• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.125-130
• /
• 2018

Linear discriminant analysis is a statistical analysis method that is generally used for dimensionality reduction of the feature vectors or for class classification. However, in the case of a data set that cannot be linearly separated, it is possible to make a linear separation by mapping a feature vector into a higher dimensional space using a nonlinear function. This method is called generalized discriminant analysis or kernel discriminant analysis. In this paper, we carried out target classification experiments with active sonar target signals available on the Internet using both liner discriminant and generalized discriminant analysis methods. Experimental results are analyzed and compared with discussions. For 104 test data, LDA method has shown correct recognition rate of 73.08%, however, GDA method achieved 95.19% that is also better than the conventional MLP or kernel-based SVM.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.4
• /
• pp.387-402
• /
• 2014

In congested urban areas, constructions of tunnel structures have became necessary due to a lack of surface space. The excavation of any tunnel generated the ground disturbances of surrounding ground and displacements is major concern. Therefore, a study of tunnel stability is necessary. In this study, the authors have investigated the stability and failure pattern of tunnel through the model tunnel test. In this study, the close range photogrammetry was used to measure the ground deformation. The measured data was converted to displacement vectors and contours. And then it compared to FE analysis and empirical formula. In addition, this study presented the comparison between steel pipe reinforced model tunnel and unreinforced model tunnel. The ground deformation for both the steel pipe reinforced model tunnel and the unreinforced model tunnel was analysed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.9
• /
• pp.783-790
• /
• 2016

One of the main factors related to the deterioration of estimation accuracy in inertial measurement unit (IMU)-based orientation determination is the object's acceleration. This is because accelerometer signals under accelerated motion conditions cannot be longer reference vectors along the vertical axis. In order to deal with this issue, some orientation estimation algorithms adopt acceleration-compensating mechanisms. Such mechanisms include the simple switching techniques, mechanisms with adaptive estimation of acceleration, and acceleration model-based mechanisms. This paper compares these three mechanisms in terms of estimation accuracy. From experimental results under accelerated dynamic conditions, the following can be concluded. (1) A compensating mechanism is essential for an estimation algorithm to maintain accuracy under accelerated conditions. (2) Although the simple switching mechanism is effective to some extent, the other two mechanisms showed much higher accuracies, particularly when test conditions were severe.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.1
• /
• pp.56-61
• /
• 2001

This paper presents the real-time implementation of an AMR (Adaptive Multi Rate) vocoder which is included in the asynchronous International Mobile Telecommunication (IMT)-2000 mobile ASIC. The implemented AMR vocoder is a multi-rate coder with 8 modes operating at bit rates from 12.2kbps down to 4.75kbps. Not only the encoder and the decoder as basic functions of the vocoder are implemented, but VAD (Voice Activity Detection), SCR (Source Controlled Rate) operation and frame structuring blocks for the system interface are also implemented in this vocoder. The DSP for AMR vocoder implementation is a 16bit fixed-point DSP which is based on the TeakLite core and consists of memory block, serial interface block, register files for the parallel interface with CPU, and interrupt control logic. Through the implementation, we reduce the maximum operating complexity to 24MIPS by efficiently managing the memory structure. The AMR vocoder is verified throughout all the test vectors provided by 3GPP, and stable operation in the real-time testing board is also proved.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.8
• /
• pp.1002-1009
• /
• 2012

This paper shows the research about radar target recognition using the measured radar signals from MSU(Michgan State University) bistatic radar system. In this research, we first did the bistatic measurements at $30^{\circ}$, $60^{\circ}$, $90^{\circ}$ using F-14, Mig-29, and F-22 scale models. Then, we extract the target feature vectors using time-frequency analysis methods such as STFT(Short Time Fourier Transform) and CWT(Continous Wavelet Transform) and perform the target classification test using MLP(Multi-layerd Perceptron) neural network. The results show that the target classification performance is too much dependent on the bistatic angles and the best performance is obtained at the $60^{\circ}$ bistatic angle.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.222-228
• /
• 2022

