• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.392-399
• /
• 2023

This paper proposes a deep learning model to determine the region and depth of cabbage cores for robotic automation of the cabbage core removal process during the kimchi manufacturing process. In addition, rather than predicting the depth of the measured cabbage, a model was presented that simultaneously detects and classifies the area by converting it into a discrete class. For deep learning model learning and verification, RGB images of the harvested cabbage 522 were obtained. The core region and depth labeling and data augmentation techniques from the acquired images was processed. MAP, IoU, acuity, sensitivity, specificity, and F1-score were selected to evaluate the performance of the proposed YOLO-v4 deep learning model-based cabbage core area detection and classification model. As a result, the mAP and IoU values were 0.97 and 0.91, respectively, and the acuity and F1-score values were 96.2% and 95.5% for depth classification, respectively. Through the results of this study, it was confirmed that the depth information of cabbage can be classified, and that it can be used in the development of a robot-automation system for the cabbage core removal process in the future.

• Journal of Environmental Impact Assessment
• /
• v.33 no.2
• /
• pp.64-73
• /
• 2024

As the seriousness of habitat destruction caused by development projects emerges, the importance of environmental impact assessment (EIA) is increasing to preserve biodiversity. In previous studies, research is being conducted to quantitatively evaluate the biodiversity impact of development factors and surrounding environmental factors on the landscape scale, but research on the factors affecting the reduction of biodiversity based on development projects is insufficient. This study examined whether independent variables (size of development project, type of the development, DEM, ecosystem and nature map, distance from the green land, distance from the protected area), which have been proven to effect biodiversity through the previous researches, have a significant effect on the change of richness index (RI) through multi-class logistic regression analysis, T-test, and analysis of the development type. As a result, only the size of development project and the first richness index in EIA showed p-value less than 0.05. And it was confirmed that the reduction in biodiversity was significantly changed in the following construction types: installation of sports facilities, energy development, and development of industrial location and industrial complex. Since the results of this study confirmed that the impact of the variables may be inconsistent depending on the analysis scale, additional study of necessary indicators at the development project is needed to analyze biodiversity changes in EIA accurately.

• Cartoon and Animation Studies
• /
• s.33
• /
• pp.31-53
• /
• 2013

In the early twentieth century, history of animation began by modern artists, they produced various experimental images with the newly invented film and cameras. Artists in the field of movie, photography, paintings and others manipulated images in motion. But as some animated movies won industrial success and popularity, they became the trend but experimental style of early animation preserved by so-called non-mainstreamers or experimental animators, counteracting commercialism. Disney animation also followed the trend by applying realistic Hollywood film style, the worse critics placed a low value on the animation and it tarnished the image, although it was profitable investment from a business standpoint. To make images realistic, they opened a drawing class that animators developed skills to imitate motions and forms from subjects in real life. Also some techniques and gizmos were used to mimic and simulate three dimensional objects and spaces, multiplane camera and compositing 3D CG images with 2D drawings. Moreover, they brought animation stories from fairly tales or folk tales, and Walt's personal interest in live-action movies, they applied Hollywood-film-like narratives and realistic visual, and harsh criticism ensued. On the surface early disney animations' potential seems to be weakened, but in reality it still exists by simplifying and exaggerating forms and color as modern arts. Disney animation employs concepts of the modernism paintings such as simplified shapes and colors to a character design, when their characters are placed together in a scene, that visual elements cause mental reaction. This modification gives a new internal experience to audiences. As conceptual colors in abstract paintings make images appeared to be flat, coloring characters with no shading make them look flat and comparing to them, background images are also appeared to be flat. On top of that, multi-perspective at background images recalls modernist paintings. This essay goes in details with the animation pioneers' works and how Disney animation developed its techniques to emulate real life and analyses color schemes, forms, and spaces in Disney animation compared with modern artists' works, in that the visual language of Disney animation reminds of impression from abstract paintings in the beginning of the twentieth centuries.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.3
• /
• pp.74-83
• /
• 2005

