• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.778-781
• /
• 2015

The paper presents a new way of visual descriptor for deformable object retrieval on the basis of partition based description. The proposed descriptor technology partitions a given object into boundary area and interior area and extracts a descriptor from each area. The final descriptor combines these descriptors. From a given image, deformable object is segmented. The center position of the deformable object is calculated. The object is partitioned into N × N blocks on the basis of the given center position. Blocks are classified as boundary area and interior area depending on the pixels in the block. The proposed descriptor consists of extracted MPEG-7 dominant descriptors from both the boundary and interior area. The performance of proposed method is tested on a database of 1,973 handbag images constructed with view point changes. ARR (Average Retrieval Rate) is used for the retrieval accuracy of the proposed algorithm, compared with MPEG-7 dominant color descriptor.

• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.1061-1068
• /
• 2012

This paper deals with a noise reduction algorithm which uses the binary masking approach in the time-frequency domain to improve speech intelligibility. In the binary masking approach, the noise-corrupted speech is decomposed into time-frequency units. Noise-dominant time-frequency units are removed by setting the corresponding binary masks as "0"s and target-dominant units are retained untouched by assigning mask "1"s. We propose a binary mask estimation by comparing the local signal-to-noise ratio (SNR) to a threshold. The local SNR is estimated by a training-based approach. An optimal threshold is proposed, which is obtained from observing the distribution of the training database. The proposed method is evaluated by normal-hearing subjects and the intelligibility scores are computed by counting the number of words correctly recognized.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.2
• /
• pp.73-79
• /
• 2012

This study attempts to analyze changes in land use patterns in a compound urban and agricultural city Kimje-si, using LANDSAT TM imagery and to forecast future changes accordingly. As a new approach to supervised classification, HSB(Hue, Saturation, Brightness)-transformed images were used to select training zones, and in doing so classification accuracy increased by more than 5 percent. Land use changes were forecasted by using a cellular automaton algorithm developed by applying Markov Chain techniques, and by taking into account classification results and GIS data, such as population of the pertinent region by area, DEMs, road networks, water systems. Upon comparing the results of the forecast of the land use changes, it appears that geographical features had the greatest influence on the changes. Moreover, a forecast of post-2030 land use change patterns demonstrates that 21.67 percent of mountain lands in Kimje-si is likely to be farmland, and 13.11 percent is likely to become city areas. The major changes are likely to occur in small mountain lands located in the heart of the city. Based on the study result, it seems certain that forecasting future land use changes can help plan land use in a compound urban and agricultural city to procure food resources.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.1-9
• /
• 2012

The popularity of digital music and smart phones led to develope noise-robust real-time audio fingerprinting system in various ways. In particular, The Multiple Hashing(MLH) of fingerprint algorithms is robust to noise and has an elaborate structure. In this paper, we propose a filter engine based on MLH to achieve better performance. In this approach, we compose a energy-intensive filter to improve the accuracy of Q/R from music database and a statistic filter to remove continuity and redundancy. The energy-intensive filter uses the Discrite Cosine Transform(DCT)'s feature gathering energy to low-order bits and the statistic filters use the correlation between searched fingerprint's information. Experimental results show that the superiority of proposed algorithm consists of the energy and statistical filtering in noise environment. It is found that the proposed filter engine achieves more robust to noise than Philips Robust Hash(PRH), and a more compact way than MLH.

• International Journal of Contents
• /
• v.7 no.3
• /
• pp.13-18
• /
• 2011

Oriental medicine statistics are essential in research planning, research evaluation, and policy decision based on objective data. However, integrated administration of such statistics is not presently possible in the oriental medicine field, which has been slow in incorporating information communication technology. In an effort to address this problem, the Korea Institute of Oriental Medicine (KIOM) developed an oriental medicine statistical system in 2009, and the system has been offered in the traditional medicine information portal of OASIS. However, according to a 2010 survey targeting OASIS users, those surveys reported that needs for a system where various statistical data can be extracted via an interactive approach to multidimensional data. As a result of an analysis of the functions of the existing system, it was found that it is necessary to array and arithmetically analyze Stats Value, Drill Up & Drill Down, and Pivot. To this end, the existing DB schema should be redesigned. Based on our analysis result, we redesigned the database into a structure that is applicable to the reverse pivot algorithm. We used J2EE/JSP and a Flex framework to design and develop an oriental medicine statistical system that can provide multidimensional statistical data. Considering that the improved oriental medicine statistical system is planned to be offered by OASIS of KIOM, utilization and value of oriental medicine statistical data are expected to be enhanced.

