• Title/Summary/Keyword: Information Granules

Search Result 67, Processing Time 0.024 seconds

The Design of Genetic Fuzzy Set Polynomial Neural networks based on Information Granules and Its Application of Multi -variables System (정보 입자 기반 유전론적 퍼지 집합 다항식 뉴럴네트워크 설계와 다변수 시스템으로의 응용)

  • Lee In-Tae;Oh Sung-Kwun;Kim Hyun-Ki;Seo Ki-Sung
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2005.11a
    • /
    • pp.479-482
    • /
    • 2005
  • 본 논문에서는 퍼지 뉴럴네트워크의 새로운 구조인 Fuzzy Set-based Polynomial Neural Networks(FSPNN)을 소개한다. 제안된 모델은 일반적인 최적화 방법과 정보 입자를 이용하여 네트워크를 설계한다. 최종 구조는 Fuzzy Set-based Polynomial Neuron(FSPN)을 기반으로 설계한 FPNN과 동일하다. 첫째로 FSPNS의 종합적인 설계방법(유전자 알고리즘을 이용한 최적 구조 탐색)에 대해 소개한다. FSPNN에 관계되는 입력변수의 개수, 후반부 다항식의 차수, 멤버쉽 함수의 수 그리고 입력변수 개수에 따른 입력변수를 유전자 알고리즘을 통하여 동조한다. 두 번째로, 입력 변수의 개별적인 퍼지 규칙 형성과 퍼지 공간 분할 및 삼각형 멤버쉽 함수의 초기 정점을 HCM 클러스터링을 통한 Information Granules로 정의한다. 또한 데이터 입자의 중심을 이용하여 후반부의 구조를 결정한다. 이 네트워크의 성능은 기존에 퍼지 또는 뉴로퍼지 모델링에서 실험된 모델링 표준치를 이용하여 평가한다.

  • PDF

Mechanism of Cryogenic Shredding Process of Scrap Tire

  • Taipau Chia;Shanshin Ton;Shu, Hung-Yee;Chien, Yeh-chung;Lee, Ming-Huang
    • Proceedings of the IEEK Conference
    • /
    • 2001.10a
    • /
    • pp.225-229
    • /
    • 2001
  • There are about 41% (by weight) of scrap tires were pulverized to produce rubber powder and granules in the tire recycling industry of Taiwan. However, the reuse of the by-products, steel and fiber, of the scrap tires still needs to be improved. It is difficult to remove the remaining rubber on the surface of steel or fiber. This problem reduce the availability for further reuse of steel and fiber. In addition to the improvement of magnetic, gravity separation techniques or carbonization process, using cryogenic shredding process to separate rubber and fiber (or steel) had been used as another alternative. Cryogenic shredding process for scrap tires showed many advantages, the objective of this paper is to explore the mechanisms for the cryogenic shredding process of scrap tires. Cryo-SEM is used to investigate the topographic information, in-situ, from room temperature to -195$^{\circ}C$ . One square inch shredded tire chips are prepared for SEM study. The percentage of the shrinkage of rubber is also estimated, ca. 6.7%. Mechanisms of cryogenic shredding effects on the tire chips are discussed. The proper practice of cryogenic shredding process far scrap tires is also suggested.

  • PDF

A New Approach of Self-Organizing Fuzzy Polynomial Neural Networks Based on Information Granulation and Genetic Algorithms (정보 입자화와 유전자 알고리즘에 기반한 자기구성 퍼지 다항식 뉴럴네트워크의 새로운 접근)

  • Park Ho-Sung;Oh Sung-Kwun;Kim Hvun-Ki
    • The Transactions of the Korean Institute of Electrical Engineers D
    • /
    • v.55 no.2
    • /
    • pp.45-51
    • /
    • 2006
  • In this paper, we propose a new architecture of Information Granulation based genetically optimized Self-Organizing Fuzzy Polynomial Neural Networks (IG_gSOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially information granulation and genetic algorithms. The proposed IG_gSOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). To evaluate the performance of the IG_gSOFPNN, the model is experimented with using two time series data(gas furnace process and NOx process data).

