• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.183-186
• /
• 2024

IoT(Internet of Things) 기기가 다양한 산업 분야에 활용되면서, 보안과 유지 보수를 위한 관리의 중요성이 커지고 있다. 편리한 IoT 기기 관리를 위해 무선 네트워크를 통한 펌웨어 업데이트 기술인 FOTA(Firmware Over The Air)가 적용되어 있지만, 컴퓨팅 파워가 제한된 경량 IoT 기기 특성상 취약점 탐지를 수행하기 어렵다. 본 연구에서는 IoT 기기들이 퍼징 테스트 케이스를 분할하여 협력적으로 퍼징하고, 노드 간의 퍼징 결과가 다르면 재검증을 수행하는 협력적 퍼징 기법을 제안한다. 실험 결과에 따르면, 중복되는 테스트 케이스를 2 개나 3 개 퍼징하는 협력적 퍼징 기법은 종래 방식 대비 연산량을 최소 약 16%, 최대 약 48% 줄였다. 또한, 종래 퍼징 기법 대비 취약점 탐지 성공률(Success rate of vulnerability detection)을 최소 약 3 배, 최대 약 3.4 배 개선시켰다.

• The Plant Pathology Journal
• /
• v.40 no.4
• /
• pp.337-345
• /
• 2024

Soybean (Glycine max L.) is one of the most widely planted and used legumes in the world, being used for food, animal feed products, and industrial production. The soybean mosaic virus (SMV) is the most prevalent virus infecting soybean plants. This study developed a diagnostic method for the rapid and sensitive detection of SMV using a reverse transcription-recombinase polymerase amplification (RT-RPA) technique combined with a lateral flow strip (LFS). The RT-RPA and RT-RPA-LFS conditions to detect the SMV were optimized using the selected primer set that amplified part of the VPg protein gene. The optimized reaction temperature for the RT-RPA primer and RT-RPA-LFS primer used in this study was 38℃ for both, and the minimum reaction time was 10 min and 5 min, respectively. The RT-RPA-LFS was as sensitive as RT-PCR to detect SMV with 10 pg/µl of total RNA. The reliability of the developed RT-RPA-LFS assay was evaluated using leaves collected from soybean fields. The RT-RPA-LFS diagnostic method developed in this study will be useful as a diagnostic method that can quickly and precisely detect SMV in the epidemiological investigation of SMV, in the selection process of SMV-resistant varieties, on local farms with limited resources.

• Clinical Endoscopy
• /
• v.55 no.2
• /
• pp.183-190
• /
• 2022

Colorectal cancer is an important cause of morbidity and mortality worldwide. Optical colonoscopy (OC) is widely accepted as the reference standard for the screening of colorectal polyps and cancers, and computed tomography colonography (CTC) is a valid alternative to OC. The purpose of this review was to assess the diagnostic accuracy of OC and CTC for colorectal lesions. A literature search was performed in PubMed, Embase, and Cochrane Library, and 18 articles were included. CTC has emerged in recent years as a potential screening examination with high accuracy for the detection of colorectal lesions. However, the clinical application of CTC as a screening technique is limited because it is highly dependent on the size of the lesions and has poor performance in detecting individual lesions <5 mm or flat lesions, which, although rarely, can have a malignant potential.

• Journal of the Korean Society of Visualization
• /
• v.22 no.2
• /
• pp.35-43
• /
• 2024

Microparticle separation has demonstrated significant potential for biological, chemical, and medical applications. We introduce a surface acoustic wave (SAW)-based microfluidic device for separation of elastic and rigid microspheres based on their property and size. By tuning the SAWs to match the resonant frequencies of certain microspheres, those particles could be selectively separated from the other microspheres. When microspheres are exposed to an acoustic field, they experience the SAW-induced acoustic radiation force (ARF), whose magnitude is dependent on the microparticle size and properties. We modeled the SAW-induced ARF based on elastic sphere theory and conducted a series of experiments to separate elastic and rigid microspheres. We further utilized the acoustofluidic method for the separation of Thalassiosira Eccentrica microalgae based on the differences in their sizes with purity exceeding 90%. We anticipate that our technique will open up new possibilities for sample preparation, detection, and diagnosis in various emerging biological and medical analyses.

• Journal of Wind Energy
• /
• v.13 no.3
• /
• pp.33-42
• /
• 2022

In this paper, a semi-supervised machine learning technique applied to actual field vibration data acquired from Jeju-do wind turbines for predictive diagnosis of abnormal conditions of offshore wind turbines is introduced. Semi-supervised machine learning, which combines un-supervised learning with supervised learning, can be used to perform anomaly detection in situations where sufficient fault data cannot be obtained. The signal processing results using the spectrogram of the original signal were shown, and external data were used to overcome the problem that disturbance reactions easily occurred due to the imbalance between the number of normal and abnormal data. Out of distribution (OOD), which uses external data, is a technology that is regarded as abnormal data that is unlikely to occur in reality, but we were able to use it by expanding it. By rearranging the distribution of data in this way, classification can be performed more robustly. Specifically, by observing the trends of the abnormal score and the change in the feature of the representation layer, continuous learning was performed through a mixture of existing and new data.

