• Journal of Advanced Navigation Technology
• /
• v.22 no.3
• /
• pp.213-219
• /
• 2018

In this paper, we propose a design method and process for hardware and software of hybrid V2X communication module that supports both C-ITS communication protocol designed for vehicle environment and Legacy LTE communication technology. C-ITS is suitable for safety service applications due to its low latency characteristics, and Legacy LTE is a technology suitable for non-safety applications such as traffic information and infotainment due to high latency and high capacity. The hybrid V2X communication module supports multiple communication technologies of WAVE and LTE, in which WAVE supports multiple channels, so that it is designed to transmit road information such as LDM and positioning correction information to an autonomous vehicle in real time. The main design results presented in this paper will be applied to the implementation of future hybrid V2X communication terminals for vehicles.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.2
• /
• pp.53-60
• /
• 2020

Sentiment analysis is the automated process of understanding attitudes and opinions about a given topic from written or spoken text. One of the sentiment analysis approaches is a dictionary-based approach, in which a sentiment dictionary plays an much important role. In this paper, we propose a method to automatically generate Korean sentiment lexicon from the well-known English sentiment lexicon called VADER (Valence Aware Dictionary and sEntiment Reasoner). The proposed method consists of three steps. The first step is to build a Korean-English bilingual lexicon using a Korean-English parallel corpus. The bilingual lexicon is a set of pairs between VADER sentiment words and Korean morphemes as candidates of Korean sentiment words. The second step is to construct a bilingual words graph using the bilingual lexicon. The third step is to run the label propagation algorithm throughout the bilingual graph. Finally a new Korean sentiment lexicon is generated by repeatedly applying the propagation algorithm until the values of all vertices converge. Empirically, the dictionary-based sentiment classifier using the Korean sentiment lexicon outperforms machine learning-based approaches on the KMU sentiment corpus and the Naver sentiment corpus. In the future, we will apply the proposed approach to generate multilingual sentiment lexica.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• Journal of Veterinary Clinics
• /
• v.30 no.4
• /
• pp.268-272
• /
• 2013

The purpose of this study was to assess the effects of reconstruction kernel, and slice thickness on the accuracy of spiral CT-based volume assessment over a range of object sizes typical of synthetic simulated tumor. Spiral CT scanning was performed at various reconstruction kernels (soft tissue, standard, bone), and slice thickness (1, 2, 3 mm) using a phantom made of gelatin and 10 synthetic simulated tumors of different sizes (diameter 3.0-12.0 mm). Three-dimensional volume assessments were obtained using an automated software tool. Results were compared with the reference volume by calculating the percentage error. Statistical analysis was performed using ANOVA and setting statistical significance at P < 0.05. In general, smaller slice thickness and larger sphere diameters produced more accurate volume assessment than larger slice thickness and smaller sphere diameter. The measured volumes were larger than the actual volumes by a common factor depending on slice thickness; in 100HU simulated tumors that had statistically significant, 1 mm slice thickness produced on average 27.41%, 2 mm slice thickness produced 45.61%, 3 mm slice thickness produced 93.36% overestimates of volume. However, there was no statistically significant difference in volume error for spiral CT scans taken with techniques where only reconstruction kernel was changed. These results supported that synthetic simulated tumor size, slice thickness were significant parameters in determining volume measurement errors. For an accurate volumetric measurement of an object, it is critical to select an appropriate slice thickness and to consider the size of an object.

• Journal of radiological science and technology
• /
• v.30 no.3
• /
• pp.281-287
• /
• 2007

Contrast media may cause tissue injury by extravasation during intravenous automated injection during CT examination. Here, we present a study in which contrast media extravasation was detected and localized in the neck and thorax by three-dimensional(3D) CT data reformation. The CT studies of the extavasation site were performed using a 3D software program with four different display techniques axial, multi planar reformation(MPR), maximum intensity projection(MIP), and volume rendering displays are currently available for reconstructing MDCT data. 3D image reconstructions provide accurate views of high-resolution imaging. This paper introduces extravasation with the MDCT and 3D reformation findings of contrast media extravasation in neck ant thorax. The followed injection of the external jugular vein into an existing intravenous catheter and a large volume of extravasation was demonstrated on by 3D MDCT.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.1
• /
• pp.60-67
• /
• 2014

