• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.5
• /
• pp.11-19
• /
• 2020

A daily progress monitoring and further schedule management of a construction project have a significant impact on the construction manager's decision making in schedule change and controlling field operation. However, a current site monitoring method highly relies on the manually recorded daily-log book by the person in charge of the work. For this reason, it is difficult to take a detached view and sometimes human error such as omission of contents may occur. In order to resolve these problems, previous researches have developed automated site monitoring method with the object recognition-based visualization or BIM data creation. Despite of the research results along with the related technology development, there are limitations in application targeting the practical construction projects due to the constraints in the experimental methods that assume the fixed equipment at a specific location. To overcome these limitations, some smart devices carried by the field workers can be employed as a medium for data creation. Specifically, the extracted information from the site picture by object recognition technology of CNN model, and positional information by GIPS are applied to update 4D BIM data. A standard CNN model is developed and BIM data modification experiments are conducted with the collected data to validate the research suggestion. Based on the experimental results, it is confirmed that the methods and performance are applicable to the construction site management and further it is expected to contribute speedy and precise data creation with the application of automated progress monitoring methods.

• Journal of agriculture & life science
• /
• v.45 no.4
• /
• pp.65-72
• /
• 2011

The objective of this research is to develop biomass allometric equation for Pinus densiflora in central region and Quercus variabilis. To develop the biomass allometric equation by species and tree component, data for Pinus densiflora in central region is collected to 30 plots (70 trees) and for Quercus variabilis is collected to 15 plots (32 trees). This study is used two independent values; (1) one based on diameter beast height, (2) the other, diameter beast height and height. And the equation forms were divided into exponential, logarithmic, and quadratic functions. The validation of biomass allometric equations were fitness index, standard error of estimate, and bias. From these methods, the most appropriate equations in estimating total tree biomass for each species are as follows: $W=aD^b$, $W=aD^bH^c$; fitness index were 0.937, 0.943 for Pinus densiflora in central region stands, and $W=a+bD+cD^2$, $W=aD^bH^c$; fitness index were 0.865, 0.874 for Quercus variabilis stands. in addition, the best performance of biomass allometric equation for Pinus densiflora in central region is $W=aD^b$, and Quercus variabilis is $W=a+bD+cD^2$. The results of this study could be useful to overcome the disadvantage of existing the biomass allometric equation and calculate reliable carbon stocks for Pinus densiflora in central region and Quercus variabilis in Korea.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.621-626
• /
• 2006

Today's commercial high resolution satellite imagery such as IKONOS and QuickBird, offers the potential to extract useful spatial information for geographical database construction and GIS applications. Extraction of 3D building information from high resolution satellite imagery is one of the most active research topics. There have been many previous works to extract 3D information based on stereo analysis, including sensor modelling. Practically, it is not easy to obtain stereo high resolution satellite images. On single image performance, most studies applied the roof-bottom points or shadow length extracted manually to sensor models with DEM. It is not suitable to apply these algorithms for dense buildings. We aim to extract 3D building information from a single satellite image in a simple and practical way. To measure as many buildings as possible, in this paper, we suggested a new way to extract building height by triangular vector structure that consists of a building bottom point, its corresponding roof point and a shadow end point. The proposed method could increase the number of measurable building, and decrease the digitizing error and the computation efficiency.

