• Journal of Biomedical Engineering Research
• /
• v.24 no.5
• /
• pp.411-419
• /
• 2003

This paper aims at developing 'gyro-mouse' which provides decent and comfortable human-computer interface that supports the usage of such software as an internet-browser in PC for the people paralyzed in upper limbs. This interface operates on information collected from head movement to get the cursor control. The interface is composed of two modules. One is hardware module in which the head horizontal and vertical angular velocities are detected and transmitted into PC. The other is a PC software that translates the received data into movement and click signals of the mouse. The ANN (artificial neural network) learns the quick nodding pattern of each user as click input so that it can provide user-friendly interface. The performance of the system was evaluated by three indices that are click recognition rate. error in cursor position control. and click rate of the moving target box. The performance result of the gyro-mouse was compared with that of the optical-mouse to assess the efficiency of the gyro-mouse. The average click recognition rate was 93%, average error in cursor position control was 1.4∼5 times of optical mouse. and the click rate with 50 pixels target box was 40%(30 clicks/min) to that of optical mouse. The click rate increased monotonously with the number of trial from 35% to 44%. The suggested system is expected to provide a new possibility to communicate with the society.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.447-454
• /
• 2007

To assess the port development and maritime traffic environment, the future traffic volume has been estimated using the number of inbound and outbound vessel for a specific port. The estimation of future traffic volume should be considered as an important factor to establish the degree of fairway congestion, the determination of fairway width and the operational role. Until now, the number of in and out vessel for the port has been only estimated mainly, but the type and size of inbound and outbound ships are different depending on the port's characteristics. So, it is difficult to estimate the future traffic volume using the change of only one item. This paper calculates the future traffic volume using the marine traffic characteristic factors as the number of coastal ship and ocean-going ship, the size of ship and the change of cargo volume per a ship etc. And it compared with the results of Artificial Neural Network(ANN) for accurate identification of nonlinear system.

• International Journal of Highway Engineering
• /
• v.6 no.4 s.22
• /
• pp.75-89
• /
• 2004

Long term performance of concrete pavement significantly depends on the given construction and environmental condition. It means that random cracks and extreme crack width due to inappropriate quality control at the early age might lead to decreasing the pavement service life. The temperature and moisture during the construction, cement and aggregate types, curing condition are major components to affect the quality of the concrete pavement at the early age. First of all, the high temperature differential, that is made by increasing air temperature and the heat of cement hydration, is known as the major contributor to severe cracks. In this study, tent covering was used for controlling temperature of the concrete slab. The field measurement data indicates that the effect of the tent covering is very significant to decrease possibilities of random crack occurrence and curling stress and enhance the long-term concrete strength. HIPERPAV(High PERformance PAVing software), a program predicting the strength and stress of an earty-age concrete pavement (72 hour after placement), is used for simulating the effects of tent covering. The HIPERPAVE results showed that the section with the tent covering has higher reliability than the section without the tent covering by 22.5%. In details, reliability is increased 72.5% (without the tent covering) to 95% (with the tent covering).

• Korean Journal of Soil Science and Fertilizer
• /
• v.29 no.3
• /
• pp.243-248
• /
• 1996

To find out the oxidation process of potential acid sulfate soil(PASS) along with time. the PASS were treated with lime and ammonia water to adjust soil pH in laboratory column condition. pH range of PASS showed 6.5 to 7.5. however, complete oxidized PASS by $H_2O_2$ showed 2.1 to 2.5. After pilling the PASS under the natural condition. oxidation occured slowly from surface of the pilled soil. The oxidation of PASS proceeded slowly when the soil was in submerged condition. but quickly in dried condition. The content of sulfide-sulfur in PASS sharply decreased after exposing to the air and the decreasing rate was greater in dried than in submerged condition. The content of sulfate-sulfur continuously decreased in submerged condition. but increased in dried condition. Contents of $Fe^{+{+}}$ and $Al^{+{+}}$ in PASS were generally increased with time and the increasing rate was greater in submerged than in dried condition. Liming to PASS was slowly acting to pH change and ammonia water caused fast pH change within a short period of time. The contents of sulfate-sulfur and exchangeable aluminum in drainage water decreased with time and the contents of sulfide-sulfur and ferrous iron were increased.

• Journal of Korea Water Resources Association
• /
• v.53 no.2
• /
• pp.97-105
• /
• 2020

Recently, Artificial Neural Network receives attention as a data prediction method. Among these, a Long Shot-term Memory (LSTM) model specialized for time-series data prediction was utilized as a prediction method of hydrological time series data. In this study, the LSTM model was constructed utilizing deep running open source library TensorFlow which provided by Google, to predict inflows of multipurpose dams. We predicted the inflow of the Yongdam Multipurpose Dam which is located in the upper stream of the Geumgang. The hourly flow data of Yongdam Dam from 2006 to 2018 provided by WAMIS was used as the analysis data. Predictive analysis was performed under various of variable condition in order to compare and analyze the prediction accuracy according to four learning parameters of the LSTM model. Root mean square error (RMSE), Mean absolute error (MAE) and Volume error (VE) were calculated and evaluated its accuracy through comparing the predicted and observed inflows. We found that all the models had lower accuracy at high inflow rate and hourly precipitation data (2006~2018) of Yongdam Dam utilized as additional input variables to solve this problem. When the data of rainfall and inflow were utilized together, it was found that the accuracy of the prediction for the high flow rate is improved.

