Korean | English

pISSN : 1975-7700 / eISSN : 2734-0570

Home > Explore Content > All Issues > Article List

2019, Vol.14, No.4

  • 1.

    Reliability Analysis of Fuzzy Systems Based on Pythagorean Fuzzy Sets

    Cho, Sang Yeop | 2019, 14(4) | pp.319~326 | number of Cited : 1
    Abstract PDF
    Reliability models play an important role when we design the engineering systems. In conventional reliability model we attempts to describe the values for the reliability of the systems with accurateness. But in real world it is often difficult to get the these exact values. To overcome these problem the fuzzy set theory is used in the reliability model for engineering systems. In the fuzzy sets, the reliability is represented by a real number as the degree of membership of the fuzzy set. ∈ . In the interval valued fuzzy sets, the reliability is described by an interval as the degree of membership of the interval valued fuzzy sets. 0 ≤ ≤ ≤ 1, ⊆ . In the intuitionistic fuzzy sets to express the belief in a belief systems, the reliability is represented by the degree of true membership and degree of falsity membership . , ∈ , 0 ≤ + ≤ 1. In the neurotrophic sets that can represent indeterminacy the reliability is represented as a true membership value , an indeterminacy membership value , and a false membership value . In the multicriteria decision making, the decision maker may or may not provide a degree of satisfying the criteria . In this case, the preference for can be 0 ≤ ≰ 1, which is difficult to process with the conventional fuzzy sets. In this paper, we propose a method to evaluate the reliability of decision making system using Pythagorean fuzzy sets which can be used to solve this problem.
  • 2.

    A Study of User Text Sentiment Dictionary for Food Recommendation Service on Big Data Environment

    Cho Jin Kwan | 2019, 14(4) | pp.327~334 | number of Cited : 2
    Abstract PDF
    In general, it is practice to assess food tastes based on sensory tests, however, this method has a considerable disadvantage in which it is pricey and need to required more time. In addition, important disparity appear in relying on each evaluator. We make a good food tastes up, we are necessary to process as following; Firstly, a pre-taste User text sentiment dictionary is based on establishment a kind of food studies and then gather this information on twitter data of social network service, internet and social media so on. Secondary, many information are based on anticipate in original food tastes data by web-based and mobile-based from their systems. Food name of providing on social network service and internet is different each of names with their food tastes. After all, This data is divided into four different names look over stemming that new savors and foods words are found in order to add keyword to taste sentiment dictionary. Accordingly, frequency measurement of newly formated taste keyword is important based on sensitivity of filtering data by utilizing a pre-taste word emotional dictionary determined by the weight of the food taste keyword and it also illustrates the taste of foods by taste dictionary.
  • 3.

    A Recommendation Technique Based on Offline Product Using Similarity

    Kim Chul Jin , Cheon-Woo Jo , Jeong, JiHyun | 2019, 14(4) | pp.335~344 | number of Cited : 1
    Abstract PDF
    The online shopping mall can efficiently provide the recommendation product to the user by using the purchase transaction information of the user. However, in the offline store, there is a limit in providing recommended products in real time using information of users or purchase transaction information. Currently, O2O service provision is spreading, but development and research on personalized recommendation service based on offline products are insufficient. In this paper, we propose an architecture for recommending products suitable for users by calculating similarity between products based on offline individual products and online transaction information. We also propose a procedure for deriving a recommendation product among the constituent modules constituting the architecture. The offline individual product is identified through the Beacon sensor, and the user selects the offline product received from the beacon sensor to determine interest. It calculates the similarity based on offline products and online transaction information and provides top-n recommended products to users. We prove the feasibility of the architecture of this study by constructing a system that recommends products that interest the user by calculating the similarity for offline clothing of clothing store. The existing researches recommend brand based on the purchase history of the offline store visited by the user, but in this paper, it is different in terms of providing recommended products for individual products.
  • 4.

    Analysis and Development Direction of Education Content on AI speakers Based on Gagné’s Instructional Theory: Focused on Amazon Alexa Skills

    Jun Seo Park , Yujin Kim , Kim, Min Young and 1 other persons | 2019, 14(4) | pp.345~358 | number of Cited : 4
    Abstract PDF
    The artificial intelligence (AI) speaker, as an intelligent personal assistant, interacts with users and delivers content under voice user interfaces. Amazon is leading the market by running open the AI Speaker “skills” ecosystem. Accordingly, educational content skills on AI speakers are increasing and the future of learning could use some features of AI speakers. This research was conducted to analyze major educational content in terms of Gagné’s instructional theory of nine events including “gaining attention (reception),” “informing learners of the objective (expectancy),” “stimulating recall of prior learning (retrieval),” “presenting the stimulus (selective perception),” “providing learning guidance (semantic encoding),” “eliciting performance (responding),” “providing feedback (reinforcement),” “assessing performance (retrieval),” and “enhancing retention and transfer (generalization)” and to suggest future directions. A total of 30 representative educational skills from Amazon “Echo” were investigated to check the effective applications of nine instructional events. As a result, “gaining attention,” “informing learners of objectives,” and “eliciting performance” were applied to many of the skills. However, “stimulating recall of prior learning” and “enhance retention and transfer” were not. Based on the findings, design based on structural understandings and technical properties of the AI speaker, design applied to constructivist learning paradigm, and design for effective instructional strategies were suggested.
  • 5.

