• Title/Summary/Keyword: Fitness Sharing

Search Result 28, Processing Time 0.03 seconds

Performance Improvement of Ensemble Speciated Neural Networks using Kullback-Leibler Entropy (Kullback-Leibler 엔트로피를 이용한 종분화 신경망 결합의 성능향상)

  • Kim, Kyung-Joong;Cho, Sung-Bae
    • The Transactions of the Korean Institute of Electrical Engineers D
    • /
    • v.51 no.4
    • /
    • pp.152-159
    • /
    • 2002
  • Fitness sharing that shares fitness if calculated distance between individuals is smaller than sharing radius is one of the representative speciation methods and can complement evolutionary algorithm which converges one solution. Recently, there are many researches on designing neural network architecture using evolutionary algorithm but most of them use only the fittest solution in the last generation. In this paper, we elaborate generating diverse neural networks using fitness sharing and combing them to compute outputs then, propose calculating distance between individuals using modified Kullback-Leibler entropy for improvement of fitness sharing performance. In the experiment of Australian credit card assessment, breast cancer, and diabetes in UCI database, proposed method performs better than not only simple average output or Pearson Correlation but also previous published methods.

Fitness Sharing Particle Swarm Optimization Approach to FACTS Installation for Transmission System Loadability Enhancement

  • Chang, Ya-Chin
    • Journal of Electrical Engineering and Technology
    • /
    • v.8 no.1
    • /
    • pp.31-39
    • /
    • 2013
  • Proper installation of Flexible AC Transmission Systems (FACTS) devices in existing transmission networks can enable power systems to accommodate more power transfer with less network expansion cost. The problem to maximize transmission system loadability by determining optimal locations and settings for installations of two types of FACTS devices, namely static var compensator (SVC) and thyristor controlled series compensator (TCSC), is formulated as a mixed discrete-continuous nonlinear optimization problem (MDCP). For solving the MDCP, in the paper, the proposed method with fitness sharing technique involved in the updating process of the particle swarm optimization (PSO) algorithm, can diversify the particles over the search regions as much as possible, making it possible to achieve the optimal solution with a big probability. The modified IEEE-14 bus network and a practical power system are used to validate the proposed method.

An Improved FastSLAM Algorithm using Fitness Sharing Technique (적합도 공유 기법을 적용한 향상된 FastSLAM 알고리즘)

  • Kwon, Oh-Sung;Hyeon, Byeong-Yong;Seo, Ki-Sung
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.22 no.4
    • /
    • pp.487-493
    • /
    • 2012
  • SLAM(Simultaneous Localization And Mapping) is a technique used by robots and autonomous vehicles to build up a map within an unknown environment and estimate a place of robot. FastSLAM(A Factored Solution to the SLAM) is one of representative method of SLAM, which is based on particle filter and extended Kalman filter. However it is suffered from loss of particle diversity. In this paper, new approach using fitness sharing is proposed to supplement loss of particle diversity, compared and analyzed with existing methods.

Mobile Fitness Recommendation System Based on Data Sharing Mechanism (데이터 공유 메커니즘을 이용한 모바일 피트니스 추천 시스템)

  • Lee, Jong-Won;Kang, Hee-Beom;Bae, Keun-Ho;Ban, Tae-Hak;Jung, Hoe-Kyung
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2015.10a
    • /
    • pp.661-663
    • /
    • 2015
  • It is currently being used or being developed mobile fitness application systems associated with the most obese. These systems give or notify the user to reduce the weight, check your momentum to inform your calories burned. However, the accuracy is low because it provides and manages the common data without considering the individual characteristics or the environment of the user. In this paper analyzes the disadvantage of mobile fitness system. To solve this problem it presents the data sharing mechanism to alert you to the exercise equipment with the other users belonging to the BMI group, such as yourself. And it proposes the design of a mobile fitness system which is based on the data sharing mechanism.

