• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.8
• /
• pp.1352-1357
• /
• 2002

This Paper describes algorithm to extract license plates in vehicle images. Conventional methods perform preprocessing on the entire vehicle image to produce the edge image and binarize it. Hough transform is applied to the binary image to find horizontal and vertical lines, and the license plate area is extracted using the characteristics of license plates. Problems with this approach are that real-time processing is not feasible due to long processing time and that the license plate area is not extracted when lighting is irregular such as at night or when the plate boundary does not show up in the image. This research uses the gray level transition characteristics of license plates to verify the digit area by examining the digit width and the level difference between the background area the digit area, and then extracts the plate area by testing the distance between the verified digits. This research solves the problem of failure in extracting the license plates due to degraded plate boundary as in the conventional methods and resolves the problem of the time requirement by processing the real time such that practical application is possible. This paper Presents a power automated license plate recognition system, which is able to read license numbers of cars, even under circumstances, which are far from ideal. In a real-life test, the percentage of rejected plates wan 13%, whereas 0.4% of the plates were misclassified. Suggestions for further improvements are given.

• Journal of the Korean Chemical Society
• /
• v.61 no.2
• /
• pp.51-56
• /
• 2017

N-nitrosamines are the nitroso compounds which are produced by nitrosation reactions of the secondary amine and nitrite under acidic conditions. Approximately 300 species of N-nitrosamine have been tested for carcinogenicity in laboratory experiments, with 90% of them demonstrated carcinogenic effects different animal species, including higher primates. In 1978, IARC classified NDMA and NDEA as Group 2A, and NDPA, NDBA, NPIP, NPYR and NMOR as Group 2B. In this study, we established pretreatment and analytical method for N-nitrosamines (NDMA, NDEA, NMEA, NDPA, NDBA, NPIP, NPYR and NMOR) in human urine for biological monitoring of N-nitrosamines. The analytes were extracted using solid phase extraction (SPE), then quantitative analysis was performed by LC-(APCI)-MS/MS. The accuracies of the established method were between 85.8~108.7% and precisions were lower than 20%. The limit of detection (LOD) were between 0.0002 (NDBA) and 0.0793 (NDMA) ng/ml. The linearity obtained was satisfying for the 8 N-nitrosamines, with a coefficient of determination ($r^2$) higher than 0.999. The mean concentrations of N-nitrosamines in the urine were 2.645 mg/g creatinine for NDMA, 0.067 mg/g creatinine for NDEA, 0.009 mg/g creatinine for NMEA, 0.011 mg/g creatinine for NDBA, 0.271 mg/g creatinine for NPIP and 0.413 mg/g creatinine for NPYR. NDPA and NMOR were not detected. It can be used as a instrumental methodology for evaluation and risk assessment of human exposure to N-nitrosamines for the further research.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.91-99
• /
• 2010

Recently, recognizing user resource for personalized service has been needed in digital content service fields. Especially, to analyze user taste, recommend music and service music related information need recognition of user music file in case of online music service. Music related information service is offered through recognizing user music based on tag information. Recognition error has grown by weak points like changing and removing of tag information. Techniques of content based user music recognition with music signal itself are researched for solving upper problems. In this paper, we propose user music recognition on the internet by extracted feature from music signal. Features are extracted after suitable preprocessing for structure of content based user music recognition. Recognizing on music server consist of feature form are progressed with extracted feature. Through this, user music can be recognized independently of tag data. 600 music was collected and converted to each 5 music qualities for proving of proposed recognition. Converted 3000 experiment music on this method is used for recognition experiment on music server including 300,000 music. Average of recognition ratio was 85%. Weak points of tag based music recognition were overcome through proposed content based music recognition. Recognition performance of proposed method show a possibility that can be adapt to online music service in practice.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.33-46
• /
• 2011

Since an e-mail has been an important mean of communication and information sharing, there have been much effort to classify e-mails efficiently by their contents. An e-mail has various forms in length and style, and words used in an e-mail are usually irregular. In addition, the criteria of an e-mail classification are subjective. As a result, it is quite difficult for the conventional text classification technique to be adapted to an e-mail classification efficiently. An e-mail classification technique in a commercial e-mail program uses a simple text filtering technique in an e-mail client. In the previous studies on automatic classification of an e-mail, the Naive Bayesian technique based on the probability has been used to improve the classification accuracy, and most of them are on an e-mail in English. This paper proposes the personalized recommendation technique of an email in Korean using a data mining technique of frequent patterns. The proposed technique consists of two phases such as the pre-processing of e-mails in an e-mail folder and the generating a profile for the e-mail folder. The generated profile is used for an e-mail to be classified into the most appropriate e-mail folder by the subjective criteria. The e-mail classification system is also implemented, which adapts the proposed technique.