    A Study on System Identification Using Deep Learning

    Joung, Houng Kun , Wongeun Oh | 2019, 14(4) | pp.359~368 | number of Cited : 3
    Abstract PDF
    This paper deals with a study on a system identification using deep learning in the case of a controller tuning for the system where a time delay exists. Of studies on the controller tuning for the system identification, the controller tuning method suggested by Yunwana and Seborg(1982) has an advantage of taking a good control over either none or small time delays due to phase error by Pade' approximation, whereas it comes with a disadvantage of having a greater estimated of time delay over the presence of a large time delay and of being unable to be used in a system. Furthermore, the trial-and-error method suggested by Zigler-Nichols and commonly used in industrial fields shows a disadvantage which is time consuming for a controller tuning. The controller tuning using a process response curve suggested by Cohen-Coon has a benefit of cutting more time taken for a controller tuning than the method by Zigler-Nichols does. It also faces a limitation of being applicable only to the open loop system but not applicable to the close loop system. To make up for these disadvantages, the Suh-suggested method, as its benefit, is applicable even to the close loop system. On top of this, it proposed a controller's optimal tuning method by reducing phase error through setting up control factors in the Pade' approximation with respect to the phase error generated in converting time delay into Pade' approximation. This method, however, involves putting control factors in proportion to time-delay constant values, which is therefore - as a disadvantage - not analytical. This paper went through a theoretical analysis on phase error as an analytical method to solve an issue involving the large estimation of phase error by Pade' approximation and time delay with the use of deep learning. Presented based on the findings of this existing researcher Suh (1984) was a new optimal tuning method dedicated to reducing phase error to a optimal level by setting control factors using the deep belief network algorithm out of deep learning algorithms. Besides, a related simulation was performed to compare the trial-and-error method by Zielger-Nichols and the tuning method for a controller suggested by Yunwana-Seborg, and the validity of the methods suggested in this paper was verified, accordingly.
  • 6.

    A Study on the Dynamic Characteristics of the Mobile Telecommunication Standard Essential Patents

    Sangoon Yang , Taehyun Jung | 2019, 14(4) | pp.369~380 | number of Cited : 0
    Abstract PDF
    Using 23,879 standard essential patents across three generations of mobile telecommunication technologies, we analyze technology and market characteristics of standard technologies. We collected standard essential patents from the ETSI online IPR database and matched the collected standard patent data with patent information from the European Patent Office patent database to form a set of analysis data. Analytic criteria include the type of firms, geographical features, the type of products, market positions of firms, and application year. Analysis implies strengthening competition for standard essential patents along with the evolution of standard technology. Mobile handsets and equipment manufacturers have the highest share of standard patents across all of its standard technologies, from the second to the fourth generation, and has steadily grown. In contrast, non-practicing entities did not have a high share, but their share growth was evident from the late 1990s when standardization began. Geographically, while the share of European firms decreased, the share of Asian firms has increased. The results of these standard essential patent analyses were similar to the major trends of firms in the mobile telecommunication market, indicating that the standard essential patent analysis can be an appropriate approach for analyzing the status and strategy of the firm's research and development.
  • 7.

    High-School Baseball Pitcher’s Pitching Speed Prediction Using Linear Regression Analysis Method

    Young Hwan Oh | 2019, 14(4) | pp.381~390 | number of Cited : 4
    Abstract PDF
    Recently, studies on artificial intelligence such as AlphaGo and machine learning have been actively conducted. In statistics, linear regression is a regression method that models the linear correlation between dependent variable y and one or more independent variables y. Generally, a linear regression model is established using least square method. In other words, linear regression analysis is a method of modeling the relationship between independent variables, dependent variables, and constant terms. There is a simple linear regression method that models the relationship between two variables and a multiple linear regression method based on two or more independent variables. In a baseball game, the pitcher must be good at ball speed, pitching control, pitching balance, etc., in order to get good results when dealing with batter. High school baseball player’s pitching speed is important factor to grow as excellent pitcher. Also, pitcher's ball speed is one of the important factors that determine the winning or defeat of the baseball game. In this paper, we use the Deep Learning Framework(Tensorflow) to measure ball speed of pitcher among high school baseball players and use it for athlete 's exercise and training rehabilitation. In this study, we generate training data about stride and speed of the pitcher and perform the linear regression prediction method using the gradient-descent method which is the optimization algorithm.
  • 8.

