• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.367-373
• /
• 2022

VANET (Vehicular Ad hoc NETwork) is one of the special cases of the ad hoc networks in which car nodes communicate with each other and/or with RSUs (Road Side Unit) in order for the drivers to receive nearby road traffic information as well as for the passengers to retrieve nearby gas price or hotel information. In case of constructing VANET over CCN, users do not need to specify a destination server address rather to input a key word such as nearby congestion in order to gather surrounding traffic congestion information. Furthermore, each car node caches its retrieved data for forwarding other nodes when requested. In addition, the data transmission is inherently multicast, which implies fast data propagation to the participating car nodes. This paper measures and evaluates the data transmission performance of the VCCN (VANET over CCN) in which nodes are equipped with diverse wireless communication channels. The simulation result indicates that 802.11a shows the best performance of the data transmission against other wireless channels. Moreover, it indicates that VCCN improves overall data transmission and provides benefit to the nodes that request the same traffic information by exploiting inherent multicast communication.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.4
• /
• pp.191-199
• /
• 2008

In this paper, we propose a MWF-PMC noise processing method which enhances the input speech by using Mel-warped Wiener Filtering (MWF) at pre-processing stage and compensates the recognition model by using PMC (Parallel Model Combination) at post-processing stage for speech recognition in noisy environments. The PMC uses the residual noise extracted from the silence region of enhanced speech at pre-processing stage to compensate the clean speech model and thus this method is considered to improve the performance of speech recognition in noisy environments. For recognition experiments we dew.-sampled KLE PBW (Phoneme Balanced Words) 452 word speech data to 8kHz and made 5 different SNR levels of noisy speech, i.e., 0dB. 5dB, 10dB, 15dB and 20dB, by adding Subway, Car and Exhibition noise to clean speech. From the recognition results, we could confirm the effectiveness of the proposed MWF-PMC method by obtaining the improved recognition performances over all compared with the existing combined methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.51-64
• /
• 2004

The purpose of this paper is to establish the Standard Korean Vocal Sound into Character Conversion Rule (Standard VSCC Rule) by reversely applying the Korean Standard Pronunciation Rule that regulates the way of reading written Hangeul sentences. The Standard VSCC Rule performs a crucially important role in Korean speech recognition. The general method of speech recognition is to find the most similar pattern among the standard voice patterns to the input voice pattern. Each of the standard voice patterns is an average of several sample voice patterns. If the unit of the standard voice pattern is a word, then the number of entries of the standard voice pattern will be greater than a few millions (taking inflection and postpositional particles into account). This many entries require a huge database and an impractically too many comparisons in the process of finding the most similar pattern. Therefore, the unit of the standard voice pattern should be a syllable. In this case, we have to resolve the problem of the difference between the Korean vocal sounds and the writing characters. The process of converting a sequence of Korean vocal sounds into a sequence of characters requires our Standard VSCC Rule. Making use of our Standard VSCC Rule, we have implemented a Korean vocal sounds into Hangeul character conversion system. The Korean Standard Pronunciation Rule consists of 30 items. In order to show soundness and completeness of our Standard VSCC Rule, we have tested the conversion system with various data sets reflecting all the 30 items. The test results will be presented in this paper.

• The Journal of Society for e-Business Studies
• /
• v.25 no.1
• /
• pp.13-33
• /
• 2020

This study proposes a Korean sentimental analysis algorithm that utilizes a letter-unit embedding and convolutional neural networks. Sentimental analysis is a natural language processing technique for subjective data analysis, such as a person's attitude, opinion, and propensity, as shown in the text. Recently, Korean sentimental analysis research has been steadily increased. However, it has failed to use a general-purpose sentimental dictionary and has built-up and used its own sentimental dictionary in each field. The problem with this phenomenon is that it does not conform to the characteristics of Korean. In this study, we have developed a model for analyzing emotions by producing syllable vectors based on the onset, peak, and coda, excluding morphology analysis during the emotional analysis procedure. As a result, we were able to minimize the problem of word learning and the problem of unregistered words, and the accuracy of the model was 88%. The model is less influenced by the unstructured nature of the input data and allows for polarized classification according to the context of the text. We hope that through this developed model will be easier for non-experts who wish to perform Korean sentimental analysis.

