• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.145-152
• /
• 2019

In this paper, we proposed a shaking image stabilization algorithm using deep learning. The proposed algorithm utilizes deep learning, unlike some 2D, 2.5D and 3D based stabilization techniques. The proposed algorithm is an algorithm that extracts and compares features of shaky images through CNN network structure and LSTM network structure, and transforms images in reverse order of movement size and direction of feature points through the difference of feature point between previous frame and current frame. The algorithm for stabilizing the shake is implemented by using CNN network and LSTM structure using Tensorflow for feature extraction and comparison of each frame. Image stabilization is implemented by using OpenCV open source. Experimental results show that the proposed algorithm can be used to stabilize the camera shake stability in the up, down, left, and right shaking images.

• The Journal of the Korean dental association
• /
• v.57 no.3
• /
• pp.149-160
• /
• 2019

Atrophic alveolar ridge of maxillary anterior area is commonly observed after the extraction of teeth in patients with severely compromised periodontal disease, causing difficulties with implant placement. Successful esthetics and functional implant rehabilitation rely on sufficient bone volume, adequate bone contours, and ideal implant positioning and angulation. The present case report categorized the ridge augmentation techniques using guided bone regeneration (GBR) on the maxillary anterior site by Seibert classification. Case I patient presented for implant placement in the position of tooth #11. The alveolar ridge was considered a Seibert classification I ridge defect. Simultaneous implant placement and GBR were performed. Eight months after implantation, clinical and radiological examinations were performed. Case III patient presented with discomfort due to mobility of the upper maxillary anterior site. Due to severe destruction of alveolar bone, teeth #11 and #12 were extracted. After three months, the alveolar ridge was considered a Seibert classification III ridge defect. A GBR procedure was performed; implantation was performed 6 months later. Approximately 1-year after implantation, clinical and radiological examinations were performed. During the whole treatment period, healing was uneventful without membrane exposure, severe swelling, or infection in all cases. Radiographic and clinical examinations revealed that atrophic hard tissues and buccal bone contour were restored to the acceptable levels for implant placement and esthetic restoration. In conclusion, severely resorbed alveolar ridge of the maxillary anterior area can be reconstructed with ridge augmentation using the GBR procedure so that dental implants could be successfully placed.

• Journal of the Korean Society of Mineral and Energy Resources Engineers
• /
• v.55 no.6
• /
• pp.614-623
• /
• 2018

The recent occurrence of consecutive large earthquakes in the southeastern part of the Korean peninsula has brought significant attention to the prevention of earthquake damage in Korea. This article aims to explore a technology-based approach for earthquake drills using state-of-the-art visual intelligence and virtual reality technologies. The technical process consists of several stages, including acquisition of image information in living spaces using a camera, recognition of objects from the acquired image information, extraction of three dimensional geometric information, simulation of virtual earthquakes using dynamic modelling techniques such as the discrete element method, and realization of the simulated earthquake in a virtual reality environment. This article provides a comprehensive analysis of the individual processes at each stage of the technical process, a survey on the current status of related technologies, and discussion of the technical challenges in its execution.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.311-318
• /
• 2021

Research has been ongoing to detect ships from offshore photographs for a variety of reasons, including maritime security, identifying international trends, and social scientific research. Due to the development of artificial intelligence, R-CNN models for object detection in photographs and images have emerged, and the performance of object detection has risen dramatically. Ship detection in offshore photographs using the R-CNN model has also begun to apply to satellite photography. However, satellite images project large areas, so various objects such as vehicles, landforms, and buildings are sometimes recognized as ships. In this paper, we propose a novel methodology to improve the performance of ship detection in satellite photographs using R-CNN series models. We separate land and sea via marker-based watershed algorithm and perform morphology operations to specify RoI one more time, then detect vessels using R-CNN family models on specific RoI to reduce typology. Using this method, we could reduce the misdetection rate by 80% compared to using only the Fast R-CNN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2049-2068
• /
• 2021

AI combined with NLP techniques has promoted the use of Virtual Assistants and have made people rely on them for many diverse uses. Conversational Agents are the most promising technique that assists computer users through their operation. An important challenge in developing Conversational Agents globally is transferring the groundbreaking expertise obtained in English to other languages. AI is making it possible to transfer this learning. There is a dire need to develop systems that understand secular languages. One such difficult language is Hindi, which is the fourth most spoken language in the world. Semantic similarity is an important part of Natural Language Processing, which involves applications such as ontology learning and information extraction, for developing conversational agents. Most of the research is concentrated on English and other European languages. This paper presents a Corpus-based word semantic similarity measure for Hindi. An experiment involving the translation of the English benchmark dataset to Hindi is performed, investigating the incorporation of the corpus, with human and machine similarity ratings. A significant correlation to the human intuition and the algorithm ratings has been calculated for analyzing the accuracy of the proposed similarity measures. The method can be adapted in various applications of word semantic similarity or module for any other language.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1031-1041
• /
• 2020