    A Study on the Spoken Language Processing Technology Based on Big Data

    Cho Jin Kwan | 2019, 14(4) | pp.391~399 | number of Cited : 1
    Abstract PDF
    Among the age of multiple information processing with smart device, many users feel each information and comfortable life through their smart device and computer so on. The area of language processing about multiple information make an automatically recognition and processing by computer with human language, and study their algorithm. In addition, it provides a several of application services such as siri, speech conversation system. Especially, language processing technology offer to valuable service in big data environment, and necessary to essential technology to processing big speech and text information. Moreover, big data-based application system become main resource that make a good performance using language processing technology by huge data. Moreover, our research provide web/app environment-based speech collaboration, big data-based both speech signal processing, and speech collaboration algorithm. Big data-based both speech signal processing and speech algorithm carry out by transaction procedure organically. By the transaction procedure, we had an experiment with Trek user speech data using RLS and SNR algorithm for big data-based language processing. Accordingly, in this paper, we propose big data-based information processing with many pre-research in order to improve a capability of the information processing technology using big data.
  • 9.

    An Agricultural IoT Service Configuration System Using Smart Devices

    Byoung-Chan Jeon , Da-Hyun Kang , Ki-Young Kim and 1 other persons | 2019, 14(4) | pp.401~410 | number of Cited : 2
    Abstract PDF
    As the IoT market grows, IoT services are being commercialized in various fields. However, existing IoT applications are built with proprietary protocols and vertical configurations of devices. Therefore, it requires managing , such as initialization and registration, of IoT devices based on standard protocols and flexible user service configuration that satisfy user needs. It is more important in agricultural IoT services which collects environmental data with various sensors to configure devices and user services easily and efficiently. In this paper, we design smart devices which can be managed efficiently and provide user-oriented services. Also, agricultural IoT service configuration system is proposed using the devices. Proposed smart device uses MQTT protocol which is easy to expand the device to initialized, collect sensor data and control actuators. Also, Node-RED, which is a visual IoT application development tool, is used to construct flexible services based on user's needs. The prototype for the service configuration of agricultural environment sensors is implemented and tested using the proposed service configuration techniques. In the future, we will study environmental sensors for the improvement of agricultural productivity, facilities control and growth environment management system based on facility sensors. Also, big data platform will be implemented using the information of the smart devices.
  • 10.

    A Comparative Study of the Speech Signal Parameters for the Consonants of Pyongyang and Seoul Dialects - Focused on the affricates “ㅈ/ㅉ/ㅊ”

    Kwang-Bock You , So, Shin-ae , Kanghee Lee | 2019, 14(4) | pp.411~423 | number of Cited : 0
    Abstract PDF
    In this paper, from the point of view of speech signal processing as an engineering application, the comparative study of the Pyongyang and Seoul dialects is performed. In special, the affricates "ㅈ, ㅉ, ㅊ", which would have different phonetic values between Pyongyang and Seoul dialects, are focused and compared. For these consonants, the speech parameters such as the spectrogram, pitch, and Formant frequencies are extracted (measured) and the differences in their phonetic values of these two regions have been compared. It is confirmed that for these consonants, the Pyongyang dialects have higher energy cohesion than the Seoul dialects, and the distribution of Formant frequency was well distinguished. With the vowel study of Pyongyang dialect, which was carried out with phonological or experimental phonological methods, this paper presents the study of consonants in Pyongyang dialect by using the speech signal parameters. In this paper, a method is proposed for verifying linguistic investigations and experimental phonetic results by using signal processing.
  • 11.

    A Study on Character Setup for 3D Animation: Focusing on Human Style Character

    Hunjin Park | 2019, 14(4) | pp.425~433 | number of Cited : 0
    Abstract PDF
    Making Full 3D Animation is required for many experts include animators and technical directors compared to hand drawn animation. Every artist and technical director has their own task while on production and sometimes consume time as encountering some preventable issues that can be sorted out in early stage of animation. This study provides the ideal rig can be improved before animation process so that production reduces inefficient internal communication and achieving good quality of animation. In animation production, Character Setup is an important process to animate a character. Since Character Technical Directors who conduct Character setup are not always required to have animation experience and sometimes character rig for animation is not good enough to animate in the production ramp-up. Inefficient communication and heavy workload can be caused by the poor condition of rigs. In this paper, at first, We observe the primary character rig that still has potential issues to animate. At second, as researching improved character rigs We provide a better status of character rig. Observation and analysis in this paper is focused on character rigs using Autodesk Maya, which is an animation software as well known in the animation industry nowadays.