• The Transactions of the Korea Information Processing Society
• /
• v.4 no.10
• /
• pp.2461-2469
• /
• 1997

Target detection and recognition problems, in which neural networks are widely used, require translation invariant and real-time processing in addition to the requirements that general pattern recognition problems need. This paper presents a novel architecture that meets the requirements and explains effective methodology to train the network. The proposed neural network is an architectural extension of the shared-weight neural network that is composed of the feature extraction stage followed by the pattern recognition stage. Its feature extraction stage performs correlational operation on the input with a weight kernel, and the entire neural network can be considered a nonlinear correlation filter. Therefore, the output of the proposed neural network is correlational plane with peak values at the location of the target. The architecture of this neural network is suitable for implementing with parallel or distributed computers, and this fact allows the application to the problems which require realtime processing. Net training methodology to overcome the problem caused by unbalance of the number of targets and non-targets is also introduced. To verify the performance, the proposed network is applied to detection and recognition problem of a specific automobile driving around in a parking lot. The results show no false alarms and fast processing enough to track a target that moves as fast as about 190 km per hour.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.51-61
• /
• 2008

Most of Korea's 15 local airports, with the exception Jeju, Gimpo and Gimhae airports, have been several billion Won in the red each year. It has been reported that one of the causes of the poor financial performance is inaccurate air traffic demand predictions. Under the situation, the entry of low-cost carrier air service using turbo-prop airplanes into the domestic airlines market gets a wide range of support, which is expected to promote the convenience of consumers and help to activate local airports. In this study, the authors (1) suggest a high-speed transport demand model among existing airlines, Korea Train Express (KTX) and low-cost carrier air service; (2) try to make low-cost air carrier demand predictions for a route between Seoul and Daegu through a stated-preference survey; and (3), examine possible effectiveness of selected policy measures by establishing an estimation model. First, fare has a strong influence for mode choice between high-speed transport modes when considering the entry of low-cost carrier air service between Seoul and Daegu. Even low-cost carrier air service fare is set at 38,000 won, which is considerably low compared with that of KTX, in the regions where the total travel time is the same for both low-cost carrier air service and KTX, the probability of selecting low-cost carrier air service is 0.1, which shows little possibility of modal change between high speed transportation means. It is suggested that the fare of low-cost air service between Seoul and Daegu should be within the range of from of 38,000 to 44,000 Won; if it is higher, the demand is likely to be lower than expected.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.7
• /
• pp.221-228
• /
• 2020

Part-of-Speech (POS) tagged corpus is a collection of electronic text in which each word is annotated with a tag as the corresponding POS and is widely used for various training data for natural language processing. The training data generally assumes that there are no errors, but in reality they include various types of errors, which cause performance degradation of systems trained using the data. To alleviate this problem, we propose a novel method for detecting errors in the existing POS tagged corpus using the classifier of XGBoost and cross-validation as evaluation techniques. We first train a classifier of a POS tagger using the POS-tagged corpus with some errors and then detect errors from the POS-tagged corpus using cross-validation, but the classifier cannot detect errors because there is no training data for detecting POS tagged errors. We thus detect errors by comparing the outputs (probabilities of POS) of the classifier, adjusting hyperparameters. The hyperparameters is estimated by a small scale error-tagged corpus, in which text is sampled from a POS-tagged corpus and which is marked up POS errors by experts. In this paper, we use recall and precision as evaluation metrics which are widely used in information retrieval. We have shown that the proposed method is valid by comparing two distributions of the sample (the error-tagged corpus) and the population (the POS-tagged corpus) because all detected errors cannot be checked. In the near future, we will apply the proposed method to a dependency tree-tagged corpus and a semantic role tagged corpus.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.55-64
• /
• 2013

Due to the popularization of digital high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy for anyone to make a high-quality counterfeit money. However, the probability of detecting a counterfeit money to the general public is extremely low. In this paper, we propose a counterfeit money detection algorithm using a general purpose scanner. This algorithm determines counterfeit money based on the different features in the printing process. After the non-local mean value is used to analyze the noises from each money, we extract statistical features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and test the support vector machine classifier for identifying either original or counterfeit money. In the experiment, we use total 324 images of original money and counterfeit money. Also, we compare with noise features from previous researches using wiener filter and discrete wavelet transform. The accuracy of the algorithm for identifying counterfeit money was over 94%. Also, the accuracy for identifying the printing source was over 93%. The presented algorithm performs better than previous researches.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1307-1315
• /
• 2021

