance. The performance of ANN-FA is 22.72 percent more robust and effective than that of the other metaheuristic algorithm, according to experimental findings. The proposed ANN-FA model is simulated using the NS2 simulator, The results are evaluated in terms of average interference ratio, spectrum opportunity utilization, three metrics are measured: packet delivery ratio (PDR), end-to-end delay, and end-to-average throughput for a variety of different CRs found in the network.

• Journal of Korean Society of Water and Wastewater
• /
• v.25 no.4
• /
• pp.581-589
• /
• 2011

Generally, treated water or raw water is transported into storage reservoirs which are receiving facilities of local governments from multi-regional water supply systems. A water supply control and operation center is operated not only to manage the water facilities more economically and efficiently but also to mitigate the shortage of water resources due to the increase in water consumption. To achieve the goal, important information such as the flow-rate in the systems, water levels of storage reservoirs or tanks, and pump-operation schedule should be considered based on the resonable water demand forecasting. However, it is difficult to acquire the pattern of water demand used in local government, since the operating information is not shared between multi-regional and local water systems. The pattern of water demand is irregular and unpredictable. Also, additional changes such as an abrupt accident and frequent changes of electric power rates could occur. Consequently, it is not easy to forecast accurate water demands. Therefore, it is necessary to introduce a short-term water demands forecasting and to develop an application of the forecasting models. In this study, the forecasting simulator for water demand is developed based on mathematical and neural network methods as linear and non-linear models to implement the optimal water demands forecasting. It is shown that MLP(Multi-Layered Perceptron) and ANFIS(Adaptive Neuro-Fuzzy Inference System) can be applied to obtain better forecasting results in multi-regional water supply systems with a large scale and local water supply systems with small or medium scale than conventional methods, respectively.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.111-116
• /
• 2022

In this study, the applicability of machine learning for the development of a simulator for general X-ray examination education is evaluated. To this end, k-nearest neighbor(kNN), support vector machine(SVM) and neural network(NN) classification models are analyzed to present the most suitable model by analyzing the results. Image data was obtained by taking 100 photos each corresponding to Posterior anterior(PA), Posterior anterior oblique(Obl), Lateral(Lat), Fan lateral(Fan lat). 70% of the acquired 400 image data were used as training sets for learning machine learning models and 30% were used as test sets for evaluation. and prediction model was constructed for right-handed PA, Obl, Lat, Fan lat image classification. Based on the data set, after constructing the classification model using the kNN, SVM, and NN models, each model was compared through an error matrix. As a result of the evaluation, the accuracy of kNN was 0.967 area under curve(AUC) was 0.993, and the accuracy of SVM was 0.992 AUC was 1.000. The accuracy of NN was 0.992 and AUC was 0.999, which was slightly lower in kNN, but all three models recorded high accuracy and AUC. In this study, right-handed PA, Obl, Lat, Fan lat images were classified and predicted using the machine learning classification models, kNN, SVM, and NN models. The prediction showed that SVM and NN were the same at 0.992, and AUC was similar at 1.000 and 0.999, indicating that both models showed high predictive power and were applicable to educational simulators.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.124-129
• /
• 1992

The goal of the proposed Intelligent Assisting System - IAS is to assist human operators in an intelligent way, while leaving decision and goal planning instances for the human. To realize the IAS the very important issue of manipulation skill identification and analysis has to be solved, which then is stored in a Skill Data Base. Using this data base the IAS is able to perform complex manipulations on the motion control level and to assist the human operator flexibly. We propose a model for manipulation skill based on the dynamics of the grip transformation matrix, which describes the dynamic transformation between object space and finger joint space. Interaction with a virtual world simulator allows the calculation and feedback of appropriate forces through controlled actuators of the sensor glove with 10 degrees-of-freedom. To solve the sensor glove calibration problem, we learn the nonlinear calibration mapping by an artificial neural network(ANN). In this paper we also describe the experimental system setup of the skill acquisition and transfer system as a first approach to the IAS. Some simple manipulation examples and simulation results show the feasibility of the proposed manipulation skill model.