• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.351-360
• /
• 2018

The LWR (Locally Weighted Regression) model, which is traditionally a lazy learning model, is designed to obtain the solution of the prediction according to the input variable, the query point, and it is a kind of the regression equation in the short interval obtained as a result of the learning that gives a higher weight value closer to the query point. We study on an incremental ensemble learning approach for LWR, a form of lazy learning and memory-based learning. The proposed incremental ensemble learning method of LWR is to sequentially generate and integrate LWR models over time using a genetic algorithm to obtain a solution of a specific query point. The weaknesses of existing LWR models are that multiple LWR models can be generated based on the indicator function and data sample selection, and the quality of the predictions can also vary depending on this model. However, no research has been conducted to solve the problem of selection or combination of multiple LWR models. In this study, after generating the initial LWR model according to the indicator function and the sample data set, we iterate evolution learning process to obtain the proper indicator function and assess the LWR models applied to the other sample data sets to overcome the data set bias. We adopt Eager learning method to generate and store LWR model gradually when data is generated for all sections. In order to obtain a prediction solution at a specific point in time, an LWR model is generated based on newly generated data within a predetermined interval and then combined with existing LWR models in a section using a genetic algorithm. The proposed method shows better results than the method of selecting multiple LWR models using the simple average method. The results of this study are compared with the predicted results using multiple regression analysis by applying the real data such as the amount of traffic per hour in a specific area and hourly sales of a resting place of the highway, etc.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.20-27
• /
• 2010

This paper proposes a saturation compensating method by embedding pseudo-random code information in wavelet packet based colorization algorithm. In the color-to-gray process, an input RGB image is converted into YCbCr images, and a 2-level wavelet packet transform is applied to the Y image. And then, color components of CbCr are embedded into two sub-bands including minimum amount of energy on the Y image. At this time, in order to compensate the color saturations of the recovered color image during the printing and scanning process, the maximum and minimum values of CbCr components of an original image are also embedded into the diagonal-diagonal sub-band by a form of pseudo-random code. This pseudo-random code has the maximum and minimum values of an original CbCr components, and is expressed by the number of white pixels. In the gray-to-color process, saturations of the recovered color image are compensated using the ratio of the original CbCr values to the extracted CbCr values. Through the experiments, we can confirm that the proposed method improves color saturations in the recovered color images by the comparison of color difference and PSNR values.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.2
• /
• pp.197-204
• /
• 2018

One of the hottest issues in our 21st century is AI. Just as the automation of manual labor has been achieved through the Industrial Revolution in the agricultural society, the intelligence information society has come through the SW Revolution in the information society. With the advent of Google 'Alpha Go', the computer has learned and predicted its own machine learning, and now the time has come for the computer to surpass the human, even to the world of Baduk, in other words, the computer. Machine learning ML (machine learning) is a field of artificial intelligence. Machine learning ML (machine learning) is a field of artificial intelligence, which means that AI technology is developed to allow the computer to learn by itself. The time has come when computers are beyond human beings. Many companies use machine learning, for example, to keep learning images on Facebook, and then telling them who they are. We also used a neural network to build an efficient energy usage model for Google's data center optimization. As another example, Microsoft's real-time interpretation model is a more sophisticated translation model as the language-related input data increases through translation learning. As machine learning has been increasingly used in many fields, we have to jump into the AI industry to move forward in our 21st century society.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.111-123
• /
• 2013

To verify software vulnerability, the method of conjecturing software structure and then testing the software based on the conjectured structure has been highlighted. To utilize the method, an efficient way to conjecture software structure is required. The popular graph and tree methods such as DFG(Data Flow Graph), CFG(Control Flow Graph) and CFA(Control Flow Automata) have a serious drawback. That is, they cannot express software in a hierarchical fashion. In this paper, we propose a method to overcome the drawback. The proposed method applies various input data to a binary code, generate CFG's based on the code output and construct a HCFG (Hierarchical Control Flow Graph) to express the generated CFG's in a hierarchical structure. The components required for HCFG and progressive algorithm to construct HCFG are also proposed. The proposed method is verified through constructing the software architecture of an open SMTP(Simple Mail Transfer Protocol) server program. The structure generated by the proposed method and the real program structure are compared and analyzed.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.3 s.303
• /
• pp.47-52
• /
• 2005

Obstructive Sleep Apnea (OSA) is a representative symptom of sleep disorder caused by the obstruction of upper airway. Because OSA causes not only excessive daytime sleepiness and fatigue, hypertension and arrhythmia but also cardiac arrest and sudden death during sleep in the severe case, it is very important to detect the occurrence and the frequency of OSA. OSA is usually diagnosed through the laboratory-based Polysomnography (PSG) which is uncomfortable and expensive. Therefore researches to improve the disadvantages of PSG are needed and studies for the detection of OSA using only one or two parameters are being made as alternatives to PSG. In this paper, we developed an algorithm for the detection of OSA based on Heart Rate Variability (HRV). The proposed method is applied to the ECG data sets provided from PhysioNet which consist of learning set and training set. We extracted features for the detection of OSA such as average and standard deviation of 1 minute R-R interval, power spectrum of R-R interval and S-peak amplitude from data sets. These features are applied to the input of neural network. As a result, we obtained sensitivity of $89.66\%$ and specificity of $95.25\%$. It shows that the features suggested in this study are useful to detect OSA.