Cloud computing technology plays an important role in the deep learning industry as deep learning services are deployed frequently on top of cloud infrastructures. In such cloud environment, virtualization technology provides logically independent and isolated computing space for each tenant. However, recent studies demonstrate that by leveraging vulnerabilities of virtualization techniques and shared processor architectures in the cloud system, various side-channels can be established between cloud tenants. In this paper, we propose a novel attack scenario that can steal internal information of deep learning models by exploiting the Meltdown vulnerability in a multi-tenant system environment. On the basis of our experiment, the proposed attack method could extract internal information of a TensorFlow deep-learning service with 92.875% accuracy and 1.325kB/s extraction speed.

• The Plant Pathology Journal
• /
• v.37 no.2
• /
• pp.162-172
• /
• 2021

Soybean mosaic virus (SMV) is the predominant viral pathogen that affects the yield and quality of soybean. The natural host range for SMV is very narrow, and generally limited to Leguminosae. However, we found that SMV can naturally infect Pinellia ternata and Atractylodes macrocephala. In order to clarify the molecular mechanisms underlying the cross-family infection of SMV, we used double-stranded RNA extraction, rapid amplification of cDNA ends polymerase chain reaction and Gibson assembly techniques to carry out SMV full-length genome amplification from susceptible soybeans and constructed an infectious cDNA clone for SMV. The genome of the SMV Shanxi isolate (SMV-SX) consists of 9,587 nt and encodes a polyprotein consisting of 3,067 aa. SMV-SX and SMV-XFQ008 had the highest nucleotide and amino acid sequence identities of 97.03% and 98.50%, respectively. A phylogenetic tree indicated that SMV-SX and SMV-XFQ018 were clustered together, sharing the closest relationship. We then constructed a pSMV-SX infectious cDNA clone by Gibson assembly technology and used this clone to inoculate soybean and Ailanthus altissima; the symptoms of these hosts were similar to those caused by the virus isolated from natural infected plant tissue. This method of construction not only makes up for the time-consuming and laborious defect of traditional methods used to construct infectious cDNA clones, but also avoids the toxicity of the Potyvirus special sequence to Escherichia coli, thus providing a useful cloning strategy for the construction of infectious cDNA clones for other viruses and laying down a foundation for the further investigation of SMV cross-family infection mechanisms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.411-416
• /
• 2020

Field investigations of forests are carried out by writing measured data by hand, and it is a hassle to reorganize the results after a field survey. In this study, a method using object modeling and augmented reality (AR) was applied in a test forest to increase the efficiency of a field investigations. Using a 3D laser scanner, data on were acquired 387 trees within an area of 1 ha at the study site. The coordinates, height, and diameter were calculated through object extraction and modeling of a tree. The proposed can reduce the time required to acquire data in the field and can be used as basic data for building related systems. In addition, the modeling results of trees and a survey using GNSS and AR techniques can be used check coordinates, labor, and attribute information, such as the chest height diameter of the trees being surveyed in the field. The shortcomings of the survey method could be improved. In the future, the method could greatly improve the efficiency of tree surveys and monitoring by reducing the manpower and time required for field surveys.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• Food Science of Animal Resources
• /
• v.42 no.1
• /
• pp.1-17
• /
• 2022

Lipids are one of the major macronutrients essential for adequate growth and maintenance of human health. Their structure is not only complex but also diverse, which makes systematic and holistic analyses challenging; consequently, little is known regarding the relationship between phenotype and mechanism of action. In recent years, rapid advancements have been made in the fields of lipidomics and bioinformatics. In comparison with traditional approaches, mass spectrometry-based lipidomics can rapidly identify as well as quantify >1,000 lipid species at the same time, facilitating comprehensive, robust analyses of lipids in tissues, cells, and body fluids. Accordingly, lipidomics is now being widely applied in various fields, particularly food and nutrition science. In this review, we discuss lipid classification, extraction techniques, and detection and analysis using lipidomics. We also cover how lipidomics is being used to assess food obtained from livestock and poultry. The information included herein should serve as a reference to determine how to characterize lipids in animal food samples, enhancing our understanding of the application of lipidomics in the field in animal husbandry.