AUTOMATIC DETECTION AND EXTRACTION ALGORITHM OF INTER-GRANULAR BRIGHT POINTS

  • Feng, Song;Ji, Kai-Fan;Deng, Hui;Wang, Feng;Fu, Xiao-Dong
    • Journal of The Korean Astronomical Society
    • /
    • v.45 no.6
    • /
    • pp.167-173
    • /
    • 2012
  • Inter-granular Bright Points (igBPs) are small-scale objects in the Solar photosphere which can be seen within dark inter-granular lanes. We present a new algorithm to automatically detect and extract igBPs. Laplacian and Morphological Dilation (LMD) technique is employed by the algorithm. It involves three basic processing steps: (1) obtaining candidate "seed" regions by Laplacian; (2) determining the boundary and size of igBPs by morphological dilation; (3) discarding brighter granules by a probability criterion. For validating our algorithm, we used the observed samples of the Dutch Open Telescope (DOT), collected on April 12, 2007. They contain 180 high-resolution images, and each has a $85{\times}68\;arcsec^2$ field of view (FOV). Two important results are obtained: first, the identified rate of igBPs reaches 95% and is higher than previous results; second, the diameter distribution is $220{\pm}25km$, which is fully consistent with previously published data. We conclude that the presented algorithm can detect and extract igBPs automatically and effectively.

Self-Organizing Fuzzy Polynomial Neural Networks by Means of IG-based Consecutive Optimization : Design and Analysis (정보 입자기반 연속전인 최적화를 통한 자기구성 퍼지 다항식 뉴럴네트워크 : 설계와 해석)

  • Park, Ho-Sung;Oh, Sung-Kwun
    • The Transactions of the Korean Institute of Electrical Engineers D
    • /
    • v.55 no.6
    • /
    • pp.264-273
    • /
    • 2006
  • In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) by means of consecutive optimization and also discuss its comprehensive design methodology involving mechanisms of genetic optimization. The network is based on a structurally as well as parametrically optimized fuzzy polynomial neurons (FPNs) conducted with the aid of information granulation and genetic algorithms. In structurally identification of FPN, the design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics and addresses specific aspects of parametric optimization. In addition, the fuzzy rules used in the networks exploit the notion of information granules defined over system's variables and formed through the process of information granulation. That is, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. This granulation is realized with the aid of the hard c-menas clustering method (HCM). For the parametric identification, we obtained the effective model that the axes of MFs are identified by GA to reflect characteristic of given data. Especially, the genetically dynamic search method is introduced in the identification of parameter. It helps lead to rapidly optimal convergence over a limited region or a boundary condition. To evaluate the performance of the proposed model, the model is experimented with using two time series data(gas furnace process, nonlinear system data, and NOx process data).

The Effect of Adding Kami-guibi-tang to Acetylcholinesterase Inhibitor Treatment on the Cognitive Function of Mild Alzheimer's Disease Patients: Study Protocol of a Randomized, Placebo-Controlled, Double-Blind Pilot Trial

