• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.

• Journal of Life Science
• /
• v.31 no.11
• /
• pp.1028-1036
• /
• 2021

Firefly luciferase (FLuc) can function as an efficient marker in the gene and viral therapies. Nonetheless, its clinical translation has been unaccomplished with the concerns on its exogenous nature and the similarity with human fatty acyl-CoA synthetase. In this study, we aimed to show safety of FLuc by conducting a set of preclinical experiments and a human use. Initially, FLuc permeability across the plasma membrane was investigated by delivering the FLuc-carrying viral vector, OTS-412, or the FLuc recombinant protein. After in vitro infection of OTS-412 into different cancer cell lines, FLuc activity was detected only in the cell lysates, but not in culture media. In addition, recombinant FLuc protein further showed the impermeability against the plasma membrane. Similar result was also observed in the in vivo experiment. After being injected into the VX2 tumor-bearing rabbit, the FLuc exclusively resided within the tumor tissue without being detected in the blood plasma or other organs. Human cancer cell lines originated from various organs were lysed and treated to the FLuc, and none of the human substrates was reactive against the FLuc. As a final step, FLuc recombinant protein was intravenously injected into a human. The luciferase was degraded with the half-life of 20 to 30 minutes in blood, and was untraceable from 1.5 hr after the injection. In addition, the blood plasma was nonresponsive against the fatty acids. Hematological analysis was also comparable between the pre- and post-injection. Altogether, our study collectively demonstrates the safety of the firefly luciferase.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

• Journal of Life Science
• /
• v.32 no.4
• /
• pp.271-278
• /
• 2022

The detailed mechanism by which cancer upregulated gene 2 (CUG2) overexpression induces cancer stem cell-like phenotypes is not fully understood. The downregulation of FBXW7 E3 ligase, a tumor suppressor known for its proteolytic regulation of oncogenic proteins such as cyclin E, c-Myc, Notch, and Yap1, has been frequently reported in several types of tumor tissues, including those in the large intestine, cervix, and stomach. Therefore, we investigated whether FBXW7 is involved in CUG2-induced oncogenesis. In this study, the decreased expression of FBXW7 was examined in human lung adenocarcinoma A549 (A549-CUG2) and human bronchial BEAS-2B cells (BEAS-CUG2) overexpressing CUG2 and compared with control cells stably expressing an empty vector (A549-Vec or BEAS-Vec). Treatment with MG132 (a proteosome inhibitor) prevented the degradation of FBXW7 and Yap1 proteins, which are substrates of the FBXW7 E3 ligase. To address the role of Fbxw7 in the development of cancer stem cell (CSC) phenotypes, we suppressed Fbxw7 protein levels using its siRNA. We observed that decreased levels of FBXW7 enhanced cell migration, invasion, and spheroid size and number in A549-Vec and BEAS-Vec cells. The enforced expression of FBXW7 produced the opposite results in A549-CUG2 and BEAS-CUG2 cells. Furthermore, the downregulation of FBXW7 elevated the activities of EGFR, Akt, and ERK1/2 and upregulated β-catenin, Yap1, and NEK2, while the enforced expression of FBXW7 generated the opposite results. We thus propose that FBXW7 downregulation induced by CUG2 confers CSC-like phenotypes through the upregulation of both the EGFR-ERK1/2 and β-catenin-Yap1-NEK2 signaling pathways.

• Economic and Environmental Geology
• /
• v.55 no.5
• /
• pp.551-561
• /
• 2022

Geophysical exploration methods are very useful for generating high-resolution images of underground structures, and such methods can be applied to investigation of buried cultural properties and for determining their exact locations. In this study, image feature extraction and image segmentation methods were applied to automatically distinguish the structures of buried relics from the high-resolution ground-penetrating radar (GPR) images obtained at the center of Silla Kingdom, Gyeongju, South Korea. The major purpose for image feature extraction analyses is identifying the circular features from building remains and the linear features from ancient roads and fences. Feature extraction is implemented by applying the Canny edge detection and Hough transform algorithms. We applied the Hough transforms to the edge image resulted from the Canny algorithm in order to determine the locations the target features. However, the Hough transform requires different parameter settings for each survey sector. As for image segmentation, we applied the connected element labeling algorithm and object-based image analysis using Orfeo Toolbox (OTB) in QGIS. The connected components labeled image shows the signals associated with the target buried relics are effectively connected and labeled. However, we often find multiple labels are assigned to a single structure on the given GPR data. Object-based image analysis was conducted by using a Large-Scale Mean-Shift (LSMS) image segmentation. In this analysis, a vector layer containing pixel values for each segmented polygon was estimated first and then used to build a train-validation dataset by assigning the polygons to one class associated with the buried relics and another class for the background field. With the Random Forest Classifier, we find that the polygons on the LSMS image segmentation layer can be successfully classified into the polygons of the buried relics and those of the background. Thus, we propose that these automatic classification methods applied to the GPR images of buried cultural heritage in this study can be useful to obtain consistent analyses results for planning excavation processes.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.145-165
• /
• 2023