• Progress in Medical Physics
• /
• v.16 no.3
• /
• pp.148-154
• /
• 2005

Since the output of retina for visual stimulus is carried by neurons of very diverse functional properties, it is not adequate to use conventional single electrode for recording the retinal action potential. For this purpose, we used newly developed multichannel recording system for monitoring the simultaneous electrical activities of many neurons in a functioning piece of retina. Retinal action potentials are recorded with an extra-cellular planar array of 60 microelectrodes. In studying the collective activity of the ganglion cell population it is essential to recognize basic functional distinctions between individual neurons. Therefore, it is necessary to detect and to classify the action potential of each ganglion cell out of mixed signal. We programmed M-files with MATLAB for this sorting process. This processing is mandatory for further analysis, e.g. poststimulus time histogram (PSTH), auto-correlogram, and cross-correlogram. We established MATLAB based protocol for waveform classification and verified that this approach was effective as an initial spike sorting method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.8-15
• /
• 2020

A forecasting method using deep learning does not have consistent results due to the differences in the characteristics of the dataset, even though they have the same forecasting models and parameters. For example, the forecasting model X optimized with dataset A would not produce the optimized result with another dataset B. The forecasting model with the characteristics of the dataset needs to be optimized to increase the accuracy of the forecasting model. Therefore, this paper proposes novel optimization steps for outlier removal, dataset classification, and a CNN-LSTM-based hyperparameter tuning process to forecast the daily power usage of a university campus based on the hourly interval. The proposing model produces high forecasting accuracy with a 2% of MAPE with a single power input variable. The proposing model can be used in EMS to suggest improved strategies to users and consequently to improve the power efficiency.

• Journal of Korean Society of Environmental Engineers
• /
• v.36 no.11
• /
• pp.753-757
• /
• 2014

Anode electrode in a microbial fuel cell (MFC) should transfer the receiving electron as well as provide large surface area that can be immobilized microorganisms. Microorganisms' population is one of important factors to improve the current generation and to treat the livestock wastewater by biological treatment. These studies were attempted to investigate if stainless-steel wire skein (SSWS) could be used as anode electrode replacement a graphite felt electrode in microbial fuel cell. For these studies, pretreated livestock wastewater was used diluted to 500 mg/L as COD before use. At this time, the current showed a little difference of about 5% when using each of a SSW and graphite felt (control). There was no significant difference in the current value. The organic removal rate in the microbial fuel cells used graphite felt and SSWS was 82.4% and 88.3%, respectively. The COD removal in the MFC used the SSWS was higher than that of graphite felt. Ammonium nitrogen was showed similar trend in two case all. These results about current generation and organic matter reduction seem possible that SSWS was used to anode electrode. When SSWS is used, the initial investment for system construction is expected to be able to reduce by approximately 1/50.

• Journal of Biomedical Engineering Research
• /
• v.25 no.2
• /
• pp.137-144
• /
• 2004

ECG signals are often contaminated with high-frequency noise such as muscle artifact, power line interference, and others. In the ECG signal processing, especially during a pre-processing stage, numerous noise removal techniques have been used to reduce these high-frequency noise without much distorting the original signal. This paper proposes a new type of digital filter with a continuously variable cutoff frequency to improve the signal quality This filter consists of a cutoff frequency controller (CFC) and variable cutoff frequency lowpass filter (VCF-LPF). From the noisy input ECG signal, CFC produces a cutoff frequency control signal using the signal slew rate. We implemented VCF-LPF based on two new filter design methods called convex combination filter (CCF) and weight interpolation fille. (WIF). These two methods allow us to change the cutoff frequency of a lowpass filter In an arbitrary fine step. VCF-LPF shows an excellent noise reduction capability for the entire time segment of ECG excluding the rising and falling edge of a very sharp QRS complex. We found VCF-LPF very useful and practical for better signal visualization and probably for better ECG interpretation. We expect this new digital filter will find its applications especially in a home health management system where the measured ECG signals are easily contaminated with high-frequency noises .

• Korean Journal of Food Science and Technology
• /
• v.31 no.3
• /
• pp.593-599
• /
• 1999

Substrate specificity of a flow-injection-analysis (FIA)-type biogenic amine sensor with enzyme reactor was determined. The enzyme reactor was prepared with a diamine oxidase immobilized on preactivated chitosan porous beads (Chitopearl) by intramolecular cross-linking via glutaraldehyde. The sensor showed a rapid response to putrescine and a quasi-linear calibration curve was obtained up to 15.0 mM. The optimal pH and temperature of the enzyme reactor system were 7.5 and $35^{\circ}C$. Interferences due to ATP-related compounds and trimethylamine, and the effects of NaCl and amino acids were measured. Inhibitory effects owing to these components could be mitigated by sample extraction with perchloric acid. Polyamines except putrescine were determined by a putrescine calibration range within 26.7%. This system was confirmed as rapid and convenient for biogenic amine determination.

• Korean Journal of Ecology and Environment
• /
• v.47 no.3
• /
• pp.214-218
• /
• 2014

We introduce a technical equipment of GATe (Green (algae)-tide) water combine developed by K-water. The GATe water combine consists of five modules: main body and buoyant, transfer hopper, screen conveyer, sludge remover, and separator of algae and waste. Also a sprinkler, as the pre-treatment step if necessary, is equipped to the device to spread out environmental-friendly algaecide under the circumstance that the level of algal bloom does not reach to the scum-forming condition. The overall module system of this device is very simple. Based on the field test, the device covers surface area of ca. $500,000m^2day^{-1}$ during the period from May to July, and treats water volume as much as $500,000m^3day^{-1}$ in spite of some variation depending on the water quality condition. The removal efficiency of the device appeared to be over 90%. In addition, the operating duration of the device was able to expand to cover the period between March and November. We expect this new technology can be used to solve algal bloom problems in drinking water resource and public water area.