  • Yang, Seung-bo;Kim, Ha-ri;Shin, Hee-yeon;Kim, Jeong-hwa;Lee, Chang-woo;Jahng, Geon-ho;Park, Seong-uk;Ko, Chang-nam;Park, Jung-mi
    • The Journal of Internal Korean Medicine
    • /
    • v.41 no.3
    • /
    • pp.326-338
    • /
    • 2020
  • Background: Alzheimer's disease (AD) is a chronic neurodegenerative disease that causes disorientation, mood swings, problems with language, and difficulty remembering recent events. Acetylcholinesterase inhibitors (AchEIs) and memantine have been used to slow the course of the disease, but they can neither modify its progression nor prevent disease onset. Previous studies have suggested that Kami-guibi-tang (KGT) could be beneficial for supporting cognitive function in AD patients, but few clinical trials have been published. This pilot study aimed to evaluate the effect of KGT in improving cognitive function in AD patients. Methods: The study will be a randomized, placebo-controlled, double-blind, single-center trial conducted using subjects diagnosed with mild AD by neurologists. Study subjects will be randomly assigned to either a treatment or control group. The treatment group will receive KGT granules for 24 weeks, while the control group will receive placebo granules. AchEI administration will be maintained in both groups during the entirety of the study. Subjects will be assessed using the following exams: the Seoul Neuropsychologic Screening Battery (SNSB) for cognitive function; brain magnetic resonance imaging (MRI) for brain metabolite, neurotransmitter, and cerebral blood flow (CBF) measurements; the Korean version of Quality of Life-Alzheimer's Disease (KQol-AD) for quality of life; the Caregiver-Administered Neuropsychiatric Inventory (CGA-NPI) for neurobehavioral symptoms; blood tests for amyloid and tau proteins and general blood parameters; and electrocardiography (ECG) before and after taking the medication. Discussion: Our findings will provide insight into the feasibility of large-scale trials to consolidate evidence for the efficacy of KGT for dementia treatment. Registration ID in CRIS: KCT0002904 (Clinical Research Information Service of the Republic of Korea).

A new Design of Granular-oriented Self-organizing Polynomial Neural Networks (입자화 중심 자기구성 다항식 신경 회로망의 새로운 설계)

  • Oh, Sung-Kwun;Park, Ho-Sung
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.61 no.2
    • /
    • pp.312-320
    • /
    • 2012
  • In this study, we introduce a new design methodology of a granular-oriented self-organizing polynomial neural networks (GoSOPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). In contrast to the typical architectures encountered in polynomial neural networks (PNN), our main objective is to develop a methodological design strategy of GoSOPNNs as follows : (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context-based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets (so-called contexts) defined in the output space. (b) The proposed design procedure being applied at each layer of GoSOPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics (such as the number of contexts, the number of clusters, a collection of the specific subset of input variables, and the order of the polynomial) can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed GoSOPNN network, we describe a detailed characteristic of the proposed model using a well-known learning machine data(Automobile Miles Per Gallon Data, Boston Housing Data, Medical Image System Data).

Review of Clinical Studies for Herbal Medicine Treatment on Childhood Obesity - Focusing on Studies from the China Academic Journal (CAJ) - (중의학 데이터베이스 (CAJ)를 이용한 소아 비만의 한약치료에 대한 임상 연구 동향)

  • Kim, Seo Hyeong;Ryu, Hyang;Kim, Kibong;Cheon, Jin Hong
    • The Journal of Pediatrics of Korean Medicine
    • /
    • v.32 no.3
    • /
    • pp.26-43
    • /
    • 2018
  • Objectives The purpose of this study was to analyze recent traditional Chinese medicine clinical studies for treatment of childhood obesity. Methods We analyzed 11 clinical studies from January, 2000 to March, 2018 about childhood obesity from the China Academic Journal (CAJ) and China National Knowledge Infrastructure (CNKI). All selected studies were Randomized Controlled Trials and analyzed in order of publication year, demographic information, treatment method, evaluation methods, results, adverse reactions and relapse after treatment discontinuation. Results The main Traditional Chinese Medicine (TCM) treatment was the herbal decoctions, granules and pills. In most studies, the total efficacy of the treatment group was reported to be higher than that of the control group. Adverse reactions were found in small number of studies. Frequently used medical herbs were Crataegi Fructus (山?), Atractylodis Rhizoma (蒼朮), Citri Pericarpium (陳皮), Poria (茯?), and Nelumbinis Folium (荷葉). Also, Water-draining and swelling-dispersing medicinal (利水退腫藥), Qi-regulating medicinal (理氣藥), Resolving dampness with aroma medicinal (芳香化濕藥), Blood-activating and stasis-dispelling medicinal (活血祛瘀藥), Qi-tonifying medicinal (補氣藥), and Digestant medicinal (消食藥) were commonly used. Conclusions This study showed that traditional Chinese medicine, especially herbal medicine treatment can be effective and safe option for treating childhood obesity. These research results can be utilized in other clinical studies as well as in treatment of childhood obesity. Additional well-designed randomized controlled trials and systematic reviews are need to confirm the conclusion.

