• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.9-17
• /
• 2016

This study identifies major features in water supply and introduces important factors in water services based on the information from data mining analysis of water quantity and water pressure measured from sensors. It also suggests more accurate methods using multiple regression analysis and neural network in predicting short term prediction of water demand in water service. A small block of a county is selected for the data collection and tests. There isa water demand on business such as public offices and hospitalstoo in this area. Real stream data from sensors in this area is collected. Among 2,728 data sets collected, 2,632 sets are used for modelling and 96 sets are used for testing. The shows that neural network is better than multiple regression analysis in their prediction performance.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.209-219
• /
• 2016

SVM is a machine learning method used for image processing. It is well known for its high classification performance. We have to perform multiple MAC operations in order to use SVM for image classification. However, if the resolution of the target image or the number of classification cases increases, the execution time of SVM also increases, which makes it difficult to be performed in real-time applications. In this paper, we propose an hardware architecture which enables real-time applications using SVM classification. We used parallel architecture to simultaneously calculate MAC operations, and also designed the system for several feature extractors for compatibility. RBF kernel was used for hardware implemenation, and the exponent calculation formular included in the kernel was modified to enable fixed point modelling. Experimental results for the system, when implemented in Xilinx ZC-706 evaluation board, show that it can process 60.46 fps for $1360{\times}800$ resolution at 100MHz clock frequency.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.1
• /
• pp.291-297
• /
• 2018

In this paper, we present an automatic image object tracking system for Studio cameras on the stage. For object tracking, we use the OpenCV-based Python program using PC, Raspberry Pi 3 and mobile devices. There are many methods of image object tracking such as mean-shift, CAMshift (Continuously Adaptive Mean shift), background modelling using GMM(Gaussian mixture model), template based detection using SURF(Speeded up robust features), CMT(Consensus-based Matching and Tracking) and TLD methods. CAMshift algorithm is very efficient for real-time tracking because of its fast and robust performance. However, in this paper, we implement an image object tracking system for studio cameras based CMT algorithm. This is an optimal image tracking method because of combination of static and adaptive correspondences. The proposed system can be applied to an effective and robust image tracking system for continuous object tracking on the stage in real time.

• Journal of Radiation Protection and Research
• /
• v.29 no.3
• /
• pp.157-163
• /
• 2004

Atmospheric dispersion modelling has been widely used to predict the fate and transport of radioactive or toxic materials released from nuclear facilities which is an unlikely accidental event. To improve the forecasting performance of the dispersion model, it is required that source rate and dispersion characteristics must be defined appropriately. Generally, source term of the radioactive materials is much uncertain at the early phase of an accidental event. In this study, we computed the source rate with the experimental field data monitored at the Yeoung-Kwang nuclear site and obtained the optimal source rate to minimize the errors between the measured concentrations and the computed ones by the Gaussian plume model. Computed source term showed a good result within 24% of the artificially released source rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1625-1631
• /
• 2005

This paper describes an optimization of a language model and an acoustic model that improve the ability of speech recognition with Korean nit digit. Recognition errors of the language model are decreasing by analysis of the grammatical feature of korean unit digits, and then is made up of fsn-node with a disyllable. Acoustic model make use of demi-syllable pair to decrease recognition errors by inaccuracy division of a phone, a syllable because of a monosyllable, a short pronunciation and an articulation. we have used the k-means clustering algorithm with the transformed successive state splining in feature level for the efficient modelling of the feature of recognition unit . As a result of experimentations, $10.5\%$ recognition rate is raised in the case of the proposed language model. The demi-syllable pair with an acoustic model increased $12.5\%$ recognition rate and $1.5\%$ recognition rate is improved in transformed successive state splitting.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.778-804
• /
• 2017

Software today has become an inseparable part of our life. In order to achieve the ever demanding needs of customers, it has to rapidly evolve and include a number of changes. In this paper, our aim is to study the relationship of object oriented metrics with change proneness attribute of a class. Prediction models based on this study can help us in identifying change prone classes of a software. We can then focus our efforts on these change prone classes during testing to yield a better quality software. Previously, researchers have used statistical methods for predicting change prone classes. But machine learning methods are rarely used for identification of change prone classes. In our study, we evaluate and compare the performances of ten machine learning methods with the statistical method. This evaluation is based on two open source software systems developed in Java language. We also validated the developed prediction models using other software data set in the same domain (3D modelling). The performance of the predicted models was evaluated using receiver operating characteristic analysis. The results indicate that the machine learning methods are at par with the statistical method for prediction of change prone classes. Another analysis showed that the models constructed for a software can also be used to predict change prone nature of classes of another software in the same domain. This study would help developers in performing effective regression testing at low cost and effort. It will also help the developers to design an effective model that results in less change prone classes, hence better maintenance.