• Structural Monitoring and Maintenance
• /
• v.2 no.1
• /
• pp.77-93
• /
• 2015

The idea of using measured dynamic characteristics for damage detection is attractive because it allows for a global evaluation of the structural health and condition. However, vibration-based damage detection for complex structures such as long-span cable-supported bridges still remains a challenge. As a suspension or cable-stayed bridge involves in general thousands of structural components, the conventional damage detection methods based on model updating and/or parameter identification might result in ill-conditioning and non-uniqueness in the solution of inverse problems. Alternatively, methods that utilize, to the utmost extent, information from forward problems and avoid direct solution to inverse problems would be more suitable for vibration-based damage detection of long-span cable-supported bridges. The auto-associative neural network (ANN) technique and the probabilistic neural network (PNN) technique, that both eschew inverse problems, have been proposed for identifying and locating damage in suspension and cable-stayed bridges. Without the help of a structural model, ANNs with appropriate configuration can be trained using only the measured modal frequencies from healthy structure under varying environmental conditions, and a new set of modal frequency data acquired from an unknown state of the structure is then fed into the trained ANNs for damage presence identification. With the help of a structural model, PNNs can be configured using the relative changes of modal frequencies before and after damage by assuming damage at different locations, and then the measured modal frequencies from the structure can be presented to locate the damage. However, such formulated ANNs and PNNs may still be incompetent to identify damage occurring at the deck members of a cable-supported bridge because of very low modal sensitivity to the damage. The present study endeavors to enhance the damage identification capability of ANNs and PNNs when being applied for identification of damage incurred at deck members. Effort is first made to construct combined modal parameters which are synthesized from measured modal frequencies and modal shape components to train ANNs for damage alarming. With the purpose of improving identification accuracy, effort is then made to configure PNNs for damage localization by adapting the smoothing parameter in the Bayesian classifier to different values for different pattern classes. The performance of the ANNs with their input being modal frequencies and the combined modal parameters respectively and the PNNs with constant and adaptive smoothing parameters respectively is evaluated through simulation studies of identifying damage inflicted on different deck members of the double-deck suspension Tsing Ma Bridge.

• Journal of Environmental Science International
• /
• v.5 no.6
• /
• pp.813-826
• /
• 1996

The toxic effects of aluminium (Al) on growth, chlorophyll content, $\delta-aminolevulinic$ acid dehydratase (ALAD) activity and anatomy of root and shoot were investigated in 7-day-old azuki bean (Vigna angularis) seedlings. Significant depressions in root elongation was observed in the low concentrations of Al (50, 100 $\muM)$ and increasing Al concentrations caused a sharp decline of root and shoot growth. The degree of inhibition was dependent upon Al supply. Exposure to 50 $\muM$ Al or more inhibited root elongation within 1 day. In the 50 $\muM$ Al treatments, a recovery of root growth was seen after 7 days exposure. In contrast, lateral root initials was little affected by Al exposure. Al toxicity symptoms and growth responses were more well developed in the roots than in the shoots. Analysis of Al localization in root cells by hematoxylin stAlning showed that Al entered root apices and accumulated in the epidermal and cortical cells immeadiately below the epidermis. There was a good positive correlation between the level of chlorophyll and ALAD activity. Increasing Al concentrations caused a decrease in total chlorophyll contents, accompanied by proportional changes in ALAD activity, suggesting a cootr-dinated reduction of a photosynthetic machinery. Al exerted specific influence on the morphology of root ann shoot. At higher concentrations of Al the roots induced drastic anatomical changes. The epidermal cells were disorganized or destructed while the cortical cells exhibited distortion of cell shape and/or disintegration. The diameter of root and transectional area of cortical cells decreased considerably with Al treatment. In the shoot Al also enhanced reduction of diameter of shoot and cell size. Gross anatomy of leaves treated with Al did not differ significantly from the controls, except for fewer and smaller chloroplast. Our results indicate that toxic effect of Al appear to be manifested primarily in roots and secondarily on shoots, and changes in root morphology are related to changes in the root growth patterns. Results are further discussed in re181ion to the findings in other plant species, and it is concluded that Al causes morphological, structural and, presumably, functional damage to the roots of the species investigated.