Effects of a Herbal Medicine, Yukgunja-Tang Extract Granule, on Functional Dyspepsia Patients by Sasang Constitution: Placebo-Controlled, Double-Blind, Randomized Trial (기능성 소화불량에 대한 육군자탕 엑스과립의 사상체질별 치료효과: 위약 대조, 이중 맹검, 무작위 시험)

  • Jeon, Su-Hyeong;Kim, Jong-Won
    • Journal of Sasang Constitutional Medicine
    • /
    • v.30 no.2
    • /
    • pp.42-54
    • /
    • 2018
  • Objectives This study was aimed to compare effects of Yukgunja-tang (YGJT) extract granule on functional dyspepsia (FD) by sasang constitution. Methods A placebo-controlled, double-blind, randomized, two-center trial was performed. We obtained 3D face images of FD patients participating in this study using face-only scanner and classified them into two types as narrow face and wide face by 3D facial shape diagnosis system (3-FSDS). 96 subjects (48 subjects per type) were enrolled and were randomly allocated into treatment or control groups in a 2:1 ratio. YGJT extract granule or placebo were administered to each group during the 8 week treatment period. One of sasang constitutional specialist diagnosed their constitutions by referring to questionnaires and 3D face images. The primary outcome was total dyspepsia symptom scale (TDS scale), the secondary outcomes were single dyspepsia symptom scale (SDS scale), visual analog scale (VAS) and so on. This trial was registered with clinical research information service identifier: KCT0001920, 15 May, 2016. Results In the Taeeumin treatment group, the TDS scale was significantly decreased after 8 weeks compared to the control group (t=2.331, p=0.025) and the SDS scale also significantly decreased. (t=2.042, p=0.048). The specific effects of the YGJT extract granule without the placebo effect on the Taeeumin with functional dyspepsia were 30.61% in TDS scale and 28.33% in SDS scale. Conclusions The effects of Yukgunja-tang extract granule on functional dyspepsia was different according to Sasang constitution. So the constitution should be considered in randomized controlled trials using herbal extract granules.

Fine Structure of the Integumentary Supporting Cell and Gland Cell of the Sea Bass, Lateolabrax japonicus (Teleostei: Moronidae) (농어 (Lateolabrax japonicus) 피부계 지지세포와 선세포의 미세구조)

  • Lee, Jung-Sick;Kim, Jae-Won
    • Applied Microscopy
    • /
    • v.29 no.4
    • /
    • pp.417-426
    • /
    • 1999
  • The present investigation is designed to provide basic information on fine structure of the skin of the sea bass, Lateolabrax japonicks in relation to study of epidermal change with environmental and physiological change. The skin of the sea bass is divided into the epidermal layer and dermal layer. Epidermal layer consists of supporting cells and unicellular glands. The supporting cells were classified into the superficial cell, intermediated cell and basal cell. Gland cells were classified into the mucous secretory cell and club cell which is more frequently observed. Superficial cell of epidermal layer is squamous or cuboidal and contains well-developed rough endoplasmic reticulum and the surface is covered with numerous microridges. Superficial cells are connected to another cell with membrane interdigitations and desmosomes. Intermediated cell is ovoid and the electron density is higher than the other supporting cells. Basal cell is cuboidal and has a well-developed mitochondria and membrane interdigitation. The mucous secretory cell has a numerous membrane bounded secretory granules. The cytoplasm of club cell is divided into cortex and medullar. The medullar cytoplasm has a nucleus, intracellular organelles and central vacuole, and the cortical cytoplasm has a well-developed tonofilament. Club cells are connected to another cell with well -developed membrane interdigitations and desmosomes.

  • PDF