• Journal of Korean Society of Transportation
• /
• v.34 no.2
• /
• pp.158-167
• /
• 2016

This study evaluates potential sources of errors in k-NN(k-nearest neighbor) algorithm such as procedures, variables, and input data. Previous research has been thoroughly reviewed for understanding fundamentals of k-NN algorithm that has been widely used for short-term traffic states prediction. The framework of this algorithm commonly includes historical data smoothing, pattern database, similarity measure, k-value, and prediction horizon. The outcomes of this study suggests that: i) historical data smoothing is recommended to reduce random noise of measured traffic data; ii) the historical database should contain traffic state information on both normal and event conditions; and iii) trial and error method can improve the prediction accuracy by better searching for the optimum input time series and k-value. The study results also demonstrates that predicted error increases with the duration of prediction horizon and rapidly changing traffic states.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.3
• /
• pp.123-129
• /
• 2009

Ubiquitous home is emerging as the future digital home environments that provide various ubiquitous home services like u-Life, u-Health, etc. It is composed of some home appliances and sensors which are connected through wired/wireless network. Ubiquitous home services become aware of user's context with the information gathered from sensors and make home appliances adapt to the current home situation for maximizing user convenience. In these context-aware home environments, it is the one of significant research topics to predict user behaviors in order to proactively control the home environment. In this paper, we propose Multi-Level prediction algorithm for context-aware services in ubiquitous home environment. The algorithm has two phases, prediction and execution. In the first prediction phase, the next location of user is predicted using tree algorithm with information on users, time, location, devices. In the second execution phase, our table matching method decides home appliances to run according to the prediction, device's location, and user requirement. Since usually home appliances operate together rather than separately, our approach introduces the concept of mode service, so that it is possible to control multiple devices as well as a single one. We also devised some scenarios for the conceptual verification and validated our algorithm through simulations.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.4
• /
• pp.295-303
• /
• 2018

The stereo camera system has a fixed baseline and therefore has a constant scale. However, it is difficult to measure the actual three-dimensional coordinate since the scale is not fixed when relative orientation parameters are determined through the key-point matching in the stereo image each time. Therefore, the purpose of this study was to perform the stereo camera calibration that simultaneously determines the internal characteristics of the left and right cameras and the camera relationship between them using the modified collinearity equation and compared it with the two independent single cameras calibration. In the experiment using the images taken at close range, the RMSE (Root Mean Square Error) of ${\pm}0.014m$ was occurred when the three dimensional distances were compared in the single calibration results. On the other hand, the accuracy of the three-dimensional distance of the stereo camera calibration was better because the stereo camera results were almost no error compared to the results from two single cameras. In the comparison of the epipolar images, the RMSE of the stereo camera was 0.3 pixel more than that of the two single cameras, but the effect was not significant.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.141-148
• /
• 2004

The ground positions and elevations information called DEMs(Digital Elevation Models) which are extracted from the stereo aerial photographs and/or satellite images using image matching method have the natural errors caused by variant environments. This study suggests the method to evaluate DEMs using correlation values between the reference and the target DEMs. This would be strongly helpful for experts to correct these errors. To evaluate the whole area of DEMs in the horizontal and vertical errors, the target cell is matched for each reference cell using the correlation values of these two cells. When the target cell is matched for each reference cell, horizontal and vertical error was calculated so as to help experts to recognize a certain area of DEMs which should be corrected and edited. If the correlation value is low and tile difference in height is high, the target cell will be candidated as changed or corrupted cell. When the area is clustered with those candidated cells, that area will be regarded as changed or corrupted area to be corrected and edited. Using this method, the evaluation for all DEM cells is practicable, the horizontal errors as well as vertical errors is calculable and the changed or corrupted area can be detected more efficiently.

• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.151-159
• /
• 2010

This paper presents a research result that was performed to develop a more accurate freeway crash prediction model than existing models. While the existing crash models only focus on developing crash relationships associated with highway geometric conditions found on a short section of a crash site, this research applies a different approach considering the upstream highway geometric conditions as well. Theoretically, crashes occur while motorists are in motion, and particularly at freeways vehicle speed at one specific point is very sensitive to upstream geometric conditions. Therefore, this is a reasonable approach. To form the analysis data base, this research gathers the geometric conditions of the West Seaside Freeway 269.3 km and six years crash data ranging 2003-2008 for these freeway sections. As a result, it is found that crashes fit well into Negative Binomial Distribution, and, based on the developed model, total number of crashes is inversely proportional to highway curve length and radius. Contrarily, crash occurrences are proportional to tangent length. This result is different from existing crash study results, and it seems to be resulted from this research assumption that a crash is influenced greatly by upstream geometric conditions. Also, this research provides the expected effects on crash occurrences of the length of downgrade sections, speed camera placements, and the on- and off- ramp presences. It is expected that this research result is useful for doing more reasonable highway designs and safety audit analysis, and applying the same research approach to national roads and other major roads in urban areas is recommended.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.143-151
• /
• 2010