• Journal of the Korean Vacuum Society
• /
• v.20 no.3
• /
• pp.165-175
• /
• 2011

This paper introduces statistical features observed from measured batch data from the multiple operation state variables of dry vacuum pumps running in the semiconductor processes. The amplitude distribution characteristics of such state variables as inlet pressures, supply currents of the booster and dry pumps, and exhaust pressures are shown to be divided into two or three distinctive regions. This observation gives an idea of using an adaptive parametric model (APM) chosen to describe their statistical features. This modelling, in comparison to the traditional dynamic time wrapping algorithm, is shown to provide superior performance in computation time and memory resources required in the preprocessing stage of sampled batch data for the diagnosis of running dry vacuum pumps. APM model-based batch data are demonstrated to be very appropriate for monitoring and diagnosing the running conditions of dry vacuum pumps.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.392-403
• /
• 1997

There is a strong international move towards performance based fire regulations for buildings with New Zealand and Australia at the forefront of research in this fold. The reform of regulations is thought to offer more innovation and flexibility in building design and greater cost effectiveness in construction. An important part of the research in this area is related to the development of agreed approaches to fire safety design, such as the Fire Code Reform Centre's "Fire Engineering Guidelines" or New Zealand's "Fire Engineering Design Guide". Such design process documents have incorporated or referenced much of the latest research in areas such as: tenability criteria fire compartment models egress models risk assessment. Use of such design guidelines or equivalents in major projects in countries such as Hong Kong and Australia have highlighted where fro engineering can offer real benefits to building designers and ultimately building owners and operators. However, there is still much research to be done and use of a systematic, logical design approach clearly identifies where design data or modelling techniques are still urgently required. Such areas are: fire growth rates and peak heat release rates for non-residential occupancies pre-movement times related to egress experimental validation and limits of applicability of CFD and other compartment Ire models probability/reliability data on fire protection systems for risk based analysis. Examples from case studies will be shown where lack of such research and poor judgement can lead to inferior design solutions or where unnecessarily conservative designs can lead to cost excesses. In summary, the link between Ire engineering designers and the research community is very important to highlight areas of fire research that will have the most benefit to the building and construction industry.nstruction industry.

• Membrane and Water Treatment
• /
• v.9 no.2
• /
• pp.115-121
• /
• 2018

Artificial neural network (ANN) simulation is used to predict the dynamic change of permeate flux during wheat starch industry wastewater microfiltration with and without static turbulence promoter. The experimental program spans range of a sedimentation times from 2 to 4 h, for feed flow rates 50 to 150 L/h, at transmembrane pressures covering the range of $1{\times}10^5$ to $3{\times}10^5Pa$. ANN predictions of the wastewater microfiltration are compared with experimental results obtained using two different set of microfiltration experiments, with and without static turbulence promoter. The effects of the training algorithm, neural network architectures on the ANN performance are discussed. For the most of the cases considered, the ANN proved to be an adequate interpolation tool, where an excellent prediction was obtained using automated Bayesian regularization as training algorithm. The optimal ANN architecture was determined as 4-10-1 with hyperbolic tangent sigmoid transfer function transfer function for hidden and output layers. The error distributions of data revealed that experimental results are in very good agreement with computed ones with only 2% data points had absolute relative error greater than 20% for the microfiltration without static turbulence promoter whereas for the microfiltration with static turbulence promoter it was 1%. The contribution of filtration time variable to flux values provided by ANNs was determined in an important level at the range of 52-66% due to increased membrane fouling by the time. In the case of microfiltration with static turbulence promoter, relative importance of transmembrane pressure and feed flow rate increased for about 30%.

• Korean Journal of Remote Sensing
• /
• v.14 no.3
• /
• pp.232-249
• /
• 1998

The first Korean remote sensing satellite, Korea Multi-Purpose Satellite (KOMPSAT-1), is going to be launched in 1999. This will carry a 7m resolution Electro-Optical Camera (EOC) for earth observation. The primary mission of the KOMPSAT-1 is to acquire stereo imagery over the Korean peninsular for the generation of 1:25,000 scale cartographic maps. For this mission, research is being carried out to assess the possibilities of automated or semi-automated mapping of EOC data and to develop, if necessary, such enabling tools. This paper discusses the issue of automated digital elevation model (DEM) generation from EOC data and identifies some important aspects in developing a DEM generation system from EOC data. This paper also presents the current status of the development work for such a system. The development work will be described in three pares of sensor modelling, stereo matching and DEM interpolation. The performance of the system is shown with a SPOT stereo pair. A DEM generated from commercial software is also presented for comparison. The proposed system seems to generate promising results.