• Toxicological Research
• /
• v.32 no.4
• /
• pp.289-300
• /
• 2016

Non-genotoxic carcinogens are substances that induce tumorigenesis by non-mutagenic mechanisms and long term rodent bioassays are required to identify them. Recent studies have shown that transcription profiling can be applied to develop early identifiers for long term phenotypes. In this study, we used rat liver expression profiles from the NTP (National Toxicology Program, Research Triangle Park, USA) DrugMatrix Database to construct a gene classifier that can distinguish between non-genotoxic carcinogens and other chemicals. The model was based on short term exposure assays (3 days) and the training was limited to oxidative stressors, peroxisome proliferators and hormone modulators. Validation of the predictor was performed on independent toxicogenomic data (TG-GATEs, Toxicogenomics Project-Genomics Assisted Toxicity Evaluation System, Osaka, Japan). To build our model we performed Random Forests together with a recursive elimination algorithm (VarSelRF). Gene set enrichment analysis was employed for functional interpretation. A total of 770 microarrays comprising 96 different compounds were analyzed and a predictor of 54 genes was built. Prediction accuracy was 0.85 in the training set, 0.87 in the test set and increased with increasing concentration in the validation set: 0.6 at low dose, 0.7 at medium doses and 0.81 at high doses. Pathway analysis revealed gene prominence of cellular respiration, energy production and lipoprotein metabolism. The biggest target of toxicogenomics is accurately predict the toxicity of unknown drugs. In this analysis, we presented a classifier that can predict non-genotoxic carcinogenicity by using short term exposure assays. In this approach, dose level is critical when evaluating chemicals at early time points.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.146-149
• /
• 2002

The aim of stereotactic radiosurgery(SRS) is to deliver a high dose to a target region and a low dose to critical organ through only one or a few irradiation. To satisfy this aim, optimized irradiating conditions must be searched in the planning. Thus, many mathematical methods such as gradient method, simulated annealing and genetic algorithm had been proposed to find out the conditions automatically. There were some limitations using these methods: the long calculation time, and the difficulty of unique solution due to the different shape of tumor. In this study, optimization protocol using ideal models and data base was proposed. Proposed optimization protocol constitutes two steps. First step was a preliminary work. Some possible ideal geometry shapes, such as sphere, cylinder, cone shape or the combination, were assumed to approximate the real tumor shapes. Optimum variables such as isocenter position or collimator size, were determined so that the high dose region could be shaped to fit ideal models with the arrangement of multiple isocenter. Data base were formed with those results. Second, any shaped real targets were approximated to these models using geometry comparison. Then, optimum variables for ideal geometry were chosen from the data base predetermined, and final parameters were obtained by adjusting these data. Although the results of applying the data base to patients were not superior to the result of optimization in each case, it can be acceptable as a starting point of plan.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.3
• /
• pp.35-42
• /
• 2012

The database for driving patterns can be utilized in various system such as automatic driving system, driver safety system, and it can be helpful to monitor driving style. Therefore, we propose a driving pattern recognition system in which the sensor streams from a smartphone are recorded and used for recognizing driving events. In this paper we focus on the driving pattern recognition that is an essential and preliminary step of driving style recognition. We divide input sensor streams into 7 driving patterns such as, Left-turn(L), U-turn(U), Right-turn(R), Rapid-Braking(RB), Quick-Start(QS), Rapid-Acceleration (RA), Speed-Bump(SB). To classify driving patterns, first, a preprocessing step for data smoothing is followed by an event detection step. Last the detected events are classified by DTW(Dynamic Time Warping) algorithm. For assisting drivers we provide the classified pattern with the corresponding video stream which is recorded with its sensor stream. The proposed system will play an essential role in the safety driving system or driving monitoring system.

• Structural Engineering and Mechanics
• /
• v.57 no.4
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.123-129
• /
• 2016

In the manufacturing industry fields, thousands of quality characteristics are measured in a day because the systems of process have been automated through the development of computer and improvement of techniques. Also, the process has been monitored in database in real time. Particularly, the data in the design step of the process have contributed to the product that customers have required through getting useful information from the data and reflecting them to the design of product. In this study, first, characteristics and variables affecting to them in the data of the design step of the process were analyzed by decision tree to find out the relation between explanatory and target variables. Second, the tolerance of continuous variables influencing on the target variable primarily was shown by the application of algorithm of decision tree, C4.5. Finally, the target variable, loss, was calculated by a loss function of Taguchi and analyzed. In this paper, the general method that the value of continuous explanatory variables has been used intactly not to be transformed to the discrete value and new method that the value of continuous explanatory variables was divided into 3 categories were compared. As a result, first, the tolerance obtained from the new method was more effective in decreasing the target variable, loss, than general method. In addition, the tolerance levels for the continuous explanatory variables to be chosen of the major variables were calculated. In further research, a systematic method using decision tree of data mining needs to be developed in order to categorize continuous variables under various scenarios of loss function.