• KIISE Transactions on Computing Practices
• /
• v.20 no.9
• /
• pp.492-497
• /
• 2014

In this paper, we propose a method of retrieving opinioned tweets in Twitter, which is the one of the popular Social Network Services and shares diverse opinions among various users. In typical opinion retrieval systems, they may consider the presence of sentiment phrases (subjectivity) as the important factor even if the subjective phrases are not related to a given query or speaker. To alleviate these problems, we utilized the syntactic structure of a sentence to identify the relationships between 1) subjectivity-query and 2) subjectivity-speaker and 3) the syntactic role of subjectivity. Besides, our learning-to-rank approach is trained to retrieve opinioned tweets based on query-relevance, textual features, user information, and Twitter-specific features. Experimental results on real world data show that our proposed method can achieve better performance than several baseline methods in terms of precision and nDCG.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.81-88
• /
• 2018

Spectrum sensing, the key technology of the cognitive radio networks, is used by a secondary user to determine the frequency state of a primary user. The energy detection in the spectrum sensing determines the presence or absence of a primary user according to the intensity of the allocated channel signal. Since this technique simply uses the strength of the signal for spectrum sensing, it is difficult to detect the signal of a primary user in the low SNR band. In this paper, we propose a way to combine spectrum sensing and support vector machine using wavelet packet decomposition to overcome performance degradation in low SNR band. In our proposed scheme, the sensing signals were extracted by wavelet packet decomposition and then used as training data and test data for support vector machine. The simulation results of the proposed scheme are compared with the energy detection using the AUC of the ROC curve and the accuracy according to the SNR band. With simulation results, we demonstrate that the proposed scheme show better determining performance than one of energy detection in the low SNR band.

• The Journal of Korean Association of Computer Education
• /
• v.15 no.1
• /
• pp.55-64
• /
• 2012

The purpose of this study is to identify how realism of pedagogical agent can have impacts on persona effect and cognitive load factors. Eighty-two college students participated, and the independent variables of this study were the degree of image details and presence of gesture. The degree of image details were picture, illustration, and line-drawing. The $3{\times}2$ factorial design was applied. There was a significant interaction effect on the engaging of agent persona instrument. When the learners were under the condition of line-drawing agent without gesture, they showed the highest score on engaging of the agent persona instrument. Regarding the cognitive load factors, when learners under the condition of line-drawing showed the highest score of self-evaluation.

• Journal of The Korean Association For Science Education
• /
• v.24 no.6
• /
• pp.1206-1215
• /
• 2004

In this study, we explored the students' perceptions on the online discussion system for physics investigation as the physics education program. With these, we explored the characteristics of online discussion system. For these, the questions and interviews were executed in order to get informations about user-friendly characteristics of on-line discussion learning system of physics investigation, asynchronicity of on-line investigation discussion, on-line investigation discussion related to writing, visual cues and physical presence of on-line investigation discussion and preference of on-line investigation discussion. The students represented that there were two advantages in the online investigation discussion. One is that they could participate in the on-line investigation discussion without the restriction of time and space, and the other is that they could enter into a dispute with sufficient consideration because of the asynchronicity characteristic of online investigation discussion. Although the online educational activity is mainly achieved by independent work on the part of students, the role of teacher and parents is more important than the technical part of online educational system for the active participation.

• CELLMED
• /
• v.6 no.1
• /
• pp.6.1-6.6
• /
• 2016

Polycystic Ovarian Syndrome (PCOS) has now become more common in occurrence in women of reproductive age, particularly in urban and semi-urban population in India. So there is a need to investigate this phenomenon taking into consideration various aspects including possible treatment method to ameliorate/eradicate this syndrome, which has far reaching socio-economic impact and consequences, in view of infertility and irregular menstrual cycles frequently associated with this syndrome. Homeopathy is a branch of traditional alternative medicine which is gaining popularity in India and some other developing countries, as also in some of the developed countries in Europe. With this background scenario, we have made an attempt to treat cases of confirmed PCOS and tried to compare the relative efficacy of two potentized homeopathic drugs, namely, Lycopodium clavatum (Lyco) and Calcarea carbonica (Calc), most frequently used by homeopathic practitioners, selecting different potencies of the drugs, depending on condition/guiding symptom(s) of the patients. While the main focus was pointed on total/partial removal of cysts, data pertaining to different PCOS associated symptoms were also compared for the sake of learning if the two drugs had differential effects on these symptoms also. The study parameters in this investigation included: regularity/irregularity of menstrual cycle, presence/absence of acne, hirsutism, male type alopecia, acanthosis nigricans, body/mass index (BMI) and waist-hip ratio. Overall results provided clear evidences that both these homeopathic drugs had great ameliorating effects on PCOS, although each drug had a little different effect in respect of the individual parameters of this study.

• Journal of Engineering Education Research
• /
• v.11 no.3
• /
• pp.78-89
• /
• 2008

This paper analyses the codes of ethics of eight engineering societies in USA and Korea focusing on fundamental canons, and major findings are as follows. Firstly, engineering societies in Korea began to make a code of ethics recent1y. Secondly, codes of ethics in USA have similar contents by mutual learning contrary to Korean cases. Thirdly, some codes of ethics in Korea are very poor and their presence are not well perceived. Fourthly, codes of ethics in Korea don't cover comprehensively responsibility to the public, to employers or clients, and to the profession. Fifthly, engineering societies in USA hold paramount the safety, health, and welfare of the public. Sixthly, new social issues including sustainable development are well discussed in the codes of ethics in USA.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.48-55
• /
• 2009

Prior research works in indoor-outdoor classification have been conducted based on a simple combination of low-level features. However, since there are many challenging problems due to the extreme variability of the scene contents, most methods proposed recently tend to combine the low-level features with high-level information such as the presence of trees and sky. To extract these regions from videos, we need to conduct additional tasks, which may yield the increasing number of feature dimensions or computational burden. Therefore, an efficient indoor-outdoor scene classification method is proposed in this paper. First, the video is divided into the five same-sized blocks. Then we define and use the edge and color orientation histogram (ECOH) descriptors to represent each sub-block efficiently. Finally, all ECOH values are simply concatenated to generated the feature vector. To justify the efficiency and robustness of the proposed method, a diverse database of over 1200 videos is evaluated. Moreover, we improve the classification performance by using different weight values determined through the learning process.

• Journal of Wetlands Research
• /
• v.21 no.4
• /
• pp.267-280
• /
• 2019

Adaptive Management (AM) is one of the best available approaches for managing natural resources in the presence of uncertainty. In spite of the limitations, AM has been widely applied in nature resource management policies and plans internationally, while application of AM in nature resource management in Korea is limitedly used. Accordingly, this study reviews application of AM in nature resource management research in Korea with respect to its definitions, procedures, impediments and considerations. The present study also reviews recent ecological modelling studies which is an essential component of AM approach. Finally, management of artificial sea forest, coastal wetlands and fisheries are suggested as the recommended fields to adopt AM.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1574-1580
• /
• 2020

Traditional pose estimation methods include using special devices or images through image processing. The disadvantage of using a device is that the environment in which the device can be used is limited and costly. The use of cameras and image processing has the advantage of reducing environmental constraints and costs, but the performance is lower. CNN(Convolutional Neural Networks) were studied for pose estimation just using only camera without these disadvantage. Various techniques were proposed to increase cognitive performance. In this paper, the effect of the skip connection on the network was experimented by using various skip connections on the joint recognition of the hand. Experiments have confirmed that the presence of additional skip connections other than the basic skip connections has a better effect on performance, but the network with downward skip connections is the best performance.