• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.247-264
• /
• 2016

With the rapid acceleration of low-birth rate and population aging, the employment of the neglected groups of people including the middle aged class is a crucial issue in South Korea. In particular, in the 2010s, the number of the middle aged who want to find a new job after retirement age is significantly increasing with the arrival of the retirement time of the baby boom generation (born 1955-1963). Despite the importance of matching jobs to this emerging middle aged class, private job portals as well as the Korean government do not provide any online job service tailored for them. A gigantic amount of job information is available online; however, the current recruiting systems do not meet the demand of the middle aged class as their primary targets are young workers. We are in dire need of a specially designed recruiting system for the middle aged. Meanwhile, when users are searching the desired occupations on the Worknet website, provided by the Korean Ministry of Employment and Labor, users are experiencing discomfort to search for similar jobs because Worknet is providing filtered search results on the basis of exact matches of a preferred job code. Besides, according to our Worknet data analysis, only about 24% of job seekers had landed on a job position consistent with their initial preferred job code while the rest had landed on a position different from their initial preference. To improve the situation, particularly for the middle aged class, we investigate a soft job matching technique by performing the following: 1) we review a user behavior logs of Worknet, which is a public job recruiting system set up by the Korean government and point out key system design implications for the middle aged. Specifically, we analyze the job postings that include preferential tags for the middle aged in order to disclose what types of jobs are in favor of the middle aged; 2) we develope a new occupation classification scheme for the middle aged, Korea Occupation Classification for the Middle-aged (KOCM), based on the similarity between jobs by reorganizing and modifying a general occupation classification scheme. When viewed from the perspective of job placement, an occupation classification scheme is a way to connect the enterprises and job seekers and a basic mechanism for job placement. The key features of KOCM include establishing the Simple Labor category, which is the most requested category by enterprises; and 3) we design MOMA (Middle-aged Occupation Matching Algorithm), which is a hybrid job matching algorithm comprising constraint-based reasoning and case-based reasoning. MOMA incorporates KOCM to expand query to search similar jobs in the database. MOMA utilizes cosine similarity between user requirement and job posting to rank a set of postings in terms of preferred job code, salary, distance, and job type. The developed system using MOMA demonstrates about 20 times of improvement over the hard matching performance. In implementing the algorithm for a web-based application of recruiting system for the middle aged, we also considered the usability issue of making the system easier to use, which is especially important for this particular class of users. That is, we wanted to improve the usability of the system during the job search process for the middle aged users by asking to enter only a few simple and core pieces of information such as preferred job (job code), salary, and (allowable) distance to the working place, enabling the middle aged to find a job suitable to their needs efficiently. The Web site implemented with MOMA should be able to contribute to improving job search of the middle aged class. We also expect the overall approach to be applicable to other groups of people for the improvement of job matching results.

• Journal of Global Scholars of Marketing Science
• /
• v.12
• /
• pp.99-119
• /
• 2003

