• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.81-87
• /
• 2023

Intrusion detection systems that learn metadata of network packets have been proposed recently. However these approaches require time to analyze packets to generate metadata for model learning, and time to pre-process metadata before learning. In addition, models that have learned specific metadata cannot detect intrusion by using original packets flowing into the network as they are. To address the problem, this paper propose a natural language processing-based intrusion detection system that detects intrusions by learning the packet payload as a single sentence without an additional conversion process. To verify the performance of our approach, we utilized the UNSW-NB15 and Transformer models. First, the PCAP files of the dataset were labeled, and then two Transformer (BERT, DistilBERT) models were trained directly in the form of sentences to analyze the detection performance. The experimental results showed that the binary classification accuracy was 99.03% and 99.05%, respectively, which is similar or superior to the detection performance of the techniques proposed in previous studies. Multi-class classification showed better performance with 86.63% and 86.36%, respectively.

• Journal of The Korean Association For Science Education
• /
• v.17 no.1
• /
• pp.11-19
• /
• 1997

Students' protocols obtained from think-aloud interviews were analyzed in the aspects of the success at first two problem-solving stages (understanding and planning), the time to complete a problem, the time at each problem-solving stage, the number of transition, and the transition rate. These were compared in the aspects of the context of problem, the success in solving problem, students' logical reasoning ability, spatial ability, and learning approach. The results were as follows:1. Students tended to spend more time in everyday contexts than in scientific contexts, especially at the stages of understanding and reviewing. The transition rate during solving a problem in everyday contexts was greater than that in scientific contexts. 2. Unsuccessful students spent more time at the stage of understanding, but successful students spent more time at the stage of planning. 3. Students' logical reasoning ability, as measured with the Group Assessment of Logical Thinking, was significantly correlated with the success in solving problem. Concrete-operational students spent more time in completing a problem, especially understanding the problem. 4. Students' spatial ability, as measured with the Purdue Visualization of Rotations Test and the Find A Shape Puzzle, was significantly correlated with their abilities to understand a problem and to plan for its solution. 5. Students' learning approach, as measured with the Questionnaire on Approaches to Learning and Studying, was not significantly correlated with the success in solving problem. However, the students in deep approach had more transitions and greater transition rates than the students in surface approach.

• Journal of Science Education
• /
• v.43 no.3
• /
• pp.318-328
• /
• 2019

The purpose of this study is to investigate the teacher-students interactions shown in the images of elementary science class by preservice teachers. We applied nine analysis criteria in three domains such as emotional support (climate, regard for student perspectives, teacher sensitivity), classroom organization (instructional learning formats, behavior management, productivity), and instructional support (quality of feedback, language modeling, concept development) in the aspects of positive or negative interactions The results show that majority of student-teachers tended to prefer positive interactions especially regarding instructional learning formats or concept development. For the image of avoided class, they tended to show negative interactions related to instructional learning formats or regard for student perspectives. However, they showed extremely lower frequencies for some categories of negative interactions. Female preservice teachers tended to have slightly higher frequencies for some positive interactions than their counterpart. The findings indicate possible approaches to teachers' professional development and further research.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.631-636
• /
• 2019

Over the last decade, many researchers have investigated a number of vision-based construction object detection algorithms for the purpose of construction site monitoring. However, previous methods require the ground truth labeling, which is a process of manually marking types and locations of target objects from training image data, and thus a large amount of time and effort is being wasted. To address this drawback, this paper proposes a vision-based construction object detection framework that employs an active learning technique while reducing manual labeling efforts. For the validation, the research team performed experiments using an open construction benchmark dataset. The results showed that the method was able to successfully detect construction objects that have various visual characteristics, and also indicated that it is possible to develop the high performance of an object detection model using smaller amount of training data and less iterative training steps compared to the previous approaches. The findings of this study can be used to reduce the manual labeling processes and minimize the time and costs required to build a training database.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Information Systems Review
• /
• v.25 no.2
• /
• pp.57-76
• /
• 2023

This study classifies the success of creators and YouTubers who have created channels on YouTube recently, which is the most influential digital platform. Based on the actual information disclosure of YouTubers who are in the field of science and technology category, video upload cycle, video length, number of selectable multilingual subtitles, and information from other social network channels that are being operated, the success of YouTubers using machine learning was classified and analyzed, which is the closest to the YouTube revenue structure. Our findings showed that neural network algorithm provided the best performance to predict the success or failure of YouTubers. In addition, our five factors contributed to improve the performance of the classification. This study has implications in suggesting various approaches to new individual entrepreneurs who want to start YouTube, influencers who are currently operating YouTube, and companies who want to utilize these digital platforms. We discuss the future direction of utilizing digital platforms.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.513-524
• /
• 2011

Digital Technology actively utilized in all spheres by rapid changes in information and knowledge demands transformations not only in the sociocultural and educational spheres but also specifically in the field of arts education. Digital Technology becomes a challenging factor for the field of arts education. In this study purposed a new teaching-learning approach method in arts education, called "Music Technology-Based Learning"(hereafter, MTBL), which is to, first, take interdisciplinary approaches combining various subjects in the field of arts education. In the case study was conducted to examine the educational effects of the MTBL approach to the liberal arts course in university: mind maps derived from 2 sessions (pre-class and post-class), evaluation sheets regarding self-directed learning and in-depth interviews with ten voluntary learners after the class were used as methods for data collection. The result of case study shows positive changes in the terms of the degrees of emotional sensibilities of the learners. Moreover, the research confirmed the potential of MTBL as a new teaching and learning methodology in art education.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.77-97
• /
• 2017

A recent sharp increase of the biomedical literature causes researchers to struggle to grasp the current research trends and conduct creative studies based on the previous results. In order to alleviate their difficulties in keeping up with the latest scholarly trends, numerous attempts have been made to develop specialized analytic services that can provide direct, intuitive and formalized scholarly information by using various text mining technologies such as information extraction and event detection. This paper introduces and evaluates total 8 Convolutional Neural Network (CNN) models for extracting biomedical events from academic abstracts by applying various feature utilization approaches. Also, this paper conducts performance comparison evaluation for the proposed models. As a result of the comparison, we confirmed that the Entity-Type-Fully-Connected model, one of the introduced models in the paper, showed the most promising performance (72.09% in F-score) in the event classification task while it achieved a relatively low but comparable result (21.81%) in the entire event extraction process due to the imbalance problem of the training collections and event identify model's low performance.

• Journal of the Korea Convergence Society
• /
• v.10 no.8
• /
• pp.59-65
• /
• 2019

There are various subtypes of cells in cancer tissues, but it is hard to confirm their composition experimentally. Here, we estimated the cell composition of each sample from gene expression data by using statistical machine learning approaches, two different regression models and investigated whether the cell composition was different between cancer and normal tissue. As a result, we found that CD8 T cell and Neutrophil were increased in oral cancer tissues compared to normal tissues. In addition, we applied t-SNE, which is one of the unsupervised learning, to verify whether normal tissue and oral cancer tissue can be clustered by the derived cell composition. Moreover, we showed that it is possible to predict oral cancer and normal tissue by several supervised classification algorithms. The study would help to improve the understanding of the immune cell infiltration at oral cancer.