• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.2
• /
• pp.85-96
• /
• 2021

Irrigation return flow is defined as the excess of irrigation water that is not evapotranspirated by direct surface drainage, and which returns to an aquifer. It is important to quantitatively estimate the irrigation return flow of the water cycle in an agricultural watershed. However, the previous studies on irrigation return flow rates are limitations in quantifying the return flow rate by region. Therefore, simulating irrigation return flow by accounting for various water loss rates derived from agricultural practices is necessary while the hydrologic and hydraulic modeling of cultivated canal-irrigated watersheds. In this study, the irrigation return flow rate of agricultural water, especially for the entire agricultural watershed, was estimated using the SWMM (Storm Water Management Model) module from 2010 to 2019 for the Madun reservoir located in Anseong, Gyeonggi-do. The results of SWMM simulation and water balance analysis estimated irrigation return flow rate. The estimated average annual irrigation return flow ratio during the period from 2010 to 2019 was approximately 55.3% of the annual irrigation amounts of which 35.9% was rapid return flow and 19.4% was delayed return flow. Based on these results, the hydrologic and hydraulic modeling approach can provide a valuable approach for estimating the irrigation return flow under different hydrological and water management conditions.

• Geomechanics and Engineering
• /
• v.31 no.6
• /
• pp.545-556
• /
• 2022

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R²) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

• International Journal of Computer Science & Network Security
• /
• v.23 no.6
• /
• pp.27-34
• /
• 2023

This paper proposed an Inter-Carrier-Interference (ICI) Canceling Orthogonal Frequency Division Multiplexing (OFDM) receiver for 5G mobile system to support 500 km/h linear motor high speed terrestrial transportation service. A receiver in such high-speed train sees the transmission channel which is composed of multiple Doppler-shifted propagation paths. Then, a loss of sub-carrier orthogonality due to Doppler-spread channels causes ICI. The ICI Canceler is realized by the following three steps. First, using the Demodulation Reference Symbol (DMRS) pilot signals, it analyzes three parameters such as attenuation, relative delay, and Doppler-shift of each multi-path component. Secondly, based on the sets of three parameters, Channel Transfer Function (CTF) of sender sub-carrier number 𝒏 to receiver sub-carrier number 𝒍 is generated. In case of 𝒏≠𝒍, the CTF corresponds to ICI factor. Thirdly, since ICI factor is obtained, by applying ICI reverse operation by Multi-Tap Equalizer, ICI canceling can be realized. ICI canceling performance has been simulated assuming severe channel condition such as 500 km/h, 2 path reverse Doppler Shift for QPSK, 16QAM, 64QAM and 256QAM modulations. In particular, for modulation schemes below 16QAM, we confirmed that the difference between BER in a 2 path reverse Doppler shift environment and stationary environment at a moving speed of 500 km/h was very small when the number of taps in the multi-tap equalizer was set to 31 taps or more. We also confirmed that the BER performance in high-speed mobile communications for multi-level modulation schemes above 64QAM is dramatically improved by the use of a multi-tap equalizer.

• Applied Microscopy
• /
• v.36 no.2
• /
• pp.83-91
• /
• 2006

The number and structure of synapses are dynamically changed in response to diverse physiological and pathological conditions. Since strength of synaptic transmission is closely related to the synaptic density on a neuron, both synaptogenesis and synapse loss may play important roles in controlling neuronal activity. Thus it is essential to estimate the number of synapses using an accurate quantitative method for better understanding of the numerical alteration of synapses under terrain experimental conditions. We applied physical disector principle to estimating the number of synapses per neuron in the dentate gyrus of adult mice. First, we measured the numerical density of granule cells using the physical disector principle. Second, the density of medial perforant path to granule cell synapses was estimated using the bidirectional physical disector. Then, the volume ratio of molecular layer to granule cell layer was measured. With these numerial values, we successfully calculated the number of synapses per neuron. Individual granule cells have approximately 6500 synapses in the dentate gyrus of adult mice $(6,545{\pm}330)$, which are comparable to those of other researchers. Our results showed that the estimation of synapse numbers per neuron using the physical disector principle would provide accurate and precise information on the numerical alteration of synapses in diverse physiological and pathological conditions. Following analyses of synapse numbers using this method will contribute to the better understanding of structural synaptic plasticity in a variety of experimental animal models.

• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.3
• /
• pp.320-328
• /
• 2016

Among biogenic volatile organic compounds (BVOCs) in the natural ecosystem, monoterpenes, along with isoprene, play important roles in atmospheric chemistry and make significant impacts on air pollution and climate change, especially due to their contribution to secondary organic aerosol production and photochemical ozone formation. It is essential to measure monoterpene concentrations accurately for understanding their oxidation processes, emission processes and estimation, and interactions between biosphere and atmosphere. Thus, traceable calibration standards are crucial for the accurate measurement of monoterpenes at ambient levels. However, there are limited information about developing calibrations standards for monoterpenes in pressured cylinders. This study describes about developing primary standard gas mixtures (PSMs) for monoterpenes at about 2 nmol/mol, near ambient levels. The micro-gravimetric method was applied to prepare monoterpene (${\alpha}$-pinene, 3-carene, R-(+)-limonene, 1,8-cineole) PSMs at $10{\mu}mol/mol$ and then the PSMs were further diluted to 2 nmol/mol level. To select an optimal cylinder for the development of monoterpene PSMs, three different kinds of cylinders were used for the preparation and were evaluated for uncertainty sources including long-term stability. Results showed that aluminum cylinders with a special internal surface treatment (Experis) had little adsorption loss on the cylinder internal surface and good long-term stability compared to two other cylinder types with no treatment and a special treatment (Aculife). Results from uncertainty estimation suggested that monoterpene PSMs can be prepared in pressured cylinders with a special treatment (Experis) at 2 nmol/mol level with an uncertainty of less than 4%.

