• The Pure and Applied Mathematics
• /
• v.14 no.1 s.35
• /
• pp.37-48
• /
• 2007

In this paper, we introduce and study a class of generalized multivalued quasivariational inclusions for fuzzy mappings, and establish its equivalence with a class of fuzzy fixed-point problems by using the resolvent operator technique. We suggest a new iterative algorithm for the generalized multivalued quasivariational inclusions. Further, we establish a few existence results of solutions for the generalized multivalued quasivariational inclusions involving $F_r$-relaxed Lipschitz and $F_r$-strongly monotone mappings, and discuss the convergence criteria for the algorithm.

• Research in Mathematical Education
• /
• v.18 no.3
• /
• pp.187-208
• /
• 2014

This study engages in the features of interaction in elementary school mathematics lessons as reflected in the class discourse. 28 pre-service teachers documented the discourse during observation of their tutor-teachers' lessons. Mapping the interaction patterns was performed by a unique graphic model developed for that purpose and enabled providing a spatial picture of the discourse conducted in the lesson. The research findings present the known discourse pattern "initiation-response-evaluation / feedback" (IRE/F) which is recurrent in all the lessons and the teacher's exclusive control over the class discourse patterns. Hence, the remaining time of the lesson for the pupils' discourse is short and meaningless.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.45-59
• /
• 2023

Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated to produce multi-head attention maps as an auxiliary detector. By integrating the CNN-based CAMs and attention maps, our approach localizes defective regions without requiring bounding box or pixel-level supervision during training. We evaluate our approach on a dataset of apple images with only image-level labels of defect categories. Experiments demonstrate our proposed method aligns with several Object Detection models performance, hold a promise for improving localization.

• Journal of Environmental Science International
• /
• v.18 no.11
• /
• pp.1189-1197
• /
• 2009

The purpose of this research was develop tailored landslide hazard assessment table (LHAT) in Gyeongsangbuk-do Province and propose building strategies on environmental information system to estimate landslide hazard area according to LHAT. To accomplish this purpose, this research investigated factors occurring landslide at 172 landslide occurred sites in 23 city and county of Gyeongsangbuk-do Province and analyzed what factors effected landslide occurrence quantity using the multiple statistics of quantification method(I). The results of analysis, factors affecting landslide occurrence quantity were shown in order of slope position, slope length, bedrock, aspect, forest age, slope form and slope. And results of the development of LHAT for predict mapping of landslide-susceptible area in Gyeongsangbuk-do Province, total score range was divided that 107 under is stable area(IV class), 107~176 is area with little susceptibility to landslide(III class), 177~246 is area with moderate susceptibility to landslide(II class), above 247 area with severe susceptibility to landslide(I class). According to LHAT, this research built landslide attribute database and made 7 digital theme maps at mountainous area located in Goryeong Gun, Seongju-Gun, and Kimcheon-City. The results of prediction on degree of landslide hazard using environmental information system, area with little susceptibility to landslide(III class) occupied 65.56% and severe susceptibility to landslide(I class) occupied 0.51%.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.31-40
• /
• 2019

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.

• Korean Journal of Agricultural Science
• /
• v.50 no.3
• /
• pp.357-364
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.

• Korean Journal of Cognitive Science
• /
• v.21 no.1
• /
• pp.95-126
• /
• 2010

This study proposes a bottom-up and inductive manual mapping methodology for integrating two heterogenous fine-grained ontologies which were built by a top-down and deductive methodology, namely the Sejong semantic classes (SJSC) and the upper nodes in KorLexNoun 1.5 (KLN), for HLP applications. It also discusses various problematics in the mapping processes of two language resources caused by their heterogeneity and proposes the solutions. The mapping methodology of heterogeneous fine-grained ontologies uses terminal nodes of SJSC and Least Upper Bounds (LUB) of KLN as basic mapping units. Mapping procedures are as follows: first, the mapping candidate groups are decided by the lexfollocorrelation between the synsets of KLN and the noun senses of Sejong Noun Dfotionaeci(SJND) which are classified according to SJSC. Secondly, the meanings of the candidate groups are precisely disambiguated by linguistic information provided by the two ontologies, i.e. the hierarchicllostructures, the definitions, and the exae les. Thirdly, the level of LUB is determined by applying the appropriate predicates and definitions of SJSC to the upper-lower and sister nodes of the candidate LUB. Fourthly, the mapping possibility ic inthe terminal node of SJSC is judged by che aring hierarchicllorelations of the two ontologies. Finally, the ituorrect synsets of KLN and terminologiollocandidate groups are excluded in the mapping. This study positively uses various language information described in each ontology for establishing the mapping criteria, and it is indeed the advantage of the fine-grained manual mapping. The result using the proposed methodology shows that 6,487 LUBs are mapped with 474 terminal and non-terminal nodes of SJSC, excluding the multiple mapped nodes, and that 88,255 nodes of KLN are mapped including all lower-level nodes of the mapped LUBs. The total mapping coverage is 97.91% of KLN synsets. This result can be applied in many elaborate syntactic and semantic analyses for Korean language processing.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.8C
• /
• pp.675-680
• /
• 2007

This paper presents a new method for classification of underwater transient signals, which employs frame-based decision with Mel Frequency Cepstral Coefficients(MFCC). The MFCC feature vector is extracted frame-by-frame basis for an input signal that is detected as a transient signal, and Euclidean distances are calculated between this and all MFCC feature. vectors in the reference database. Then each frame of the detected input signal is mapped to the class having minimum Euclidean distance in the reference database. Finally the input signal is classified as the class that has maximum mapping rate in the reference database. Experimental results demonstrate that the proposed method is very promising for classification of underwater transient signals.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.89-98
• /
• 2010

The enterprise system is becoming more complex and larger. With the changes of the times, the system is developing to object-oriented programming method(OOP). However, the same code inserts to the core class repetitiously in the OOP, that causes a decrease in productivity and a trouble of application of another requirement. To solve this weak point, we propose a weaving mechanism what applies to metadata and crosscutting concern. For a class optimization and an integration between different languages, we take the following way. This paper uses three ways, those are, metadata generation using reflection, transformation to Abstract Syntax Tree, and mapping through crosscutting information specified XML. Through the proposed theory, class optimization can be accomplished by solving a functional decentralization and a confusion of codes.

• Journal of the Korean Society for information Management
• /
• v.23 no.1 s.59
• /
• pp.99-119
• /
• 2006

The most widely used information searching method in the current internet environment is the keyword-based one, which has certain limitations in terms of precision and recall. Most major internet portals provide directory-based searching as a means to complement these limitations. However, that they adopt different classification schemes brings significant inconvenience to the users, and it consequently suggests a need to develop mapping gateway to provide cross-portal, or cross-directory information searching. In this context, this study attempts to develop a prototype system of intermediary gateway for integrated search, using the directory services of three major portals, Naver, Yahoo and Empas, and test its performance.