A model is proposed for the role of emotional intensity of a web site, and the moderating influence of product involvement, in the Integrative Framework of persuasion (Meyers-Levy and Malvaiya 1999). The model also appropriately operationalizes the constructs emotional intensity of a web site and product involvement The three routes to persuasion, Central, Peripheral, and Experiential correspond to high, moderate, and low involvement (Meyers-Levy and Malaviya 1999). The involvement construct is measured from message recipients using the Personal Product Inventory (Pill, which was developed to capture the concept of product involvement (Zaichkowsky 1985). The conceptualization of the Personal Product Inventory is a contextrree measure that also has robust psychometric properties when applied to advertisements (Zaichkowsky 1994). The propositions highlight the expected importance of emotional intensity of a web site. The moderating influence of product involvement is also proposed. Specifically, what this work proposes is that the emotional intensity of a product site has a larger impact on attitude change under low product involvement, as opposed to moderate product involvement. Support for this reasoning can be found in the persuasion literature (Petty et al 1986). The Petty et al (1986) frame work is a dual process descriptive and predictive frame work in the area of altitude formation and change. Recently, Myers Levy and Malaviya (1999) have proposed a tri-process framework. This is in tum based on the dual process model of Petty et al. (1986). The study outlined in this paper aims to deepen the Meyers Levy and Malaviya (1999) and frame work. The propositions outlined in the model are empirically tested using a repeated measures experimental design. The emotional intensity is measured using a scale that is based on experts judgments. Using a paired comparison t-test two sites are determined to be of high and low emotional intensity. The model is tested using a repeated measures experimental design. The first independent variable Emotional Intensity of the site is manipulated. The Second independent variable, Personal Product Inventory is measured. While, the dependent variable, product altitude change will also be measured. Utilizing Analysis of Variance (ANOVA) the data is analyzed using SPSS. The results suggest that besides the rational content of messages their emotional content can also influence attitude change. Specifically, it is proposed that the manipulation of emotional intensity of a product Web site has a greater impact on product altitudes under high and low product involvement conditions, rather than moderate product involvement. However, the results for product involvement as a continuous variable has a p value of 0.09. Further, the results for three levels of product involvement were far from significant. For two levels of product involvement also, the results were insignificant, the p value approached 0.20. This evidence indicates that it is premature to conclude that there are three routes to persuasion. A caveat, however, must be added, in that the manipulations may not have been strong enough to test the proposed hypotheses. Further, undoubtedly, there is unequivocal evidence the emotional intensity of a product Web site, as measured here, has a direct impact on product attitudes.

• Journal of the Korean Chemical Society
• /
• v.62 no.5
• /
• pp.398-411
• /
• 2018

The purpose of this study is to investigate the effects of research project activities using the science writing heuristic on science inquiry abilities and attitudes toward science in high school students. For this purpose, we conducted the research project activities using the science writing heuristic consisting of questioning, experimental design, observation, argument and evidence, reading, and reflection steps for 73 students of the second year of science core course in high school in Jeonnam. In order to analyze the effects of the program, we surveyed the scientific inquiry ability and attitude toward science, investigated the perception of the research project class applying science writing heuristic, and conducted interviews when there was difficulty in interpreting the results. And the results of this study are as follows. First, among the science inquiry abilities, the score of Reasoning, Hypothesis setting, Finding variables, Operational definition, Experimental design, Graphing and data interpretation, Generalization was significantly improved statistically (p<.05), but the score of Expectation was not statistically significant (p>.05). Second, among the attitudes toward science, the score of 'Leisure interest in science', 'Enjoyment of science lessons', 'Career interest in science' was significantly improved statistically (p<.05). And the score of 'Attitude to scientific inquiry' decreased but it's not significant statistically. The high school research project applying science writing heuristic had a positive effect on scientific inquiry ability and scientific attitude but it could be burden to students because it is led by students in a form different from general science class for a long time. And so continuous study on research project that minimize these disadvantages and maximize their merits is needed.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.113-130
• /
• 2010

During the decades, considerable human interventions to comprehend the web information were increased continually. The successful expansion of the web services made it more complex and required more contributions of the users. Many researchers have tried to improve the comprehension ability of computers in supporting an intelligent web service. One reasonable approach is enriching the information with machine understandable semantics. They applied ontology design, intelligent reasoning and other logical representation schemes to design an infrastructure of the semantic web. For the features, the semantic web is considered as an intelligent access to understanding, transforming, storing, retrieving, and processing the information gathered from heterogeneous, distributed web resources. The goal of this study is firstly to explore the problems that restrict the applications of web services and the basic concepts, languages, and tools of the semantic web. Then we highlight some of the researches, solutions, and projects that have attempted to combine the semantic web and business support, and find out the pros and cons of the approaches. Through the study, we were able to know that the semantic web technology is trying to offer a new and higher level of web service to the online users. The services are overcoming the limitations of traditional web technologies/services. In traditional web services, too much human interventions were needed to seek and interpret the information. The semantic web service, however, is based on machine-understandable semantics and knowledge representation. Therefore, most of information processing activities will be executed by computers. The main elements required to develop a semantic web-based business support are business logics, ontologies, ontology languages, intelligent agents, applications, and etc. In using/managing the infrastructure of the semantic web services, software developers, service consumers, and service providers are the main representatives. Some researchers integrated those technologies, languages, tools, mechanisms, and applications into a semantic web services framework. Therefore, future directions of the semantic web-based business support should be start over from the infrastructure.