• Journal of Climate Change Research
• /
• v.6 no.4
• /
• pp.357-366
• /
• 2015

This study was conducted to estimate carbon stocks of Quercus serrata with drawing volume of trees in each tree height and DBH applying the suitable stem taper equation and tree specific carbon emission factors, using collected growth data from all over the country. Information on distribution area, tree number per hectare, tree volume and volume stocks were obtained from the $5^{th}$ National Forest Inventory (2006~2010), and method provided in IPCC GPG was applied to estimate carbon storage and removals. Performance in predicting stem diameter at a specific point along a stem in Quercus serrata by applying Kozak's model,$d=a_1DBH^{a_2}a_3^{DBH}X^{b_1Z^2+b_2ln(Z+0.001)+b_3{\sqrt{Z}}+b_4e^Z+b_5({\frac{DBH}{H}})}$, which is well known equation in stem taper estimation, was evaluated with validations statistics, Fitness Index, Bias and Standard Error of Bias. Consequently, Kozak's model turned out to be suitable in all validations statistics. Stem volume tables of Quercus serrata were derived by applying Kozak's model and carbon stock tables in each tree height and DBH were developed with country-specific carbon emission factors ($WD=0.65t/m^3$, BEF=1.55, R=0.43) of Quercus serrata. As a result of carbon stock analysis by age class in Quercus serrata, carbon stocks of IV age class (11,358 ha, 36.5%) and V age class (10,432; 33.5%) which take up the largest area in distribution of age class were 957,000 tC and 1,312,000 tC. Total carbon stocks of Quercus serrata were 3,191,000 tC which is 3% compared with total percentage of broad-leaved forest and carbon sequestration per hectare(ha) was 3.8 tC/ha/yr, $13.9tCO_2/ha/yr$, respectively.

• Korean Journal of Optics and Photonics
• /
• v.13 no.5
• /
• pp.442-448
• /
• 2002

In the earth telescope for space observation, the adaptive optical (AO) system that immediately compensates atmospheric turbulence is helpful to get high-resolution images. An adaptive optics for earth telescopes is very attractive, since the Earth telescopes can be made at lower costs and have larger optical apertures than space telescopes. Generally. in order to remove the wavefront error produced by atmospheric turbulence, a deformable mirror, whose surface shape changes in a controllable way in response to a drive signal, is used. The characteristics and patterns of actuators are very important for the effective control of a deformable mirror. The mirror surface shape deformed by one actuator is defined as an influence function and the deformable mirror can be effectively modeled and designed using this influence function. In this paper. by simplifying the actual influence function obtained by FEM analyses into the Gaussian function and introducing the coupling coefficient between actuators, the influence function is constructed. The proper coupling coefficient of the target system can be obtained by performance analyses of a deformable mirror for various coupling coefficients. Using the constructed influence function, the deformable mirror with equally spaced triangular and square actuator patterns is analyzed for various spacings and an effective actuator pattern is proposed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.100-112
• /
• 2021

With the advent of big data, traffic prediction has been developed based on historical data analysis methods, but this method deteriorates prediction performance when a traffic incident that has not been observed occurs. This study proposes a method that can compensate for the reduction in traffic prediction accuracy in traffic incidents situations by hybrid approach of machine learning and traffic simulation. The blind spots of the data-driven method are revealed when data patterns that have not been observed in the past are recognized. In this study, we tried to solve the problem by reinforcing historical data using traffic simulation. The proposed method performs machine learning-based traffic prediction and periodically compares the prediction result with real time traffic data to determine whether an incident occurs. When an incident is recognized, prediction is performed using the synthetic traffic data generated through simulation. The method proposed in this study was tested on an actual road section, and as a result of the experiment, it was confirmed that the error in predicting traffic state in incident situations was significantly reduced. The proposed traffic prediction method is expected to become a cornerstone for the advancement of traffic prediction.

• Science of Emotion and Sensibility
• /
• v.23 no.4
• /
• pp.33-40
• /
• 2020

As the number of automobile registrations increases and luxury expectations grow, consumers are increasingly interested in indoor environment of vehicles. Therefore, manufacturers have an increasing interest in improving the indoor comfort as well as automobile performance. Research on indoor automobile comfort can help manufacturers increase driver satisfaction and reduce driver stress and discomfort, thereby reducing the risk of traffic accidents. Using electroencephalogram (EEG) measurements, we investigated the change in comfort and comfortable temperature according to the ventilating seat temperature change for both men and women. Results showed that the sensation of comfort was statistically significantly higher at 25℃ than at 28℃. Secondly, there was no statistically significant difference in temperature-based comfort feeling between male and female subjects. In the future, if the correlation between the driver's comfort feeling and the change in ventilating seat temperature is analyzed, it is possible to reduce traffic accidents caused by human error and reduce the electric energy consumption of the automobile.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.