  • PDF

The Effect of Virtual Reality-based Physical Activity Therapy Program on Physical Fitness Factors in Adult - Systematic Reviews - (가상현실 기반 신체활동 치유 프로그램이 성인의 체력요인에 미치는 효과 - 체계적 고찰 -)

  • Park, Sang-Kyun;Tomita, Sigeru;Kim, Dae-Sik;Lee, Wang-Lok
    • Journal of Korean Society of Rural Planning
    • /
    • v.28 no.2
    • /
    • pp.33-40
    • /
    • 2022
  • The purpose of this study is to review the effect of previous research data with virtual reality-based Physical Activity Therapy Programs(PATPs) in adult on the physical fitness factors. Research articles were retrieved from 2008 to 2021 with the Research Information Sharing Service(RISS) and Pubmed database. The main search terms were 'care', 'therapy', 'healing', 'exercise' or 'physical activity', and 'virtual reality'. The criteria for selecting articles of this study were the originality, duplication, Randomized controlled trial(RCT) experiment and subject. Finally, 18 papers were selected among 318 articles, which were excluded if any of the criteria was not satisfied. Most of papers(15) were conducted in the last 5 years, because of the high interest due to the development of virtual reality implementation technology and COVID-19 pandemic. The participants were mainly patients(8), and the types of diseases were stroke(2). The physical fitness factors were mostly balance ability(7), muscle strength(7), and range of motion(6). All the physical fitness factors were significantly improved after PATPs. However, 11 studies were conducted for less than 4 weeks, including 6 studies were performed a bout of acute exercise. Also, 14 studies did not clearly present the intensity of PATPs. In addition, there were 9 studies, that simply applied games without specialized programs. In conclusion, it seems that virtual reality-based PATPs have a positive effect on physical fitness factors. However, VR-based PATPs should be specialized and developed in order to verify their effectiveness for the further research.

A Study on the Data Sharing Mechanism Design in Android-Based Fitness System (안드로이드 기반 휘트니스 시스템에서의 데이터 공유 메커니즘 설계)

  • Kang, Hee-beom;Jang, Jae-myung;Lee, Jong-won;Jung, Hoe-kyung
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2015.05a
    • /
    • pp.614-616
    • /
    • 2015
  • Current U-Healthcare has become specialized in Wellness center in the prevention of future health care concept of a health center, treatment. Wellness is the development of which has been emerging field of fitness system to evolve along with the key areas of U-Healthcare. Traditional Fitness system, one between the trainer and the user: 1. Consultation was only possible, the number of trainers are limited, this problem can be reduced individual coaching time existed as more number of users who can receive coaching at certain times of the day. In this paper, we design a mechanism that allows management by grouping field value of a DB table in the user's BMI(Body Mass Index) index and fitness trainer system to efficiently coaching a plurality of users similar BMI index.

  • PDF

The Effect of Motivation-Reward Fit on Commitment and Knowledge Sharing Activities in Communities of Practice (CoP(Community of Practice)에서 참여동기-보상 적합이 CoP 몰입과 지식공유활동에 미치는 영향)

  • Kim, In-Hak;Lee, Ji-Hyeon;Koh, Joon;Kim, Hee-Woong
    • The KIPS Transactions:PartD
    • /
    • v.17D no.3
    • /
    • pp.209-222
    • /
    • 2010
  • As the business competition between firms is getting intense, one of the sources of competitive advantage is effectively and efficiently to create, share, and apply information/knowledge among employees. Most of the firms which conduct knowledge management are operating a Community of Practice(CoP) in order to create, share and utilize this kind of information/knowledge resource. Recently, the CoP is getting out of its informal and spontaneous manner and is beginning to be led by the top management, receiving official support, in order to achieve the organization's strategic goals. However, the corporation's strategic operation of the CoP is not only against its original characteristics but also hampers the spontaneity of its participants. Every participant has different motivation to participate and different preference for reward type. This study, with the survey of 114 respondents, found that intrinsic motivation as well as extrinsic motivation significantly affect the motivation-reward fitness. Also, the motivation-reward fit was found to influence CoP commitment which ultimately leads to knowledge sharing activity in the CoP context. This research will help knowledge management companies to figure out how the two things of participants' motivation and their reward types can fit together, and how such fitness ultimately affects the participants' commitment and their knowledge sharing activities.