In today's era of digital technologies, the problem of religious communication in the cyberspace is being actualized, since the globality and accessibility of the WWW makes it one of the most effective and promising channels for transmitting various kinds of messages, including those of a religious nature. Today, religious organizations and movements pay the closest attention to the virtual media space, not only using it to attract new followers, but also for religious PR, image-making and branding, informing the world about themselves through news from the life of the organization and its followers. An equally important form of electronic communication in the online sphere is currently the interaction of various religious movements and religious cultures in general, or the dialogue of confessions in particular. Research in the digital space makes it possible to identify important trends in religious spheres based on the analysis of the flow of information on the Internet, to demonstrate the specifics of individual media outlets and the consequences of their activities for interreligious dialogue, to study the role of the Internet in changing religious beliefs, the possibility of changing religious identity, retrospective development of religious enlightenment at the turn of the century, to determine the vectors of possible interreligious interaction and discuss the role of digital technologies in the work of religious structures, to state the need to continue an active dialogue between representatives of religious movements, to hold expert seminars on interreligious dialogue on a regular basis, and to record the risks generated by the digital space. Thus, the coronavirus pandemic served as a background and context, a litmus test and a catalyst for accelerating and intensifying interreligious, interfaith dialogue and dialogue between religious organizations and society.

• Korea Science and Art Forum
• /
• v.30
• /
• pp.41-56
• /
• 2017

This study is an intensive study on Tae Rin Lee's research results. A linear system for Estimating the Strength of Super Personal Conflict (ESSPC) in animations is proposed. Tae Rin Lee has extracted the Super Personal Conflict (SPC) shots of animations, and obtained the strength through the experts' psychological test experiment. The purpose of this study is to find a model that automatically computes the superpersonal conflict intensity value (ESSPC). By utilizing these results, 1) 20 image feature vectors are suggested for analyzing the SPC, and 2) a linear system is found for auto-calculating ESSPC by using the pseudo inverse matrix. The proposed system shows 9.25% root mean square error and the effectiveness is proven.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.3
• /
• pp.279-284
• /
• 2009

Speaker verification determines whether the claimed speaker is accepted based on the score of the test utterance. In recent years, methods based on Gaussian mixture models and universal background model have been the dominant approaches for text-independent speaker verification. These speaker verification systems based on these methods provide very good performance under laboratory conditions. However, in real situations, the performance of speaker verification system is degraded dramatically. For overcoming this performance degradation, the feature recombination method was proposed, but this method had a drawback that whole sub-band feature vectors are used to compute the likelihood scores. To deal with this drawback, a modified feature recombination method which can use each sub-band likelihood score independently was proposed in our previous research. In this paper, we propose a sub-band weighting method based on sub-band signal-to-noise ratio which is combined with previously proposed modified feature recombination. This proposed method reduces errors by 28% compared with the conventional feature recombination method.

• Asia Pacific Journal of Corpus Research
• /
• v.5 no.1
• /
• pp.23-36
• /
• 2024

This research centers on the Taiwan Eye-Movement Corpus of Spanish (TECS), a specially created corpus comprising eye-tracking data from Chinese-speaking learners of Spanish as a third language in Taiwan. Its primary purpose is to explore the broad utility of TECS in understanding language learning processes, particularly the initial stages of language learning. Constructing this corpus involves gathering data on eye-tracking, reading comprehension, and language proficiency to develop a machine-learning model that predicts learner behaviors, and subsequently undergoes a predictability test for validation. The focus is on examining attention in input processing and their relationship to language learning outcomes. The TECS eye-tracking data consists of indicators derived from eye movement recordings while reading Spanish sentences with temporal references. These indicators are obtained from eye movement experiments focusing on tense verbal inflections and temporal adverbs. Chinese expresses tense using aspect markers, lexical references, and contextual cues, differing significantly from inflectional languages like Spanish. Chinese-speaking learners of Spanish face particular challenges in learning verbal morphology and tenses. The data from eye movement experiments were structured into feature vectors, with learner behaviors serving as class labels. After categorizing the collected data, we used two types of machine learning methods for classification and regression: Random Forests and the k-nearest neighbors algorithm (KNN). By leveraging these algorithms, we predicted learner behaviors and conducted performance evaluations to enhance our understanding of the nexus between learner behaviors and language learning process. Future research may further enrich TECS by gathering data from subsequent eye-movement experiments, specifically targeting various Spanish tenses and temporal lexical references during text reading. These endeavors promise to broaden and refine the corpus, advancing our understanding of language processing.