• Journal of the Korean Wood Science and Technology
• /
• v.43 no.6
• /
• pp.701-713
• /
• 2015

A model was designed to identify wood species between Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. using the near-infrared (NIR) spectroscopy in combination with principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA). In the PCA using all of the spectra, Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. could not be classified. In the PCA using the spectrum that has been measured in sapwood, however, Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc. could be identified. In particular, it was clearly classified by sapwood in radial section. And more, these two species could be perfectly identified using PLS-DA prediction model. The best performance in species identification was obtained when the second derivative spectra was used; the prediction accuracy was 100%. For prediction model, the $R_p{^2}$ value was 0.86 and the RMSEP was 0.38 in second derivative spectra. It was verified that the model designed by NIR spectroscopy with PLS-DA is suitable for species identification between Pinus densiflora for. erecta Uyeki and Pinus densiflora Sieb. et Zucc.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.

• Food Science of Animal Resources
• /
• v.30 no.5
• /
• pp.851-859
• /
• 2010

This study was conducted to investigate the application of a model system using an MS-electronic nose based on the discriminative function analysis on volatile flavors, to prediction of the shelf-life of market milk by preservation temperature and differently-loaded heat treatment. On mass spectrum, the ion fragments of volatile flavors of milk obtained from MS-electronic nose could be distinguished at amu 60, 91, 92, and 93. The response levels of volatile flavors at each amu increased in proportion to the heat treatment loaded to the milk, in the order of LTLT, HTST, and UHT. This study indicated that the discriminative function scores of the volatile flavors seemed to correlate with the preservation temperature, storage period, and heat treatment conditions; DF1 (discriminative function first score) showed a strong relationship to storage periods, with $r^2$ of 0.9965, 0.9965, and 0.9911 at temperatures of 4, 7, and $10^{\circ}C$, respectively, while DF2 was influenced by heat treatment conditions with an $r^2$ of 0.9861 at $4^{\circ}C$. It is suggested that the discriminative function analysis given by an MS-electronic nose could be used to construct a new quality control model system for the evaluation of heat treatment loaded during the processing of milk, and for predicting storage periods of market milk.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.337-351
• /
• 2022

With the full spread and rapid development of social media, the trend of decentralization of social media information propagation is becoming clearer day by day, and the segmentation of time by audiences using social media information is clearly progressing. Therefore, this study aims to study the influence relationship between social media attitudes toward fake news, social capital, risk perception, and discriminant intentions based on existing studies. Accordingly, the research model presented related research questions and organized a questionnaire to collect a total of 500 valid surveys. The SPSS 26.0 program and the AMOS 24.0 program were used to analyze the data. The research results are as follows. First, the more positive the user's attitude towards the fake news identification intention of social media, the more they want to use various methods or tools to identify the authenticity of online information. Second, the more positive the user's attitude towards social media fake news, the more aware of the potential threats social media fake news poses to their own physical, psychological, financial and so on. At the same time, by raising one's own awareness of the dangers, counterintelligence intentions against fake news on social media will also increase. Third, the richer the social capital the user has, the stronger the information literacy, and therefore the stronger the identification intention of social media fake news. Fourth, the higher the value of social capital Chinese users have, the greater the damage they have suffered from fake news, and the higher the risk awareness of fake news to protect their interests. Fifth, it means that Chinese users recognized information suspected of social media and took corresponding measures.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.2B
• /
• pp.232-243
• /
• 2010

In this paper, various physiological signals of humans were measured and analyzed to inference their psychological state and biological information, and Bio-Signal Context aware system (BSC), which recognizes the current context of its users as well as the information of exterior environment and offers the service appropriate for them, was designed and implemented. The BSC extracts and analyzes the features from bio-signals, such as the measured electroencephalogram (EEG), electrocardiogram (ECG), and galvanic skin response (GSR), with its different sensors, has the input of the analyzed results, and discriminates four psychological states of rest, concentration, tension and melancholy. In addition to the results of the discriminated psychological states, the information of biological condition analyzed from the user's bio-signals, for example, heart rate variability (HRV), Galvanic skin response (GSR) and body temperature, and the information of external environment related to the user's are collected to offer the service fit for the user's present biological condition by inferring and recognizing the user's present situation.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.263-274
• /
• 2010