The Riparian Buffer Zone has many potential values including the preservation of water quality as well as being ecologically friendly. This study aims to quantitatively analyze the landscape structure index of the Riparian Buffer Zone in the Kyoung-an stream and to produce base information necessary for proper management. The study used aerial images that were applied to geometric corrections for a time series from 1966 to 2000 for land data and also used FRAGSTATS, which is a type of ARCVIEW extension module, as an analysis tool. An analysis of land use change and the Landscape Index revealed that the area of farm land has decreased and that the area of residential property has increased. In addition, there was a slight change for land used for purposes other than farming or for residence. The results of analyzing the Landscape Structure Index, revealed that the NP has increased from 437 in 1966 to 695 in 2000. This data reveals that the change of land use is influenced by various artificial factors. The NPS, which represents the declining degree of patch, decreased from 9.441 to 5.934, revealing that the change of land use has been progressing considerably. In regard to forest areas, land use reduced somewhat but did not indicate a significant change. Therefore, an analysis of the total index reveals that the edge of patch has become more complicated and that the variation index of patch has increased significantly. However, this study reveals that barriers to block pollution have weakened as a result and that there is a need to concentrate on the implementation and the management of the Riparian Buffer Zone. Consequently, this study reveals that substantial research is necessary in order to carry out the proper management of the Riparian Buffer Zone, especially in light of the distribution type of each patch and the change in conditions regarding them.

• Korean Journal of Construction Engineering and Management
• /
• v.1 no.2 s.2
• /
• pp.98-107
• /
• 2000

Increased use of computers in AEC (Architecture, Engineering and Construction) has expanded the amount of information gained from CAD (Computer Aided Design), PMIS (Project Management Information System), Structural Analysis Program, and Scheduling Program as well as making it more complex. And the productivity of AEC industry is largely dependent on well management and efficient reuse of this information. Accordingly, such trend incited much research and development on ITC (Information Technology in Construction) and CIC (Computer Integrated Construction) to be conducted. In exemplifying such effort, many researchers studied and researched on IFC (Industry Foundation Classes) since its development by IAI (International Alliance for Interoperability) for the product based information sharing. However, in spite of some valuable outputs, these researches are yet in the preliminary stage and deal mainly with conceptual ideas and trial implementations. Research on unveiling the process of the IFC application development, the core of the Design Information management system, and its applicable plan still need be done. Thus, the purpose of this paper is to determine the technologies needed for Design Information management system using IFC, and to present the key roles and the process of the IFC application development and its applicable plan. This system play a role to integrate the architectural information and the structural information into the product model and to group many each product items with various levels and aspects. To make the process model, we defined two activities, 'Product Modeling', 'Application Development', at the initial level. Then we decomposed the Application Development activity into five activities, 'IFC Schema Compile', 'Class Compile', 'Make Project Database Schema', 'Development of Product Frameworker', 'Make Project Database'. These activities are carried out by C++ Compiler, CAD, ObjectStore, ST-Developer, and ST-ObjectStore. Finally, we proposed the applicable process with six stages, '3D Modeling', 'Creation of Product Information', 'Creation and Update of Database', 'Reformation of Model's Structure with Multiple Hierarchies', 'Integration of Drawings and Specifications', and 'Creation of Quantity Information'. The IFCs, including the other classes which are going to be updated and developed newly on the construction, civil/structure, and facility management, will be used by the experts through the internet distribution technologies including CORBA and DCOM.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.21-44
• /
• 2018

