• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.263-271
• /
• 2008

This paper presents a Korean conversational agent system in a mobile environment using natural language processing techniques. The aim of a conversational agent in mobile environment is to provide natural language interface and enable more natural interaction between a human and an agent. Constructing such an agent, it is required to develop various natural language understanding components and effective utterance generation methods. To understand spoken style utterance, we perform morphosyntactic analysis, shallow semantic analysis including modality classification and predicate argument structure analysis, and to generate a system utterance, we perform example based search which considers lexical similarity, syntactic similarity and semantic similarity.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.28 no.1
• /
• pp.121-128
• /
• 2005

This paper proposes the heuristic approach for the generalized GT(Group Technology) problem to consider the restrictions which are given the number of cell, maximum number of machines and minimum number of machines. This approach is classified into two stages. In the first stage, we use the similarity coefficient method which is proposed and calculate the similarity values about each pair of all machines and align these values in descending order. If two machines which is selected is possible to link the each other on the edge of machine cell and they don't have zero similarity value, then we assign the machines to the machine cell. In the second stage, it is the course to form part families using proposed grouping efficacy. Finally, machine-part incidence matrix is realigned to block diagonal structure. The results of using the proposed approach are compared to the Modified p-median model.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.235-241
• /
• 2019

In this paper, we propose a new algorithm to detect rear-approaching vehicle using the frame similarity of ROI(Region of Interest) based on deep learning algorithm for use in agricultural machinery systems. Since the vehicle detection system for agricultural machinery needs to detect only a vehicle approaching from the rear. we use Faster R-CNN model that shows excellent accuracy rate in deep learning for vehicle detection. And we proposed an algorithm that uses the frame similarity for ROI using constrained conditions. Experimental results show that the proposed method has a detection rate of 99.9% and reduced the false positive values.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.97-106
• /
• 2021

Social networking platforms have become a smart way for people to interact and meet on internet. It provides a way to keep in touch with friends, families, colleagues, business partners, and many more. Among the various social networking sites, Twitter is one of the fastest-growing sites where users can read the news, share ideas, discuss issues etc. Due to its vast popularity, the accounts of legitimate users are vulnerable to the large number of threats. Spam and Malware are some of the most affecting threats found on Twitter. Therefore, in order to enjoy seamless services it is required to secure Twitter against malicious users by fixing them in advance. Various researches have used many Machine Learning (ML) based approaches to detect spammers on Twitter. This research aims to devise a secure system based on Hybrid Similarity Cosine and Soft Cosine measured in combination with Genetic Algorithm (GA) and Artificial Neural Network (ANN) to secure Twitter network against spammers. The similarity among tweets is determined using Cosine with Soft Cosine which has been applied on the Twitter dataset. GA has been utilized to enhance training with minimum training error by selecting the best suitable features according to the designed fitness function. The tweets have been classified as spammer and non-spammer based on ANN structure along with the voting rule. The True Positive Rate (TPR), False Positive Rate (FPR) and Classification Accuracy are considered as the evaluation parameter to evaluate the performance of system designed in this research. The simulation results reveals that our proposed model outperform the existing state-of-arts.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.3
• /
• pp.83-95
• /
• 2022

A technology can be newly formed through technological convergence achieved by the intersection of two or more technological fields. As the complexity of technology development increases, related interest is increasing. Researches have been carried out on the concept, related indicators and analysis of technology convergence including method of social networks. This paper intends to suggest an analysis method of technology convergence using social networks based on the company's possessing technologies. According to the similarity of technologies among companies, a social network was constructed and the technology convergence was analyzed using k-core, a social network subgroup method. Using the result of k-core, base and element technologies for convergence was identified with their relations. Using the suggested method, technology convergence was analyzed on real technology data of defense-industry companies. When the minimum technology similarity is 0, the overall technology convergence relations between technology elements can be identified. In the scope of data in this paper, technologies of defense S/W, aircraft structure and structural materials are identified as important base technology for convergence.

• Journal of KIISE:Databases
• /
• v.31 no.1
• /
• pp.13-22
• /
• 2004

With the proliferation of multimedia data, there is an increasing need to support the indexing and retrieval of high-dimensional image data. Although there have been many efforts, the performance of existing multidimensional indexing methods is not satisfactory in high dimensions. Thus the dimensionality reduction and the approximate solution methods were tried to deal with the so-called dimensionality curse. But these methods are inevitably accompanied by the loss of precision of query results. Therefore, recently, the vector approximation-based methods such as the VA- file and the LPC-file were developed to preserve the precision of query results. However, the performance of the vector approximation-based methods depend largely on the size of the approximation file and they lose the advantages of the multidimensional indexing methods that prune much search space. In this paper, we propose a new index structure called the GC-tree for efficient similarity search in image databases. The GC-tree is based on a special subspace partitioning strategy which is optimized for clustered high-dimensional images. It adaptively partitions the data space based on a density function and dynamically constructs an index structure. The resultant index structure adapts well to the strongly clustered distribution of high-dimensional images.