In this study, an automated cable non-destructive testing(NDT) system was developed to monitor the steel cables that are a core component of cable-stayed bridges. The magnetic flux leakage(MFL) method, which is suitable for ferromagnetic continuum structures and has been verified in previous studies, was applied to the cable inspection. A multi-channel MFL sensor head was fabricated using hall sensors and permanent magnets. A wheel-based cable climbing robot was fabricated to improve the accessibility to the cables, and operating software was developed to monitor the MFL-based NDT research and control the climbing robot. Remote data transmission and robot control were realized by applying wireless LAN communication. Finally, the developed element techniques were integrated into an MFL-based cable NDT system, and the field applicability of this system was verified through a field test at Seohae Bridge, which is a typical cable-stayed bridge currently in operation.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.886-895
• /
• 2006

Fingerprint classification reduces the number of matches required in automated fingerprint identification systems by categorizing fingerprints into a predefined class. Support vector machines (SVMs), widely used in pattern classification, have produced a high accuracy rate when performing fingerprint classification. In order to effectively apply SVMs to multi-class fingerprint classification systems, we propose a novel method in which SVMs are generated with the one-vs-all (OVA) scheme and dynamically ordered with $na{\ddot{i}}ve$ Bayes classifiers. More specifically, it uses representative fingerprint features such as the FingerCode, singularities and pseudo ridges to train the OVA SVMs and $na{\ddot{i}}ve$ Bayes classifiers. The proposed method has been validated on the NIST-4 database and produced a classification accuracy of 90.8% for 5-class classification. Especially, it has effectively managed tie problems usually occurred in applying OVA SVMs to multi-class classification.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.196-203
• /
• 2016

Due to the limitations of budget, resources, and time invested in a project, software requirements should be prioritized and be implemented in order of importance. Existing approaches to prioritizing requirements mostly depend on human decisions. The manual prioritization process is based on intensive interactions with the stakeholders, thus raising the issues of scalability and biased prioritization. To solve these problems, we propose a fully automated requirements prioritization approach, ToMSN (Topic Modeling Stakeholder Needs for requirements prioritization), by topic modeling the stakeholder needs-artifacts earned in the requirements elicitation phase. The requirements dataset of a 30,000-user system was utilized for the performance evaluation. ToMSN showed competitive prioritizing accuracy with existing approaches without human aids, therefore solving scalability and biased prioritization issues.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1136-1146
• /
• 2005

Fingerprint classification is useful in an automated fingerprint identification system (AFIS) to reduce the matching time by categorizing fingerprints. Based on Henry system that classifies fingerprints into S classes, various techniques such as neural networks and support vector machines (SVMs) have been widely used to classify fingerprints. Especially, SVMs of high classification performance have been actively investigated. Since the SVM is binary classifier, we propose a novel classifier-combination model, multiple decision templates (MuDTs), to classily fingerprints. The method extracts several clusters of different characteristics from samples of a class and constructs a suitable combination model to overcome the restriction of the single model, which may be subject to the ambiguous images. With the experimental results of the proposed on the FingerCodes extracted from NIST Database4 for the five-class and four-class problems, we have achieved a classification accuracy of $90.4\%\;and\;94.9\%\;with\;1.8\%$ rejection, respectively.

• International Journal of Advanced Culture Technology
• /
• v.3 no.1
• /
• pp.1-12
• /
• 2015

The current scenario of the transportation sector reflects the urgent need to address issues such as depletion of traditional fuel reserves and ever growing pollution levels. Researchers around the world are focussing on alternatives as well as optimisation of currently employed devices to reduce the pollution levels generated by the commonly used fuels. One such optimisation involves the study of air flow within the intake manifolds of SI engines. It is a well-known fact that alterations in the air manifolds of engines have a significant impact on the engine performance parameters, fuel consumption and emission levels. Previous works have demonstrated the impacts of runner lengths, diameter, plenum volume, taper angle of distribution manifolds and other factors on in-cylinder fluid motion and engine performance. However, a static setup provides an optimal configuration only at a specific engine speed. This paper aims to investigate the variations in the same parameters on a four stroke, naturally aspirated single cylinder SI engine through varying the cross section design over the intake runner with the aid of Computational Fluid Dynamics. The system consists of segments that form the intake runner with projections on the inside that allow various permutations of the intake runner segments. The various configurations provide the optimised fluid flow characteristics within the intake manifold at specific engine speed intervals. The variations such as turbulence, air fuel mixing are analysed using the three dimensional CFD software FLUENT. The results can be used further for developing an automated or manually adjustable intake manifold.