• Structural Monitoring and Maintenance
• /
• v.11 no.3
• /
• pp.203-217
• /
• 2024

Electro-mechanical impedance (EMI) technique is a low-cost structural damage detection method. It reflects structural damage through the change in admittance signal which contains the structural mechanical impedance information. The ambient temperature greatly affects the admittance signal, which hides the changes caused by structural damage and reduces the accuracy of damage identification. This study introduces a convolutional neural network to compensate for the temperature effect. The proposed method uses a framework that consists of a feature extraction network and a decoding network, and the original admittance signal with temperature information is used as the input. The output admittance signal is eliminated from the temperature effect, improving damage identification robustness. The admittance data simulated by the finite element model of the spatial grid structure is used to verify the effectiveness of the proposed method. The results show that the proposed method has advantages in identification accuracy compared with the damage index minimization method and the principal component analysis method.

• Journal of Web Engineering
• /
• v.21 no.2
• /
• pp.497-522
• /
• 2021

Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1065-1072
• /
• 2024

Previous approaches to 3D excavator pose estimation via synthetic data training utilized a single virtual excavator model, low polygon objects, relatively poor textures, and few background objects, which led to reduced accuracy when the resulting models were tested on differing excavator types and more complex backgrounds. To address these limitations, the authors present a realism-centric synthetization and labeling approach that synthesizes results with improved image quality, more detailed excavator models, additional excavator types, and complex background conditions. Additionally, the data generated includes dense pose labels and depth maps for the excavator models. Utilizing the realism-centric generation method, the authors achieved significantly greater image detail, excavator variety, and background complexity for potentially improved labeling accuracy. The dense pose labels, featuring fifty points instead of the conventional four to six, could allow inferences to be made from unclear excavator pose estimates. The synthesized depth maps could be utilized in a variety of DNN applications, including multi-modal data integration and object detection. Our next step involves training and testing DNN models that would quantify the degree of accuracy enhancement achieved by increased image quality, excavator diversity, and background complexity, helping lay the groundwork for broader application of synthetic models in construction robotics and automated project management.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.183-203
• /
• 2018

News articles are the most suitable medium for examining the events occurring at home and abroad. Especially, as the development of information and communication technology has brought various kinds of online news media, the news about the events occurring in society has increased greatly. So automatically summarizing key events from massive amounts of news data will help users to look at many of the events at a glance. In addition, if we build and provide an event network based on the relevance of events, it will be able to greatly help the reader in understanding the current events. In this study, we propose a method for extracting event networks from large news text data. To this end, we first collected Korean political and social articles from March 2016 to March 2017, and integrated the synonyms by leaving only meaningful words through preprocessing using NPMI and Word2Vec. Latent Dirichlet allocation (LDA) topic modeling was used to calculate the subject distribution by date and to find the peak of the subject distribution and to detect the event. A total of 32 topics were extracted from the topic modeling, and the point of occurrence of the event was deduced by looking at the point at which each subject distribution surged. As a result, a total of 85 events were detected, but the final 16 events were filtered and presented using the Gaussian smoothing technique. We also calculated the relevance score between events detected to construct the event network. Using the cosine coefficient between the co-occurred events, we calculated the relevance between the events and connected the events to construct the event network. Finally, we set up the event network by setting each event to each vertex and the relevance score between events to the vertices connecting the vertices. The event network constructed in our methods helped us to sort out major events in the political and social fields in Korea that occurred in the last one year in chronological order and at the same time identify which events are related to certain events. Our approach differs from existing event detection methods in that LDA topic modeling makes it possible to easily analyze large amounts of data and to identify the relevance of events that were difficult to detect in existing event detection. We applied various text mining techniques and Word2vec technique in the text preprocessing to improve the accuracy of the extraction of proper nouns and synthetic nouns, which have been difficult in analyzing existing Korean texts, can be found. In this study, the detection and network configuration techniques of the event have the following advantages in practical application. First, LDA topic modeling, which is unsupervised learning, can easily analyze subject and topic words and distribution from huge amount of data. Also, by using the date information of the collected news articles, it is possible to express the distribution by topic in a time series. Second, we can find out the connection of events in the form of present and summarized form by calculating relevance score and constructing event network by using simultaneous occurrence of topics that are difficult to grasp in existing event detection. It can be seen from the fact that the inter-event relevance-based event network proposed in this study was actually constructed in order of occurrence time. It is also possible to identify what happened as a starting point for a series of events through the event network. The limitation of this study is that the characteristics of LDA topic modeling have different results according to the initial parameters and the number of subjects, and the subject and event name of the analysis result should be given by the subjective judgment of the researcher. Also, since each topic is assumed to be exclusive and independent, it does not take into account the relevance between themes. Subsequent studies need to calculate the relevance between events that are not covered in this study or those that belong to the same subject.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.708-718
• /
• 2002

In this paper, the problems in identifying the noise sources by using the sound intensity technique are dealt with for the general radiated near-field from vibro-acoustic sources. For this purpose, a three-dimensional model structure resembling the engine room of a car or heavy equipment is considered. Similar to the practical situations, the model contains many mutually coherent and incoherent noise sources distributed on the complicated surfaces. The sources are located on the narrow, connected, reflecting planes constructed with rigid boxes, of which a small clearance exists between the whole box structure and the reflecting bottom. The acoustic boundary element method is employed to calculate the acoustic intensity at the near-field surfaces and interior spaces. The effects of relative source phases, frequencies, and locations are investigated, from which the results are illustrated by the contour map, vector plot, and energy streamlines. It is clearly observed that the application of sound intensity technique to the reactive or reverberant field, e.g., scanning over the upper engine room as is usually practiced, can yield the detection of fake sources. For the precise result for such a field, the field reactivity should be checked a priori and the proper effort should be directed to reduce or improve the reactivity of sound field.