• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4527-4548
• /
• 2017

This paper proposes a method to generate panoramic images by combining conventional feature extraction algorithms (e.g., SIFT, SURF, MPEG-7 CDVS) with sensed data from inertia sensors to enhance the stitching results. The challenge of image stitching increases when the images are taken from two different mobile phones with no posture calibration. Using inertia sensor data obtained by the mobile phone, images with different yaw, pitch, and roll angles are preprocessed and adjusted before performing stitching process. Performance of stitching (e.g., feature extraction time, inlier point numbers, stitching accuracy) between conventional feature extraction algorithms is reported along with the stitching performance with/without using the inertia sensor data. In addition, the stitching accuracy of video data was improved using the same sensed data, with discrete calculation of homograph matrix. The experimental results for stitching accuracies and speed using sensed data are presented in this paper.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1639-1658
• /
• 2019

Named entity recognition (NER) is an important technique for improving the performance of data mining and big data analytics. In previous studies, NER systems have been employed to identify named-entities using statistical methods based on prior information or linguistic features; however, such methods are limited in that they are unable to recognize unregistered or unlearned objects. In this paper, a method is proposed to extract objects, such as technologies, theories, or person names, by analyzing the collocation relationship between certain words that simultaneously appear around specific words in the abstracts of academic journals. The method is executed as follows. First, the data is preprocessed using data cleaning and sentence detection to separate the text into single sentences. Then, part-of-speech (POS) tagging is applied to the individual sentences. After this, the appearance and collocation information of the other POS tags is analyzed, excluding the entity candidates, such as nouns. Finally, an entity recognition model is created based on analyzing and classifying the information in the sentences.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• Journal of Biosystems Engineering
• /
• v.33 no.1
• /
• pp.63-68
• /
• 2008

This study was carried out to find a useful method to predict hardness of tomato using optical spectrum data. Optical spectrum of reflectance and transmittance data were collected processed by 9 kind of preprocessing methods-normalizations of mean, maximum and range, SNV (standard normal variate), MSC (multiplicative scatter correction), the first derivative and second derivative of Savitzky-Golay and Norris-Gap. With the preprocessed and non-processed original spectrum data, prediction models of hardness of tomato were developed using analytical tools of PLS (partial least squares) and MLR (multiple linear regression) and tested for their validation. The test of validation resulted that the analytical tools of PLS and MLR output similar performances while the transmittance spectra showed much better result than the reflectance spectra.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.31-43
• /
• 2023

In this paper, we propose a method for generating a global path for an unmanned vehicle using public data of road section information. First, the method of analyzing road section information of the Ministry of Land, Infrastructure and Transport is presented. Second, we propose a method of preprocessing the acquired road section information and processing it into meaningful data that can be used for global routes. Third, we present a method for generating a global path using the preprocessed road section information. The proposed method has proven its effectiveness through actual autonomous driving experiments of unmanned ground vehicles.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.111-114
• /
• 2018

Traffic accident analysis is important to reduce the occurrence of the accidents. In this paper, we analyze the traffic accident with Apriori algorithm to find out an association rule of traffic accident in Korea. We first design the traffic accident analysis model, and then collect the traffic accidents data. We preprocessed the collected data and derived some new variables and attributes for analyzing. Next, we analyze based on statistical method and Apriori algorithm. The result shows that many large-scale accident has occurred by vans in daytime. Medium-scale accident has occurred more in day than nighttime, and by cars more than vans. Small-scale accident has occurred more in night time than day time, however, the numbers were similar. Also, car-human accident is more occurred than car-car accident in small-scale accident.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.712-720
• /
• 2011

Radio frequency identification (RFID) is an established technology and has the potential, in a variety of applications, to significantly reduce cost and improve performance. As RFID-enabled applications will fulfill similar tasks across a range of processes adapted to use the data gained from RFID tags, they can be considered as software products derived from a common infrastructure and assets that capture specific ions in the domain. This paper discusses a framework that supports the development of RFID-enabled applications based on a business process family model (BPFM), explicitly representing both commonalities and variabilities. To develop this framework, common activities are identified from RFID-enabled applications and the variabilities in the common activities are analyzed in detail using variation point concepts. Through this framework, RFID data is preprocessed, and thus, RFID-enabled applications can be developed without having to process RFID data. Sharing a common model and reusing assets to deploy recurrent services may be considered an advantage in terms of economic significance and the overall product quality afforded.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.261-270
• /
• 1999

Sintering transforms powdered ore into lumped ore so that the latter can be used in a blast furnace. The powdered ore combined with coke and other materials is loaded into a container and moved along by a pallet while the ignited coke bums. The speed by which the pallet moves determines how much sintering takes place. Since the process is complicated and lacks an accurate mathematical model, human operators manually control the speed by monitoring various factors in the plant. In this paper, we propose a neural network-based pallet speed controller which copies human operator knowledge. Actual process data were collected from a sintering plant fer eight months and preprocessed to remove noisy and inconsistent data. A multilayer perceptron was trained using a back-propagation learning algorithm. In on-line testing at the sinter plant, the proposed model reliably controlled pallet speed during normal operation without the help of human operators. Moreover, the duality and productivity was as good as with human operators.

• Bulletin of the Korean Space Science Society
• /
• 2009.10a
• /
• pp.48.3-49
• /
• 2009

The purpose of this paper is to introduce the KOMPSAT-2 Direct Receiving and Processing System, hereafter DRS, located in Svalbard, Tromso and Toulouse. The KOMPSAT-2 from KOMPSAT-2 satellite and generating preprocessed image data that is a kind of raw image data for standard image production. The products generate from this system are comprised of 1R and 1G product upon having a geographic coordinates. In the following paragraph, it is described that DRS configuration, data processing procedure and product characteristics and then, the value-added image production test such orthoimage is introduced.