• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.3
• /
• pp.261-268
• /
• 2002

This paper represents that auto tunings of membership functions and weights in the fuzzy neural networks are effectively performed by immune algorithm. A number of hybrid methods in fuzzy-neural networks are considered in the context of tuning of learning method, a general view is provided that they are the special cases of either the membership functions or the gain modification in the neural networks by genetic algorithms. On the other hand, since the immune network system possesses a self organizing and distributed memory, it is thus adaptive to its external environment and allows a PDP (parallel distributed processing) network to complete patterns against the environmental situation. Also, it can provide optimal solution. Simulation results reveal that immune algorithms are effective approaches to search for optimal or near optimal fuzzy rules and weights.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.6
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Research in Mathematical Education
• /
• v.14 no.4
• /
• pp.347-360
• /
• 2010

Motivating students to study mathematics is a concern for many mathematics educators. In this paper, we present the outcome of a one semester experiment in which group-work and academic advising were used as teaching strategies in order to improve the motivational level of our students in learning mathematics. Although the students' performance did not show any statistically significant difference between the experimental and control groups, qualitative and other quantitative data collected indicate that the participants in the experiment, especially weak students, have in one way or the other benefited from the teaching approaches. Details of the experiment, the findings and their educational implications are presented.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.12
• /
• pp.1665-1670
• /
• 2018

A convolutional neural network (CNN), which is one of the deep learning models, has been very successful in a variety of computer vision tasks. Filters of a CNN are automatically generated, however, they can be further optimized since there exist the possibility of existing redundant and less important features. Therefore, the aim of this paper is a filter reduction to accelerate and compress CNN models. Evolutionary algorithms is adopted to remove the unnecessary filters in order to minimize the parameters of CNN networks while maintaining a good performance of classification. We demonstrate the proposed filter reduction methods performing experiments on CIFAR10 data based on the classification performance. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• Elastomers and Composites
• /
• v.59 no.1
• /
• pp.22-33
• /
• 2024

Passive radiative cooling is a promising technology for cooling objects without energy input. Passive radiative cooling works by radiating heat from the surface, which then passes through the atmosphere and into space. Achieving efficient passive radiative cooling is mainly accomplished by using materials with high emissivity in the atmospheric window (8-13 ㎛). Research has shown that polymers tend to exhibit high emissivity in this spectral range. In addition to elastomers, other materials with potential for passive radiative cooling include metal oxides, carbon-based materials, and polymers. The structure of a passive radiative cooling device can affect its cooling performance. For example, a device with a large surface area will have a greater amount of surface area exposed to the sky, which increases the amount of thermal radiation emitted. Passive radiative cooling has a wide range of potential applications, including building cooling, electronics cooling, healthcare, and transportation. Current research has focused on improving the efficiency of passive radiative cooling materials and devices. With further development, passive radiative cooling can significantly affect a wide range of sectors.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.23 no.3
• /
• pp.5-17
• /
• 2012

In citation analysis, author names are often used as the unit of analysis and some authors are indexed under the same name in bibliographic databases where the citation counts are obtained from. There are many techniques for author name disambiguation, using supervised, unsupervised, or semisupervised learning algorithms. Unsupervised approach uses machine learning algorithms to extract necessary bibliographic information from large-scale databases and digital libraries, while supervised approaches use manually built training datasets for clustering author groups for combining them with learning algorithms for author name disambiguation. The study examines various techniques for author name disambiguation in the hope for finding an aid to improve the precision of citation counts in citation analysis, as well as for better results in information retrieval.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.65-77
• /
• 2021

COVID-19 has recently impacted the world with the large numbers of infected and deaths. The development of effective COVID-19 vaccine has not been successful. Hence, people have a high concern on the infection of this disease. The infection information from the governmantal public organizations are mainly based on simple summary statistics. Consequently, it is hard to assess the infection risks of individual person and the current location of the person. In this paper, we present a machine learning-based software system that analyzes COVID-19 infection risks and guidelines for safe activities.This paper proposes a suite of risk factors regarding COVID-19 infection and deaths and methods to quantitatively measure the individual and group risks using the proposed metrics. The proposed system utilizes a clustering algorithms and various software approaches that reflect the information and features of inviduals and their geograpical locations.

• Journal of IKEEE
• /
• v.26 no.1
• /
• pp.62-66
• /
• 2022

Recently, there have been many research efforts based on data-based deep learning technologies to deal with the interference problem between heterogeneous wireless communication devices in unlicensed frequency bands. However, existing approaches are commonly based on the use of complex neural network models, which require high computational power, limiting their efficiency in resource-constrained network interfaces and Internet of Things (IoT) devices. In this study, we address the problem of classifying heterogeneous wireless technologies including Wi-Fi and ZigBee in unlicensed spectrum bands. We focus on a data-driven approach that employs a supervised-learning method that uses received signal strength indicator (RSSI) data to train Deep Convolutional Neural Networks (CNNs). We propose a simple measurement methodology for collecting RSSI training data which preserves temporal and spectral properties of the target signal. Real experimental results using an open-source 2.4 GHz wireless development platform Ubertooth show that the proposed sampling method maintains the same accuracy with only a 10% level of sampling data for the same neural network architecture.