• Journal of KIISE
• /
• v.42 no.8
• /
• pp.998-1009
• /
• 2015

In recent years, there has been a growing interest in RDFS Inference to build a rich knowledge base. However, it is difficult to improve the inference performance with large data by using a single machine. Therefore, researchers are investigating the development of a RDFS inference engine for a distributed computing environment. However, the existing inference engines cannot process data in real-time, are difficult to implement, and are vulnerable to repetitive tasks. In order to overcome these problems, we propose a method to construct an in-memory distributed inference engine that uses a parallel graph structure. In general, the ontology based on a triple structure possesses a graph structure. Thus, it is intuitive to design a graph structure-based inference engine. Moreover, the RDFS inference rule can be implemented by utilizing the operator of the graph structure, and we can thus design the inference engine according to the graph structure, and not the structure of the data table. In this study, we evaluate the proposed inference engine by using the LUBM1000 and LUBM3000 data to test the speed of the inference. The results of our experiment indicate that the proposed in-memory distributed inference engine achieved a performance of about 10 times faster than an in-storage inference engine.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.55-68
• /
• 2024

Plant engineering companies create or refer to requirements documents for each related field, such as plant process/equipment/piping/instrumentation, in different engineering departments. The process-related requirements document includes not only a description of the process but also the requirements of the equipment or related facilities that will operate it. Since the authors and reviewers of the requirements documents are different, there is a possibility that inconsistencies may occur between equipment or parts design specifications described in different requirement documents. Ensuring consistency in these matters can increase the reliability of the overall plant design information. However, the amount of documents and the scattered nature of requirements for a same equipment and parts across different documents make it challenging for engineers to trace and manage requirements. This paper proposes a method to analyze requirement sentences and calculate the similarity of requirement sentences in order to identify semantically identical sentences. To calculate the similarity of requirement sentences, we propose a named entity recognition method to identify compound words for the parts and properties that are semantically central to the requirements. A method to calculate the similarity of the identified compound words for parts and properties is also proposed. The proposed method is explained using sentences in practical documents, and experimental results are described.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.45 no.6
• /
• pp.50-61
• /
• 2017

This study devised a user-participatory design process for users to participate directly in the design process and was implemented at Daegu Padong Elementary School. Users of the school forest were divided into four groups: the lower grades, the upper grades, local residents(parents included), and faculty. The methods of this study were image survey, preference survey, card playing, and model playing. Researchers investigated the level of user satisfaction the following year. The specific design process is as follows: First of all, the concept of the school forest was established through audio-visual education for students and image research was conducted through drawing and painting activities entitled 'The School Forest I Want'. Second, in the image survey, a survey of areas and facilities with high frequency use was conducted in the study of the lower grades, the upper grades, local residents, and the faculty. Image cards of spaces and facilities that showed high preference were produced and the cards were placed in four groups on the school lot plan to check the location of place and facilities desired. Based on this, a model and a basic idea were created through consultation with future users. Lastly, the study design was completed. After 1 year from the completion of the school forest, users were again surveyed regarding their satisfaction with use. The importance of this study is as follows: 1) Treating all potential users of a school forest as the subject of design participation, 2) Reasoning out a plan created by the users themselves through consultation and discussion throughout all steps of the design process, 3) Grasping how users utilize a school forest and the type of spaces most preferred via preference survey after completion of the school forest and showing the importance of user participation by showing that spaces preferred by users were similar to those in which experts were also highly interested.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06a
• /
• pp.17-18
• /
• 2007