• Journal of the Korean Society for Library and Information Science
• /
• v.23
• /
• pp.207-261
• /
• 1992

The purpose of this study is (1) to design and test a database which can be automatically classified, and (2) to generate automatic classification number by processing the keywords in titles using the code combination method of Colon Classification(CC) as well as an automatic recognition of subjects in order to develop an automatic classification system (Auto BC System) based on CC which can be applied to any research library. To conduct this study, 1,510 words in the fields of agricultrue and medicine were selected, analized in terms of [P], [M], [E], [S], [T] employed in CC, and included in a database for classification. For the above-mentioned subject fields, the principle of an automatic classification was specified in order to generate automatic classification codes as well as to perform an automatic subject recognition of the titles included. Whenever necessary, editing, deleting, appending and reindexing of a database can be made in this automatic classification system. Appendix 1 shows the result of the automatic classification of books in the fields of agriculture and medicine. The results of the study are summarized below. 1. The classification number for the title of a book can be automatically generated by using the facet principles of Colon Classification. 2. The automatic subject recognition of a book is achieved by designing a database making use of a globe-principle, and by specifying the subject field for each word. 3. The automatic subject-recognition of input data is achieved by measuring the number of searched words by each subject field. 4. The combination of classification numbers is achieved by flowcharting of classification formular of each subject field. 5. The efficient control of classification numbers is achieved by designing control codes on the database for classification. 6. The automatic classification by means of Auto BC has been proved to be successful in the research library concentrating on a Single field. The general library may have some problem in employing this system. The automatic classification through Auto BC has the following advantages: 1. Speed of the classification process can be improve. 2. The revision or updating of classification schemes can be facilitated. 3. Multiple concepts can be expressed in a single classification code. 4. The consistency of classification can be achieved with the classification formular rather than the classifier's subjective judgement. 5. A user's retrieving process can be made after combining the classification numbers through keywords relating to the material to be searched. 6. The materials can be classified by a librarian without subject backgrounds. 7. The large body of materials can be quickly classified by means of a machine processing. 8. This automatic classification is expected to make a good contribution to design of the total system for library operations. 9. The information flow among libraries can be promoted owing to the use of the same program for the automatic classification.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.51-56
• /
• 2000

Is this paper, we studied on the automatic speech control system in real-time windows environment using voice recognition. The applied reference pattern is the variable DMS model which is proposed to fasten execution speed and the one-stage DP algorithm using this model is used for recognition algorithm. The recognition vocabulary set is composed of control command words which are frequently used in windows environment. In this paper, an automatic speech period detection algorithm which is for on-line voice processing in windows environment is implemented. The variable DMS model which applies variable number of section in consideration of duration of the input signal is proposed. Sometimes, unnecessary recognition target word are generated. therefore model is reconstructed in on-line to handle this efficiently. The Perceptual Linear Predictive analysis method which generate feature vector from extracted feature of voice is applied. According to the experiment result, but recognition speech is fastened in the proposed model because of small loud of calculation. The multi-speaker-independent recognition rate and the multi-speaker-dependent recognition rate is 99.08% and 99.39% respectively. In the noisy environment the recognition rate is 96.25%.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.97-102
• /
• 2000

Subband coding is to divide the signal frequency band into a set of uncorrelated frequency bands by filtering and then to encode each of these subbands using a bit allocation rationale matched to the signal energy in that subband. The actual coding of the subband signal can be done using waveform encoding techniques such as PCM, DPCM and vector quantizer(VQ) in order to obtain higher data compression. Most researchers have focused on the error in the quantizer, but not on the overall reconstruction error and its dependence on the filter bank. This paper provides a thorough analysis of subband codecs and further development of optimum filter bank design using vector quantizer. We compute the mean squared reconstruction error(MSE) which depends on N the number of entries in each code book, k the length of each code word, and on the filter bank coefficients. We form this MSE measure in terms of the equivalent quantization model and find the optimum FIR filter coefficients for each channel in the M-band structure for a given bit rate, given filter length, and given input signal correlation model. Specific design examples are worked out for 4-tap filter in 2-band paraunitary filter bank structure. These optimum paraunitary filter coefficients are obtained by using Monte Carlo simulation. We expect that the results of this work could be contributed to study on the optimum design of subband codecs using vector quantizer.

• Knowledge Management Research
• /
• v.23 no.3
• /
• pp.129-152
• /
• 2022

As a key infrastructure for digital transformation, the spread of data, network, artificial intelligence (D.N.A.) fields and the emergence of promising industries are laying the groundwork for active digital innovation throughout the economy. In this study, by applying the text mining methodology, major topics were derived by using the abstract, publication year, and research field of the study corresponding to the SCIE, SSCI, and A&HCI indexes of the WoS database as input variables. First, main keywords were identified through TF and TF-IDF analysis based on word appearance frequency, and then topic modeling was performed using g-DMR. With the advantage of the topic model that can utilize various types of variables as meta information, it was possible to properly explore the meaning beyond simply deriving a topic. According to the analysis results, topics such as business intelligence, manufacturing production systems, service value creation, telemedicine, and digital education were identified as major research topics in digital transformation. To summarize the results of topic modeling, 1) research on business intelligence has been actively conducted in all areas after COVID-19, and 2) issues such as intelligent manufacturing solutions and metaverses have emerged in the manufacturing field. It has been confirmed that the topic of production systems is receiving attention once again. Finally, 3) Although the topic itself can be viewed separately in terms of technology and service, it was found that it is undesirable to interpret it separately because a number of studies comprehensively deal with various services applied by combining the relevant technologies.