• Korean Journal of Environment and Ecology
• /
• v.35 no.6
• /
• pp.632-643
• /
• 2021

The objective of this study was to examine vegetation community structure and distribution of Fraxinus chiisanensis in Mt.Minjuji of Chungcheongbuk-do by setting up and surveying 8 plots (400 m² each). Mean Importance Value (MIV) of Fraxinus chiisanensis in 8 plots was 35.19% in average (ranging from 26.07~42.74%). Since it is the dominant species in all plots, it is expected to maintain the present vegetation structure. The analysis of the DBH (diameter at breast height) showed that the diameter of Fraxinus chiisanensis in Mt.Minjuji ranges from 2 to 43cm. The majority of Fraxinus chiisanensis is expected to maintain current state unless disturbance or rapid environmental change occurs. The Species Diversity (H') was 0.8498~1.0261, Evenness (J') was 0.8160~0.9256, Dominance Index (D) was 0.0789~0.1840, Maximum Diversity (H'max) was 1.0414~1.2041. The analysis of annual ring and radial growth showed that the average age of Fraxinus chiisanensis in Mt.Minjuji was 29.1years(ranging from 22~58years). The average annual radial growth of Fraxinus chiisanensis was the highest in community G with 5.84mm and the lowest in community B with 2.80mm. The similarity index analysis revealed that the similarity index between community B and E, C and F, H was the highest with 69.0%, and the similarity index between community E and F was the lowest with 29.6%. Both the area of Fraxinus chiisanensis community of Mt.Minjuji and its population size are very small. Therefore, this area needs to be designated as Forest Genetic Resource Reserve.

• ALGAE
• /
• v.18 no.3
• /
• pp.225-232
• /
• 2003

Species composition, community structure and biodiversity of marine benthic community were studied in the rocky shore of Dongbaekseom, Busan. A total of 82 species of marine algae including 4 Cyanophyta, 11 Chlorophyta, 20 Phaeophyta and 47 Rhodophyta are listed. The dominant algal species were Ulva pertusa, Chondria crassicaulis, Corallina spp. and Melobesioidean algae. Sargassum thunbergii, Chondracanthus intermedia, Gelidium divaricatum and Ralfsia verrucosa were subdominant in cases of different seasons and vertical layers. Chthamalus challengeri, Littorina brevicula and Mytilus edulis were dominant zoobenthic species upper-middle layer of the intertidal zone. The community structure of this area seemed to be controlled by spatial competition with benthic marine algae. The species diversity indices estimated from different sources were quite different. Indices from coverage were 1.87, 3.98 from frequency, 2.26 from the average of total frequency and coverage and 2.15 from importance value. The similarity indices on the present study showed decreasing trends comparing to the previous benthic algal composition researches.

• Journal of the Ergonomics Society of Korea
• /
• v.18 no.1
• /
• pp.41-53
• /
• 1999

The effect of menu width and depth on the efficiency of information search and menu preference was investigated to identify an optimal menu structure for EIG which reflects the characteristics of human information processing. Information search time increased stepwisely as the menu width exceeded 6 items and linearly as the level of menu depth increased. The linear relationship between the error rate and the number of depth levels seems to be caused by the increase in the items to be remembered. When a menu structure was constructed by combining different menu depths and widths, it was observed that making the menu width wider rather than the depth deeper allows better information search. The menu structure rated as the most preferable and the easiest to user was that of pyramidal form. Such a result seems to come from its structural similarity to general categories which people get used to and implies that one should consider user preference as well as efficiency of search when he/she designs an EIG menu.

• East Asian Economic Review
• /
• v.18 no.4
• /
• pp.367-394
• /
• 2014

In this study, we examined the fractal structure of the Nikkei225, HangSeng, Shanghai Stock Exchange and Straits Times Index of Singapore. Empirical analysis was performed via non-parametric, semi-parametric long memory tests and also fractal dimension calculations. In order to avoid spurious long memory features, besides the Detrended Fluctuations Analysis (DFA), we also used Smith's (2005) modified GPH method. As for fractal dimension calculations, they were conducted via Box-Counting and Variation (p=1) tests. According to the results, while there is no long memory property in log returns of any index, we found evidence for long memory properties in the volatility of the HangSeng, the Shanghai Stock Exchange and the Straits Times Index. However, we could not find any sign of long memory in the volatility of Nikkei225 index using either the DFA or modified GPH test. Fractal dimension analysis also demonstrated that all raw index prices have fractal structure properties except for the Nikkei225 index. These findings showed that the Nikkei225 index has the most efficient market properties among these markets.