데이터베이스 튜닝은 일반적으로 데이터베이스 어플리케이션을 "좀 더 빠르게" 실행하게 하는 일련의 활동을 뜻한다[1]. 데이터베이스 관리자가 튜닝에 필요한 주먹구구식 룰(Rule of thumb)들을 모두 파악 하고 상황에 맞추어 적용하는 것은 비싼 비용과 오랜 시간을 요구한다. 그렇게 때문에 서로 다른 어플 리케이션들이 맞물려 있는 복잡한 서비스는 필수적으로 자동화된 데이터베이스 성능 관리와 튜닝을 필 요로 한다. 본 논문에서는 이를 해결하기 위하여 지식 도매인(Knowledge Domain)을 기초로 한 자동화 된 데이터베이스 튜닝 원칙(Tuning Principle)을 제시하는 시스템을 제안한다. 각각의 데이터베이스 튜닝 이론들은 지식 도매인의 지식으로 활용되며, 성능에 영향을 미치는 요소들을 개체(Object)와 콘셉트 (Concept)로 구성하고 추론 시스템을 통해 튜닝 원칙을 추론하여 쉽고 빠르게 현재 상황에 맞는 튜닝 방법론을 적용시킬 수 있다. 자동화된 데이터베이스 튜닝에 대해 여러 분야에 걸쳐 학문적인 연구가 이루어지고 있다. 그 예로써 Microsoft의 AutoAdmin Project[2], Oracle의 SQL 튜닝 아키텍처[3], COLT[4], DBA Companion[5], SQUASH[6] 등을 들 수 있다. 이러한 최적화 기법들을 각각의 기능적인 방법론에 따라 다시 분류하면 크게 Design Tuning, Logical Structure Tuning, Sentence Tuning, SQL Tuning, Server Tuning, System/Network Tuning으로 나누어 볼 수 있다. 이 중 SQL Tuning 등은 수치적으로 결정되어 이미 존재하는 정보를 이용하기 때문에 구조화된 모델로 표현하기 쉽고 사용자의 다양한 요구에 의해 변화하는 조건들을 수용하기 쉽기 때문에 이에 중점을 두고 성능 문제를 해결하는 데 초점을 맞추었다. 데이터베이스 시스템의 일련의 처리 과정에 따라 DBMS를 구성하는 개체들과 속성, 그리고 연관 관계들이 모델링된다. 데이터베이스 시스템은 Application / Query / DBMS Level의 3개 레벨에 따라 구조화되며, 본 논문에서는 개체, 속성, 연관 관계 및 데이터베이스 튜닝에 사용되는 Rule of thumb들을 분석하여 튜닝 원칙을 포함한 지식의 형태로 변환하였다. 튜닝 원칙은 데이터베이스 시스템에서 발생하는 문제를 해결할 수 있게 하는 일종의 황금률로써 지식 도매인의 바탕이 되는 사실(Fact)과 룰(Rule) 로써 표현된다. Fact는 모델링된 시스템을 지식 도매인의 하나의 지식 개체로 표현하는 방식이고, Rule 은 Fact에 기반을 두어 튜닝 원칙을 지식의 형태로 표현한 것이다. Rule은 다시 시스템 모델링을 통해 사전에 정의되는 Rule와 튜닝 원칙을 추론하기 위해 사용되는 Rule의 두 가지 타업으로 나뉘며, 대부분의 Rule은 입력되는 값에 따라 다른 솔루션을 취하게 하는 분기의 역할을 수행한다. 사용자는 제한적으로 자동 생성된 Fact와 Rule을 통해 튜닝 원칙을 추론하여 데이터베이스 시스템에 적용할 수 있으며, 요구나 필요에 따라 GUI를 통해 상황에 맞는 Fact와 Rule을 수동으로 추가할 수도 었다. 지식 도매인에서 튜닝 원칙을 추론하기 위해 JAVA 기반의 추론 엔진인 JESS가 사용된다. JESS는 스크립트 언어를 사용하는 전문가 시스템[7]으로 선언적 룰(Declarative Rule)을 이용하여 지식을 표현 하고 추론을 수행하는 추론 엔진의 한 종류이다. JESS의 지식 표현 방식은 튜닝 원칙을 쉽게 표현하고 수용할 수 있는 구조를 가지고 있으며 작은 크기와 빠른 추론 성능을 가지기 때문에 실시간으로 처리 되는 어플리케이션 튜닝에 적합하다. 지식 기반 모률의 가장 큰 역할은 주어진 데이터베이스 시스템의 모델을 통하여 필요한 새로운 지식을 생성하고 저장하는 것이다. 이를 위하여 Fact와 Rule은 지식 표현 의 기본 단위인 트리플(Triple)의 형태로 표현된다, 트리플은 Subject, Property, Object의 3가지 요소로 구성되며, 대부분의 Fact와 Rule들은 트리플의 기본 형태 또는 트리플의 조합으로 이루어진 C Condition과 Action의 두 부분의 결합으로 구성된다. 이와 같이 데이터베이스 시스템 모델의 개체들과 속성, 그리고 연관 관계들을 표현함으로써 지식들이 추론 엔진의 Fact와 Rule로 기능할 수 있다. 본 시스템에서는 이를 구현 및 실험하기 위하여 웹 기반 서버-클라이언트 시스템을 가정하였다. 서버는 Process Controller, Parser, Rule Database, JESS Reasoning Engine으로 구성 되 어 있으며, 클라이 언트는 Rule Manager Interface와 Result Viewer로 구성되어 었다. 실험을 통해 얻어지는 튜닝 원칙 적용 전후의 실행 시간 측정 등 데이터베이스 시스템 성능 척도를 비교함으로써 시스템의 효용을 판단하였으며, 실험 결과 적용 전에 비하여 튜닝 원칙을 적용한 경우 최대 1초 미만의 전처리에 따른 부하 시간 추가와 최소 약 1.5배에서 최대 약 3배까지의 처리 시간 개선을 확인하였다. 본 논문에서 제안하는 시스템은 튜닝 원칙을 자동으로 생성하고 지식 형태로 변형시킴으로써 새로운 튜닝 원칙을 파생하여 제공하고, 성능에 영향을 미치는 요소와 함께 직접 Fact과 Rule을 추가함으로써 커스터마이정된 튜닝을 수행할 수 있게 하는 장점을 가진다. 추후 쿼리 자체의 튜닝 및 인텍스 최적화 등의 프로세스 자동화와 Rule을 효율적으로 정의하고 추가하는 방법 그리고 시스템 모델링을 효과적으로 구성하는 방법에 대한 연구를 통해 본 연구를 더욱 개선시킬 수 있을 것이다.