In recent years, the rapid development of internet technology and the popularization of smart devices have resulted in massive amounts of text data. Those text data were produced and distributed through various media platforms such as World Wide Web, Internet news feeds, microblog, and social media. However, this enormous amount of easily obtained information is lack of organization. Therefore, this problem has raised the interest of many researchers in order to manage this huge amount of information. Further, this problem also required professionals that are capable of classifying relevant information and hence text classification is introduced. Text classification is a challenging task in modern data analysis, which it needs to assign a text document into one or more predefined categories or classes. In text classification field, there are different kinds of techniques available such as K-Nearest Neighbor, Naïve Bayes Algorithm, Support Vector Machine, Decision Tree, and Artificial Neural Network. However, while dealing with huge amount of text data, model performance and accuracy becomes a challenge. According to the type of words used in the corpus and type of features created for classification, the performance of a text classification model can be varied. Most of the attempts are been made based on proposing a new algorithm or modifying an existing algorithm. This kind of research can be said already reached their certain limitations for further improvements. In this study, aside from proposing a new algorithm or modifying the algorithm, we focus on searching a way to modify the use of data. It is widely known that classifier performance is influenced by the quality of training data upon which this classifier is built. The real world datasets in most of the time contain noise, or in other words noisy data, these can actually affect the decision made by the classifiers built from these data. In this study, we consider that the data from different domains, which is heterogeneous data might have the characteristics of noise which can be utilized in the classification process. In order to build the classifier, machine learning algorithm is performed based on the assumption that the characteristics of training data and target data are the same or very similar to each other. However, in the case of unstructured data such as text, the features are determined according to the vocabularies included in the document. If the viewpoints of the learning data and target data are different, the features may be appearing different between these two data. In this study, we attempt to improve the classification accuracy by strengthening the robustness of the document classifier through artificially injecting the noise into the process of constructing the document classifier. With data coming from various kind of sources, these data are likely formatted differently. These cause difficulties for traditional machine learning algorithms because they are not developed to recognize different type of data representation at one time and to put them together in same generalization. Therefore, in order to utilize heterogeneous data in the learning process of document classifier, we apply semi-supervised learning in our study. However, unlabeled data might have the possibility to degrade the performance of the document classifier. Therefore, we further proposed a method called Rule Selection-Based Ensemble Semi-Supervised Learning Algorithm (RSESLA) to select only the documents that contributing to the accuracy improvement of the classifier. RSESLA creates multiple views by manipulating the features using different types of classification models and different types of heterogeneous data. The most confident classification rules will be selected and applied for the final decision making. In this paper, three different types of real-world data sources were used, which are news, twitter and blogs.

• The Journal of Society for e-Business Studies
• /
• v.8 no.2
• /
• pp.99-111
• /
• 2003

By virtue of diverse advantages derived from digital media, eBook is getting started to use. And many market research agencies have predicted that its market will be greatly expanded soon. But against those expectations, copyright-related problems and the difficulties of its accessing inherited from various eBook content formats become an obstacle to its diffusion. The first problems can be solved by DRM technology. And to solve the second problems, each nation has published its own content standard format. But the domestic standards are useful only the domestic level, they still leave the problems in the national level. The variety of content formats has created a demand for mechanisms that allow the exchange of eBook contents. Therefore we study the mapping relations between eBook contents for conversion. To define the mapping relations, first we extract the mapping both between eBook contents and between normal XML documents. From those mappings, we define seven mapping relations and classify them by cardinality. And we analyze the classified relations, which can be generated by automatic, or not. Using these results, we also classify the eBook content conversion as automatic, semi-automatic, and manual. Besides, we provide the conversion templates for mapping relations for automatic generation of conversion scripts. To show the feasibility of conversion templates, we apply them to the eBook content conversion. Experiment shows that our conversion templates generate the conversion scripts properly. We expected that defined mapping relations and conversion templates can be used not only in eBook content conversion , but also in normal XML document conversion.