Fusion of Evolutionary Neural Networks Speciated by Fitness Sharing (적합도 공유에 의해 종분화된 진화 신경망의 결합)

  • Ahn, Joon-Hyun;Cho, Sung-Bae
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.1_2
    • /
    • pp.1-9
    • /
    • 2002
  • Evolutionary artificial neural networks (EANNs) are towards the near optimal ANN using the global search of evolutionary instead of trial-and-error process. However, many real-world problems are too hard to be solved by only one ANN. Recently there has been plenty of interest on combining ANNs in the last generation to improve the performance and reliability. This paper proposes a new approach of constructing multiple ANNs which complement each other by speciation. Also, we develop a multiple ANN to combine the results in abstract, rank, and measurement levels. The experimental results on Australian credit approval data from UCI benchmark data set have shown that combining of the speciated EANNs have better recognition ability than EANNs which are not speciated, and the average error rate of 0.105 proves the superiority of the proposed EANNs.

Validity analysis of the social emotion model based on relation types in SNS (SNS 사용자의 관계유형에 따른 사회감성 모델의 타당화 분석)

  • Cha, Ye-Sool;Kim, Ji-Hye;Kim, Jong-Hwa;Kim, Song-Yi;Kim, Dong-Keun;Whang, Min-Cheol
    • Science of Emotion and Sensibility
    • /
    • v.15 no.2
    • /
    • pp.283-296
    • /
    • 2012
  • The goal of this study is to determine the social emotion model as an emotion sharing relationship and information sharing relationship based on the user's relations at social networking services. 26 social emotions were extracted by verification of compliance among 92 different emotions collected from the literature survey. The survey on the 26 emotion words was verified to the similarity of social relation types to the Likert 7-points scale. The principal component analysis of the survey data determined 12 representative social emotions in the emotion sharing relation and 13 representative social emotions in the information sharing relation. Multidimensional scaling developed the two-dimensional social emotion model of emotion sharing relation and of information sharing relation based on online communication environment. Meanwhile, insignificant factors in the suggest social emotion models were removed by the structural equation modeling analysis, statistically. The test result of validity analysis demonstrated the fitness of social emotion models at emotion sharing relationships (CFI: .887, TLI: .885, RMSEA: .094), social emotion model of information sharing relationships (CFI: .917, TLI: .900, RMSEA : 0.050). In conclusion, this study presents two different social emotion models based on two different relation types. The findings of this study will provide not only a reference of evaluating social emotions in designing social networking services but also a direction of improving social emotions.

  • PDF

An Attribute Replicating Vertical File Partition Method by Genetic Algorithm (유전알고리듬을 이용한 속성의 중복 허용 파일 수직분할 방법)

  • 김재련;유종찬
    • The Journal of Information Technology and Database
    • /
    • v.6 no.2
    • /
    • pp.71-86
    • /
    • 1999
  • The performance of relational database is measured by the number of disk accesses necessary to transfer data from disk to main memory. The paper proposes to vertically partition relations into fragments and to allow attribute replication to reduce the number of disk accesses. To reduce the computational time, heuristic search method using genetic algorithm is used. Genetic algorithm used employs a rank-based-sharing fitness function and elitism. Desirable parameters of genetic algorithm are obtained through experiments and used to find the solutions. Solutions of attribute replication and attribute non-replication problems are compared. Optimal solutions obtained by branch and bound method and by heuristic solutions(genetic algorithm) are also discussed. The solution method proposed is able to solve large-sized problems within acceptable time limit and shows solutions near the optimal value.

  • PDF