• Journal of Korean Home Economics Education Association
• /
• v.25 no.2
• /
• pp.103-128
• /
• 2013

The purpose of this study was to develop a school violence prevention program featuring the Practical Action Teaching Model(hereafter, PATM) for middle school students to prevent school violence by Home Economics Education. To accomplish this purpose, the processes of analysis, design, development, and evaluation based on ADDIE were conducted. The validity of the program was evaluated twice by Home Economics education experts(36 experts for the first group and 10 experts for the second group) and the contents of the program were modified according to the comments from the evaluators. The school violence prevention program in Home Economics classes consisted of 5 topics such as changing perception on school violence, enhancing self-esteem, relating with others, practicing consideration and sharing, and strengthening the will of preventing school violence. Twenty-four units were developed with 7 practical problems(What should I do to make friends to help with each other?, What should I do to establish positive self-concept?, What should I do to communicate to build good relationship?, What should I do to solve the conflicts peacefully?, What should I do to practice consideration and sharing in food consumption?, and What should I do to practice consideration and sharing in clothing?) in 5 topic areas. Teaching-learning plans included four steps such as problem perception, practical reasoning, action, and evaluation that comprise PATM to solve the practical problems. Every step of the teaching-learning plan consisted of questions for practical reasoning and activity assignments. Materials for students and teachers were developed. Materials for students comprised 80 pieces in total including student activity, reading, movie, and clips to make students enhance understanding and interest. Materials for teachers comprised 35 pieces in total such as rationales, newspaper articles, and movies that make teachers that lesson teaching loads and were helpful for teachers. The PATM was incorporated into developing the program and a Likert-scale was used to assess usefulness, applicability, appropriateness, fidelity, substantiality, and validity of this program. This program gained more than 4.00 on a 1-5 Likert scale. This result indicated that program is expected to be effective and useful to school violence prevention.