• Journal of Bio-Environment Control
• /
• v.29 no.3
• /
• pp.209-218
• /
• 2020

This paper investigated actual crop evapotranspiration (ET_c) of tomato and paprika planted in test beds of the greenhouse. Crop water requirement (CWR) is the amount of water required to compensate ET_c loss from the crop. The main objectives of the study are to assess whether the actual crop watering (ACW) was adequate CWR of tomato and paprika and which amount of ACW should be irrigated to each crop. ET_c was estimated using the Penman-Monteith model (P-M) for each crop. ACW was calculated from the difference of amount of nutrient supply water and amount of nutrient drainage water. ACW and CWR of each crop were determined, compared and assessed. Results indicated CWR-tomato was around 100 to 1,200 ml/day, while CWR-paprika ranged from 100 to 500 ml/day. Comparison of ACW and CWR of each crop found that the difference of ACW and CWR are fluctuated following day of planting (DAP). However, the differences could divide into two phases, first the amount of ACWs of each crop are less than CWR in the initial phase (60 DAP) around 500 ml/day and 91 ml/day, respectively. Then, ACWs of each crop are greater than the CWR after 60 DAP until the end of cultivation approximately 400 ml/day in tomato and 178 ml/day in paprika. ET_c assessment is necessary to correctly quantify crop irrigation water needs and it is an accurate short-term estimation of CWR in greenhouse for optimal irrigation scheduling. Thus, reducing ACW of tomato and paprika in the greenhouse is a recommendation. The amount of ACW of tomato should be applied from 100 to 1,200 ml/day and paprika is 100 to 500 ml/day depend on DAP.

• Journal of Aquaculture
• /
• v.22 no.1
• /
• pp.105-111
• /
• 2009

In this study, we carried out an experiment for estimation the larval digestibility in aspects which digestive enzymatic activities and nutrition of the rotifers, Brachionus rotundiformis. Thus we enhanced the digestive enzymatic activity through the addition of starch for the increase of digestibility of rotifer (starch-rotifer), and compared with the feed efficiency through rearing of the olive flounder, Paralichthys olivaceus used rotifer lipid-enriched with Algamac $2000^{(R)}$ (CE-rotifer). The digestive enzyme activities (except for TG-lipase), total protein contents, total essential amino acid, essential amino acids (methionin and phenylalanine) of starch-rotifer (the rotifer used a starch as additive, and enriched not) was assayed significantly higher than CE-rotifer (P<0.05). And total lipid, lipid classes (except for sterol) and fatty acids as DHA and EPA showed higher in CE-rotifer than starch-rotifer (P<0.05). But, sterol contents and ST/TG ratio were shown significantly higher in starch-rotifer (P<0.05). The flounder larvae supplied the two rotifers showed standard length and body weight that not significantly differed with ranges $3.72{\sim}3.79\;mm$ and $32.9{\sim}37.8\;mg$/larva on 6 days after hatching (DAH), respectively (P>0.05). However, these of 12 DAH showed the values of significantly higher to $5.94{\pm}0.249\;mm$, $144.0{\pm}23.86\;mg$/larva and $26.2{\pm}12.13%$ in standard length, body weight and survival in CE-flounder than that of starch-flounder (P<0.05). The hydrolytic enzymatic activities of flounder larvae severally supplied the two rotifers showed the significantly higher activities in acidic -amylase, neutral -amylase, TG-lipase, lysozyme and acidic phosphatase in starch-flounder on 5 DAH (P<0.05). But neutral $\alpha$-amylase, three proteases and two phosphatases of CE-flounder on 11 DAH showed the significantly higher activities than that of starch-flounder (P<0.05). Therefore, for the flounder, Paralichthys olivaceus larvae just depleted yolk was more beneficial to supply the feed, rotifer, enhanced the digestibility than to supply the feed lipid-enriched for aspect of larval digestibility up to 6 DAH, thereafter nutrition of absorption due to the development of digestive organs suggested that enrichment effect appeared with larval somatic growth. Consequently, investigation more detailed about the larval digestive physiological and nutritional requirement variations after 6 DAH will be necessary, thereafter.