• Investigative Magnetic Resonance Imaging
• /
• v.14 no.1
• /
• pp.56-63
• /
• 2010

Purpose : DIR image is relatively free from susceptibility artifacts therefore, DIR image can make it possible to reliably measure cortical thickness/volume. One drawback of the DIR acquisition is the long scan time to acquire the fully sampled 3D data set. To solve this problem, we applied a parallel imaging method (GRAPPA) and verify the reliability of using the volumetric study. Materials and methods : Six healthy volunteers (3 males and 3 females; age $25.33{\pm}2.25$ years) underwent MRI using the 3D DIR sequence at a 3.0T Siemens Tim Trio MRI scanner. GRAPPA simulation was performed from the fully sampled data set for reduction factor 2. Data reconstruction was performed using MATLAB R2009b. Freesurfer v.4.3.0 was used to evaluate the cortical thickness of the entire brain, and to extract white matter information from the DIR image, Analyze 9.0 was used. The global cortical thickness estimated from the reconstructed image was compared with reference image by using a T-test in SPSS. Results : Although reduced SNR and blurring are observed from the reconstructed image, in terms of segmentation the effect was not so significant. The volumetric result was validated that there were no significant differences in many cortical regions. Conclusion : This study was performed with DIR image for a volumetric MRI study. To solve the long scan time of 3D DIR imaging, we applied GRAPPA algorithm. According to the results, fast imaging can be done with reduction factor 2 with little loss of image quality at 3.0T.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.31-42
• /
• 2021

We propose a deep learning-based method that can estimate an appropriate lighting of both indoor and outdoor images. The method consists of two networks: Crop-to-PanoLDR network and LDR-to-HDR network. The Crop-to-PanoLDR network predicts a low dynamic range (LDR) environment map from a single partially observed normal field of view image, and the LDR-to-HDR network transforms the predicted LDR image into a high dynamic range (HDR) environment map which includes the high intensity light information. The HDR environment map generated through this process is applied when rendering virtual objects in the given image. The direction of the estimated light along with ambient light illuminating the virtual object is examined to verify the effectiveness of the proposed method. For this, the results from our method are compared with those from the methods that consider either indoor images or outdoor images only. In addition, the effect of the loss function, which plays the role of classifying images into indoor or outdoor was tested and verified. Finally, a user test was conducted to compare the quality of the environment map created in this study with those created by existing research.

• The KIPS Transactions:PartC
• /
• v.17C no.6
• /
• pp.471-484
• /
• 2010

In the wireless communication systems, the power consumption of a mobile device is very important issue due to its battery limitations. Hence most of the standards for wireless networks including a mobile WiMAX system are supporting their own power saving mode in way that a mobile device is able to reduce its energy usage while in the mode. However, those standards just define the arrangement of special time intervals, called a paging listening interval, during which the device needs to receive the paging-related control messages, and they do not specify how to effectively reduce the power in many different network environments. This means the amount of power spent by the device is very dependent on the implementations of individual device-vendors, and undesirable paging loss may happen according to the channel conditions. To reduce unnecessary power usage and the risk of paging loss, this paper proposes the effective frequency/BS selection algorithm applicable to a mobile device operating in the power saving mode, which serves the device with better BS based on the tracking for channel variation. This algorithm consists of the channel estimation phase during each paging listening interval, the tracking phase for the measured results, the frequency reselection phase based on the tracking activity, and the preferred BS reselection phase. Thus the proposed method can improve the paging performance while the device is moving in the network. Also the simulation result shows that the presented scheme is superior to other candidates in energy efficiency due to the channel-adaptive frequency/BS selection.

• Journal of Korea Water Resources Association
• /
• v.41 no.2
• /
• pp.149-162
• /
• 2008

The Soil and Water Assessment Tool (SWAT) developed by the USDA-Agricultural Research Service for the prediction of land management impact on water, sediment, and agricultural chemical yields in a large-scale basin was applied to Daecheong Reservoir basin to estimate the amount of soil losses from different land uses. The research outcomes provide important indications for reservoir managers and policy makers to search alternative watershed management practices for the mitigation of reservoir turbidity flow problems. After calibrations of key model parameters, SWAT showed fairly good performance by adequately simulating observed annual runoff components and replicating the monthly flow regimes in the basin. The specific soil losses from agricultural farm field, forest, urban area, and paddy field were 33.1, $2.3{\sim}5.4$ depending on the tree types, 1.0, and 0.1 tons/ha/yr, respectively in 2004. It was noticed that about 55.3% of the total annual soil loss is caused by agricultural activities although agricultural land occupies only 10% in the basin. Although the soil erosion assessment approach adopted in this study has some extent of uncertainties due to the lack of detailed information on crop types and management activities, the results at least imply that soil erosion control practices for the vulnerable agricultural farm lands can be one of the most effective alternatives to reduce the impact of turbidity flow in the river basin system.