• Spatial Information Research
• /
• v.22 no.1
• /
• pp.75-84
• /
• 2014

Power lines are one of the main obstacles causing an aircraft crash and thus their realtime detection is significantly important during flight. To avoid such flight obstacles, the use of LIDAR has been recently increasing thanks to its advantages that it is less sensitive to weather conditions and can operate in day and night. In this study, we suggest a fast method to detect power lines from LIDAR data for flight obstacle avoidance. The proposed method first extracts non-ground points by eliminating the points reflected from ground surfaces using a filtering process. Second, we calculate the eigenvalues for the covariance matrix from the coordinates of the generated non-ground points and obtain the ratio of eigenvalues. Based on the ratio of eigenvalues, we can classify the points on a linear structure. Finally, among them, we select the points forming horizontally long straight as power-line points. To verify the algorithm, we used both real and simulated data as the input data. From the experimental results, it is shown that the average detection rate and time are 80% and 0.2 second, respectively. If we would improve the method based on the experiment results from the various flight scenario, it will be effectively utilized for a flight obstacle avoidance system.

• Journal of Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.51-61
• /
• 2002

In this dissertation, We demonstrated the Travel Time forecasting model in the freeway of multi-section with regard of drives' attitude. Recently, the forecasted travel time that is furnished based on expected travel time data and advanced experiment isn't being able to reflect the time-lag phenomenon specially in case of long distance trip, so drivers don't believe any more forecasted travel time. And that's why the effects of ATIS(Advanced Traveler Information System) are reduced. Therefore, in this dissertation to forecast the travel time of the freeway of multi-section reflecting the time-lag phenomenon & the delay of tollgate, we used traffic volume data & TCS data that are collected by Korea Highway Cooperation. Also keep the data of mixed unusual to applicate real system. The applied model for forecasting is consisted of feed-forward structure which has three input units & two output units and the back-propagation is utilized as studying method. Furthermore, the optimal alternative was chosen through the twelve alternative ideas which is composed of the unit number of hidden-layer & repeating number which affect studying speed & forecasting capability. In order to compare the forecasting capability of developed ANN model. the algorithm which are currently used as an information source for freeway travel time. During the comparison with reference model, MSE, MARE, MAE & T-test were executed, as the result, the model which utilized the artificial neural network performed more superior forecasting capability among the comparison index. Moreover, the calculated through the particularity of data structure which was used in this experiment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.7
• /
• pp.1296-1306
• /
• 2015

Nowadays the research of energy saving on the IP networks have been studied the various methods in many research institutes. This paper suggests the energy saving method in IP networks which have the various energy profiles, and analyzes its energy saving characteristics in detail. Especially this paper proposes the energy profile based OSPF routing method which have the selectable weighted value in OSPF metric and energy consumption in IP network. This paper analyzes the energy saving effects of the various situations to minimize the energy consumption using the various weighted value on the proposed scheme. The results show that the energy saving efficiency can get about 67% at in ingress input load ${\rho}=0.5$ by using random energy profiles in IP networks. Although the number of hops is a slight increased due to routing the paths for the minimum energy consumption in the algorithm of this method, the increment hop number is limited the mean 1.4 hops. This paper confirms that the energy profile of core router has the large effects of energy saving than the energy profile of edge router, and the proposed method has the excellent energy saving characteristics in IP networks.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.4
• /
• pp.819-830
• /
• 2017

An FM radio based PCL system is a passive radar technique for detecting the multiple moving targets from FM radio signals and tracking the trajectories of the targets by calculating the cross-correlation function of direct-path signal and target echo signals. However, the interference signals are received from a surveillance channel, which is designed to receive the target echo signals. Because of this problem, the target echo signals are masked by the strong interference signals and this makes it difficult to detect the true targets from the cross-correlation function. Adaptive filters are known as effective methods for suppressing the interference signals but there is a problem to present their accurate performances in the PCL system because many literatures used the cross-correlation function and the ratio of input and output power as a measure of the performance analysis. In this paper, a performance analysis method is proposed to evaluate the performance of interference cancellation algorithms. By using the property that each component of the filter weight vector is adjusted to suppress the specific interference signal, a performance measure of the interference signal suppression is defined by a function of adaptive filter weights. Based on the proposed method, we compare the performance of the adaptive filters used in the PCL system. Simulation results show that the proposed method can be very effective for evaluating the performance of interference cancellation algorithms.