To provide context-aware music recommendation service, first of all, we need to catch music mood that a user prefers depending on his situation or context. Among various music characteristics, music mood has a close relation with people‘s emotion. Based on this relationship, some researchers have studied on music mood detection, where they manually select a representative segment of music and classify its mood. Although such approaches show good performance on music mood classification, it's difficult to apply them to new music due to the manual intervention. Moreover, it is more difficult to detect music mood because the mood usually varies with time. To cope with these problems, this paper presents an automatic method to classify the music mood. First, a whole music is segmented into several groups that have similar characteristics by structural information. Then, the mood of each segments is detected, where each individual's preference on mood is modelled by regression based on Thayer's two-dimensional mood model. Experimental results show that the proposed method achieves 80% or higher accuracy.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1372-1379
• /
• 2015

This paper presents an analysis of feature extraction methods used for distinguishing the speech of patients with cleft palates and people with normal palates. This research is a basic study on the development of a software system for automatic recognition and restoration of speech disorders, in pursuit of improving the welfare of speech disabled persons. Monosyllable voice data for experiments were collected for three groups: normal speech, cleft palate speech, and simulated clef palate speech. The data consists of 14 basic Korean consonants, 5 complex consonants, and 7 vowels. Feature extractions are performed using three well-known methods: LPC, MFCC, and PLP. The pattern recognition process is executed using the acoustic model GMM. From our experiments, we concluded that the MFCC method is generally the most effective way to identify speech distortions. These results may contribute to the automatic detection and correction of the distorted speech of cleft palate patients, along with the development of an identification tool for levels of speech distortion.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1493-1504
• /
• 2016

As cyber threats have been increased over the Internet, the invasions of personal information are constantly occurring. A malicious user can access the Web site as a normal user using leaked personal information and does illegal activities. This paper proposes an effective method which authenticates a genuine user with real-time. The method use the user's profile which is a record of user's behavior created by Membership Analysis(MA) and Markov Chain Model(MCM). In addition to, user's profile is augmented by a Time Weight(TW) which reflects the user's tendency. This method can detect a malicious user who camouflage normal user. Even if it is a genuine user, it can be determined as an abnomal user if the user acts beyond the record profile. The result of experiment showed a high accuracy, 96%, for the correct user.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.6
• /
• pp.537-544
• /
• 2009

This paper concerns analysis technique on determining of attitude control gain in the low frequency region using stability area. The stability area is defined by the D-Decomposition method, which was designed by Neimark. In this paper, it is introduced D-Decomposition method from reference paper and design attitude control gain of generic launch vehicle during first stage flight phase. For selecting PD control gain, it is considered the system parameter uncertainty about whole first-stage flight phase, represented the stability area boundary on each case. After deciding the PD control gain using stability area method, it is applied to launch vehicle linear model, and checking the stability margin requirement, frequency response characteristics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.163-170
• /
• 2023

This paper introduces the semantic modeling technology for autonomous control of manufacturing facilities and status definition algorithm. With the development of digital twin technology and various ICT technologies of the smart factory, a new production management model is being built in the manufacturing industry. Based on the advanced smart manufacturing technology, the status determination algorithm was presented as a methodology to quickly identify and respond to problems with autonomous control and facilities in the factory. But the existing status determination algorithm informs the user or administrator of error information through the grid map and is presented as a model for coping with it. However, the advancement and direction of smart manufacturing technology is diversifying into flexible production and production tailored to consumer needs. Accordingly, in this paper, a technology that can design and build a factory using a semantic-based Linked List data structure and provide only necessary information to users or managers through graph-based information is introduced to improve management efficiency. This methodology can be used as a structure suitable for flexible production and small-volume production of various types.