• Journal of Environmental Science International
• /
• v.25 no.11
• /
• pp.1575-1582
• /
• 2016

In this study, to provide basic information for design of a large-scale recycling system for fishery by-products, the food nutrient components, fertilizer components, and microbial composition of fertilizers and feed which were made of fishery by-products were analyzed before and after fermentation. The results of the analysis of the edible portion of fishery by-products indicated that calories per 100 g of crustaceans were the highest followed by those of fish and brown algae in order of precedence with values as follows; Korean Krill 94 Kcal, Portunus trituberculatus 65 Kcal, Lophiomus setigerus 58 Kcal, and Undaria pinnatifida 16 Kcal. As for changes in amino acids per 100 g of fishery by-products between before and after fermentation, calories per 100 g of P. trituberculatus decreased by 74.7% from 15.7 g to 4.0 g, that of L. setigerus decreased by 61.1% from 11.9 g to 4.6 g, that of Korean Krill decreased by 53.5% from 11.6 g to 5.4 g, and that of U. pinnatifida decreased by 49.4% from 1.7 g to 0.9 g. Among amino acids, those contained in fishery by-product fertilizers (liquid fertilizer) in large amounts were shown to be Glutaminic acid, Aspartic acid, Glycine, Lysin, and Leucine. The lipid content of Korean Krill decreased by 11.9% from 3.2 g to 2.8 g, that of L. setigerus increased by 2.0 times from 1.1 g to 2.2 g, that of P. trituberculatus increased by 4.5 times from 0.4 g to 1.7 g, and that of U. pinnatifida increased by 9.4 times from 0.2 g to 1.9 g. The ash (mineral) content of P. trituberculatus decreased by 82.5% from 26.2 g to 4.6 g, that of U. pinnatifida increased by 27.6% from 3.3 g to 4.2 g, that of Korean Krill increased by 21.9% from 3.1 g to 3.8 g, and that of L. setigerus increased by 88.7% from 1.2 g to 2.2 g. The microbial composition of liquid fertilizer using recycled fishery by-products was shown to be Bacteria, Actinomycetes, Fungi, Yeast, and Lactobacillus sp.

• Journal of Environmental Science International
• /
• v.25 no.11
• /
• pp.1583-1587
• /
• 2016

The purpose of this study was to investigate the effects of fertilizer application on the content of functional materials, such as fatty acids and organic acids in perilla leaves. (1) As compared to the controlled with Ammonium sulfate fertilizer, the yield of Perilla frutescens leaves increased by 7.3% and 12.8% of biomass at 2000 and 1000 times liquid respectively, but decreased by 7.6% at 500 times. The lipid and protein contents of perilla leaves were higher than those of Portunus trituberculatus liquid at 1000 times. The average contents of minerals (mg/100g) were as follows; K (638.4) > Ca (561.6) > P (145.4) > Mg (133.5) > Fe (36.2) > Zn (1.9) > Mn (1.6) > Na (1.4 mg). However, the correlation between the controlled with P. trituberculatus liquid was relatively low. (2) The fat-soluble vitamin E content of P. frutescens leaves was 3.4, 3.9, 3.3, and 3.9 mg in the controlled with liquid by 500, and 1000, 2000 times respectively; Vitamin A contents were 6.4, 8.9, 10.9, and 8.5 mg respectively, which was more than twice as much as the corresponding vitamin E content. The water soluble vitamin C contents were 177.9, 172.6, 195.2, and 163.5 mg respectively. (3) Amino acid contents of P. frutescens leaves in 100 g of fresh weight were 3821.7 mg in the controlled with Ammonium sulfate fertilizer and 3918.8, 4054.0, and 4005.4 mg in the controlled with P. trituberculatus liquid at 2,000, 1000, 500 times respectively. Amino acid contents of each controlled group with P. trituberculatus liquid above were as small as 2.5~6.1%, and these contents of amino acid were as follows: Glutaminic acid > Aspartic acid > Leucine > Arginine > Phenylalanine. In further study, it is necessary to develop an effective microorganism and a variety of amino acid fertilizer to supplement the study on new manufacturing.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.9
• /
• pp.794-806
• /
• 2017

It is essential to protect the national space assets and space environment safely as a space development country from the continuously increasing space debris. And Active Debris Removal(ADR) is the most active way to solve this problem. In this paper, we studied the Artificial Neural Network(ANN) for a stable recognition model of vision-based space debris tracking system. We obtained the simulated image of the space environment by the KARICAT which is the ground-based space debris clearing satellite testbed developed by the Korea Aerospace Research Institute, and created the vector which encodes structure and color-based features of each object after image segmentation by depth discontinuity. The Feature Vector consists of 3D surface area, principle vector of point cloud, 2D shape and color information. We designed artificial neural network model based on the separated Feature Vector. In order to improve the performance of the artificial neural network, the model is divided according to the categories of the input feature vectors, and the ensemble technique is applied to each model. As a result, we confirmed the performance improvement of recognition model by ensemble technique.