The Changjiang Diluted Water (CDW) spreads over the East China Sea every summer and significantly affects the sea surface salinity changes in the seas around Jeju Island and the southern coast of Korea peninsula. Sometimes its effect extends to the eastern coast of Korea peninsula through the Korea Strait. Specifically, the CDW has a significant impact on marine physics and ecology and causes damage to fisheries and aquaculture. However, due to the limited field surveys, continuous observation of the CDW in the East China Sea is practically difficult. Many studies have been conducted using satellite measurements to monitor CDW distribution in near-real time. In this study, an algorithm for estimating Sea Surface Salinity (SSS) in the East China Sea was developed using the Geostationary Ocean Color Imager (GOCI). The Multilayer Perceptron Neural Network (MPNN) method was employed for developing an algorithm, and Soil Moisture Active Passive (SMAP) SSS data was selected for the output. In the previous study, an algorithm for estimating SSS using GOCI was trained by 2016 observation data. By comparison, the train data period was extended from 2015 to 2020 to improve the algorithm performance. The validation results with the National Institute of Fisheries Science (NIFS) serial oceanographic observation data from 2011 to 2019 show 0.61 of coefficient of determination (R²) and 1.08 psu of Root Mean Square Errors (RMSE). This study was carried out to develop an algorithm for monitoring the surface salinity of the East China Sea using GOCI and is expected to contribute to the development of the algorithm for estimating SSS by using GOCI-II.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.479-487
• /
• 2021

In this paper, we propose an Sound Event Detection (SED) model using self-training based on a noisy student model. The proposed SED model consists of two stages. In the first stage, a mean-teacher model based on an Residual Convolutional Recurrent Neural Network (RCRNN) is constructed to provide target labels regarding weakly labeled or unlabeled data. In the second stage, a self-training-based noisy student model is constructed by applying different noise types. That is, feature noises, such as time-frequency shift, mixup, SpecAugment, and dropout-based model noise are used here. In addition, a semi-supervised loss function is applied to train the noisy student model, which acts as label noise injection. The performance of the proposed SED model is evaluated on the validation set of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge Task 4. The experiments show that the single model and ensemble model of the proposed SED based on the noisy student model improve F1-score by 4.6 % and 3.4 % compared to the top-ranked model in DCASE 2020 challenge Task 4, respectively.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.9
• /
• pp.721-736
• /
• 2019

In this paper, the behavior of the fire smoke due to the operation of the ventilation systems when the fire occurred in the underground station (6 basement floors) and the tunnel at the great depth was measured. Fire smoke was generated by using a smoke generator which realized heat buoyancy effect by using hot air blower. The two locations of the fire were selected on the platform and on the platform of the tunnel located outside the screen door. A ventilation mode is generally used in which smoke is exhausted through a vent hole provided in a platform when a platform fire occurs. The tests were performed by operating the exhaust through the ventilation holes of the tunnel part located at both ends of the platform. The smoke density and the wind speed/velocity were measured at various positions, and the videos were taken to analyze the movement and smoke of the smoke. In both cases for fire inside the platform and in the railway tunnel, due to the ventilation mode operation of the fan for the platform and the exhaust of the fans in the tunnel smoke were well exhausted and the smoke propagation to the area near the smoke zone was suppressed. The smoke-control mode, which is applied to both fans for the platform and fans for in the tunnel at both ends of the platform, can provide a safer evacuation environment to the passengers from the fire smoke when the platform fire or fire train stops.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.293-302
• /
• 2019

This study systematically analyzed computer-based driving intervention programs for seniors, to provide the academic background for driving intervention for seniors. Articles published from January 2009 till December 2018 were researched and analyzed. 'PubMed, Google Scholar, and Science Direct' were used to search articles published overseas, and 'RISS, KERIS, and KISS' searched for articles published in Korea. Based on the inclusion and exclusion criteria, totally 359 papers were retrieved, and 10 articles were finally analyzed; 8 articles (80%) were evidence level I, and 2 articles (20%) were evidence level III. Amongst the computer-based interventions, driving simulators (70%) were the most common, followed by two video image training (20%) and one Nintendo Wii program (10%). In most studies, driving simulators trained the cognitive and visual abilities of seniors and enhanced their abilities to cope with risk situations under various simulated circumstances. Other interventions were also reported to have a positive effect. For evaluating elderly drivers, the driving performance evaluation using a driving simulator was the most common; in addition, evaluations of attention, space-time ability, cognitive function, risk perception, depression and anxiety were also commonly used. We believe that it is appropriate to employ computer-based driving intervention programs for seniors to train and evaluate various domains. We expect that these interventions can be used as an effective tool for safe driving.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.541-549
• /
• 2018

This paper deals with the braking dynamic behavior of diesel electric locomotive pulling domestic cargo and passenger vehicles. Friction coefficient, pneumatic pressure, and running resistance affecting the braking system were tested. For the friction coefficient, the Dynamo test was performed with reference to UIC 541-4. The results are analyzed by multivariate regression and the relationship between braking force and ititial velocity is presented. The pneumatic pressure were classified into service braking and emergency braking. In order to reflect the characteristics of the brake valve and piping, the pressure rising over time was measured in the vehicle. In order to reflect the external force acting on the vehicle, we carried out the test of EN 14067-4 and presented the second order polynomial formula on a running resistance. The running resistance test results were compared with other countries. The dynamic behavior of a diesel electric locomotive running on a straight flat track based on vehicle resources, friction coefficient, braking pressure, and running resistance is simulated using the time integration presented in EN 14531-1. The simulation results were compared and verified with the vehicle braking test results. The results of this study can be used to analyze the dynamic braking behavior of a train. Also, it is expected that various parameters affecting braking in vehicle design can be analyzed and used as basic data for braking performance improvement.