Recommendation system plays a significant role on relieving difficulties of selecting information among rapidly increasing amount of information caused by the development of the Internet and on efficiently displaying information that fits individual personal interest. In particular, without the help of recommendation system, E-commerce and OTT companies cannot overcome the long-tail phenomenon, a phenomenon in which only popular products are consumed, as the number of products and contents are rapidly increasing. Therefore, the research on recommendation systems is being actively conducted to overcome the phenomenon and to provide information or contents that are aligned with users' individual interests, in order to induce customers to consume various products or contents. Usually, collaborative filtering which utilizes users' historical behavioral data shows better performance than contents-based filtering which utilizes users' preferred contents. However, collaborative filtering can suffer from cold-start problem which occurs when there is lack of users' historical behavioral data. In this paper, hybrid music recommendation system, which can solve cold-start problem, is proposed based on the playlist data of Melon music streaming service that is given by Kakao Arena for music playlist continuation competition. The goal of this research is to use music tracks, that are included in the playlists, and metadata of music tracks and playlists in order to predict other music tracks when the half or whole of the tracks are masked. Therefore, two different recommendation procedures were conducted depending on the two different situations. When music tracks are included in the playlist, LightFM is used in order to utilize the music track list of the playlists and metadata of each music tracks. Then, the result of Item2Vec model, which uses vector embeddings of music tracks, tags and titles for recommendation, is combined with the result of LightFM model to create final recommendation list. When there are no music tracks available in the playlists but only playlists' tags and titles are available, recommendation was made by finding similar playlists based on playlists vectors which was made by the aggregation of FastText pre-trained embedding vectors of tags and titles of each playlists. As a result, not only cold-start problem can be resolved, but also achieved better performance than ALS, BPR and Item2Vec by using the metadata of both music tracks and playlists. In addition, it was found that the LightFM model, which uses only artist information as an item feature, shows the best performance compared to other LightFM models which use other item features of music tracks.

• Journal of Science Education
• /
• v.47 no.2
• /
• pp.180-191
• /
• 2023

The purpose of this study was to investigate the preferred SSI topics of students and teachers in elementary, middle, and high schools. It analyzed the similarity of students' and teachers' preferred SSI topics by school level using the cosine similarity measure. A total of 566 students and 327 teachers from elementary, middle, and high schools participated in the study. Sixty topics were identified and listed in the areas of environment, science and technology, health and medicine, and other social issues based on the literature and SSI programs. Students and teachers were asked to select five of their favorite topics. The data was collected online using SurveyMonkey. The collected data was divided into six groups of students and teachers, and the frequency of topic selection was analyzed within each group. The topic preference similarity was analyzed by calculating vector values based on the frequency of the selected topics and measuring the cosine similarity between students, teachers, and teachers and students by school level. The results are as follows: First, the cosine similarity of SSI Preferred Topics between students' school-level cohorts was higher between middle and high school students (0.982) than between elementary and middle school students (0.651) or between elementary and high school students (0.662). Second, the cosine similarity of SSI Preferred Topics between teachers' school-level cohorts was similar for all comparison groups between elementary, middle, and high school. Third, the SSI topic preference similarity between students and teachers by school level had a higher cosine similarity between the elementary student and teacher cohorts (0.974) than the other school level comparisons, middle school (0.621) or high school (0.645). Access to topics of interest to students in SSI education is strongly associated with motivation and persistence in learning, as well as an enjoyable learning experience and positive attitudes toward learning. Therefore, when designing SSI lessons, it is important to examine topics from the perspective of student interest, especially if the teacher has selected SSI topics that are different from students' preferences. Careful instructional design will be needed to overcome the gap.

• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.261-272
• /
• 2023

In recent years, natural disasters such as heavy rainfall and typhoons have occurred more frequently, and their severity has increased due to climate change. The Korea Meteorological Administration (KMA) currently uses the same criteria for all regions in Korea for watch and warning based on the maximum cumulative rainfall with durations of 3-hour and 12-hour to reduce damage. However, KMA's criteria do not consider the regional characteristics of damages caused by heavy rainfall and typhoon events. In this regard, it is necessary to develop new criteria considering regional characteristics of damage and cumulative rainfalls in durations, establishing four stages: blue, yellow, orange, and red. A classification model, called DSCM (Disaster Severity Classification Model), for the four-stage disaster severity was developed using four machine learning models (Decision Tree, Support Vector Machine, Random Forest, and XGBoost). This study applied DSCM to local governments of Seoul, Incheon, and Gyeonggi Province province. To develop DSCM, we used data on rainfall, cumulative rainfall, maximum rainfalls for durations of 3-hour and 12-hour, and antecedent rainfall as independent variables, and a 4-class damage scale for heavy rain damage and typhoon damage for each local government as dependent variables. As a result, the Decision Tree model had the highest accuracy with an F1-Score of 0.56. We believe that this developed DSCM can help identify disaster risk at each stage and contribute to reducing damage through efficient disaster management for local governments based on specific events.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.329-352
• /
• 2022

It is reported that particulate matter(PM) penetrates the lungs and blood vessels and causes various heart diseases and respiratory diseases such as lung cancer. The subway is a means of transportation used by an average of 10 million people a day, and although it is important to create a clean and comfortable environment, the level of particulate matter pollution is shown to be high. It is because the subways run through an underground tunnel and the particulate matter trapped in the tunnel moves to the underground station due to the train wind. The Ministry of Environment and the Seoul Metropolitan Government are making various efforts to reduce PM concentration by establishing measures to improve air quality at underground stations. The smart air quality management system is a system that manages air quality in advance by collecting air quality data, analyzing and predicting the PM concentration. The prediction model of the PM concentration is an important component of this system. Various studies on time series data prediction are being conducted, but in relation to the PM prediction in subway stations, it is limited to statistical or recurrent neural network-based deep learning model researches. Therefore, in this study, we propose four transformer-based models including spatiotemporal transformers. As a result of performing PM concentration prediction experiments in the waiting rooms of subway stations in Seoul, it was confirmed that the performance of the transformer-based models was superior to that of the existing ARIMA, LSTM, and Seq2Seq models. Among the transformer-based models, the performance of the spatiotemporal transformers was the best. The smart air quality management system operated through data-based prediction becomes more effective and energy efficient as the accuracy of PM prediction improves. The results of this study are expected to contribute to the efficient operation of the smart air quality management system.