• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.2
• /
• pp.33-49
• /
• 2002

CBM (Condition-Based Maintenance) has increasingly drawn attention in industry because of its many benefits. CBM Problem Is characterized as a state-dependent scheduling model that demands simultaneous maintenance actions, each for an attribute that influences on machine condition. This problem is very hard to solve within conventional Markov decision process framework. In this paper, we present an intelligent machine maintenance scheduler, for which a new incremental decision tree learning method as evolutionary system identification model and shortest path problem as schedule generation model are developed. Although our approach does not guarantee an optimal scheduling policy in mathematical viewpoint, we verified through simulation based experiment that the intelligent scheduler is capable of providing good scheduling policy that can be used in practice.

• The KIPS Transactions:PartA
• /
• v.15A no.3
• /
• pp.155-160
• /
• 2008

RFID technology has been gradually expanding its application. One of the important performance issues in RFID systems is to resolve the collision among multi-tags identification on restricted area. We consider a new anti-collision scheme based on Class Identification algorithm using Depth-First scheme. We evaluate how much performance can be improved by Class identification algorithm in the cases of Query-tree more then 17% identification rate and 150% performance.

• The Plant Pathology Journal
• /
• v.21 no.1
• /
• pp.27-32
• /
• 2005

Leaf anthracnose was observed on leaves of Japanese spindle tree in Seoul, Korea from autumn 2003 to spring 2004. The causal fungus was purely isolated from he leaf spot lesions and cultured on PDA. The colony on PDA was cream to orange but blackish in the center n old cultures. Conidia were formed in blackish orange asses and were cylindrical in shape, measured 13-17${\times}$5-7 ${\mu}$m in size. Blackish brown setae were often observed on PDA and ranged up to 100 ${\mu}$m in length. Based on morphological and ITS region sequence analyses, the fungal strain was identified as Colletotrichum boninense. Koch’s postulates were fulfilled by inoculating tree leaves with 1 ${\times}$ $106^6$ conidia per ml in a moist chamber. This is the first study on the pathogenicity, growth and phylogenetic characteristics of C. boninense causing leaf anthracnose on Japanese spindle tree in Korea.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.7
• /
• pp.1624-1637
• /
• 2013

In RFID systems, one important issue is how to effectively address tag collision, which occurs when multiple tags reply simultaneously to a reader, so that all the tags are correctly identified. However, most existing anti-collision protocols assume isotropic collisions where a reader cannot detect any of the tags from the collided signals. In practice, this assumption turns out to be too pessimistic since the capture effect may take place, in which the reader considers the strongest signal as a successful transmission and the others as interference. In this case, the reader disregards the other collided tags, and in turn, fails to read the tag(s) with weaker signal(s). In this paper, we propose a capture effect-aware anti-collision protocol, called Multi-Round Collision Tree (MRCT) protocol, which efficiently identifies the tags in real RFID environments. MRCT deals with the capture effect as well as channel error by employing a multi-round based identification algorithm. We also analyze the performance of MRCT in terms of the number of slots required for identifying all tags. The simulation results show that MRCT significantly outperforms the existing protocol especially in a practical environment where the capture effect occurs.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.5 s.335
• /
• pp.47-54
• /
• 2005

This paper proposes and analyzes a Tag Anti-collision algorithm in RFID system. We mathematically compare the performance of the proposed algorithm with existing binary algorithms(binary search algorithm, slotted binary tree algorithm using time slot, and bit-by-bit binary tree algorithm proposed by Auto-ID center). We also validated analytic results using OPNET simulation. Based on analytic result, comparing the proposed Improved bit-by-bit binary tree algerian with bit-by-bit binary tree algorithm which is the best of existing algorithms, the performance of Improved bit-by-bit binary tree algorithm is about $304\%$ higher when the number of tags is 20, and $839\%$ higher when the number of tags is 200.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.531-540
• /
• 2010

In this paper, we present a two-phase shallow semantic parsing method based on a maximum entropy model. The first phase is to recognize semantic arguments, i.e., argument identification. The second phase is to assign appropriate semantic roles to the recognized arguments, i.e., argument classification. Here, the performance of the first phase is crucial for the success of the entire system, because the second phase is performed on the regions recognized at the identification stage. In order to improve performances of the argument identification, we incorporate syntactic knowledge into its pre-processing step. More precisely, boundaries of the immediate clause and the upper clauses of a predicate obtained from clause identification are utilized for reducing the search space. Further, the distance on parse trees from the parent node of a predicate to the parent node of a parse constituent is exploited. Experimental results show that incorporation of syntactic knowledge and the separation of argument identification from the entire procedure enhance performances of the shallow semantic parsing system.

• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.75-82
• /
• 2015

Major corporations and portals have implemented a link server that connects Content Management Systems (CMS) to the physical address of content in a database (DB) to support efficient content use in web-based environments. In particular, a link server automatically connects the physical address of content in a DB to the content URL shown through a web browser screen, and re-connects the URL and the physical address when either is modified. In recent years, the number of users of digital content over the web has increased significantly because of the advent of the Big Data environment, which has also increased the number of link validity checks that should be performed in a CMS and a link server. If the link validity check is performed through an existing URL-based sequential method instead of petabyte or even etabyte environments, the identification rate of dead links decreases because of the degradation of validity check performance; moreover, frequent link checks add a large amount of workload to the DB. Hence, this study is aimed at providing a link server that can recognize URL link deletion or addition through analysis on the B-tree-based Information Identifier count per interval based on a large amount of URLs in order to resolve the existing problems. Through this study, the dead link check that is faster and adds lower loads than the existing method can be performed.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.92-97
• /
• 2022

Plastics are classified into 7 types such as PET (PETE), HDPE, PVC, LDPE, PP, PS, and Other for separation and recycling. Recently, large corporations advocating ESG management are replacing them with bioplastics. Incineration and landfill of disposal of plastic waste are responsible for air pollution and destruction of the ecosystem. Because it is not easy to accurately classify plastic materials with the naked eye, automated system-based screening studies using various sensor technologies and AI-based software technologies have been conducted. In this paper, NIR scanning devices considering the NIR wavelength characteristics that appear differently for each plastic material and a system that can identify the type of plastic by learning the NIR spectrum data collected through it. The accuracy of plastic material identification was evaluated through a decision tree-based SVM model for multiclass classification on NIR spectral datasets for 8 types of plastic samples including biodegradable plastic.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• Mycobiology
• /
• v.50 no.4
• /
• pp.231-237
• /
• 2022

Penicillium species have been actively studied in various fields, and many new and unrecorded species continue to be reported in Korea. Moreover, unidentified and misidentified Korean Penicillium species still exist in GenBank. Therefore, it is necessary to revise the Korean Penicillium inventory based on accurate identification. We collected Korean Penicillium nucleotide sequence records from GenBank using the newly developed software, GenMine, and re-identified Korean Penicillium based on the maximum likelihood trees. A total of 1681 Korean Penicillium GenBank nucleotide sequence records were collected from GenBank. In these records, 1208 strains with four major genes (Internal Transcribed Spacer rDNA region, b-tubulin, Calmodulin and RNA polymerase II) were selected for Penicillium reidentification. Among 1208 strains, 927 were identified, 82 were identified as other genera, the rest remained undetermined due to low phylogenetic resolution. Identified strains consisted of 206 Penicillium species, including 156 recorded species and 50 new species candidates. However, 37 species recorded in the national list of species in Korea were not found in GenBank. Further studies on the presence or absence of these species are required through literature investigation, additional sampling, and sequencing. Our study can be the basis for updating the Korean Penicillium inventory.