Fingerprint classification is a step to increase the efficiency of an 1:N fingerprint recognition system and plays a role to reduce the matching time of fingerprint and to increase accuracy of recognition. It is difficult to classify fingerprints, because the ridge pattern of each fingerprint class has an overlapping characteristic with more than one class, fingerprint images may include a lot of noise and an input condition is an exceptional case. In this paper, we propose a novel approach to design a stochastic model and to accomplish fingerprint classification using a directional characteristic of fingerprints for an effective classification of various qualities. We compute the directional value by searching a fingerprint ridge pixel by pixel and extract a directional characteristic by merging a computed directional value by fixed pixels unit. The modified Markov model of each fingerprint class is generated using Markov model which is a stochastic information extraction and a recognition method by extracted directional characteristic. The weight list of classification model of each class is decided by analyzing the state transition matrixes of the generated Markov model of each class and the optimized value which improves the performance of fingerprint classification using GA (Genetic Algorithm) is estimated. The performance of the optimized classification model by GA is superior to the model before the optimization by the experiment result of applying the fingerprint database of various qualities to the optimized model by GA. And the proposed method effectively achieved fingerprint classification to exceptional input conditions because this approach is independent of the existence and nonexistence of singular points by the result of analyzing the fingerprint database which is used to the experiments.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.577-587
• /
• 2023

The utilization of crowdsourced spatial data has been actively researched; however, issues stemming from the uncertainty of data quality have been raised. In particular, when low-quality data is mixed into drone imagery datasets, it can degrade the quality of spatial information output. In order to address these problems, the study presents a methodology for automatically validating the geometric quality of crowdsourced imagery. Key quality factors such as spatial resolution, resolution variation, matching point reprojection error, and bundle adjustment results are utilized. To classify imagery suitable for spatial information generation, training and validation datasets are constructed, and machine learning is conducted using a radial basis function (RBF)-based support vector machine (SVM) model. The trained SVM model achieved a classification accuracy of 99.1%. To evaluate the effectiveness of the quality validation model, imagery sets before and after applying the model to drone imagery not used in training and validation are compared by generating orthoimages. The results confirm that the application of the quality validation model reduces various distortions that can be included in orthoimages and enhances object identifiability. The proposed quality validation methodology is expected to increase the utility of crowdsourced data in spatial information generation by automatically selecting high-quality data from the multitude of crowdsourced data with varying qualities.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.1
• /
• pp.225-236
• /
• 2023

Policy implications were derived by comparing/analyzing innovative SMEs and general SMEs that obtained innovation certification from 2015 to 2021 in terms of survival period. Work experience, scale (employment, capital and debt size, sales and operating profit) Korean standard industry classification (2 digit) was used to select general SMEs similar to innovative SMEs. Survival period was calculated by defining suspension, closure and overdue equivalent to default as events. As a result of the survival analysis, innovative SMEs showed a 9.8% reduction in the risk of delinquency compared to general SMEs, indicating that the survival period of innovative SMEs was significantly longer. In addition, it was found that the work experience and size (employment, capital) of SMEs had a positive effect on the survival period, but debt had a negative effect on the survival period. This means that the innovation certification system centered on innovation capabilities and future growth potential is a significant indicator in terms of survival period. As a result, it was concluded that the benefits and support policies provided by the innovation certification system need to be more systematic and sophisticated by reflecting the work experience and industry for the actual growth and survival of SMEs.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.4
• /
• pp.101-114
• /
• 2022

Recently, various studies on the entrepreneurial ecosystem have been conducted. The entrepreneurial ecosystem is composed of various elements such as entrepreneurs, governments, and infrastructure, and these factors interact to contribute to economic development. The purpose of this study was to analyze differences in importance and performance of the entrepreneurial ecosystem for startups using the importance-performance analysis (IPA) method. Based on this, the importance and current level of the components of the entrepreneurial ecosystem were identified and policy implications were presented. The results of the study are as follows. The importance ranking was in the order of startup support program(4.43), startup funding (4.39), market accessibility(4.30). The ranking of performance was startup support program(3.81), ease of starting a business(3.76), support for startup support institutions(3.66), and startup funding(3.66). All elements of the entrepreneurial ecosystem showed higher importance than performance. This means that the components of the entrepreneurial ecosystem in Korea are recognized as important, but do not play a significant role in terms of performance for startups. In addition, the factors with the highest improvement in the importance-performance matrix were 「safety nets for startup failure」, 「culture of acceptance of failure」, 「ease of market entry」, 「ease of startup survival」, and 「ease of exit」. This study suggested improvement measures such as establishing a social safety net, improving awareness of startup failure culture, matching successful startups, strengthening scale-up support by growth stage, easing regulations in new business fields, and diversifying investment recovery strategies.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.6
• /
• pp.147-157
• /
• 2023

This paper investigates the financial factors affecting angel investors' investment decisions for 818 firms from 2009 to 2018 in the Korean venture investment market. We construct a quasi-experimental design using propensity scoring matching and compare the investment determinants between investment firms and matching firms. The main empirical findings are as follows. First, we find that angel investors are more likely to choose firms based on a firm's growth such as profit and assets rather than profitability or financial stability. In addition, we identify that they prefer the firm not only higher intangible assets but also higher R&D expenditures. Second, we find that angel investors consider both growth and activity ratios in the firms for over three years and have entered the mid-stage of startups. Overall, we confirm that the investment decision of angel investors mainly focuses on the venture startups' growth trend or future growth potential rather than the realized profitability or financial stability. We also infer that the possibility of performance creation is an important investment factor along with growth for the mid-stage startup.